Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +156 -3
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- checkpoint-147/README.md +202 -0
- checkpoint-147/adapter_config.json +34 -0
- checkpoint-147/adapter_model.safetensors +3 -0
- checkpoint-147/optimizer.pt +3 -0
- checkpoint-147/rng_state.pth +3 -0
- checkpoint-147/scheduler.pt +3 -0
- checkpoint-147/special_tokens_map.json +24 -0
- checkpoint-147/tokenizer.model +3 -0
- checkpoint-147/tokenizer_config.json +45 -0
- checkpoint-147/trainer_state.json +1146 -0
- checkpoint-147/training_args.bin +3 -0
- checkpoint-196/README.md +202 -0
- checkpoint-196/adapter_config.json +34 -0
- checkpoint-196/adapter_model.safetensors +3 -0
- checkpoint-196/optimizer.pt +3 -0
- checkpoint-196/rng_state.pth +3 -0
- checkpoint-196/scheduler.pt +3 -0
- checkpoint-196/special_tokens_map.json +24 -0
- checkpoint-196/tokenizer.model +3 -0
- checkpoint-196/tokenizer_config.json +45 -0
- checkpoint-196/trainer_state.json +1521 -0
- checkpoint-196/training_args.bin +3 -0
- checkpoint-49/README.md +202 -0
- checkpoint-49/adapter_config.json +34 -0
- checkpoint-49/adapter_model.safetensors +3 -0
- checkpoint-49/optimizer.pt +3 -0
- checkpoint-49/rng_state.pth +3 -0
- checkpoint-49/scheduler.pt +3 -0
- checkpoint-49/special_tokens_map.json +24 -0
- checkpoint-49/tokenizer.model +3 -0
- checkpoint-49/tokenizer_config.json +45 -0
- checkpoint-49/trainer_state.json +396 -0
- checkpoint-49/training_args.bin +3 -0
- checkpoint-98/README.md +202 -0
- checkpoint-98/adapter_config.json +34 -0
- checkpoint-98/adapter_model.safetensors +3 -0
- checkpoint-98/optimizer.pt +3 -0
- checkpoint-98/rng_state.pth +3 -0
- checkpoint-98/scheduler.pt +3 -0
- checkpoint-98/special_tokens_map.json +24 -0
- checkpoint-98/tokenizer.model +3 -0
- checkpoint-98/tokenizer_config.json +45 -0
- checkpoint-98/trainer_state.json +771 -0
- checkpoint-98/training_args.bin +3 -0
- config.json +43 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
README.md
CHANGED
|
@@ -1,3 +1,156 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 7 |
+
model-index:
|
| 8 |
+
- name: outputs/lora-out
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 16 |
+
<details><summary>See axolotl config</summary>
|
| 17 |
+
|
| 18 |
+
axolotl version: `0.4.0`
|
| 19 |
+
```yaml
|
| 20 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 21 |
+
model_type: LlamaForCausalLM
|
| 22 |
+
tokenizer_type: LlamaTokenizer
|
| 23 |
+
|
| 24 |
+
load_in_8bit: true
|
| 25 |
+
load_in_4bit: false
|
| 26 |
+
strict: false
|
| 27 |
+
|
| 28 |
+
datasets:
|
| 29 |
+
- path: burkelibbey/colors
|
| 30 |
+
type:
|
| 31 |
+
field_instruction: color
|
| 32 |
+
field_output: description
|
| 33 |
+
conversation: chatml
|
| 34 |
+
chat_template: chatml
|
| 35 |
+
|
| 36 |
+
dataset_prepared_path:
|
| 37 |
+
val_set_size: 0.05
|
| 38 |
+
output_dir: ./outputs/lora-out
|
| 39 |
+
|
| 40 |
+
sequence_len: 4096
|
| 41 |
+
sample_packing: true
|
| 42 |
+
eval_sample_packing: false
|
| 43 |
+
pad_to_sequence_len: true
|
| 44 |
+
|
| 45 |
+
adapter: lora
|
| 46 |
+
lora_model_dir:
|
| 47 |
+
lora_r: 32
|
| 48 |
+
lora_alpha: 16
|
| 49 |
+
lora_dropout: 0.05
|
| 50 |
+
lora_target_linear: true
|
| 51 |
+
lora_fan_in_fan_out:
|
| 52 |
+
|
| 53 |
+
wandb_project:
|
| 54 |
+
wandb_entity:
|
| 55 |
+
wandb_watch:
|
| 56 |
+
wandb_name:
|
| 57 |
+
wandb_log_model:
|
| 58 |
+
|
| 59 |
+
gradient_accumulation_steps: 4
|
| 60 |
+
micro_batch_size: 2
|
| 61 |
+
num_epochs: 4
|
| 62 |
+
optimizer: adamw_bnb_8bit
|
| 63 |
+
lr_scheduler: cosine
|
| 64 |
+
learning_rate: 0.0002
|
| 65 |
+
|
| 66 |
+
train_on_inputs: false
|
| 67 |
+
group_by_length: false
|
| 68 |
+
bf16: auto
|
| 69 |
+
fp16:
|
| 70 |
+
tf32: false
|
| 71 |
+
|
| 72 |
+
gradient_checkpointing: true
|
| 73 |
+
early_stopping_patience:
|
| 74 |
+
resume_from_checkpoint:
|
| 75 |
+
local_rank:
|
| 76 |
+
logging_steps: 1
|
| 77 |
+
xformers_attention:
|
| 78 |
+
flash_attention: true
|
| 79 |
+
|
| 80 |
+
warmup_steps: 10
|
| 81 |
+
evals_per_epoch: 4
|
| 82 |
+
saves_per_epoch: 1
|
| 83 |
+
debug:
|
| 84 |
+
deepspeed:
|
| 85 |
+
weight_decay: 0.0
|
| 86 |
+
fsdp:
|
| 87 |
+
fsdp_config:
|
| 88 |
+
special_tokens:
|
| 89 |
+
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
</details><br>
|
| 93 |
+
|
| 94 |
+
# outputs/lora-out
|
| 95 |
+
|
| 96 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
|
| 97 |
+
It achieves the following results on the evaluation set:
|
| 98 |
+
- Loss: 1.2375
|
| 99 |
+
|
| 100 |
+
## Model description
|
| 101 |
+
|
| 102 |
+
More information needed
|
| 103 |
+
|
| 104 |
+
## Intended uses & limitations
|
| 105 |
+
|
| 106 |
+
More information needed
|
| 107 |
+
|
| 108 |
+
## Training and evaluation data
|
| 109 |
+
|
| 110 |
+
More information needed
|
| 111 |
+
|
| 112 |
+
## Training procedure
|
| 113 |
+
|
| 114 |
+
### Training hyperparameters
|
| 115 |
+
|
| 116 |
+
The following hyperparameters were used during training:
|
| 117 |
+
- learning_rate: 0.0002
|
| 118 |
+
- train_batch_size: 2
|
| 119 |
+
- eval_batch_size: 2
|
| 120 |
+
- seed: 42
|
| 121 |
+
- gradient_accumulation_steps: 4
|
| 122 |
+
- total_train_batch_size: 8
|
| 123 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 124 |
+
- lr_scheduler_type: cosine
|
| 125 |
+
- lr_scheduler_warmup_steps: 10
|
| 126 |
+
- num_epochs: 4
|
| 127 |
+
|
| 128 |
+
### Training results
|
| 129 |
+
|
| 130 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 131 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 132 |
+
| 2.7509 | 0.0204 | 1 | 2.6902 |
|
| 133 |
+
| 1.8064 | 0.2653 | 13 | 1.6735 |
|
| 134 |
+
| 1.5513 | 0.5306 | 26 | 1.4832 |
|
| 135 |
+
| 1.482 | 0.7959 | 39 | 1.4111 |
|
| 136 |
+
| 1.392 | 1.0408 | 52 | 1.3677 |
|
| 137 |
+
| 1.3414 | 1.3061 | 65 | 1.3319 |
|
| 138 |
+
| 1.3213 | 1.5714 | 78 | 1.3029 |
|
| 139 |
+
| 1.3028 | 1.8367 | 91 | 1.2795 |
|
| 140 |
+
| 1.2761 | 2.0816 | 104 | 1.2697 |
|
| 141 |
+
| 1.2509 | 2.3469 | 117 | 1.2587 |
|
| 142 |
+
| 1.2884 | 2.6122 | 130 | 1.2472 |
|
| 143 |
+
| 1.254 | 2.8776 | 143 | 1.2410 |
|
| 144 |
+
| 1.2523 | 3.1224 | 156 | 1.2403 |
|
| 145 |
+
| 1.2468 | 3.3878 | 169 | 1.2385 |
|
| 146 |
+
| 1.2476 | 3.6531 | 182 | 1.2370 |
|
| 147 |
+
| 1.2366 | 3.9184 | 195 | 1.2375 |
|
| 148 |
+
|
| 149 |
+
|
| 150 |
+
### Framework versions
|
| 151 |
+
|
| 152 |
+
- PEFT 0.10.0
|
| 153 |
+
- Transformers 4.40.2
|
| 154 |
+
- Pytorch 2.1.2+cu118
|
| 155 |
+
- Datasets 2.19.1
|
| 156 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1f20d120db2b5b6953281cb7fa6e550c36182e6da8f44b598738a5995d5be6f
|
| 3 |
+
size 101036698
|
checkpoint-147/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-147/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-147/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb2ebdaf4b36ef443d056e4e52b5f0bf8223038232557b97bb7ce888df4d3c48
|
| 3 |
+
size 100966336
|
checkpoint-147/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88cf550811bb96f9852bdb7a8952d49f6f0bf413e95b0759a8db28fcab406988
|
| 3 |
+
size 50916644
|
checkpoint-147/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4e8611d6bcf761201e741bdb2188a6ac976702d2e3f1a3ecc21fff90ea8a001
|
| 3 |
+
size 14244
|
checkpoint-147/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c1e2e1bea1da15cd4a47196fc191277510622d916f0b4b5e8c95f3258d5825
|
| 3 |
+
size 1064
|
checkpoint-147/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-147/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-147/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false,
|
| 44 |
+
"use_fast": true
|
| 45 |
+
}
|
checkpoint-147/trainer_state.json
ADDED
|
@@ -0,0 +1,1146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9591836734693877,
|
| 5 |
+
"eval_steps": 13,
|
| 6 |
+
"global_step": 147,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02040816326530612,
|
| 13 |
+
"grad_norm": 0.7881951332092285,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.7509,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02040816326530612,
|
| 20 |
+
"eval_loss": 2.6902382373809814,
|
| 21 |
+
"eval_runtime": 269.5606,
|
| 22 |
+
"eval_samples_per_second": 6.288,
|
| 23 |
+
"eval_steps_per_second": 3.146,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04081632653061224,
|
| 28 |
+
"grad_norm": 0.789082407951355,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 2.7449,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.061224489795918366,
|
| 35 |
+
"grad_norm": 0.7354114055633545,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 2.7164,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08163265306122448,
|
| 42 |
+
"grad_norm": 0.7292255759239197,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 2.7174,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10204081632653061,
|
| 49 |
+
"grad_norm": 0.6898028254508972,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 2.6891,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12244897959183673,
|
| 56 |
+
"grad_norm": 0.6861400604248047,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 2.6545,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14285714285714285,
|
| 63 |
+
"grad_norm": 0.7510350346565247,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 2.5656,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16326530612244897,
|
| 70 |
+
"grad_norm": 0.8011165261268616,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 2.4519,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1836734693877551,
|
| 77 |
+
"grad_norm": 0.8624005317687988,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 2.3178,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.20408163265306123,
|
| 84 |
+
"grad_norm": 0.8004987835884094,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 2.1783,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22448979591836735,
|
| 91 |
+
"grad_norm": 0.6362400054931641,
|
| 92 |
+
"learning_rate": 0.000199985736255971,
|
| 93 |
+
"loss": 2.0252,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24489795918367346,
|
| 98 |
+
"grad_norm": 0.7930936217308044,
|
| 99 |
+
"learning_rate": 0.0001999429490929718,
|
| 100 |
+
"loss": 1.8839,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2653061224489796,
|
| 105 |
+
"grad_norm": 0.5149843096733093,
|
| 106 |
+
"learning_rate": 0.00019987165071710527,
|
| 107 |
+
"loss": 1.8064,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2653061224489796,
|
| 112 |
+
"eval_loss": 1.6734941005706787,
|
| 113 |
+
"eval_runtime": 271.2615,
|
| 114 |
+
"eval_samples_per_second": 6.249,
|
| 115 |
+
"eval_steps_per_second": 3.126,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2857142857142857,
|
| 120 |
+
"grad_norm": 0.42121434211730957,
|
| 121 |
+
"learning_rate": 0.00019977186146800707,
|
| 122 |
+
"loss": 1.7922,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.30612244897959184,
|
| 127 |
+
"grad_norm": 0.3523242771625519,
|
| 128 |
+
"learning_rate": 0.0001996436098130433,
|
| 129 |
+
"loss": 1.7711,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.32653061224489793,
|
| 134 |
+
"grad_norm": 0.3384595215320587,
|
| 135 |
+
"learning_rate": 0.00019948693233918952,
|
| 136 |
+
"loss": 1.7152,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3469387755102041,
|
| 141 |
+
"grad_norm": 0.34942421317100525,
|
| 142 |
+
"learning_rate": 0.00019930187374259337,
|
| 143 |
+
"loss": 1.7112,
|
| 144 |
+
"step": 17
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3673469387755102,
|
| 148 |
+
"grad_norm": 0.31712639331817627,
|
| 149 |
+
"learning_rate": 0.00019908848681582391,
|
| 150 |
+
"loss": 1.7059,
|
| 151 |
+
"step": 18
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3877551020408163,
|
| 155 |
+
"grad_norm": 0.2875436842441559,
|
| 156 |
+
"learning_rate": 0.00019884683243281116,
|
| 157 |
+
"loss": 1.6468,
|
| 158 |
+
"step": 19
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.40816326530612246,
|
| 162 |
+
"grad_norm": 0.24433130025863647,
|
| 163 |
+
"learning_rate": 0.00019857697953148037,
|
| 164 |
+
"loss": 1.6408,
|
| 165 |
+
"step": 20
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.42857142857142855,
|
| 169 |
+
"grad_norm": 0.21414674818515778,
|
| 170 |
+
"learning_rate": 0.00019827900509408581,
|
| 171 |
+
"loss": 1.616,
|
| 172 |
+
"step": 21
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.4489795918367347,
|
| 176 |
+
"grad_norm": 0.21537622809410095,
|
| 177 |
+
"learning_rate": 0.00019795299412524945,
|
| 178 |
+
"loss": 1.609,
|
| 179 |
+
"step": 22
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.46938775510204084,
|
| 183 |
+
"grad_norm": 0.2432074397802353,
|
| 184 |
+
"learning_rate": 0.00019759903962771156,
|
| 185 |
+
"loss": 1.6066,
|
| 186 |
+
"step": 23
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4897959183673469,
|
| 190 |
+
"grad_norm": 0.2359839379787445,
|
| 191 |
+
"learning_rate": 0.00019721724257579907,
|
| 192 |
+
"loss": 1.5851,
|
| 193 |
+
"step": 24
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.5102040816326531,
|
| 197 |
+
"grad_norm": 0.22065888345241547,
|
| 198 |
+
"learning_rate": 0.00019680771188662044,
|
| 199 |
+
"loss": 1.5739,
|
| 200 |
+
"step": 25
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5306122448979592,
|
| 204 |
+
"grad_norm": 0.20339132845401764,
|
| 205 |
+
"learning_rate": 0.0001963705643889941,
|
| 206 |
+
"loss": 1.5513,
|
| 207 |
+
"step": 26
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5306122448979592,
|
| 211 |
+
"eval_loss": 1.4832030534744263,
|
| 212 |
+
"eval_runtime": 271.2449,
|
| 213 |
+
"eval_samples_per_second": 6.249,
|
| 214 |
+
"eval_steps_per_second": 3.126,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5510204081632653,
|
| 219 |
+
"grad_norm": 0.18875224888324738,
|
| 220 |
+
"learning_rate": 0.00019590592479012023,
|
| 221 |
+
"loss": 1.5378,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5714285714285714,
|
| 226 |
+
"grad_norm": 0.18564417958259583,
|
| 227 |
+
"learning_rate": 0.00019541392564000488,
|
| 228 |
+
"loss": 1.5212,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5918367346938775,
|
| 233 |
+
"grad_norm": 0.16226942837238312,
|
| 234 |
+
"learning_rate": 0.00019489470729364692,
|
| 235 |
+
"loss": 1.5391,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6122448979591837,
|
| 240 |
+
"grad_norm": 0.15650039911270142,
|
| 241 |
+
"learning_rate": 0.00019434841787099803,
|
| 242 |
+
"loss": 1.511,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6326530612244898,
|
| 247 |
+
"grad_norm": 0.15976540744304657,
|
| 248 |
+
"learning_rate": 0.00019377521321470805,
|
| 249 |
+
"loss": 1.5119,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6530612244897959,
|
| 254 |
+
"grad_norm": 0.16409288346767426,
|
| 255 |
+
"learning_rate": 0.00019317525684566685,
|
| 256 |
+
"loss": 1.4909,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.673469387755102,
|
| 261 |
+
"grad_norm": 0.15468019247055054,
|
| 262 |
+
"learning_rate": 0.00019254871991635598,
|
| 263 |
+
"loss": 1.4951,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6938775510204082,
|
| 268 |
+
"grad_norm": 0.1462036371231079,
|
| 269 |
+
"learning_rate": 0.00019189578116202307,
|
| 270 |
+
"loss": 1.4643,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7142857142857143,
|
| 275 |
+
"grad_norm": 0.1541963368654251,
|
| 276 |
+
"learning_rate": 0.00019121662684969335,
|
| 277 |
+
"loss": 1.5159,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7346938775510204,
|
| 282 |
+
"grad_norm": 0.14798064529895782,
|
| 283 |
+
"learning_rate": 0.00019051145072503215,
|
| 284 |
+
"loss": 1.4741,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.7551020408163265,
|
| 289 |
+
"grad_norm": 0.13914817571640015,
|
| 290 |
+
"learning_rate": 0.00018978045395707418,
|
| 291 |
+
"loss": 1.4788,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7755102040816326,
|
| 296 |
+
"grad_norm": 0.15608824789524078,
|
| 297 |
+
"learning_rate": 0.00018902384508083517,
|
| 298 |
+
"loss": 1.4687,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.7959183673469388,
|
| 303 |
+
"grad_norm": 0.14460116624832153,
|
| 304 |
+
"learning_rate": 0.00018824183993782192,
|
| 305 |
+
"loss": 1.482,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.7959183673469388,
|
| 310 |
+
"eval_loss": 1.411073088645935,
|
| 311 |
+
"eval_runtime": 271.292,
|
| 312 |
+
"eval_samples_per_second": 6.248,
|
| 313 |
+
"eval_steps_per_second": 3.126,
|
| 314 |
+
"step": 39
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8163265306122449,
|
| 318 |
+
"grad_norm": 0.15740551054477692,
|
| 319 |
+
"learning_rate": 0.00018743466161445823,
|
| 320 |
+
"loss": 1.4486,
|
| 321 |
+
"step": 40
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8367346938775511,
|
| 325 |
+
"grad_norm": 0.14149661362171173,
|
| 326 |
+
"learning_rate": 0.00018660254037844388,
|
| 327 |
+
"loss": 1.4353,
|
| 328 |
+
"step": 41
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8571428571428571,
|
| 332 |
+
"grad_norm": 0.14034292101860046,
|
| 333 |
+
"learning_rate": 0.0001857457136130651,
|
| 334 |
+
"loss": 1.4523,
|
| 335 |
+
"step": 42
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.8775510204081632,
|
| 339 |
+
"grad_norm": 0.1487722396850586,
|
| 340 |
+
"learning_rate": 0.00018486442574947511,
|
| 341 |
+
"loss": 1.4095,
|
| 342 |
+
"step": 43
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.8979591836734694,
|
| 346 |
+
"grad_norm": 0.17400234937667847,
|
| 347 |
+
"learning_rate": 0.00018395892819696389,
|
| 348 |
+
"loss": 1.4414,
|
| 349 |
+
"step": 44
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9183673469387755,
|
| 353 |
+
"grad_norm": 0.1741325408220291,
|
| 354 |
+
"learning_rate": 0.00018302947927123766,
|
| 355 |
+
"loss": 1.4379,
|
| 356 |
+
"step": 45
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9387755102040817,
|
| 360 |
+
"grad_norm": 0.15319454669952393,
|
| 361 |
+
"learning_rate": 0.00018207634412072764,
|
| 362 |
+
"loss": 1.405,
|
| 363 |
+
"step": 46
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9591836734693877,
|
| 367 |
+
"grad_norm": 0.15876264870166779,
|
| 368 |
+
"learning_rate": 0.00018109979465095013,
|
| 369 |
+
"loss": 1.4122,
|
| 370 |
+
"step": 47
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9795918367346939,
|
| 374 |
+
"grad_norm": 0.17120805382728577,
|
| 375 |
+
"learning_rate": 0.00018010010944693848,
|
| 376 |
+
"loss": 1.4132,
|
| 377 |
+
"step": 48
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.0,
|
| 381 |
+
"grad_norm": 0.1436116099357605,
|
| 382 |
+
"learning_rate": 0.00017907757369376985,
|
| 383 |
+
"loss": 1.416,
|
| 384 |
+
"step": 49
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.0204081632653061,
|
| 388 |
+
"grad_norm": 0.1707429438829422,
|
| 389 |
+
"learning_rate": 0.0001780324790952092,
|
| 390 |
+
"loss": 1.3913,
|
| 391 |
+
"step": 50
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.0204081632653061,
|
| 395 |
+
"grad_norm": 0.17117524147033691,
|
| 396 |
+
"learning_rate": 0.00017696512379049325,
|
| 397 |
+
"loss": 1.3963,
|
| 398 |
+
"step": 51
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.0408163265306123,
|
| 402 |
+
"grad_norm": 0.13410089910030365,
|
| 403 |
+
"learning_rate": 0.0001758758122692791,
|
| 404 |
+
"loss": 1.392,
|
| 405 |
+
"step": 52
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0408163265306123,
|
| 409 |
+
"eval_loss": 1.3676769733428955,
|
| 410 |
+
"eval_runtime": 270.8566,
|
| 411 |
+
"eval_samples_per_second": 6.258,
|
| 412 |
+
"eval_steps_per_second": 3.131,
|
| 413 |
+
"step": 52
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.0612244897959184,
|
| 417 |
+
"grad_norm": 0.18877607583999634,
|
| 418 |
+
"learning_rate": 0.00017476485528478093,
|
| 419 |
+
"loss": 1.3854,
|
| 420 |
+
"step": 53
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.0816326530612246,
|
| 424 |
+
"grad_norm": 0.1752927452325821,
|
| 425 |
+
"learning_rate": 0.00017363256976511972,
|
| 426 |
+
"loss": 1.3759,
|
| 427 |
+
"step": 54
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.1020408163265305,
|
| 431 |
+
"grad_norm": 0.17180170118808746,
|
| 432 |
+
"learning_rate": 0.000172479278722912,
|
| 433 |
+
"loss": 1.3614,
|
| 434 |
+
"step": 55
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1224489795918366,
|
| 438 |
+
"grad_norm": 0.1640290915966034,
|
| 439 |
+
"learning_rate": 0.00017130531116312203,
|
| 440 |
+
"loss": 1.3853,
|
| 441 |
+
"step": 56
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.1428571428571428,
|
| 445 |
+
"grad_norm": 0.2047068476676941,
|
| 446 |
+
"learning_rate": 0.0001701110019892053,
|
| 447 |
+
"loss": 1.3699,
|
| 448 |
+
"step": 57
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.163265306122449,
|
| 452 |
+
"grad_norm": 0.1835869997739792,
|
| 453 |
+
"learning_rate": 0.00016889669190756868,
|
| 454 |
+
"loss": 1.3403,
|
| 455 |
+
"step": 58
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.183673469387755,
|
| 459 |
+
"grad_norm": 0.16733241081237793,
|
| 460 |
+
"learning_rate": 0.00016766272733037576,
|
| 461 |
+
"loss": 1.3609,
|
| 462 |
+
"step": 59
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.2040816326530612,
|
| 466 |
+
"grad_norm": 0.178726926445961,
|
| 467 |
+
"learning_rate": 0.00016640946027672392,
|
| 468 |
+
"loss": 1.3651,
|
| 469 |
+
"step": 60
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.2244897959183674,
|
| 473 |
+
"grad_norm": 0.16719630360603333,
|
| 474 |
+
"learning_rate": 0.00016513724827222227,
|
| 475 |
+
"loss": 1.3676,
|
| 476 |
+
"step": 61
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.2448979591836735,
|
| 480 |
+
"grad_norm": 0.15999363362789154,
|
| 481 |
+
"learning_rate": 0.00016384645424699835,
|
| 482 |
+
"loss": 1.3651,
|
| 483 |
+
"step": 62
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2653061224489797,
|
| 487 |
+
"grad_norm": 0.1705988198518753,
|
| 488 |
+
"learning_rate": 0.00016253744643216368,
|
| 489 |
+
"loss": 1.3757,
|
| 490 |
+
"step": 63
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.2857142857142856,
|
| 494 |
+
"grad_norm": 0.14996370673179626,
|
| 495 |
+
"learning_rate": 0.0001612105982547663,
|
| 496 |
+
"loss": 1.3474,
|
| 497 |
+
"step": 64
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.306122448979592,
|
| 501 |
+
"grad_norm": 0.19127260148525238,
|
| 502 |
+
"learning_rate": 0.0001598662882312615,
|
| 503 |
+
"loss": 1.3414,
|
| 504 |
+
"step": 65
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.306122448979592,
|
| 508 |
+
"eval_loss": 1.331880807876587,
|
| 509 |
+
"eval_runtime": 270.8424,
|
| 510 |
+
"eval_samples_per_second": 6.258,
|
| 511 |
+
"eval_steps_per_second": 3.131,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.3265306122448979,
|
| 516 |
+
"grad_norm": 0.16125527024269104,
|
| 517 |
+
"learning_rate": 0.00015850489985953076,
|
| 518 |
+
"loss": 1.3509,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.346938775510204,
|
| 523 |
+
"grad_norm": 0.1979473978281021,
|
| 524 |
+
"learning_rate": 0.00015712682150947923,
|
| 525 |
+
"loss": 1.3579,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3673469387755102,
|
| 530 |
+
"grad_norm": 0.18317992985248566,
|
| 531 |
+
"learning_rate": 0.00015573244631224365,
|
| 532 |
+
"loss": 1.3341,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.3877551020408163,
|
| 537 |
+
"grad_norm": 0.1646898239850998,
|
| 538 |
+
"learning_rate": 0.0001543221720480419,
|
| 539 |
+
"loss": 1.3361,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.4081632653061225,
|
| 544 |
+
"grad_norm": 0.1760271042585373,
|
| 545 |
+
"learning_rate": 0.00015289640103269625,
|
| 546 |
+
"loss": 1.358,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.4285714285714286,
|
| 551 |
+
"grad_norm": 0.165283203125,
|
| 552 |
+
"learning_rate": 0.0001514555400028629,
|
| 553 |
+
"loss": 1.3072,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.4489795918367347,
|
| 558 |
+
"grad_norm": 0.1507076472043991,
|
| 559 |
+
"learning_rate": 0.00015000000000000001,
|
| 560 |
+
"loss": 1.3133,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.469387755102041,
|
| 565 |
+
"grad_norm": 0.16913647949695587,
|
| 566 |
+
"learning_rate": 0.00014853019625310813,
|
| 567 |
+
"loss": 1.3232,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.489795918367347,
|
| 572 |
+
"grad_norm": 0.18266479671001434,
|
| 573 |
+
"learning_rate": 0.0001470465480602756,
|
| 574 |
+
"loss": 1.3512,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.510204081632653,
|
| 579 |
+
"grad_norm": 0.19301828742027283,
|
| 580 |
+
"learning_rate": 0.0001455494786690634,
|
| 581 |
+
"loss": 1.3241,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.5306122448979593,
|
| 586 |
+
"grad_norm": 0.16109652817249298,
|
| 587 |
+
"learning_rate": 0.00014403941515576344,
|
| 588 |
+
"loss": 1.3256,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.5510204081632653,
|
| 593 |
+
"grad_norm": 0.17053867876529694,
|
| 594 |
+
"learning_rate": 0.00014251678830356408,
|
| 595 |
+
"loss": 1.3162,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.5714285714285714,
|
| 600 |
+
"grad_norm": 0.17348544299602509,
|
| 601 |
+
"learning_rate": 0.00014098203247965875,
|
| 602 |
+
"loss": 1.3213,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.5714285714285714,
|
| 607 |
+
"eval_loss": 1.3028697967529297,
|
| 608 |
+
"eval_runtime": 270.8095,
|
| 609 |
+
"eval_samples_per_second": 6.259,
|
| 610 |
+
"eval_steps_per_second": 3.131,
|
| 611 |
+
"step": 78
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.5918367346938775,
|
| 615 |
+
"grad_norm": 0.1703907549381256,
|
| 616 |
+
"learning_rate": 0.00013943558551133186,
|
| 617 |
+
"loss": 1.3073,
|
| 618 |
+
"step": 79
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.6122448979591837,
|
| 622 |
+
"grad_norm": 0.17313100397586823,
|
| 623 |
+
"learning_rate": 0.0001378778885610576,
|
| 624 |
+
"loss": 1.3232,
|
| 625 |
+
"step": 80
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6326530612244898,
|
| 629 |
+
"grad_norm": 0.17237025499343872,
|
| 630 |
+
"learning_rate": 0.00013630938600064747,
|
| 631 |
+
"loss": 1.3406,
|
| 632 |
+
"step": 81
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6530612244897958,
|
| 636 |
+
"grad_norm": 0.19658459722995758,
|
| 637 |
+
"learning_rate": 0.00013473052528448201,
|
| 638 |
+
"loss": 1.3114,
|
| 639 |
+
"step": 82
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6734693877551021,
|
| 643 |
+
"grad_norm": 0.20599938929080963,
|
| 644 |
+
"learning_rate": 0.0001331417568218636,
|
| 645 |
+
"loss": 1.3288,
|
| 646 |
+
"step": 83
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.693877551020408,
|
| 650 |
+
"grad_norm": 0.17759399116039276,
|
| 651 |
+
"learning_rate": 0.00013154353384852558,
|
| 652 |
+
"loss": 1.2995,
|
| 653 |
+
"step": 84
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.7142857142857144,
|
| 657 |
+
"grad_norm": 0.18712250888347626,
|
| 658 |
+
"learning_rate": 0.00012993631229733582,
|
| 659 |
+
"loss": 1.2895,
|
| 660 |
+
"step": 85
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7346938775510203,
|
| 664 |
+
"grad_norm": 0.1991330236196518,
|
| 665 |
+
"learning_rate": 0.00012832055066823038,
|
| 666 |
+
"loss": 1.2886,
|
| 667 |
+
"step": 86
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.7551020408163265,
|
| 671 |
+
"grad_norm": 0.22125203907489777,
|
| 672 |
+
"learning_rate": 0.00012669670989741517,
|
| 673 |
+
"loss": 1.3233,
|
| 674 |
+
"step": 87
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.7755102040816326,
|
| 678 |
+
"grad_norm": 0.2052813619375229,
|
| 679 |
+
"learning_rate": 0.00012506525322587207,
|
| 680 |
+
"loss": 1.3079,
|
| 681 |
+
"step": 88
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.7959183673469388,
|
| 685 |
+
"grad_norm": 0.19290736317634583,
|
| 686 |
+
"learning_rate": 0.00012342664606720822,
|
| 687 |
+
"loss": 1.3174,
|
| 688 |
+
"step": 89
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.816326530612245,
|
| 692 |
+
"grad_norm": 0.20912542939186096,
|
| 693 |
+
"learning_rate": 0.00012178135587488515,
|
| 694 |
+
"loss": 1.2915,
|
| 695 |
+
"step": 90
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.836734693877551,
|
| 699 |
+
"grad_norm": 0.20760588347911835,
|
| 700 |
+
"learning_rate": 0.00012012985200886602,
|
| 701 |
+
"loss": 1.3028,
|
| 702 |
+
"step": 91
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.836734693877551,
|
| 706 |
+
"eval_loss": 1.2795333862304688,
|
| 707 |
+
"eval_runtime": 270.6525,
|
| 708 |
+
"eval_samples_per_second": 6.263,
|
| 709 |
+
"eval_steps_per_second": 3.133,
|
| 710 |
+
"step": 91
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.8571428571428572,
|
| 714 |
+
"grad_norm": 0.1996900886297226,
|
| 715 |
+
"learning_rate": 0.00011847260560171896,
|
| 716 |
+
"loss": 1.3119,
|
| 717 |
+
"step": 92
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.8775510204081631,
|
| 721 |
+
"grad_norm": 0.23766876757144928,
|
| 722 |
+
"learning_rate": 0.00011681008942421483,
|
| 723 |
+
"loss": 1.2978,
|
| 724 |
+
"step": 93
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.8979591836734695,
|
| 728 |
+
"grad_norm": 0.19782397150993347,
|
| 729 |
+
"learning_rate": 0.00011514277775045768,
|
| 730 |
+
"loss": 1.2955,
|
| 731 |
+
"step": 94
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9183673469387754,
|
| 735 |
+
"grad_norm": 0.22519494593143463,
|
| 736 |
+
"learning_rate": 0.00011347114622258612,
|
| 737 |
+
"loss": 1.2957,
|
| 738 |
+
"step": 95
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.9387755102040818,
|
| 742 |
+
"grad_norm": 0.2590245306491852,
|
| 743 |
+
"learning_rate": 0.00011179567171508463,
|
| 744 |
+
"loss": 1.2809,
|
| 745 |
+
"step": 96
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.9591836734693877,
|
| 749 |
+
"grad_norm": 0.2235420197248459,
|
| 750 |
+
"learning_rate": 0.00011011683219874323,
|
| 751 |
+
"loss": 1.2784,
|
| 752 |
+
"step": 97
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.9795918367346939,
|
| 756 |
+
"grad_norm": 0.285740464925766,
|
| 757 |
+
"learning_rate": 0.00010843510660430447,
|
| 758 |
+
"loss": 1.309,
|
| 759 |
+
"step": 98
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.0,
|
| 763 |
+
"grad_norm": 0.20554350316524506,
|
| 764 |
+
"learning_rate": 0.00010675097468583652,
|
| 765 |
+
"loss": 1.273,
|
| 766 |
+
"step": 99
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.020408163265306,
|
| 770 |
+
"grad_norm": 0.24468418955802917,
|
| 771 |
+
"learning_rate": 0.00010506491688387127,
|
| 772 |
+
"loss": 1.2833,
|
| 773 |
+
"step": 100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.020408163265306,
|
| 777 |
+
"grad_norm": 0.21553528308868408,
|
| 778 |
+
"learning_rate": 0.00010337741418834684,
|
| 779 |
+
"loss": 1.2669,
|
| 780 |
+
"step": 101
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.0408163265306123,
|
| 784 |
+
"grad_norm": 0.22015659511089325,
|
| 785 |
+
"learning_rate": 0.0001016889480013931,
|
| 786 |
+
"loss": 1.2795,
|
| 787 |
+
"step": 102
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.061224489795918,
|
| 791 |
+
"grad_norm": 0.2028799206018448,
|
| 792 |
+
"learning_rate": 0.0001,
|
| 793 |
+
"loss": 1.2584,
|
| 794 |
+
"step": 103
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.0816326530612246,
|
| 798 |
+
"grad_norm": 0.23474323749542236,
|
| 799 |
+
"learning_rate": 9.83110519986069e-05,
|
| 800 |
+
"loss": 1.2761,
|
| 801 |
+
"step": 104
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.0816326530612246,
|
| 805 |
+
"eval_loss": 1.2696796655654907,
|
| 806 |
+
"eval_runtime": 270.6586,
|
| 807 |
+
"eval_samples_per_second": 6.263,
|
| 808 |
+
"eval_steps_per_second": 3.133,
|
| 809 |
+
"step": 104
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.1020408163265305,
|
| 813 |
+
"grad_norm": 0.21070216596126556,
|
| 814 |
+
"learning_rate": 9.662258581165319e-05,
|
| 815 |
+
"loss": 1.2808,
|
| 816 |
+
"step": 105
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.122448979591837,
|
| 820 |
+
"grad_norm": 0.21867221593856812,
|
| 821 |
+
"learning_rate": 9.493508311612874e-05,
|
| 822 |
+
"loss": 1.2873,
|
| 823 |
+
"step": 106
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.142857142857143,
|
| 827 |
+
"grad_norm": 0.21630822122097015,
|
| 828 |
+
"learning_rate": 9.324902531416349e-05,
|
| 829 |
+
"loss": 1.2527,
|
| 830 |
+
"step": 107
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.163265306122449,
|
| 834 |
+
"grad_norm": 0.2134082019329071,
|
| 835 |
+
"learning_rate": 9.156489339569554e-05,
|
| 836 |
+
"loss": 1.2755,
|
| 837 |
+
"step": 108
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.183673469387755,
|
| 841 |
+
"grad_norm": 0.22310714423656464,
|
| 842 |
+
"learning_rate": 8.98831678012568e-05,
|
| 843 |
+
"loss": 1.2512,
|
| 844 |
+
"step": 109
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.204081632653061,
|
| 848 |
+
"grad_norm": 0.2365124374628067,
|
| 849 |
+
"learning_rate": 8.820432828491542e-05,
|
| 850 |
+
"loss": 1.2725,
|
| 851 |
+
"step": 110
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.2244897959183674,
|
| 855 |
+
"grad_norm": 0.2086496651172638,
|
| 856 |
+
"learning_rate": 8.652885377741393e-05,
|
| 857 |
+
"loss": 1.2488,
|
| 858 |
+
"step": 111
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.2448979591836733,
|
| 862 |
+
"grad_norm": 0.20848101377487183,
|
| 863 |
+
"learning_rate": 8.485722224954237e-05,
|
| 864 |
+
"loss": 1.2793,
|
| 865 |
+
"step": 112
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.2653061224489797,
|
| 869 |
+
"grad_norm": 0.20784686505794525,
|
| 870 |
+
"learning_rate": 8.31899105757852e-05,
|
| 871 |
+
"loss": 1.2564,
|
| 872 |
+
"step": 113
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.2857142857142856,
|
| 876 |
+
"grad_norm": 0.21896174550056458,
|
| 877 |
+
"learning_rate": 8.15273943982811e-05,
|
| 878 |
+
"loss": 1.2515,
|
| 879 |
+
"step": 114
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.306122448979592,
|
| 883 |
+
"grad_norm": 0.21367855370044708,
|
| 884 |
+
"learning_rate": 7.987014799113397e-05,
|
| 885 |
+
"loss": 1.248,
|
| 886 |
+
"step": 115
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.326530612244898,
|
| 890 |
+
"grad_norm": 0.20891636610031128,
|
| 891 |
+
"learning_rate": 7.821864412511485e-05,
|
| 892 |
+
"loss": 1.2753,
|
| 893 |
+
"step": 116
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.3469387755102042,
|
| 897 |
+
"grad_norm": 0.2092975378036499,
|
| 898 |
+
"learning_rate": 7.65733539327918e-05,
|
| 899 |
+
"loss": 1.2509,
|
| 900 |
+
"step": 117
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.3469387755102042,
|
| 904 |
+
"eval_loss": 1.258699655532837,
|
| 905 |
+
"eval_runtime": 270.5384,
|
| 906 |
+
"eval_samples_per_second": 6.265,
|
| 907 |
+
"eval_steps_per_second": 3.134,
|
| 908 |
+
"step": 117
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.36734693877551,
|
| 912 |
+
"grad_norm": 0.1905972808599472,
|
| 913 |
+
"learning_rate": 7.493474677412794e-05,
|
| 914 |
+
"loss": 1.2516,
|
| 915 |
+
"step": 118
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.387755102040816,
|
| 919 |
+
"grad_norm": 0.19716158509254456,
|
| 920 |
+
"learning_rate": 7.330329010258483e-05,
|
| 921 |
+
"loss": 1.2665,
|
| 922 |
+
"step": 119
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.4081632653061225,
|
| 926 |
+
"grad_norm": 0.1953389048576355,
|
| 927 |
+
"learning_rate": 7.16794493317696e-05,
|
| 928 |
+
"loss": 1.2661,
|
| 929 |
+
"step": 120
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.4285714285714284,
|
| 933 |
+
"grad_norm": 0.1990067958831787,
|
| 934 |
+
"learning_rate": 7.006368770266421e-05,
|
| 935 |
+
"loss": 1.2619,
|
| 936 |
+
"step": 121
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.4489795918367347,
|
| 940 |
+
"grad_norm": 0.1954919546842575,
|
| 941 |
+
"learning_rate": 6.845646615147445e-05,
|
| 942 |
+
"loss": 1.2736,
|
| 943 |
+
"step": 122
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.4693877551020407,
|
| 947 |
+
"grad_norm": 0.18382853269577026,
|
| 948 |
+
"learning_rate": 6.685824317813643e-05,
|
| 949 |
+
"loss": 1.2732,
|
| 950 |
+
"step": 123
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.489795918367347,
|
| 954 |
+
"grad_norm": 0.18729491531848907,
|
| 955 |
+
"learning_rate": 6.526947471551798e-05,
|
| 956 |
+
"loss": 1.2509,
|
| 957 |
+
"step": 124
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.510204081632653,
|
| 961 |
+
"grad_norm": 0.2034740000963211,
|
| 962 |
+
"learning_rate": 6.369061399935255e-05,
|
| 963 |
+
"loss": 1.2829,
|
| 964 |
+
"step": 125
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.5306122448979593,
|
| 968 |
+
"grad_norm": 0.1952620893716812,
|
| 969 |
+
"learning_rate": 6.21221114389424e-05,
|
| 970 |
+
"loss": 1.2689,
|
| 971 |
+
"step": 126
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.5510204081632653,
|
| 975 |
+
"grad_norm": 0.1986168622970581,
|
| 976 |
+
"learning_rate": 6.0564414488668165e-05,
|
| 977 |
+
"loss": 1.2644,
|
| 978 |
+
"step": 127
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.571428571428571,
|
| 982 |
+
"grad_norm": 0.19526751339435577,
|
| 983 |
+
"learning_rate": 5.901796752034128e-05,
|
| 984 |
+
"loss": 1.265,
|
| 985 |
+
"step": 128
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.5918367346938775,
|
| 989 |
+
"grad_norm": 0.195367693901062,
|
| 990 |
+
"learning_rate": 5.748321169643596e-05,
|
| 991 |
+
"loss": 1.2782,
|
| 992 |
+
"step": 129
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.612244897959184,
|
| 996 |
+
"grad_norm": 0.18351928889751434,
|
| 997 |
+
"learning_rate": 5.596058484423656e-05,
|
| 998 |
+
"loss": 1.2884,
|
| 999 |
+
"step": 130
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.612244897959184,
|
| 1003 |
+
"eval_loss": 1.2471545934677124,
|
| 1004 |
+
"eval_runtime": 270.4953,
|
| 1005 |
+
"eval_samples_per_second": 6.266,
|
| 1006 |
+
"eval_steps_per_second": 3.135,
|
| 1007 |
+
"step": 130
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.63265306122449,
|
| 1011 |
+
"grad_norm": 0.2015760987997055,
|
| 1012 |
+
"learning_rate": 5.44505213309366e-05,
|
| 1013 |
+
"loss": 1.2536,
|
| 1014 |
+
"step": 131
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.6530612244897958,
|
| 1018 |
+
"grad_norm": 0.1734190732240677,
|
| 1019 |
+
"learning_rate": 5.2953451939724454e-05,
|
| 1020 |
+
"loss": 1.2628,
|
| 1021 |
+
"step": 132
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.673469387755102,
|
| 1025 |
+
"grad_norm": 0.214066281914711,
|
| 1026 |
+
"learning_rate": 5.146980374689192e-05,
|
| 1027 |
+
"loss": 1.2543,
|
| 1028 |
+
"step": 133
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.693877551020408,
|
| 1032 |
+
"grad_norm": 0.17507924139499664,
|
| 1033 |
+
"learning_rate": 5.000000000000002e-05,
|
| 1034 |
+
"loss": 1.2665,
|
| 1035 |
+
"step": 134
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.7142857142857144,
|
| 1039 |
+
"grad_norm": 0.1778109222650528,
|
| 1040 |
+
"learning_rate": 4.854445999713715e-05,
|
| 1041 |
+
"loss": 1.2789,
|
| 1042 |
+
"step": 135
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.7346938775510203,
|
| 1046 |
+
"grad_norm": 0.1856827288866043,
|
| 1047 |
+
"learning_rate": 4.710359896730379e-05,
|
| 1048 |
+
"loss": 1.2481,
|
| 1049 |
+
"step": 136
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.7551020408163263,
|
| 1053 |
+
"grad_norm": 0.17856694757938385,
|
| 1054 |
+
"learning_rate": 4.567782795195816e-05,
|
| 1055 |
+
"loss": 1.2732,
|
| 1056 |
+
"step": 137
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.7755102040816326,
|
| 1060 |
+
"grad_norm": 0.21598489582538605,
|
| 1061 |
+
"learning_rate": 4.426755368775637e-05,
|
| 1062 |
+
"loss": 1.2525,
|
| 1063 |
+
"step": 138
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.795918367346939,
|
| 1067 |
+
"grad_norm": 0.17308436334133148,
|
| 1068 |
+
"learning_rate": 4.287317849052075e-05,
|
| 1069 |
+
"loss": 1.2665,
|
| 1070 |
+
"step": 139
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 2.816326530612245,
|
| 1074 |
+
"grad_norm": 0.19207212328910828,
|
| 1075 |
+
"learning_rate": 4.149510014046922e-05,
|
| 1076 |
+
"loss": 1.2681,
|
| 1077 |
+
"step": 140
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.836734693877551,
|
| 1081 |
+
"grad_norm": 0.19626958668231964,
|
| 1082 |
+
"learning_rate": 4.013371176873849e-05,
|
| 1083 |
+
"loss": 1.2727,
|
| 1084 |
+
"step": 141
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 2.857142857142857,
|
| 1088 |
+
"grad_norm": 0.1986483484506607,
|
| 1089 |
+
"learning_rate": 3.878940174523371e-05,
|
| 1090 |
+
"loss": 1.2414,
|
| 1091 |
+
"step": 142
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.877551020408163,
|
| 1095 |
+
"grad_norm": 0.19369089603424072,
|
| 1096 |
+
"learning_rate": 3.746255356783632e-05,
|
| 1097 |
+
"loss": 1.254,
|
| 1098 |
+
"step": 143
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.877551020408163,
|
| 1102 |
+
"eval_loss": 1.2410293817520142,
|
| 1103 |
+
"eval_runtime": 270.6762,
|
| 1104 |
+
"eval_samples_per_second": 6.262,
|
| 1105 |
+
"eval_steps_per_second": 3.133,
|
| 1106 |
+
"step": 143
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.8979591836734695,
|
| 1110 |
+
"grad_norm": 0.20910531282424927,
|
| 1111 |
+
"learning_rate": 3.615354575300166e-05,
|
| 1112 |
+
"loss": 1.2541,
|
| 1113 |
+
"step": 144
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.9183673469387754,
|
| 1117 |
+
"grad_norm": 0.19536806643009186,
|
| 1118 |
+
"learning_rate": 3.4862751727777797e-05,
|
| 1119 |
+
"loss": 1.2517,
|
| 1120 |
+
"step": 145
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 2.938775510204082,
|
| 1124 |
+
"grad_norm": 0.18630966544151306,
|
| 1125 |
+
"learning_rate": 3.3590539723276083e-05,
|
| 1126 |
+
"loss": 1.2473,
|
| 1127 |
+
"step": 146
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.9591836734693877,
|
| 1131 |
+
"grad_norm": 0.1874723732471466,
|
| 1132 |
+
"learning_rate": 3.233727266962425e-05,
|
| 1133 |
+
"loss": 1.244,
|
| 1134 |
+
"step": 147
|
| 1135 |
+
}
|
| 1136 |
+
],
|
| 1137 |
+
"logging_steps": 1,
|
| 1138 |
+
"max_steps": 196,
|
| 1139 |
+
"num_input_tokens_seen": 0,
|
| 1140 |
+
"num_train_epochs": 4,
|
| 1141 |
+
"save_steps": 49,
|
| 1142 |
+
"total_flos": 3.0628052408991744e+16,
|
| 1143 |
+
"train_batch_size": 2,
|
| 1144 |
+
"trial_name": null,
|
| 1145 |
+
"trial_params": null
|
| 1146 |
+
}
|
checkpoint-147/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9cc4ff61a4799ac22d5c627a0169a20cc75619ae1b5871f2d114f95284d87a6
|
| 3 |
+
size 5816
|
checkpoint-196/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-196/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-196/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7149dfd1479c35b75fc75c4e9be3785070da91bd7c29d040e9a259ea5111014
|
| 3 |
+
size 100966336
|
checkpoint-196/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96f2429392a17aa7909b16091d5a0b62592f80090a1a9943b203b1e1c29e66f8
|
| 3 |
+
size 50916644
|
checkpoint-196/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a160c2864b63ef158843056f3ba263b2da60c6bef707459f056731cde2e27043
|
| 3 |
+
size 14244
|
checkpoint-196/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e22ca0a50bab80d00c8b8910bffb983a348f8762b7cf025e6f8e64a05a938289
|
| 3 |
+
size 1064
|
checkpoint-196/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-196/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-196/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false,
|
| 44 |
+
"use_fast": true
|
| 45 |
+
}
|
checkpoint-196/trainer_state.json
ADDED
|
@@ -0,0 +1,1521 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.938775510204082,
|
| 5 |
+
"eval_steps": 13,
|
| 6 |
+
"global_step": 196,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02040816326530612,
|
| 13 |
+
"grad_norm": 0.7881951332092285,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.7509,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02040816326530612,
|
| 20 |
+
"eval_loss": 2.6902382373809814,
|
| 21 |
+
"eval_runtime": 269.5606,
|
| 22 |
+
"eval_samples_per_second": 6.288,
|
| 23 |
+
"eval_steps_per_second": 3.146,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04081632653061224,
|
| 28 |
+
"grad_norm": 0.789082407951355,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 2.7449,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.061224489795918366,
|
| 35 |
+
"grad_norm": 0.7354114055633545,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 2.7164,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08163265306122448,
|
| 42 |
+
"grad_norm": 0.7292255759239197,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 2.7174,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10204081632653061,
|
| 49 |
+
"grad_norm": 0.6898028254508972,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 2.6891,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12244897959183673,
|
| 56 |
+
"grad_norm": 0.6861400604248047,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 2.6545,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14285714285714285,
|
| 63 |
+
"grad_norm": 0.7510350346565247,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 2.5656,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16326530612244897,
|
| 70 |
+
"grad_norm": 0.8011165261268616,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 2.4519,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1836734693877551,
|
| 77 |
+
"grad_norm": 0.8624005317687988,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 2.3178,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.20408163265306123,
|
| 84 |
+
"grad_norm": 0.8004987835884094,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 2.1783,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22448979591836735,
|
| 91 |
+
"grad_norm": 0.6362400054931641,
|
| 92 |
+
"learning_rate": 0.000199985736255971,
|
| 93 |
+
"loss": 2.0252,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24489795918367346,
|
| 98 |
+
"grad_norm": 0.7930936217308044,
|
| 99 |
+
"learning_rate": 0.0001999429490929718,
|
| 100 |
+
"loss": 1.8839,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2653061224489796,
|
| 105 |
+
"grad_norm": 0.5149843096733093,
|
| 106 |
+
"learning_rate": 0.00019987165071710527,
|
| 107 |
+
"loss": 1.8064,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2653061224489796,
|
| 112 |
+
"eval_loss": 1.6734941005706787,
|
| 113 |
+
"eval_runtime": 271.2615,
|
| 114 |
+
"eval_samples_per_second": 6.249,
|
| 115 |
+
"eval_steps_per_second": 3.126,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2857142857142857,
|
| 120 |
+
"grad_norm": 0.42121434211730957,
|
| 121 |
+
"learning_rate": 0.00019977186146800707,
|
| 122 |
+
"loss": 1.7922,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.30612244897959184,
|
| 127 |
+
"grad_norm": 0.3523242771625519,
|
| 128 |
+
"learning_rate": 0.0001996436098130433,
|
| 129 |
+
"loss": 1.7711,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.32653061224489793,
|
| 134 |
+
"grad_norm": 0.3384595215320587,
|
| 135 |
+
"learning_rate": 0.00019948693233918952,
|
| 136 |
+
"loss": 1.7152,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3469387755102041,
|
| 141 |
+
"grad_norm": 0.34942421317100525,
|
| 142 |
+
"learning_rate": 0.00019930187374259337,
|
| 143 |
+
"loss": 1.7112,
|
| 144 |
+
"step": 17
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3673469387755102,
|
| 148 |
+
"grad_norm": 0.31712639331817627,
|
| 149 |
+
"learning_rate": 0.00019908848681582391,
|
| 150 |
+
"loss": 1.7059,
|
| 151 |
+
"step": 18
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3877551020408163,
|
| 155 |
+
"grad_norm": 0.2875436842441559,
|
| 156 |
+
"learning_rate": 0.00019884683243281116,
|
| 157 |
+
"loss": 1.6468,
|
| 158 |
+
"step": 19
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.40816326530612246,
|
| 162 |
+
"grad_norm": 0.24433130025863647,
|
| 163 |
+
"learning_rate": 0.00019857697953148037,
|
| 164 |
+
"loss": 1.6408,
|
| 165 |
+
"step": 20
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.42857142857142855,
|
| 169 |
+
"grad_norm": 0.21414674818515778,
|
| 170 |
+
"learning_rate": 0.00019827900509408581,
|
| 171 |
+
"loss": 1.616,
|
| 172 |
+
"step": 21
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.4489795918367347,
|
| 176 |
+
"grad_norm": 0.21537622809410095,
|
| 177 |
+
"learning_rate": 0.00019795299412524945,
|
| 178 |
+
"loss": 1.609,
|
| 179 |
+
"step": 22
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.46938775510204084,
|
| 183 |
+
"grad_norm": 0.2432074397802353,
|
| 184 |
+
"learning_rate": 0.00019759903962771156,
|
| 185 |
+
"loss": 1.6066,
|
| 186 |
+
"step": 23
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4897959183673469,
|
| 190 |
+
"grad_norm": 0.2359839379787445,
|
| 191 |
+
"learning_rate": 0.00019721724257579907,
|
| 192 |
+
"loss": 1.5851,
|
| 193 |
+
"step": 24
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.5102040816326531,
|
| 197 |
+
"grad_norm": 0.22065888345241547,
|
| 198 |
+
"learning_rate": 0.00019680771188662044,
|
| 199 |
+
"loss": 1.5739,
|
| 200 |
+
"step": 25
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5306122448979592,
|
| 204 |
+
"grad_norm": 0.20339132845401764,
|
| 205 |
+
"learning_rate": 0.0001963705643889941,
|
| 206 |
+
"loss": 1.5513,
|
| 207 |
+
"step": 26
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5306122448979592,
|
| 211 |
+
"eval_loss": 1.4832030534744263,
|
| 212 |
+
"eval_runtime": 271.2449,
|
| 213 |
+
"eval_samples_per_second": 6.249,
|
| 214 |
+
"eval_steps_per_second": 3.126,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5510204081632653,
|
| 219 |
+
"grad_norm": 0.18875224888324738,
|
| 220 |
+
"learning_rate": 0.00019590592479012023,
|
| 221 |
+
"loss": 1.5378,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5714285714285714,
|
| 226 |
+
"grad_norm": 0.18564417958259583,
|
| 227 |
+
"learning_rate": 0.00019541392564000488,
|
| 228 |
+
"loss": 1.5212,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5918367346938775,
|
| 233 |
+
"grad_norm": 0.16226942837238312,
|
| 234 |
+
"learning_rate": 0.00019489470729364692,
|
| 235 |
+
"loss": 1.5391,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6122448979591837,
|
| 240 |
+
"grad_norm": 0.15650039911270142,
|
| 241 |
+
"learning_rate": 0.00019434841787099803,
|
| 242 |
+
"loss": 1.511,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6326530612244898,
|
| 247 |
+
"grad_norm": 0.15976540744304657,
|
| 248 |
+
"learning_rate": 0.00019377521321470805,
|
| 249 |
+
"loss": 1.5119,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6530612244897959,
|
| 254 |
+
"grad_norm": 0.16409288346767426,
|
| 255 |
+
"learning_rate": 0.00019317525684566685,
|
| 256 |
+
"loss": 1.4909,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.673469387755102,
|
| 261 |
+
"grad_norm": 0.15468019247055054,
|
| 262 |
+
"learning_rate": 0.00019254871991635598,
|
| 263 |
+
"loss": 1.4951,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6938775510204082,
|
| 268 |
+
"grad_norm": 0.1462036371231079,
|
| 269 |
+
"learning_rate": 0.00019189578116202307,
|
| 270 |
+
"loss": 1.4643,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7142857142857143,
|
| 275 |
+
"grad_norm": 0.1541963368654251,
|
| 276 |
+
"learning_rate": 0.00019121662684969335,
|
| 277 |
+
"loss": 1.5159,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7346938775510204,
|
| 282 |
+
"grad_norm": 0.14798064529895782,
|
| 283 |
+
"learning_rate": 0.00019051145072503215,
|
| 284 |
+
"loss": 1.4741,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.7551020408163265,
|
| 289 |
+
"grad_norm": 0.13914817571640015,
|
| 290 |
+
"learning_rate": 0.00018978045395707418,
|
| 291 |
+
"loss": 1.4788,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7755102040816326,
|
| 296 |
+
"grad_norm": 0.15608824789524078,
|
| 297 |
+
"learning_rate": 0.00018902384508083517,
|
| 298 |
+
"loss": 1.4687,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.7959183673469388,
|
| 303 |
+
"grad_norm": 0.14460116624832153,
|
| 304 |
+
"learning_rate": 0.00018824183993782192,
|
| 305 |
+
"loss": 1.482,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.7959183673469388,
|
| 310 |
+
"eval_loss": 1.411073088645935,
|
| 311 |
+
"eval_runtime": 271.292,
|
| 312 |
+
"eval_samples_per_second": 6.248,
|
| 313 |
+
"eval_steps_per_second": 3.126,
|
| 314 |
+
"step": 39
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8163265306122449,
|
| 318 |
+
"grad_norm": 0.15740551054477692,
|
| 319 |
+
"learning_rate": 0.00018743466161445823,
|
| 320 |
+
"loss": 1.4486,
|
| 321 |
+
"step": 40
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8367346938775511,
|
| 325 |
+
"grad_norm": 0.14149661362171173,
|
| 326 |
+
"learning_rate": 0.00018660254037844388,
|
| 327 |
+
"loss": 1.4353,
|
| 328 |
+
"step": 41
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8571428571428571,
|
| 332 |
+
"grad_norm": 0.14034292101860046,
|
| 333 |
+
"learning_rate": 0.0001857457136130651,
|
| 334 |
+
"loss": 1.4523,
|
| 335 |
+
"step": 42
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.8775510204081632,
|
| 339 |
+
"grad_norm": 0.1487722396850586,
|
| 340 |
+
"learning_rate": 0.00018486442574947511,
|
| 341 |
+
"loss": 1.4095,
|
| 342 |
+
"step": 43
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.8979591836734694,
|
| 346 |
+
"grad_norm": 0.17400234937667847,
|
| 347 |
+
"learning_rate": 0.00018395892819696389,
|
| 348 |
+
"loss": 1.4414,
|
| 349 |
+
"step": 44
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9183673469387755,
|
| 353 |
+
"grad_norm": 0.1741325408220291,
|
| 354 |
+
"learning_rate": 0.00018302947927123766,
|
| 355 |
+
"loss": 1.4379,
|
| 356 |
+
"step": 45
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9387755102040817,
|
| 360 |
+
"grad_norm": 0.15319454669952393,
|
| 361 |
+
"learning_rate": 0.00018207634412072764,
|
| 362 |
+
"loss": 1.405,
|
| 363 |
+
"step": 46
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9591836734693877,
|
| 367 |
+
"grad_norm": 0.15876264870166779,
|
| 368 |
+
"learning_rate": 0.00018109979465095013,
|
| 369 |
+
"loss": 1.4122,
|
| 370 |
+
"step": 47
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9795918367346939,
|
| 374 |
+
"grad_norm": 0.17120805382728577,
|
| 375 |
+
"learning_rate": 0.00018010010944693848,
|
| 376 |
+
"loss": 1.4132,
|
| 377 |
+
"step": 48
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.0,
|
| 381 |
+
"grad_norm": 0.1436116099357605,
|
| 382 |
+
"learning_rate": 0.00017907757369376985,
|
| 383 |
+
"loss": 1.416,
|
| 384 |
+
"step": 49
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.0204081632653061,
|
| 388 |
+
"grad_norm": 0.1707429438829422,
|
| 389 |
+
"learning_rate": 0.0001780324790952092,
|
| 390 |
+
"loss": 1.3913,
|
| 391 |
+
"step": 50
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.0204081632653061,
|
| 395 |
+
"grad_norm": 0.17117524147033691,
|
| 396 |
+
"learning_rate": 0.00017696512379049325,
|
| 397 |
+
"loss": 1.3963,
|
| 398 |
+
"step": 51
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.0408163265306123,
|
| 402 |
+
"grad_norm": 0.13410089910030365,
|
| 403 |
+
"learning_rate": 0.0001758758122692791,
|
| 404 |
+
"loss": 1.392,
|
| 405 |
+
"step": 52
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0408163265306123,
|
| 409 |
+
"eval_loss": 1.3676769733428955,
|
| 410 |
+
"eval_runtime": 270.8566,
|
| 411 |
+
"eval_samples_per_second": 6.258,
|
| 412 |
+
"eval_steps_per_second": 3.131,
|
| 413 |
+
"step": 52
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.0612244897959184,
|
| 417 |
+
"grad_norm": 0.18877607583999634,
|
| 418 |
+
"learning_rate": 0.00017476485528478093,
|
| 419 |
+
"loss": 1.3854,
|
| 420 |
+
"step": 53
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.0816326530612246,
|
| 424 |
+
"grad_norm": 0.1752927452325821,
|
| 425 |
+
"learning_rate": 0.00017363256976511972,
|
| 426 |
+
"loss": 1.3759,
|
| 427 |
+
"step": 54
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.1020408163265305,
|
| 431 |
+
"grad_norm": 0.17180170118808746,
|
| 432 |
+
"learning_rate": 0.000172479278722912,
|
| 433 |
+
"loss": 1.3614,
|
| 434 |
+
"step": 55
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1224489795918366,
|
| 438 |
+
"grad_norm": 0.1640290915966034,
|
| 439 |
+
"learning_rate": 0.00017130531116312203,
|
| 440 |
+
"loss": 1.3853,
|
| 441 |
+
"step": 56
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.1428571428571428,
|
| 445 |
+
"grad_norm": 0.2047068476676941,
|
| 446 |
+
"learning_rate": 0.0001701110019892053,
|
| 447 |
+
"loss": 1.3699,
|
| 448 |
+
"step": 57
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.163265306122449,
|
| 452 |
+
"grad_norm": 0.1835869997739792,
|
| 453 |
+
"learning_rate": 0.00016889669190756868,
|
| 454 |
+
"loss": 1.3403,
|
| 455 |
+
"step": 58
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.183673469387755,
|
| 459 |
+
"grad_norm": 0.16733241081237793,
|
| 460 |
+
"learning_rate": 0.00016766272733037576,
|
| 461 |
+
"loss": 1.3609,
|
| 462 |
+
"step": 59
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.2040816326530612,
|
| 466 |
+
"grad_norm": 0.178726926445961,
|
| 467 |
+
"learning_rate": 0.00016640946027672392,
|
| 468 |
+
"loss": 1.3651,
|
| 469 |
+
"step": 60
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.2244897959183674,
|
| 473 |
+
"grad_norm": 0.16719630360603333,
|
| 474 |
+
"learning_rate": 0.00016513724827222227,
|
| 475 |
+
"loss": 1.3676,
|
| 476 |
+
"step": 61
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.2448979591836735,
|
| 480 |
+
"grad_norm": 0.15999363362789154,
|
| 481 |
+
"learning_rate": 0.00016384645424699835,
|
| 482 |
+
"loss": 1.3651,
|
| 483 |
+
"step": 62
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2653061224489797,
|
| 487 |
+
"grad_norm": 0.1705988198518753,
|
| 488 |
+
"learning_rate": 0.00016253744643216368,
|
| 489 |
+
"loss": 1.3757,
|
| 490 |
+
"step": 63
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.2857142857142856,
|
| 494 |
+
"grad_norm": 0.14996370673179626,
|
| 495 |
+
"learning_rate": 0.0001612105982547663,
|
| 496 |
+
"loss": 1.3474,
|
| 497 |
+
"step": 64
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.306122448979592,
|
| 501 |
+
"grad_norm": 0.19127260148525238,
|
| 502 |
+
"learning_rate": 0.0001598662882312615,
|
| 503 |
+
"loss": 1.3414,
|
| 504 |
+
"step": 65
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.306122448979592,
|
| 508 |
+
"eval_loss": 1.331880807876587,
|
| 509 |
+
"eval_runtime": 270.8424,
|
| 510 |
+
"eval_samples_per_second": 6.258,
|
| 511 |
+
"eval_steps_per_second": 3.131,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.3265306122448979,
|
| 516 |
+
"grad_norm": 0.16125527024269104,
|
| 517 |
+
"learning_rate": 0.00015850489985953076,
|
| 518 |
+
"loss": 1.3509,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.346938775510204,
|
| 523 |
+
"grad_norm": 0.1979473978281021,
|
| 524 |
+
"learning_rate": 0.00015712682150947923,
|
| 525 |
+
"loss": 1.3579,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3673469387755102,
|
| 530 |
+
"grad_norm": 0.18317992985248566,
|
| 531 |
+
"learning_rate": 0.00015573244631224365,
|
| 532 |
+
"loss": 1.3341,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.3877551020408163,
|
| 537 |
+
"grad_norm": 0.1646898239850998,
|
| 538 |
+
"learning_rate": 0.0001543221720480419,
|
| 539 |
+
"loss": 1.3361,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.4081632653061225,
|
| 544 |
+
"grad_norm": 0.1760271042585373,
|
| 545 |
+
"learning_rate": 0.00015289640103269625,
|
| 546 |
+
"loss": 1.358,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.4285714285714286,
|
| 551 |
+
"grad_norm": 0.165283203125,
|
| 552 |
+
"learning_rate": 0.0001514555400028629,
|
| 553 |
+
"loss": 1.3072,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.4489795918367347,
|
| 558 |
+
"grad_norm": 0.1507076472043991,
|
| 559 |
+
"learning_rate": 0.00015000000000000001,
|
| 560 |
+
"loss": 1.3133,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.469387755102041,
|
| 565 |
+
"grad_norm": 0.16913647949695587,
|
| 566 |
+
"learning_rate": 0.00014853019625310813,
|
| 567 |
+
"loss": 1.3232,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.489795918367347,
|
| 572 |
+
"grad_norm": 0.18266479671001434,
|
| 573 |
+
"learning_rate": 0.0001470465480602756,
|
| 574 |
+
"loss": 1.3512,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.510204081632653,
|
| 579 |
+
"grad_norm": 0.19301828742027283,
|
| 580 |
+
"learning_rate": 0.0001455494786690634,
|
| 581 |
+
"loss": 1.3241,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.5306122448979593,
|
| 586 |
+
"grad_norm": 0.16109652817249298,
|
| 587 |
+
"learning_rate": 0.00014403941515576344,
|
| 588 |
+
"loss": 1.3256,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.5510204081632653,
|
| 593 |
+
"grad_norm": 0.17053867876529694,
|
| 594 |
+
"learning_rate": 0.00014251678830356408,
|
| 595 |
+
"loss": 1.3162,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.5714285714285714,
|
| 600 |
+
"grad_norm": 0.17348544299602509,
|
| 601 |
+
"learning_rate": 0.00014098203247965875,
|
| 602 |
+
"loss": 1.3213,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.5714285714285714,
|
| 607 |
+
"eval_loss": 1.3028697967529297,
|
| 608 |
+
"eval_runtime": 270.8095,
|
| 609 |
+
"eval_samples_per_second": 6.259,
|
| 610 |
+
"eval_steps_per_second": 3.131,
|
| 611 |
+
"step": 78
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.5918367346938775,
|
| 615 |
+
"grad_norm": 0.1703907549381256,
|
| 616 |
+
"learning_rate": 0.00013943558551133186,
|
| 617 |
+
"loss": 1.3073,
|
| 618 |
+
"step": 79
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.6122448979591837,
|
| 622 |
+
"grad_norm": 0.17313100397586823,
|
| 623 |
+
"learning_rate": 0.0001378778885610576,
|
| 624 |
+
"loss": 1.3232,
|
| 625 |
+
"step": 80
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6326530612244898,
|
| 629 |
+
"grad_norm": 0.17237025499343872,
|
| 630 |
+
"learning_rate": 0.00013630938600064747,
|
| 631 |
+
"loss": 1.3406,
|
| 632 |
+
"step": 81
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6530612244897958,
|
| 636 |
+
"grad_norm": 0.19658459722995758,
|
| 637 |
+
"learning_rate": 0.00013473052528448201,
|
| 638 |
+
"loss": 1.3114,
|
| 639 |
+
"step": 82
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6734693877551021,
|
| 643 |
+
"grad_norm": 0.20599938929080963,
|
| 644 |
+
"learning_rate": 0.0001331417568218636,
|
| 645 |
+
"loss": 1.3288,
|
| 646 |
+
"step": 83
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.693877551020408,
|
| 650 |
+
"grad_norm": 0.17759399116039276,
|
| 651 |
+
"learning_rate": 0.00013154353384852558,
|
| 652 |
+
"loss": 1.2995,
|
| 653 |
+
"step": 84
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.7142857142857144,
|
| 657 |
+
"grad_norm": 0.18712250888347626,
|
| 658 |
+
"learning_rate": 0.00012993631229733582,
|
| 659 |
+
"loss": 1.2895,
|
| 660 |
+
"step": 85
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7346938775510203,
|
| 664 |
+
"grad_norm": 0.1991330236196518,
|
| 665 |
+
"learning_rate": 0.00012832055066823038,
|
| 666 |
+
"loss": 1.2886,
|
| 667 |
+
"step": 86
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.7551020408163265,
|
| 671 |
+
"grad_norm": 0.22125203907489777,
|
| 672 |
+
"learning_rate": 0.00012669670989741517,
|
| 673 |
+
"loss": 1.3233,
|
| 674 |
+
"step": 87
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.7755102040816326,
|
| 678 |
+
"grad_norm": 0.2052813619375229,
|
| 679 |
+
"learning_rate": 0.00012506525322587207,
|
| 680 |
+
"loss": 1.3079,
|
| 681 |
+
"step": 88
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.7959183673469388,
|
| 685 |
+
"grad_norm": 0.19290736317634583,
|
| 686 |
+
"learning_rate": 0.00012342664606720822,
|
| 687 |
+
"loss": 1.3174,
|
| 688 |
+
"step": 89
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.816326530612245,
|
| 692 |
+
"grad_norm": 0.20912542939186096,
|
| 693 |
+
"learning_rate": 0.00012178135587488515,
|
| 694 |
+
"loss": 1.2915,
|
| 695 |
+
"step": 90
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.836734693877551,
|
| 699 |
+
"grad_norm": 0.20760588347911835,
|
| 700 |
+
"learning_rate": 0.00012012985200886602,
|
| 701 |
+
"loss": 1.3028,
|
| 702 |
+
"step": 91
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.836734693877551,
|
| 706 |
+
"eval_loss": 1.2795333862304688,
|
| 707 |
+
"eval_runtime": 270.6525,
|
| 708 |
+
"eval_samples_per_second": 6.263,
|
| 709 |
+
"eval_steps_per_second": 3.133,
|
| 710 |
+
"step": 91
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.8571428571428572,
|
| 714 |
+
"grad_norm": 0.1996900886297226,
|
| 715 |
+
"learning_rate": 0.00011847260560171896,
|
| 716 |
+
"loss": 1.3119,
|
| 717 |
+
"step": 92
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.8775510204081631,
|
| 721 |
+
"grad_norm": 0.23766876757144928,
|
| 722 |
+
"learning_rate": 0.00011681008942421483,
|
| 723 |
+
"loss": 1.2978,
|
| 724 |
+
"step": 93
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.8979591836734695,
|
| 728 |
+
"grad_norm": 0.19782397150993347,
|
| 729 |
+
"learning_rate": 0.00011514277775045768,
|
| 730 |
+
"loss": 1.2955,
|
| 731 |
+
"step": 94
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9183673469387754,
|
| 735 |
+
"grad_norm": 0.22519494593143463,
|
| 736 |
+
"learning_rate": 0.00011347114622258612,
|
| 737 |
+
"loss": 1.2957,
|
| 738 |
+
"step": 95
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.9387755102040818,
|
| 742 |
+
"grad_norm": 0.2590245306491852,
|
| 743 |
+
"learning_rate": 0.00011179567171508463,
|
| 744 |
+
"loss": 1.2809,
|
| 745 |
+
"step": 96
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.9591836734693877,
|
| 749 |
+
"grad_norm": 0.2235420197248459,
|
| 750 |
+
"learning_rate": 0.00011011683219874323,
|
| 751 |
+
"loss": 1.2784,
|
| 752 |
+
"step": 97
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.9795918367346939,
|
| 756 |
+
"grad_norm": 0.285740464925766,
|
| 757 |
+
"learning_rate": 0.00010843510660430447,
|
| 758 |
+
"loss": 1.309,
|
| 759 |
+
"step": 98
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.0,
|
| 763 |
+
"grad_norm": 0.20554350316524506,
|
| 764 |
+
"learning_rate": 0.00010675097468583652,
|
| 765 |
+
"loss": 1.273,
|
| 766 |
+
"step": 99
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.020408163265306,
|
| 770 |
+
"grad_norm": 0.24468418955802917,
|
| 771 |
+
"learning_rate": 0.00010506491688387127,
|
| 772 |
+
"loss": 1.2833,
|
| 773 |
+
"step": 100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.020408163265306,
|
| 777 |
+
"grad_norm": 0.21553528308868408,
|
| 778 |
+
"learning_rate": 0.00010337741418834684,
|
| 779 |
+
"loss": 1.2669,
|
| 780 |
+
"step": 101
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.0408163265306123,
|
| 784 |
+
"grad_norm": 0.22015659511089325,
|
| 785 |
+
"learning_rate": 0.0001016889480013931,
|
| 786 |
+
"loss": 1.2795,
|
| 787 |
+
"step": 102
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.061224489795918,
|
| 791 |
+
"grad_norm": 0.2028799206018448,
|
| 792 |
+
"learning_rate": 0.0001,
|
| 793 |
+
"loss": 1.2584,
|
| 794 |
+
"step": 103
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.0816326530612246,
|
| 798 |
+
"grad_norm": 0.23474323749542236,
|
| 799 |
+
"learning_rate": 9.83110519986069e-05,
|
| 800 |
+
"loss": 1.2761,
|
| 801 |
+
"step": 104
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.0816326530612246,
|
| 805 |
+
"eval_loss": 1.2696796655654907,
|
| 806 |
+
"eval_runtime": 270.6586,
|
| 807 |
+
"eval_samples_per_second": 6.263,
|
| 808 |
+
"eval_steps_per_second": 3.133,
|
| 809 |
+
"step": 104
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.1020408163265305,
|
| 813 |
+
"grad_norm": 0.21070216596126556,
|
| 814 |
+
"learning_rate": 9.662258581165319e-05,
|
| 815 |
+
"loss": 1.2808,
|
| 816 |
+
"step": 105
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.122448979591837,
|
| 820 |
+
"grad_norm": 0.21867221593856812,
|
| 821 |
+
"learning_rate": 9.493508311612874e-05,
|
| 822 |
+
"loss": 1.2873,
|
| 823 |
+
"step": 106
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.142857142857143,
|
| 827 |
+
"grad_norm": 0.21630822122097015,
|
| 828 |
+
"learning_rate": 9.324902531416349e-05,
|
| 829 |
+
"loss": 1.2527,
|
| 830 |
+
"step": 107
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.163265306122449,
|
| 834 |
+
"grad_norm": 0.2134082019329071,
|
| 835 |
+
"learning_rate": 9.156489339569554e-05,
|
| 836 |
+
"loss": 1.2755,
|
| 837 |
+
"step": 108
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.183673469387755,
|
| 841 |
+
"grad_norm": 0.22310714423656464,
|
| 842 |
+
"learning_rate": 8.98831678012568e-05,
|
| 843 |
+
"loss": 1.2512,
|
| 844 |
+
"step": 109
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.204081632653061,
|
| 848 |
+
"grad_norm": 0.2365124374628067,
|
| 849 |
+
"learning_rate": 8.820432828491542e-05,
|
| 850 |
+
"loss": 1.2725,
|
| 851 |
+
"step": 110
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.2244897959183674,
|
| 855 |
+
"grad_norm": 0.2086496651172638,
|
| 856 |
+
"learning_rate": 8.652885377741393e-05,
|
| 857 |
+
"loss": 1.2488,
|
| 858 |
+
"step": 111
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.2448979591836733,
|
| 862 |
+
"grad_norm": 0.20848101377487183,
|
| 863 |
+
"learning_rate": 8.485722224954237e-05,
|
| 864 |
+
"loss": 1.2793,
|
| 865 |
+
"step": 112
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.2653061224489797,
|
| 869 |
+
"grad_norm": 0.20784686505794525,
|
| 870 |
+
"learning_rate": 8.31899105757852e-05,
|
| 871 |
+
"loss": 1.2564,
|
| 872 |
+
"step": 113
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.2857142857142856,
|
| 876 |
+
"grad_norm": 0.21896174550056458,
|
| 877 |
+
"learning_rate": 8.15273943982811e-05,
|
| 878 |
+
"loss": 1.2515,
|
| 879 |
+
"step": 114
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.306122448979592,
|
| 883 |
+
"grad_norm": 0.21367855370044708,
|
| 884 |
+
"learning_rate": 7.987014799113397e-05,
|
| 885 |
+
"loss": 1.248,
|
| 886 |
+
"step": 115
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.326530612244898,
|
| 890 |
+
"grad_norm": 0.20891636610031128,
|
| 891 |
+
"learning_rate": 7.821864412511485e-05,
|
| 892 |
+
"loss": 1.2753,
|
| 893 |
+
"step": 116
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.3469387755102042,
|
| 897 |
+
"grad_norm": 0.2092975378036499,
|
| 898 |
+
"learning_rate": 7.65733539327918e-05,
|
| 899 |
+
"loss": 1.2509,
|
| 900 |
+
"step": 117
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.3469387755102042,
|
| 904 |
+
"eval_loss": 1.258699655532837,
|
| 905 |
+
"eval_runtime": 270.5384,
|
| 906 |
+
"eval_samples_per_second": 6.265,
|
| 907 |
+
"eval_steps_per_second": 3.134,
|
| 908 |
+
"step": 117
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.36734693877551,
|
| 912 |
+
"grad_norm": 0.1905972808599472,
|
| 913 |
+
"learning_rate": 7.493474677412794e-05,
|
| 914 |
+
"loss": 1.2516,
|
| 915 |
+
"step": 118
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.387755102040816,
|
| 919 |
+
"grad_norm": 0.19716158509254456,
|
| 920 |
+
"learning_rate": 7.330329010258483e-05,
|
| 921 |
+
"loss": 1.2665,
|
| 922 |
+
"step": 119
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.4081632653061225,
|
| 926 |
+
"grad_norm": 0.1953389048576355,
|
| 927 |
+
"learning_rate": 7.16794493317696e-05,
|
| 928 |
+
"loss": 1.2661,
|
| 929 |
+
"step": 120
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.4285714285714284,
|
| 933 |
+
"grad_norm": 0.1990067958831787,
|
| 934 |
+
"learning_rate": 7.006368770266421e-05,
|
| 935 |
+
"loss": 1.2619,
|
| 936 |
+
"step": 121
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.4489795918367347,
|
| 940 |
+
"grad_norm": 0.1954919546842575,
|
| 941 |
+
"learning_rate": 6.845646615147445e-05,
|
| 942 |
+
"loss": 1.2736,
|
| 943 |
+
"step": 122
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.4693877551020407,
|
| 947 |
+
"grad_norm": 0.18382853269577026,
|
| 948 |
+
"learning_rate": 6.685824317813643e-05,
|
| 949 |
+
"loss": 1.2732,
|
| 950 |
+
"step": 123
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.489795918367347,
|
| 954 |
+
"grad_norm": 0.18729491531848907,
|
| 955 |
+
"learning_rate": 6.526947471551798e-05,
|
| 956 |
+
"loss": 1.2509,
|
| 957 |
+
"step": 124
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.510204081632653,
|
| 961 |
+
"grad_norm": 0.2034740000963211,
|
| 962 |
+
"learning_rate": 6.369061399935255e-05,
|
| 963 |
+
"loss": 1.2829,
|
| 964 |
+
"step": 125
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.5306122448979593,
|
| 968 |
+
"grad_norm": 0.1952620893716812,
|
| 969 |
+
"learning_rate": 6.21221114389424e-05,
|
| 970 |
+
"loss": 1.2689,
|
| 971 |
+
"step": 126
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.5510204081632653,
|
| 975 |
+
"grad_norm": 0.1986168622970581,
|
| 976 |
+
"learning_rate": 6.0564414488668165e-05,
|
| 977 |
+
"loss": 1.2644,
|
| 978 |
+
"step": 127
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.571428571428571,
|
| 982 |
+
"grad_norm": 0.19526751339435577,
|
| 983 |
+
"learning_rate": 5.901796752034128e-05,
|
| 984 |
+
"loss": 1.265,
|
| 985 |
+
"step": 128
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.5918367346938775,
|
| 989 |
+
"grad_norm": 0.195367693901062,
|
| 990 |
+
"learning_rate": 5.748321169643596e-05,
|
| 991 |
+
"loss": 1.2782,
|
| 992 |
+
"step": 129
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.612244897959184,
|
| 996 |
+
"grad_norm": 0.18351928889751434,
|
| 997 |
+
"learning_rate": 5.596058484423656e-05,
|
| 998 |
+
"loss": 1.2884,
|
| 999 |
+
"step": 130
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.612244897959184,
|
| 1003 |
+
"eval_loss": 1.2471545934677124,
|
| 1004 |
+
"eval_runtime": 270.4953,
|
| 1005 |
+
"eval_samples_per_second": 6.266,
|
| 1006 |
+
"eval_steps_per_second": 3.135,
|
| 1007 |
+
"step": 130
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.63265306122449,
|
| 1011 |
+
"grad_norm": 0.2015760987997055,
|
| 1012 |
+
"learning_rate": 5.44505213309366e-05,
|
| 1013 |
+
"loss": 1.2536,
|
| 1014 |
+
"step": 131
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.6530612244897958,
|
| 1018 |
+
"grad_norm": 0.1734190732240677,
|
| 1019 |
+
"learning_rate": 5.2953451939724454e-05,
|
| 1020 |
+
"loss": 1.2628,
|
| 1021 |
+
"step": 132
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.673469387755102,
|
| 1025 |
+
"grad_norm": 0.214066281914711,
|
| 1026 |
+
"learning_rate": 5.146980374689192e-05,
|
| 1027 |
+
"loss": 1.2543,
|
| 1028 |
+
"step": 133
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.693877551020408,
|
| 1032 |
+
"grad_norm": 0.17507924139499664,
|
| 1033 |
+
"learning_rate": 5.000000000000002e-05,
|
| 1034 |
+
"loss": 1.2665,
|
| 1035 |
+
"step": 134
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.7142857142857144,
|
| 1039 |
+
"grad_norm": 0.1778109222650528,
|
| 1040 |
+
"learning_rate": 4.854445999713715e-05,
|
| 1041 |
+
"loss": 1.2789,
|
| 1042 |
+
"step": 135
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.7346938775510203,
|
| 1046 |
+
"grad_norm": 0.1856827288866043,
|
| 1047 |
+
"learning_rate": 4.710359896730379e-05,
|
| 1048 |
+
"loss": 1.2481,
|
| 1049 |
+
"step": 136
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.7551020408163263,
|
| 1053 |
+
"grad_norm": 0.17856694757938385,
|
| 1054 |
+
"learning_rate": 4.567782795195816e-05,
|
| 1055 |
+
"loss": 1.2732,
|
| 1056 |
+
"step": 137
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.7755102040816326,
|
| 1060 |
+
"grad_norm": 0.21598489582538605,
|
| 1061 |
+
"learning_rate": 4.426755368775637e-05,
|
| 1062 |
+
"loss": 1.2525,
|
| 1063 |
+
"step": 138
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.795918367346939,
|
| 1067 |
+
"grad_norm": 0.17308436334133148,
|
| 1068 |
+
"learning_rate": 4.287317849052075e-05,
|
| 1069 |
+
"loss": 1.2665,
|
| 1070 |
+
"step": 139
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 2.816326530612245,
|
| 1074 |
+
"grad_norm": 0.19207212328910828,
|
| 1075 |
+
"learning_rate": 4.149510014046922e-05,
|
| 1076 |
+
"loss": 1.2681,
|
| 1077 |
+
"step": 140
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.836734693877551,
|
| 1081 |
+
"grad_norm": 0.19626958668231964,
|
| 1082 |
+
"learning_rate": 4.013371176873849e-05,
|
| 1083 |
+
"loss": 1.2727,
|
| 1084 |
+
"step": 141
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 2.857142857142857,
|
| 1088 |
+
"grad_norm": 0.1986483484506607,
|
| 1089 |
+
"learning_rate": 3.878940174523371e-05,
|
| 1090 |
+
"loss": 1.2414,
|
| 1091 |
+
"step": 142
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.877551020408163,
|
| 1095 |
+
"grad_norm": 0.19369089603424072,
|
| 1096 |
+
"learning_rate": 3.746255356783632e-05,
|
| 1097 |
+
"loss": 1.254,
|
| 1098 |
+
"step": 143
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.877551020408163,
|
| 1102 |
+
"eval_loss": 1.2410293817520142,
|
| 1103 |
+
"eval_runtime": 270.6762,
|
| 1104 |
+
"eval_samples_per_second": 6.262,
|
| 1105 |
+
"eval_steps_per_second": 3.133,
|
| 1106 |
+
"step": 143
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.8979591836734695,
|
| 1110 |
+
"grad_norm": 0.20910531282424927,
|
| 1111 |
+
"learning_rate": 3.615354575300166e-05,
|
| 1112 |
+
"loss": 1.2541,
|
| 1113 |
+
"step": 144
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.9183673469387754,
|
| 1117 |
+
"grad_norm": 0.19536806643009186,
|
| 1118 |
+
"learning_rate": 3.4862751727777797e-05,
|
| 1119 |
+
"loss": 1.2517,
|
| 1120 |
+
"step": 145
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 2.938775510204082,
|
| 1124 |
+
"grad_norm": 0.18630966544151306,
|
| 1125 |
+
"learning_rate": 3.3590539723276083e-05,
|
| 1126 |
+
"loss": 1.2473,
|
| 1127 |
+
"step": 146
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.9591836734693877,
|
| 1131 |
+
"grad_norm": 0.1874723732471466,
|
| 1132 |
+
"learning_rate": 3.233727266962425e-05,
|
| 1133 |
+
"loss": 1.244,
|
| 1134 |
+
"step": 147
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.979591836734694,
|
| 1138 |
+
"grad_norm": 0.1764463186264038,
|
| 1139 |
+
"learning_rate": 3.110330809243134e-05,
|
| 1140 |
+
"loss": 1.2465,
|
| 1141 |
+
"step": 148
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 3.0,
|
| 1145 |
+
"grad_norm": 0.16570010781288147,
|
| 1146 |
+
"learning_rate": 2.9888998010794743e-05,
|
| 1147 |
+
"loss": 1.2443,
|
| 1148 |
+
"step": 149
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.020408163265306,
|
| 1152 |
+
"grad_norm": 0.18820856511592865,
|
| 1153 |
+
"learning_rate": 2.869468883687798e-05,
|
| 1154 |
+
"loss": 1.2694,
|
| 1155 |
+
"step": 150
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.020408163265306,
|
| 1159 |
+
"grad_norm": 0.2009415626525879,
|
| 1160 |
+
"learning_rate": 2.7520721277088024e-05,
|
| 1161 |
+
"loss": 1.2185,
|
| 1162 |
+
"step": 151
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 3.0408163265306123,
|
| 1166 |
+
"grad_norm": 0.1824546605348587,
|
| 1167 |
+
"learning_rate": 2.6367430234880284e-05,
|
| 1168 |
+
"loss": 1.2222,
|
| 1169 |
+
"step": 152
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 3.061224489795918,
|
| 1173 |
+
"grad_norm": 0.180531844496727,
|
| 1174 |
+
"learning_rate": 2.523514471521913e-05,
|
| 1175 |
+
"loss": 1.2592,
|
| 1176 |
+
"step": 153
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 3.0816326530612246,
|
| 1180 |
+
"grad_norm": 0.17422904074192047,
|
| 1181 |
+
"learning_rate": 2.4124187730720917e-05,
|
| 1182 |
+
"loss": 1.2429,
|
| 1183 |
+
"step": 154
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 3.1020408163265305,
|
| 1187 |
+
"grad_norm": 0.17531636357307434,
|
| 1188 |
+
"learning_rate": 2.3034876209506772e-05,
|
| 1189 |
+
"loss": 1.2459,
|
| 1190 |
+
"step": 155
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.122448979591837,
|
| 1194 |
+
"grad_norm": 0.17256909608840942,
|
| 1195 |
+
"learning_rate": 2.1967520904790827e-05,
|
| 1196 |
+
"loss": 1.2523,
|
| 1197 |
+
"step": 156
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.122448979591837,
|
| 1201 |
+
"eval_loss": 1.240277886390686,
|
| 1202 |
+
"eval_runtime": 270.7279,
|
| 1203 |
+
"eval_samples_per_second": 6.261,
|
| 1204 |
+
"eval_steps_per_second": 3.132,
|
| 1205 |
+
"step": 156
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 3.142857142857143,
|
| 1209 |
+
"grad_norm": 0.17711801826953888,
|
| 1210 |
+
"learning_rate": 2.092242630623016e-05,
|
| 1211 |
+
"loss": 1.2416,
|
| 1212 |
+
"step": 157
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 3.163265306122449,
|
| 1216 |
+
"grad_norm": 0.1642543524503708,
|
| 1217 |
+
"learning_rate": 1.9899890553061562e-05,
|
| 1218 |
+
"loss": 1.2563,
|
| 1219 |
+
"step": 158
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 3.183673469387755,
|
| 1223 |
+
"grad_norm": 0.17609795928001404,
|
| 1224 |
+
"learning_rate": 1.8900205349049904e-05,
|
| 1225 |
+
"loss": 1.2406,
|
| 1226 |
+
"step": 159
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.204081632653061,
|
| 1230 |
+
"grad_norm": 0.18534283339977264,
|
| 1231 |
+
"learning_rate": 1.7923655879272393e-05,
|
| 1232 |
+
"loss": 1.2522,
|
| 1233 |
+
"step": 160
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 3.2244897959183674,
|
| 1237 |
+
"grad_norm": 0.17926208674907684,
|
| 1238 |
+
"learning_rate": 1.6970520728762375e-05,
|
| 1239 |
+
"loss": 1.2315,
|
| 1240 |
+
"step": 161
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 3.2448979591836733,
|
| 1244 |
+
"grad_norm": 0.18245543539524078,
|
| 1245 |
+
"learning_rate": 1.60410718030361e-05,
|
| 1246 |
+
"loss": 1.2493,
|
| 1247 |
+
"step": 162
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 3.2653061224489797,
|
| 1251 |
+
"grad_norm": 0.16576482355594635,
|
| 1252 |
+
"learning_rate": 1.5135574250524897e-05,
|
| 1253 |
+
"loss": 1.2633,
|
| 1254 |
+
"step": 163
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 3.2857142857142856,
|
| 1258 |
+
"grad_norm": 0.1768399477005005,
|
| 1259 |
+
"learning_rate": 1.425428638693489e-05,
|
| 1260 |
+
"loss": 1.2399,
|
| 1261 |
+
"step": 164
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 3.306122448979592,
|
| 1265 |
+
"grad_norm": 0.17402540147304535,
|
| 1266 |
+
"learning_rate": 1.339745962155613e-05,
|
| 1267 |
+
"loss": 1.2574,
|
| 1268 |
+
"step": 165
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 3.326530612244898,
|
| 1272 |
+
"grad_norm": 0.17550399899482727,
|
| 1273 |
+
"learning_rate": 1.2565338385541792e-05,
|
| 1274 |
+
"loss": 1.2429,
|
| 1275 |
+
"step": 166
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.3469387755102042,
|
| 1279 |
+
"grad_norm": 0.18776686489582062,
|
| 1280 |
+
"learning_rate": 1.1758160062178093e-05,
|
| 1281 |
+
"loss": 1.2378,
|
| 1282 |
+
"step": 167
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 3.36734693877551,
|
| 1286 |
+
"grad_norm": 0.1816324144601822,
|
| 1287 |
+
"learning_rate": 1.097615491916485e-05,
|
| 1288 |
+
"loss": 1.2503,
|
| 1289 |
+
"step": 168
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 3.387755102040816,
|
| 1293 |
+
"grad_norm": 0.17802877724170685,
|
| 1294 |
+
"learning_rate": 1.0219546042925843e-05,
|
| 1295 |
+
"loss": 1.2468,
|
| 1296 |
+
"step": 169
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 3.387755102040816,
|
| 1300 |
+
"eval_loss": 1.2385426759719849,
|
| 1301 |
+
"eval_runtime": 270.6389,
|
| 1302 |
+
"eval_samples_per_second": 6.263,
|
| 1303 |
+
"eval_steps_per_second": 3.133,
|
| 1304 |
+
"step": 169
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.4081632653061225,
|
| 1308 |
+
"grad_norm": 0.1731177568435669,
|
| 1309 |
+
"learning_rate": 9.488549274967872e-06,
|
| 1310 |
+
"loss": 1.2431,
|
| 1311 |
+
"step": 170
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.4285714285714284,
|
| 1315 |
+
"grad_norm": 0.16203820705413818,
|
| 1316 |
+
"learning_rate": 8.783373150306661e-06,
|
| 1317 |
+
"loss": 1.2394,
|
| 1318 |
+
"step": 171
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 3.4489795918367347,
|
| 1322 |
+
"grad_norm": 0.1603914201259613,
|
| 1323 |
+
"learning_rate": 8.10421883797694e-06,
|
| 1324 |
+
"loss": 1.2317,
|
| 1325 |
+
"step": 172
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 3.4693877551020407,
|
| 1329 |
+
"grad_norm": 0.16672447323799133,
|
| 1330 |
+
"learning_rate": 7.4512800836440525e-06,
|
| 1331 |
+
"loss": 1.2382,
|
| 1332 |
+
"step": 173
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 3.489795918367347,
|
| 1336 |
+
"grad_norm": 0.16903318464756012,
|
| 1337 |
+
"learning_rate": 6.824743154333157e-06,
|
| 1338 |
+
"loss": 1.2406,
|
| 1339 |
+
"step": 174
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 3.510204081632653,
|
| 1343 |
+
"grad_norm": 0.16718582808971405,
|
| 1344 |
+
"learning_rate": 6.22478678529197e-06,
|
| 1345 |
+
"loss": 1.2253,
|
| 1346 |
+
"step": 175
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 3.5306122448979593,
|
| 1350 |
+
"grad_norm": 0.16773243248462677,
|
| 1351 |
+
"learning_rate": 5.651582129001986e-06,
|
| 1352 |
+
"loss": 1.2545,
|
| 1353 |
+
"step": 176
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.5510204081632653,
|
| 1357 |
+
"grad_norm": 0.16658060252666473,
|
| 1358 |
+
"learning_rate": 5.105292706353093e-06,
|
| 1359 |
+
"loss": 1.2329,
|
| 1360 |
+
"step": 177
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 3.571428571428571,
|
| 1364 |
+
"grad_norm": 0.16760899126529694,
|
| 1365 |
+
"learning_rate": 4.586074359995119e-06,
|
| 1366 |
+
"loss": 1.2218,
|
| 1367 |
+
"step": 178
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 3.5918367346938775,
|
| 1371 |
+
"grad_norm": 0.17462213337421417,
|
| 1372 |
+
"learning_rate": 4.094075209879788e-06,
|
| 1373 |
+
"loss": 1.236,
|
| 1374 |
+
"step": 179
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.612244897959184,
|
| 1378 |
+
"grad_norm": 0.16253593564033508,
|
| 1379 |
+
"learning_rate": 3.6294356110059157e-06,
|
| 1380 |
+
"loss": 1.2518,
|
| 1381 |
+
"step": 180
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.63265306122449,
|
| 1385 |
+
"grad_norm": 0.16653120517730713,
|
| 1386 |
+
"learning_rate": 3.1922881133795825e-06,
|
| 1387 |
+
"loss": 1.2171,
|
| 1388 |
+
"step": 181
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 3.6530612244897958,
|
| 1392 |
+
"grad_norm": 0.1757594645023346,
|
| 1393 |
+
"learning_rate": 2.7827574242009437e-06,
|
| 1394 |
+
"loss": 1.2476,
|
| 1395 |
+
"step": 182
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.6530612244897958,
|
| 1399 |
+
"eval_loss": 1.237037181854248,
|
| 1400 |
+
"eval_runtime": 270.3815,
|
| 1401 |
+
"eval_samples_per_second": 6.269,
|
| 1402 |
+
"eval_steps_per_second": 3.136,
|
| 1403 |
+
"step": 182
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.673469387755102,
|
| 1407 |
+
"grad_norm": 0.1665186882019043,
|
| 1408 |
+
"learning_rate": 2.4009603722884742e-06,
|
| 1409 |
+
"loss": 1.2497,
|
| 1410 |
+
"step": 183
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.693877551020408,
|
| 1414 |
+
"grad_norm": 0.17469817399978638,
|
| 1415 |
+
"learning_rate": 2.0470058747505516e-06,
|
| 1416 |
+
"loss": 1.2426,
|
| 1417 |
+
"step": 184
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.7142857142857144,
|
| 1421 |
+
"grad_norm": 0.17130160331726074,
|
| 1422 |
+
"learning_rate": 1.7209949059142083e-06,
|
| 1423 |
+
"loss": 1.2255,
|
| 1424 |
+
"step": 185
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.7346938775510203,
|
| 1428 |
+
"grad_norm": 0.1677573323249817,
|
| 1429 |
+
"learning_rate": 1.4230204685196203e-06,
|
| 1430 |
+
"loss": 1.2643,
|
| 1431 |
+
"step": 186
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.7551020408163263,
|
| 1435 |
+
"grad_norm": 0.16778886318206787,
|
| 1436 |
+
"learning_rate": 1.1531675671888619e-06,
|
| 1437 |
+
"loss": 1.234,
|
| 1438 |
+
"step": 187
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.7755102040816326,
|
| 1442 |
+
"grad_norm": 0.16397559642791748,
|
| 1443 |
+
"learning_rate": 9.11513184176116e-07,
|
| 1444 |
+
"loss": 1.2509,
|
| 1445 |
+
"step": 188
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.795918367346939,
|
| 1449 |
+
"grad_norm": 0.16539420187473297,
|
| 1450 |
+
"learning_rate": 6.981262574066394e-07,
|
| 1451 |
+
"loss": 1.2425,
|
| 1452 |
+
"step": 189
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.816326530612245,
|
| 1456 |
+
"grad_norm": 0.18255014717578888,
|
| 1457 |
+
"learning_rate": 5.130676608104845e-07,
|
| 1458 |
+
"loss": 1.2628,
|
| 1459 |
+
"step": 190
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.836734693877551,
|
| 1463 |
+
"grad_norm": 0.16024163365364075,
|
| 1464 |
+
"learning_rate": 3.56390186956701e-07,
|
| 1465 |
+
"loss": 1.2331,
|
| 1466 |
+
"step": 191
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.857142857142857,
|
| 1470 |
+
"grad_norm": 0.17575234174728394,
|
| 1471 |
+
"learning_rate": 2.2813853199292746e-07,
|
| 1472 |
+
"loss": 1.2497,
|
| 1473 |
+
"step": 192
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.877551020408163,
|
| 1477 |
+
"grad_norm": 0.1590609848499298,
|
| 1478 |
+
"learning_rate": 1.2834928289472416e-07,
|
| 1479 |
+
"loss": 1.2436,
|
| 1480 |
+
"step": 193
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 3.8979591836734695,
|
| 1484 |
+
"grad_norm": 0.17772971093654633,
|
| 1485 |
+
"learning_rate": 5.705090702819993e-08,
|
| 1486 |
+
"loss": 1.2361,
|
| 1487 |
+
"step": 194
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.9183673469387754,
|
| 1491 |
+
"grad_norm": 0.15970654785633087,
|
| 1492 |
+
"learning_rate": 1.426374402901942e-08,
|
| 1493 |
+
"loss": 1.2366,
|
| 1494 |
+
"step": 195
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.9183673469387754,
|
| 1498 |
+
"eval_loss": 1.2375136613845825,
|
| 1499 |
+
"eval_runtime": 270.7418,
|
| 1500 |
+
"eval_samples_per_second": 6.261,
|
| 1501 |
+
"eval_steps_per_second": 3.132,
|
| 1502 |
+
"step": 195
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 3.938775510204082,
|
| 1506 |
+
"grad_norm": 0.15187527239322662,
|
| 1507 |
+
"learning_rate": 0.0,
|
| 1508 |
+
"loss": 1.2409,
|
| 1509 |
+
"step": 196
|
| 1510 |
+
}
|
| 1511 |
+
],
|
| 1512 |
+
"logging_steps": 1,
|
| 1513 |
+
"max_steps": 196,
|
| 1514 |
+
"num_input_tokens_seen": 0,
|
| 1515 |
+
"num_train_epochs": 4,
|
| 1516 |
+
"save_steps": 49,
|
| 1517 |
+
"total_flos": 4.083740321198899e+16,
|
| 1518 |
+
"train_batch_size": 2,
|
| 1519 |
+
"trial_name": null,
|
| 1520 |
+
"trial_params": null
|
| 1521 |
+
}
|
checkpoint-196/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9cc4ff61a4799ac22d5c627a0169a20cc75619ae1b5871f2d114f95284d87a6
|
| 3 |
+
size 5816
|
checkpoint-49/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-49/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-49/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a7afbbb6db02fdac7ffe868d42729e1c9515f835763d3b9551db4ae31e3529
|
| 3 |
+
size 100966336
|
checkpoint-49/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9db4145fa287fcc2dc98bac341ab537efce6a4407796361cd24ac6b2176f6a70
|
| 3 |
+
size 50916644
|
checkpoint-49/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e595b32f221472ac195c50986dfcd13bac01a4909d487f497aaa38e078d0c2
|
| 3 |
+
size 14244
|
checkpoint-49/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e5af14094f757ccb041613325b6c93fe808050ec47f3a4ec285ab4a0e229950
|
| 3 |
+
size 1064
|
checkpoint-49/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-49/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-49/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false,
|
| 44 |
+
"use_fast": true
|
| 45 |
+
}
|
checkpoint-49/trainer_state.json
ADDED
|
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 13,
|
| 6 |
+
"global_step": 49,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02040816326530612,
|
| 13 |
+
"grad_norm": 0.7881951332092285,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.7509,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02040816326530612,
|
| 20 |
+
"eval_loss": 2.6902382373809814,
|
| 21 |
+
"eval_runtime": 269.5606,
|
| 22 |
+
"eval_samples_per_second": 6.288,
|
| 23 |
+
"eval_steps_per_second": 3.146,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04081632653061224,
|
| 28 |
+
"grad_norm": 0.789082407951355,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 2.7449,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.061224489795918366,
|
| 35 |
+
"grad_norm": 0.7354114055633545,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 2.7164,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08163265306122448,
|
| 42 |
+
"grad_norm": 0.7292255759239197,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 2.7174,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10204081632653061,
|
| 49 |
+
"grad_norm": 0.6898028254508972,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 2.6891,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12244897959183673,
|
| 56 |
+
"grad_norm": 0.6861400604248047,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 2.6545,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14285714285714285,
|
| 63 |
+
"grad_norm": 0.7510350346565247,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 2.5656,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16326530612244897,
|
| 70 |
+
"grad_norm": 0.8011165261268616,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 2.4519,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1836734693877551,
|
| 77 |
+
"grad_norm": 0.8624005317687988,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 2.3178,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.20408163265306123,
|
| 84 |
+
"grad_norm": 0.8004987835884094,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 2.1783,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22448979591836735,
|
| 91 |
+
"grad_norm": 0.6362400054931641,
|
| 92 |
+
"learning_rate": 0.000199985736255971,
|
| 93 |
+
"loss": 2.0252,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24489795918367346,
|
| 98 |
+
"grad_norm": 0.7930936217308044,
|
| 99 |
+
"learning_rate": 0.0001999429490929718,
|
| 100 |
+
"loss": 1.8839,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2653061224489796,
|
| 105 |
+
"grad_norm": 0.5149843096733093,
|
| 106 |
+
"learning_rate": 0.00019987165071710527,
|
| 107 |
+
"loss": 1.8064,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2653061224489796,
|
| 112 |
+
"eval_loss": 1.6734941005706787,
|
| 113 |
+
"eval_runtime": 271.2615,
|
| 114 |
+
"eval_samples_per_second": 6.249,
|
| 115 |
+
"eval_steps_per_second": 3.126,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2857142857142857,
|
| 120 |
+
"grad_norm": 0.42121434211730957,
|
| 121 |
+
"learning_rate": 0.00019977186146800707,
|
| 122 |
+
"loss": 1.7922,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.30612244897959184,
|
| 127 |
+
"grad_norm": 0.3523242771625519,
|
| 128 |
+
"learning_rate": 0.0001996436098130433,
|
| 129 |
+
"loss": 1.7711,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.32653061224489793,
|
| 134 |
+
"grad_norm": 0.3384595215320587,
|
| 135 |
+
"learning_rate": 0.00019948693233918952,
|
| 136 |
+
"loss": 1.7152,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3469387755102041,
|
| 141 |
+
"grad_norm": 0.34942421317100525,
|
| 142 |
+
"learning_rate": 0.00019930187374259337,
|
| 143 |
+
"loss": 1.7112,
|
| 144 |
+
"step": 17
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3673469387755102,
|
| 148 |
+
"grad_norm": 0.31712639331817627,
|
| 149 |
+
"learning_rate": 0.00019908848681582391,
|
| 150 |
+
"loss": 1.7059,
|
| 151 |
+
"step": 18
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3877551020408163,
|
| 155 |
+
"grad_norm": 0.2875436842441559,
|
| 156 |
+
"learning_rate": 0.00019884683243281116,
|
| 157 |
+
"loss": 1.6468,
|
| 158 |
+
"step": 19
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.40816326530612246,
|
| 162 |
+
"grad_norm": 0.24433130025863647,
|
| 163 |
+
"learning_rate": 0.00019857697953148037,
|
| 164 |
+
"loss": 1.6408,
|
| 165 |
+
"step": 20
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.42857142857142855,
|
| 169 |
+
"grad_norm": 0.21414674818515778,
|
| 170 |
+
"learning_rate": 0.00019827900509408581,
|
| 171 |
+
"loss": 1.616,
|
| 172 |
+
"step": 21
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.4489795918367347,
|
| 176 |
+
"grad_norm": 0.21537622809410095,
|
| 177 |
+
"learning_rate": 0.00019795299412524945,
|
| 178 |
+
"loss": 1.609,
|
| 179 |
+
"step": 22
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.46938775510204084,
|
| 183 |
+
"grad_norm": 0.2432074397802353,
|
| 184 |
+
"learning_rate": 0.00019759903962771156,
|
| 185 |
+
"loss": 1.6066,
|
| 186 |
+
"step": 23
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4897959183673469,
|
| 190 |
+
"grad_norm": 0.2359839379787445,
|
| 191 |
+
"learning_rate": 0.00019721724257579907,
|
| 192 |
+
"loss": 1.5851,
|
| 193 |
+
"step": 24
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.5102040816326531,
|
| 197 |
+
"grad_norm": 0.22065888345241547,
|
| 198 |
+
"learning_rate": 0.00019680771188662044,
|
| 199 |
+
"loss": 1.5739,
|
| 200 |
+
"step": 25
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5306122448979592,
|
| 204 |
+
"grad_norm": 0.20339132845401764,
|
| 205 |
+
"learning_rate": 0.0001963705643889941,
|
| 206 |
+
"loss": 1.5513,
|
| 207 |
+
"step": 26
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5306122448979592,
|
| 211 |
+
"eval_loss": 1.4832030534744263,
|
| 212 |
+
"eval_runtime": 271.2449,
|
| 213 |
+
"eval_samples_per_second": 6.249,
|
| 214 |
+
"eval_steps_per_second": 3.126,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5510204081632653,
|
| 219 |
+
"grad_norm": 0.18875224888324738,
|
| 220 |
+
"learning_rate": 0.00019590592479012023,
|
| 221 |
+
"loss": 1.5378,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5714285714285714,
|
| 226 |
+
"grad_norm": 0.18564417958259583,
|
| 227 |
+
"learning_rate": 0.00019541392564000488,
|
| 228 |
+
"loss": 1.5212,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5918367346938775,
|
| 233 |
+
"grad_norm": 0.16226942837238312,
|
| 234 |
+
"learning_rate": 0.00019489470729364692,
|
| 235 |
+
"loss": 1.5391,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6122448979591837,
|
| 240 |
+
"grad_norm": 0.15650039911270142,
|
| 241 |
+
"learning_rate": 0.00019434841787099803,
|
| 242 |
+
"loss": 1.511,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6326530612244898,
|
| 247 |
+
"grad_norm": 0.15976540744304657,
|
| 248 |
+
"learning_rate": 0.00019377521321470805,
|
| 249 |
+
"loss": 1.5119,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6530612244897959,
|
| 254 |
+
"grad_norm": 0.16409288346767426,
|
| 255 |
+
"learning_rate": 0.00019317525684566685,
|
| 256 |
+
"loss": 1.4909,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.673469387755102,
|
| 261 |
+
"grad_norm": 0.15468019247055054,
|
| 262 |
+
"learning_rate": 0.00019254871991635598,
|
| 263 |
+
"loss": 1.4951,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6938775510204082,
|
| 268 |
+
"grad_norm": 0.1462036371231079,
|
| 269 |
+
"learning_rate": 0.00019189578116202307,
|
| 270 |
+
"loss": 1.4643,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7142857142857143,
|
| 275 |
+
"grad_norm": 0.1541963368654251,
|
| 276 |
+
"learning_rate": 0.00019121662684969335,
|
| 277 |
+
"loss": 1.5159,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7346938775510204,
|
| 282 |
+
"grad_norm": 0.14798064529895782,
|
| 283 |
+
"learning_rate": 0.00019051145072503215,
|
| 284 |
+
"loss": 1.4741,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.7551020408163265,
|
| 289 |
+
"grad_norm": 0.13914817571640015,
|
| 290 |
+
"learning_rate": 0.00018978045395707418,
|
| 291 |
+
"loss": 1.4788,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7755102040816326,
|
| 296 |
+
"grad_norm": 0.15608824789524078,
|
| 297 |
+
"learning_rate": 0.00018902384508083517,
|
| 298 |
+
"loss": 1.4687,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.7959183673469388,
|
| 303 |
+
"grad_norm": 0.14460116624832153,
|
| 304 |
+
"learning_rate": 0.00018824183993782192,
|
| 305 |
+
"loss": 1.482,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.7959183673469388,
|
| 310 |
+
"eval_loss": 1.411073088645935,
|
| 311 |
+
"eval_runtime": 271.292,
|
| 312 |
+
"eval_samples_per_second": 6.248,
|
| 313 |
+
"eval_steps_per_second": 3.126,
|
| 314 |
+
"step": 39
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8163265306122449,
|
| 318 |
+
"grad_norm": 0.15740551054477692,
|
| 319 |
+
"learning_rate": 0.00018743466161445823,
|
| 320 |
+
"loss": 1.4486,
|
| 321 |
+
"step": 40
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8367346938775511,
|
| 325 |
+
"grad_norm": 0.14149661362171173,
|
| 326 |
+
"learning_rate": 0.00018660254037844388,
|
| 327 |
+
"loss": 1.4353,
|
| 328 |
+
"step": 41
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8571428571428571,
|
| 332 |
+
"grad_norm": 0.14034292101860046,
|
| 333 |
+
"learning_rate": 0.0001857457136130651,
|
| 334 |
+
"loss": 1.4523,
|
| 335 |
+
"step": 42
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.8775510204081632,
|
| 339 |
+
"grad_norm": 0.1487722396850586,
|
| 340 |
+
"learning_rate": 0.00018486442574947511,
|
| 341 |
+
"loss": 1.4095,
|
| 342 |
+
"step": 43
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.8979591836734694,
|
| 346 |
+
"grad_norm": 0.17400234937667847,
|
| 347 |
+
"learning_rate": 0.00018395892819696389,
|
| 348 |
+
"loss": 1.4414,
|
| 349 |
+
"step": 44
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9183673469387755,
|
| 353 |
+
"grad_norm": 0.1741325408220291,
|
| 354 |
+
"learning_rate": 0.00018302947927123766,
|
| 355 |
+
"loss": 1.4379,
|
| 356 |
+
"step": 45
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9387755102040817,
|
| 360 |
+
"grad_norm": 0.15319454669952393,
|
| 361 |
+
"learning_rate": 0.00018207634412072764,
|
| 362 |
+
"loss": 1.405,
|
| 363 |
+
"step": 46
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9591836734693877,
|
| 367 |
+
"grad_norm": 0.15876264870166779,
|
| 368 |
+
"learning_rate": 0.00018109979465095013,
|
| 369 |
+
"loss": 1.4122,
|
| 370 |
+
"step": 47
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9795918367346939,
|
| 374 |
+
"grad_norm": 0.17120805382728577,
|
| 375 |
+
"learning_rate": 0.00018010010944693848,
|
| 376 |
+
"loss": 1.4132,
|
| 377 |
+
"step": 48
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.0,
|
| 381 |
+
"grad_norm": 0.1436116099357605,
|
| 382 |
+
"learning_rate": 0.00017907757369376985,
|
| 383 |
+
"loss": 1.416,
|
| 384 |
+
"step": 49
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 1,
|
| 388 |
+
"max_steps": 196,
|
| 389 |
+
"num_input_tokens_seen": 0,
|
| 390 |
+
"num_train_epochs": 4,
|
| 391 |
+
"save_steps": 49,
|
| 392 |
+
"total_flos": 1.0209350802997248e+16,
|
| 393 |
+
"train_batch_size": 2,
|
| 394 |
+
"trial_name": null,
|
| 395 |
+
"trial_params": null
|
| 396 |
+
}
|
checkpoint-49/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9cc4ff61a4799ac22d5c627a0169a20cc75619ae1b5871f2d114f95284d87a6
|
| 3 |
+
size 5816
|
checkpoint-98/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-98/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-98/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f74a76e06a6e5698ca16a682f4fa5d7e5c10182d165fe6c9327116444b10d0
|
| 3 |
+
size 100966336
|
checkpoint-98/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c01f653a0ce9ea304a86d075b21cd51ea729659b91629c555eec65181dd1818
|
| 3 |
+
size 50916644
|
checkpoint-98/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff339d3bf5bb702320fd9a759e0988b159a701364f186575c95d51b72519d7a1
|
| 3 |
+
size 14244
|
checkpoint-98/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e31465eabc96d2c0b0dc68386782c8ea3a5771edcba13d0d620c4297cd31957
|
| 3 |
+
size 1064
|
checkpoint-98/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-98/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-98/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false,
|
| 44 |
+
"use_fast": true
|
| 45 |
+
}
|
checkpoint-98/trainer_state.json
ADDED
|
@@ -0,0 +1,771 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9795918367346939,
|
| 5 |
+
"eval_steps": 13,
|
| 6 |
+
"global_step": 98,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02040816326530612,
|
| 13 |
+
"grad_norm": 0.7881951332092285,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.7509,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02040816326530612,
|
| 20 |
+
"eval_loss": 2.6902382373809814,
|
| 21 |
+
"eval_runtime": 269.5606,
|
| 22 |
+
"eval_samples_per_second": 6.288,
|
| 23 |
+
"eval_steps_per_second": 3.146,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04081632653061224,
|
| 28 |
+
"grad_norm": 0.789082407951355,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 2.7449,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.061224489795918366,
|
| 35 |
+
"grad_norm": 0.7354114055633545,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 2.7164,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08163265306122448,
|
| 42 |
+
"grad_norm": 0.7292255759239197,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 2.7174,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10204081632653061,
|
| 49 |
+
"grad_norm": 0.6898028254508972,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 2.6891,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12244897959183673,
|
| 56 |
+
"grad_norm": 0.6861400604248047,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 2.6545,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14285714285714285,
|
| 63 |
+
"grad_norm": 0.7510350346565247,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 2.5656,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16326530612244897,
|
| 70 |
+
"grad_norm": 0.8011165261268616,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 2.4519,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1836734693877551,
|
| 77 |
+
"grad_norm": 0.8624005317687988,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 2.3178,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.20408163265306123,
|
| 84 |
+
"grad_norm": 0.8004987835884094,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 2.1783,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22448979591836735,
|
| 91 |
+
"grad_norm": 0.6362400054931641,
|
| 92 |
+
"learning_rate": 0.000199985736255971,
|
| 93 |
+
"loss": 2.0252,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24489795918367346,
|
| 98 |
+
"grad_norm": 0.7930936217308044,
|
| 99 |
+
"learning_rate": 0.0001999429490929718,
|
| 100 |
+
"loss": 1.8839,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2653061224489796,
|
| 105 |
+
"grad_norm": 0.5149843096733093,
|
| 106 |
+
"learning_rate": 0.00019987165071710527,
|
| 107 |
+
"loss": 1.8064,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2653061224489796,
|
| 112 |
+
"eval_loss": 1.6734941005706787,
|
| 113 |
+
"eval_runtime": 271.2615,
|
| 114 |
+
"eval_samples_per_second": 6.249,
|
| 115 |
+
"eval_steps_per_second": 3.126,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2857142857142857,
|
| 120 |
+
"grad_norm": 0.42121434211730957,
|
| 121 |
+
"learning_rate": 0.00019977186146800707,
|
| 122 |
+
"loss": 1.7922,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.30612244897959184,
|
| 127 |
+
"grad_norm": 0.3523242771625519,
|
| 128 |
+
"learning_rate": 0.0001996436098130433,
|
| 129 |
+
"loss": 1.7711,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.32653061224489793,
|
| 134 |
+
"grad_norm": 0.3384595215320587,
|
| 135 |
+
"learning_rate": 0.00019948693233918952,
|
| 136 |
+
"loss": 1.7152,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3469387755102041,
|
| 141 |
+
"grad_norm": 0.34942421317100525,
|
| 142 |
+
"learning_rate": 0.00019930187374259337,
|
| 143 |
+
"loss": 1.7112,
|
| 144 |
+
"step": 17
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.3673469387755102,
|
| 148 |
+
"grad_norm": 0.31712639331817627,
|
| 149 |
+
"learning_rate": 0.00019908848681582391,
|
| 150 |
+
"loss": 1.7059,
|
| 151 |
+
"step": 18
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3877551020408163,
|
| 155 |
+
"grad_norm": 0.2875436842441559,
|
| 156 |
+
"learning_rate": 0.00019884683243281116,
|
| 157 |
+
"loss": 1.6468,
|
| 158 |
+
"step": 19
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.40816326530612246,
|
| 162 |
+
"grad_norm": 0.24433130025863647,
|
| 163 |
+
"learning_rate": 0.00019857697953148037,
|
| 164 |
+
"loss": 1.6408,
|
| 165 |
+
"step": 20
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.42857142857142855,
|
| 169 |
+
"grad_norm": 0.21414674818515778,
|
| 170 |
+
"learning_rate": 0.00019827900509408581,
|
| 171 |
+
"loss": 1.616,
|
| 172 |
+
"step": 21
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.4489795918367347,
|
| 176 |
+
"grad_norm": 0.21537622809410095,
|
| 177 |
+
"learning_rate": 0.00019795299412524945,
|
| 178 |
+
"loss": 1.609,
|
| 179 |
+
"step": 22
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.46938775510204084,
|
| 183 |
+
"grad_norm": 0.2432074397802353,
|
| 184 |
+
"learning_rate": 0.00019759903962771156,
|
| 185 |
+
"loss": 1.6066,
|
| 186 |
+
"step": 23
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4897959183673469,
|
| 190 |
+
"grad_norm": 0.2359839379787445,
|
| 191 |
+
"learning_rate": 0.00019721724257579907,
|
| 192 |
+
"loss": 1.5851,
|
| 193 |
+
"step": 24
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.5102040816326531,
|
| 197 |
+
"grad_norm": 0.22065888345241547,
|
| 198 |
+
"learning_rate": 0.00019680771188662044,
|
| 199 |
+
"loss": 1.5739,
|
| 200 |
+
"step": 25
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5306122448979592,
|
| 204 |
+
"grad_norm": 0.20339132845401764,
|
| 205 |
+
"learning_rate": 0.0001963705643889941,
|
| 206 |
+
"loss": 1.5513,
|
| 207 |
+
"step": 26
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5306122448979592,
|
| 211 |
+
"eval_loss": 1.4832030534744263,
|
| 212 |
+
"eval_runtime": 271.2449,
|
| 213 |
+
"eval_samples_per_second": 6.249,
|
| 214 |
+
"eval_steps_per_second": 3.126,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.5510204081632653,
|
| 219 |
+
"grad_norm": 0.18875224888324738,
|
| 220 |
+
"learning_rate": 0.00019590592479012023,
|
| 221 |
+
"loss": 1.5378,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.5714285714285714,
|
| 226 |
+
"grad_norm": 0.18564417958259583,
|
| 227 |
+
"learning_rate": 0.00019541392564000488,
|
| 228 |
+
"loss": 1.5212,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5918367346938775,
|
| 233 |
+
"grad_norm": 0.16226942837238312,
|
| 234 |
+
"learning_rate": 0.00019489470729364692,
|
| 235 |
+
"loss": 1.5391,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6122448979591837,
|
| 240 |
+
"grad_norm": 0.15650039911270142,
|
| 241 |
+
"learning_rate": 0.00019434841787099803,
|
| 242 |
+
"loss": 1.511,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6326530612244898,
|
| 247 |
+
"grad_norm": 0.15976540744304657,
|
| 248 |
+
"learning_rate": 0.00019377521321470805,
|
| 249 |
+
"loss": 1.5119,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6530612244897959,
|
| 254 |
+
"grad_norm": 0.16409288346767426,
|
| 255 |
+
"learning_rate": 0.00019317525684566685,
|
| 256 |
+
"loss": 1.4909,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.673469387755102,
|
| 261 |
+
"grad_norm": 0.15468019247055054,
|
| 262 |
+
"learning_rate": 0.00019254871991635598,
|
| 263 |
+
"loss": 1.4951,
|
| 264 |
+
"step": 33
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6938775510204082,
|
| 268 |
+
"grad_norm": 0.1462036371231079,
|
| 269 |
+
"learning_rate": 0.00019189578116202307,
|
| 270 |
+
"loss": 1.4643,
|
| 271 |
+
"step": 34
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7142857142857143,
|
| 275 |
+
"grad_norm": 0.1541963368654251,
|
| 276 |
+
"learning_rate": 0.00019121662684969335,
|
| 277 |
+
"loss": 1.5159,
|
| 278 |
+
"step": 35
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7346938775510204,
|
| 282 |
+
"grad_norm": 0.14798064529895782,
|
| 283 |
+
"learning_rate": 0.00019051145072503215,
|
| 284 |
+
"loss": 1.4741,
|
| 285 |
+
"step": 36
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.7551020408163265,
|
| 289 |
+
"grad_norm": 0.13914817571640015,
|
| 290 |
+
"learning_rate": 0.00018978045395707418,
|
| 291 |
+
"loss": 1.4788,
|
| 292 |
+
"step": 37
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7755102040816326,
|
| 296 |
+
"grad_norm": 0.15608824789524078,
|
| 297 |
+
"learning_rate": 0.00018902384508083517,
|
| 298 |
+
"loss": 1.4687,
|
| 299 |
+
"step": 38
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.7959183673469388,
|
| 303 |
+
"grad_norm": 0.14460116624832153,
|
| 304 |
+
"learning_rate": 0.00018824183993782192,
|
| 305 |
+
"loss": 1.482,
|
| 306 |
+
"step": 39
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.7959183673469388,
|
| 310 |
+
"eval_loss": 1.411073088645935,
|
| 311 |
+
"eval_runtime": 271.292,
|
| 312 |
+
"eval_samples_per_second": 6.248,
|
| 313 |
+
"eval_steps_per_second": 3.126,
|
| 314 |
+
"step": 39
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8163265306122449,
|
| 318 |
+
"grad_norm": 0.15740551054477692,
|
| 319 |
+
"learning_rate": 0.00018743466161445823,
|
| 320 |
+
"loss": 1.4486,
|
| 321 |
+
"step": 40
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8367346938775511,
|
| 325 |
+
"grad_norm": 0.14149661362171173,
|
| 326 |
+
"learning_rate": 0.00018660254037844388,
|
| 327 |
+
"loss": 1.4353,
|
| 328 |
+
"step": 41
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8571428571428571,
|
| 332 |
+
"grad_norm": 0.14034292101860046,
|
| 333 |
+
"learning_rate": 0.0001857457136130651,
|
| 334 |
+
"loss": 1.4523,
|
| 335 |
+
"step": 42
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.8775510204081632,
|
| 339 |
+
"grad_norm": 0.1487722396850586,
|
| 340 |
+
"learning_rate": 0.00018486442574947511,
|
| 341 |
+
"loss": 1.4095,
|
| 342 |
+
"step": 43
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.8979591836734694,
|
| 346 |
+
"grad_norm": 0.17400234937667847,
|
| 347 |
+
"learning_rate": 0.00018395892819696389,
|
| 348 |
+
"loss": 1.4414,
|
| 349 |
+
"step": 44
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9183673469387755,
|
| 353 |
+
"grad_norm": 0.1741325408220291,
|
| 354 |
+
"learning_rate": 0.00018302947927123766,
|
| 355 |
+
"loss": 1.4379,
|
| 356 |
+
"step": 45
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9387755102040817,
|
| 360 |
+
"grad_norm": 0.15319454669952393,
|
| 361 |
+
"learning_rate": 0.00018207634412072764,
|
| 362 |
+
"loss": 1.405,
|
| 363 |
+
"step": 46
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9591836734693877,
|
| 367 |
+
"grad_norm": 0.15876264870166779,
|
| 368 |
+
"learning_rate": 0.00018109979465095013,
|
| 369 |
+
"loss": 1.4122,
|
| 370 |
+
"step": 47
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.9795918367346939,
|
| 374 |
+
"grad_norm": 0.17120805382728577,
|
| 375 |
+
"learning_rate": 0.00018010010944693848,
|
| 376 |
+
"loss": 1.4132,
|
| 377 |
+
"step": 48
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.0,
|
| 381 |
+
"grad_norm": 0.1436116099357605,
|
| 382 |
+
"learning_rate": 0.00017907757369376985,
|
| 383 |
+
"loss": 1.416,
|
| 384 |
+
"step": 49
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.0204081632653061,
|
| 388 |
+
"grad_norm": 0.1707429438829422,
|
| 389 |
+
"learning_rate": 0.0001780324790952092,
|
| 390 |
+
"loss": 1.3913,
|
| 391 |
+
"step": 50
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.0204081632653061,
|
| 395 |
+
"grad_norm": 0.17117524147033691,
|
| 396 |
+
"learning_rate": 0.00017696512379049325,
|
| 397 |
+
"loss": 1.3963,
|
| 398 |
+
"step": 51
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.0408163265306123,
|
| 402 |
+
"grad_norm": 0.13410089910030365,
|
| 403 |
+
"learning_rate": 0.0001758758122692791,
|
| 404 |
+
"loss": 1.392,
|
| 405 |
+
"step": 52
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0408163265306123,
|
| 409 |
+
"eval_loss": 1.3676769733428955,
|
| 410 |
+
"eval_runtime": 270.8566,
|
| 411 |
+
"eval_samples_per_second": 6.258,
|
| 412 |
+
"eval_steps_per_second": 3.131,
|
| 413 |
+
"step": 52
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.0612244897959184,
|
| 417 |
+
"grad_norm": 0.18877607583999634,
|
| 418 |
+
"learning_rate": 0.00017476485528478093,
|
| 419 |
+
"loss": 1.3854,
|
| 420 |
+
"step": 53
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.0816326530612246,
|
| 424 |
+
"grad_norm": 0.1752927452325821,
|
| 425 |
+
"learning_rate": 0.00017363256976511972,
|
| 426 |
+
"loss": 1.3759,
|
| 427 |
+
"step": 54
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.1020408163265305,
|
| 431 |
+
"grad_norm": 0.17180170118808746,
|
| 432 |
+
"learning_rate": 0.000172479278722912,
|
| 433 |
+
"loss": 1.3614,
|
| 434 |
+
"step": 55
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1224489795918366,
|
| 438 |
+
"grad_norm": 0.1640290915966034,
|
| 439 |
+
"learning_rate": 0.00017130531116312203,
|
| 440 |
+
"loss": 1.3853,
|
| 441 |
+
"step": 56
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.1428571428571428,
|
| 445 |
+
"grad_norm": 0.2047068476676941,
|
| 446 |
+
"learning_rate": 0.0001701110019892053,
|
| 447 |
+
"loss": 1.3699,
|
| 448 |
+
"step": 57
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.163265306122449,
|
| 452 |
+
"grad_norm": 0.1835869997739792,
|
| 453 |
+
"learning_rate": 0.00016889669190756868,
|
| 454 |
+
"loss": 1.3403,
|
| 455 |
+
"step": 58
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.183673469387755,
|
| 459 |
+
"grad_norm": 0.16733241081237793,
|
| 460 |
+
"learning_rate": 0.00016766272733037576,
|
| 461 |
+
"loss": 1.3609,
|
| 462 |
+
"step": 59
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.2040816326530612,
|
| 466 |
+
"grad_norm": 0.178726926445961,
|
| 467 |
+
"learning_rate": 0.00016640946027672392,
|
| 468 |
+
"loss": 1.3651,
|
| 469 |
+
"step": 60
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.2244897959183674,
|
| 473 |
+
"grad_norm": 0.16719630360603333,
|
| 474 |
+
"learning_rate": 0.00016513724827222227,
|
| 475 |
+
"loss": 1.3676,
|
| 476 |
+
"step": 61
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.2448979591836735,
|
| 480 |
+
"grad_norm": 0.15999363362789154,
|
| 481 |
+
"learning_rate": 0.00016384645424699835,
|
| 482 |
+
"loss": 1.3651,
|
| 483 |
+
"step": 62
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2653061224489797,
|
| 487 |
+
"grad_norm": 0.1705988198518753,
|
| 488 |
+
"learning_rate": 0.00016253744643216368,
|
| 489 |
+
"loss": 1.3757,
|
| 490 |
+
"step": 63
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.2857142857142856,
|
| 494 |
+
"grad_norm": 0.14996370673179626,
|
| 495 |
+
"learning_rate": 0.0001612105982547663,
|
| 496 |
+
"loss": 1.3474,
|
| 497 |
+
"step": 64
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.306122448979592,
|
| 501 |
+
"grad_norm": 0.19127260148525238,
|
| 502 |
+
"learning_rate": 0.0001598662882312615,
|
| 503 |
+
"loss": 1.3414,
|
| 504 |
+
"step": 65
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.306122448979592,
|
| 508 |
+
"eval_loss": 1.331880807876587,
|
| 509 |
+
"eval_runtime": 270.8424,
|
| 510 |
+
"eval_samples_per_second": 6.258,
|
| 511 |
+
"eval_steps_per_second": 3.131,
|
| 512 |
+
"step": 65
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.3265306122448979,
|
| 516 |
+
"grad_norm": 0.16125527024269104,
|
| 517 |
+
"learning_rate": 0.00015850489985953076,
|
| 518 |
+
"loss": 1.3509,
|
| 519 |
+
"step": 66
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.346938775510204,
|
| 523 |
+
"grad_norm": 0.1979473978281021,
|
| 524 |
+
"learning_rate": 0.00015712682150947923,
|
| 525 |
+
"loss": 1.3579,
|
| 526 |
+
"step": 67
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3673469387755102,
|
| 530 |
+
"grad_norm": 0.18317992985248566,
|
| 531 |
+
"learning_rate": 0.00015573244631224365,
|
| 532 |
+
"loss": 1.3341,
|
| 533 |
+
"step": 68
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.3877551020408163,
|
| 537 |
+
"grad_norm": 0.1646898239850998,
|
| 538 |
+
"learning_rate": 0.0001543221720480419,
|
| 539 |
+
"loss": 1.3361,
|
| 540 |
+
"step": 69
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.4081632653061225,
|
| 544 |
+
"grad_norm": 0.1760271042585373,
|
| 545 |
+
"learning_rate": 0.00015289640103269625,
|
| 546 |
+
"loss": 1.358,
|
| 547 |
+
"step": 70
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.4285714285714286,
|
| 551 |
+
"grad_norm": 0.165283203125,
|
| 552 |
+
"learning_rate": 0.0001514555400028629,
|
| 553 |
+
"loss": 1.3072,
|
| 554 |
+
"step": 71
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.4489795918367347,
|
| 558 |
+
"grad_norm": 0.1507076472043991,
|
| 559 |
+
"learning_rate": 0.00015000000000000001,
|
| 560 |
+
"loss": 1.3133,
|
| 561 |
+
"step": 72
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.469387755102041,
|
| 565 |
+
"grad_norm": 0.16913647949695587,
|
| 566 |
+
"learning_rate": 0.00014853019625310813,
|
| 567 |
+
"loss": 1.3232,
|
| 568 |
+
"step": 73
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.489795918367347,
|
| 572 |
+
"grad_norm": 0.18266479671001434,
|
| 573 |
+
"learning_rate": 0.0001470465480602756,
|
| 574 |
+
"loss": 1.3512,
|
| 575 |
+
"step": 74
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.510204081632653,
|
| 579 |
+
"grad_norm": 0.19301828742027283,
|
| 580 |
+
"learning_rate": 0.0001455494786690634,
|
| 581 |
+
"loss": 1.3241,
|
| 582 |
+
"step": 75
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.5306122448979593,
|
| 586 |
+
"grad_norm": 0.16109652817249298,
|
| 587 |
+
"learning_rate": 0.00014403941515576344,
|
| 588 |
+
"loss": 1.3256,
|
| 589 |
+
"step": 76
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.5510204081632653,
|
| 593 |
+
"grad_norm": 0.17053867876529694,
|
| 594 |
+
"learning_rate": 0.00014251678830356408,
|
| 595 |
+
"loss": 1.3162,
|
| 596 |
+
"step": 77
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.5714285714285714,
|
| 600 |
+
"grad_norm": 0.17348544299602509,
|
| 601 |
+
"learning_rate": 0.00014098203247965875,
|
| 602 |
+
"loss": 1.3213,
|
| 603 |
+
"step": 78
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.5714285714285714,
|
| 607 |
+
"eval_loss": 1.3028697967529297,
|
| 608 |
+
"eval_runtime": 270.8095,
|
| 609 |
+
"eval_samples_per_second": 6.259,
|
| 610 |
+
"eval_steps_per_second": 3.131,
|
| 611 |
+
"step": 78
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.5918367346938775,
|
| 615 |
+
"grad_norm": 0.1703907549381256,
|
| 616 |
+
"learning_rate": 0.00013943558551133186,
|
| 617 |
+
"loss": 1.3073,
|
| 618 |
+
"step": 79
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.6122448979591837,
|
| 622 |
+
"grad_norm": 0.17313100397586823,
|
| 623 |
+
"learning_rate": 0.0001378778885610576,
|
| 624 |
+
"loss": 1.3232,
|
| 625 |
+
"step": 80
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6326530612244898,
|
| 629 |
+
"grad_norm": 0.17237025499343872,
|
| 630 |
+
"learning_rate": 0.00013630938600064747,
|
| 631 |
+
"loss": 1.3406,
|
| 632 |
+
"step": 81
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6530612244897958,
|
| 636 |
+
"grad_norm": 0.19658459722995758,
|
| 637 |
+
"learning_rate": 0.00013473052528448201,
|
| 638 |
+
"loss": 1.3114,
|
| 639 |
+
"step": 82
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6734693877551021,
|
| 643 |
+
"grad_norm": 0.20599938929080963,
|
| 644 |
+
"learning_rate": 0.0001331417568218636,
|
| 645 |
+
"loss": 1.3288,
|
| 646 |
+
"step": 83
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.693877551020408,
|
| 650 |
+
"grad_norm": 0.17759399116039276,
|
| 651 |
+
"learning_rate": 0.00013154353384852558,
|
| 652 |
+
"loss": 1.2995,
|
| 653 |
+
"step": 84
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.7142857142857144,
|
| 657 |
+
"grad_norm": 0.18712250888347626,
|
| 658 |
+
"learning_rate": 0.00012993631229733582,
|
| 659 |
+
"loss": 1.2895,
|
| 660 |
+
"step": 85
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7346938775510203,
|
| 664 |
+
"grad_norm": 0.1991330236196518,
|
| 665 |
+
"learning_rate": 0.00012832055066823038,
|
| 666 |
+
"loss": 1.2886,
|
| 667 |
+
"step": 86
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.7551020408163265,
|
| 671 |
+
"grad_norm": 0.22125203907489777,
|
| 672 |
+
"learning_rate": 0.00012669670989741517,
|
| 673 |
+
"loss": 1.3233,
|
| 674 |
+
"step": 87
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.7755102040816326,
|
| 678 |
+
"grad_norm": 0.2052813619375229,
|
| 679 |
+
"learning_rate": 0.00012506525322587207,
|
| 680 |
+
"loss": 1.3079,
|
| 681 |
+
"step": 88
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.7959183673469388,
|
| 685 |
+
"grad_norm": 0.19290736317634583,
|
| 686 |
+
"learning_rate": 0.00012342664606720822,
|
| 687 |
+
"loss": 1.3174,
|
| 688 |
+
"step": 89
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.816326530612245,
|
| 692 |
+
"grad_norm": 0.20912542939186096,
|
| 693 |
+
"learning_rate": 0.00012178135587488515,
|
| 694 |
+
"loss": 1.2915,
|
| 695 |
+
"step": 90
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.836734693877551,
|
| 699 |
+
"grad_norm": 0.20760588347911835,
|
| 700 |
+
"learning_rate": 0.00012012985200886602,
|
| 701 |
+
"loss": 1.3028,
|
| 702 |
+
"step": 91
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.836734693877551,
|
| 706 |
+
"eval_loss": 1.2795333862304688,
|
| 707 |
+
"eval_runtime": 270.6525,
|
| 708 |
+
"eval_samples_per_second": 6.263,
|
| 709 |
+
"eval_steps_per_second": 3.133,
|
| 710 |
+
"step": 91
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.8571428571428572,
|
| 714 |
+
"grad_norm": 0.1996900886297226,
|
| 715 |
+
"learning_rate": 0.00011847260560171896,
|
| 716 |
+
"loss": 1.3119,
|
| 717 |
+
"step": 92
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.8775510204081631,
|
| 721 |
+
"grad_norm": 0.23766876757144928,
|
| 722 |
+
"learning_rate": 0.00011681008942421483,
|
| 723 |
+
"loss": 1.2978,
|
| 724 |
+
"step": 93
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.8979591836734695,
|
| 728 |
+
"grad_norm": 0.19782397150993347,
|
| 729 |
+
"learning_rate": 0.00011514277775045768,
|
| 730 |
+
"loss": 1.2955,
|
| 731 |
+
"step": 94
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.9183673469387754,
|
| 735 |
+
"grad_norm": 0.22519494593143463,
|
| 736 |
+
"learning_rate": 0.00011347114622258612,
|
| 737 |
+
"loss": 1.2957,
|
| 738 |
+
"step": 95
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.9387755102040818,
|
| 742 |
+
"grad_norm": 0.2590245306491852,
|
| 743 |
+
"learning_rate": 0.00011179567171508463,
|
| 744 |
+
"loss": 1.2809,
|
| 745 |
+
"step": 96
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.9591836734693877,
|
| 749 |
+
"grad_norm": 0.2235420197248459,
|
| 750 |
+
"learning_rate": 0.00011011683219874323,
|
| 751 |
+
"loss": 1.2784,
|
| 752 |
+
"step": 97
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.9795918367346939,
|
| 756 |
+
"grad_norm": 0.285740464925766,
|
| 757 |
+
"learning_rate": 0.00010843510660430447,
|
| 758 |
+
"loss": 1.309,
|
| 759 |
+
"step": 98
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 1,
|
| 763 |
+
"max_steps": 196,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 4,
|
| 766 |
+
"save_steps": 49,
|
| 767 |
+
"total_flos": 2.0418701605994496e+16,
|
| 768 |
+
"train_batch_size": 2,
|
| 769 |
+
"trial_name": null,
|
| 770 |
+
"trial_params": null
|
| 771 |
+
}
|
checkpoint-98/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9cc4ff61a4799ac22d5c627a0169a20cc75619ae1b5871f2d114f95284d87a6
|
| 3 |
+
size 5816
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"_load_in_4bit": false,
|
| 22 |
+
"_load_in_8bit": true,
|
| 23 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 24 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 25 |
+
"bnb_4bit_quant_type": "fp4",
|
| 26 |
+
"bnb_4bit_use_double_quant": false,
|
| 27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 28 |
+
"llm_int8_has_fp16_weight": false,
|
| 29 |
+
"llm_int8_skip_modules": null,
|
| 30 |
+
"llm_int8_threshold": 6.0,
|
| 31 |
+
"load_in_4bit": false,
|
| 32 |
+
"load_in_8bit": true,
|
| 33 |
+
"quant_method": "bitsandbytes"
|
| 34 |
+
},
|
| 35 |
+
"rms_norm_eps": 1e-05,
|
| 36 |
+
"rope_scaling": null,
|
| 37 |
+
"rope_theta": 10000.0,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.40.2",
|
| 41 |
+
"use_cache": false,
|
| 42 |
+
"vocab_size": 32000
|
| 43 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|