Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +150 -0
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- checkpoint-128/README.md +202 -0
- checkpoint-128/adapter_config.json +34 -0
- checkpoint-128/adapter_model.safetensors +3 -0
- checkpoint-128/optimizer.pt +3 -0
- checkpoint-128/rng_state.pth +3 -0
- checkpoint-128/scheduler.pt +3 -0
- checkpoint-128/special_tokens_map.json +24 -0
- checkpoint-128/tokenizer.model +3 -0
- checkpoint-128/tokenizer_config.json +44 -0
- checkpoint-128/trainer_state.json +1053 -0
- checkpoint-128/training_args.bin +3 -0
- checkpoint-32/README.md +202 -0
- checkpoint-32/adapter_config.json +34 -0
- checkpoint-32/adapter_model.safetensors +3 -0
- checkpoint-32/optimizer.pt +3 -0
- checkpoint-32/rng_state.pth +3 -0
- checkpoint-32/scheduler.pt +3 -0
- checkpoint-32/special_tokens_map.json +24 -0
- checkpoint-32/tokenizer.model +3 -0
- checkpoint-32/tokenizer_config.json +44 -0
- checkpoint-32/trainer_state.json +285 -0
- checkpoint-32/training_args.bin +3 -0
- checkpoint-64/README.md +202 -0
- checkpoint-64/adapter_config.json +34 -0
- checkpoint-64/adapter_model.safetensors +3 -0
- checkpoint-64/optimizer.pt +3 -0
- checkpoint-64/rng_state.pth +3 -0
- checkpoint-64/scheduler.pt +3 -0
- checkpoint-64/special_tokens_map.json +24 -0
- checkpoint-64/tokenizer.model +3 -0
- checkpoint-64/tokenizer_config.json +44 -0
- checkpoint-64/trainer_state.json +541 -0
- checkpoint-64/training_args.bin +3 -0
- checkpoint-96/README.md +202 -0
- checkpoint-96/adapter_config.json +34 -0
- checkpoint-96/adapter_model.safetensors +3 -0
- checkpoint-96/optimizer.pt +3 -0
- checkpoint-96/rng_state.pth +3 -0
- checkpoint-96/scheduler.pt +3 -0
- checkpoint-96/special_tokens_map.json +24 -0
- checkpoint-96/tokenizer.model +3 -0
- checkpoint-96/tokenizer_config.json +44 -0
- checkpoint-96/trainer_state.json +797 -0
- checkpoint-96/training_args.bin +3 -0
- config.json +43 -0
- runs/Apr30_02-51-48_663ec5cd7167/events.out.tfevents.1714445508.663ec5cd7167.5280.0 +3 -0
- special_tokens_map.json +24 -0
README.md
CHANGED
|
@@ -1,3 +1,153 @@
|
|
| 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: qlora-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: false
|
| 25 |
+
load_in_4bit: true
|
| 26 |
+
strict: false
|
| 27 |
+
|
| 28 |
+
datasets:
|
| 29 |
+
- path: totally-not-an-llm/ZorgonChat
|
| 30 |
+
type: alpaca
|
| 31 |
+
dataset_prepared_path:
|
| 32 |
+
val_set_size: 0.05
|
| 33 |
+
output_dir: ./qlora-out
|
| 34 |
+
|
| 35 |
+
adapter: qlora
|
| 36 |
+
lora_model_dir:
|
| 37 |
+
|
| 38 |
+
sequence_len: 4096
|
| 39 |
+
sample_packing: false
|
| 40 |
+
pad_to_sequence_len: true
|
| 41 |
+
|
| 42 |
+
lora_r: 32
|
| 43 |
+
lora_alpha: 16
|
| 44 |
+
lora_dropout: 0.05
|
| 45 |
+
lora_target_modules:
|
| 46 |
+
lora_target_linear: true
|
| 47 |
+
lora_fan_in_fan_out:
|
| 48 |
+
|
| 49 |
+
wandb_project:
|
| 50 |
+
wandb_entity:
|
| 51 |
+
wandb_watch:
|
| 52 |
+
wandb_name:
|
| 53 |
+
wandb_log_model:
|
| 54 |
+
|
| 55 |
+
gradient_accumulation_steps: 4
|
| 56 |
+
micro_batch_size: 2
|
| 57 |
+
num_epochs: 4
|
| 58 |
+
optimizer: paged_adamw_32bit
|
| 59 |
+
lr_scheduler: cosine
|
| 60 |
+
learning_rate: 0.0002
|
| 61 |
+
|
| 62 |
+
train_on_inputs: false
|
| 63 |
+
group_by_length: false
|
| 64 |
+
bf16: auto
|
| 65 |
+
fp16:
|
| 66 |
+
tf32: false
|
| 67 |
+
|
| 68 |
+
gradient_checkpointing: true
|
| 69 |
+
early_stopping_patience:
|
| 70 |
+
resume_from_checkpoint:
|
| 71 |
+
local_rank:
|
| 72 |
+
logging_steps: 1
|
| 73 |
+
xformers_attention:
|
| 74 |
+
flash_attention: true
|
| 75 |
+
|
| 76 |
+
warmup_steps: 10
|
| 77 |
+
evals_per_epoch: 4
|
| 78 |
+
saves_per_epoch: 1
|
| 79 |
+
debug:
|
| 80 |
+
deepspeed:
|
| 81 |
+
weight_decay: 0.0
|
| 82 |
+
fsdp:
|
| 83 |
+
fsdp_config:
|
| 84 |
+
special_tokens:
|
| 85 |
+
|
| 86 |
+
```
|
| 87 |
+
|
| 88 |
+
</details><br>
|
| 89 |
+
|
| 90 |
+
# qlora-out
|
| 91 |
+
|
| 92 |
+
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.
|
| 93 |
+
It achieves the following results on the evaluation set:
|
| 94 |
+
- Loss: 2.3466
|
| 95 |
+
|
| 96 |
+
## Model description
|
| 97 |
+
|
| 98 |
+
More information needed
|
| 99 |
+
|
| 100 |
+
## Intended uses & limitations
|
| 101 |
+
|
| 102 |
+
More information needed
|
| 103 |
+
|
| 104 |
+
## Training and evaluation data
|
| 105 |
+
|
| 106 |
+
More information needed
|
| 107 |
+
|
| 108 |
+
## Training procedure
|
| 109 |
+
|
| 110 |
+
### Training hyperparameters
|
| 111 |
+
|
| 112 |
+
The following hyperparameters were used during training:
|
| 113 |
+
- learning_rate: 0.0002
|
| 114 |
+
- train_batch_size: 2
|
| 115 |
+
- eval_batch_size: 2
|
| 116 |
+
- seed: 42
|
| 117 |
+
- gradient_accumulation_steps: 4
|
| 118 |
+
- total_train_batch_size: 8
|
| 119 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 120 |
+
- lr_scheduler_type: cosine
|
| 121 |
+
- lr_scheduler_warmup_steps: 10
|
| 122 |
+
- num_epochs: 4
|
| 123 |
+
|
| 124 |
+
### Training results
|
| 125 |
+
|
| 126 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 127 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 128 |
+
| 3.9295 | 0.03 | 1 | 3.9073 |
|
| 129 |
+
| 3.5364 | 0.25 | 8 | 3.6199 |
|
| 130 |
+
| 3.263 | 0.5 | 16 | 3.1821 |
|
| 131 |
+
| 2.798 | 0.75 | 24 | 2.8962 |
|
| 132 |
+
| 2.7787 | 1.0 | 32 | 2.6773 |
|
| 133 |
+
| 2.5959 | 1.25 | 40 | 2.5506 |
|
| 134 |
+
| 2.4793 | 1.5 | 48 | 2.4955 |
|
| 135 |
+
| 2.5221 | 1.75 | 56 | 2.4613 |
|
| 136 |
+
| 2.4384 | 2.0 | 64 | 2.4055 |
|
| 137 |
+
| 2.295 | 2.25 | 72 | 2.3923 |
|
| 138 |
+
| 2.3943 | 2.5 | 80 | 2.3862 |
|
| 139 |
+
| 2.2398 | 2.75 | 88 | 2.3605 |
|
| 140 |
+
| 2.2693 | 3.0 | 96 | 2.3526 |
|
| 141 |
+
| 2.425 | 3.25 | 104 | 2.3471 |
|
| 142 |
+
| 2.2857 | 3.5 | 112 | 2.3468 |
|
| 143 |
+
| 2.2448 | 3.75 | 120 | 2.3451 |
|
| 144 |
+
| 2.1836 | 4.0 | 128 | 2.3466 |
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
### Framework versions
|
| 148 |
+
|
| 149 |
+
- PEFT 0.10.0
|
| 150 |
+
- Transformers 4.40.0.dev0
|
| 151 |
+
- Pytorch 2.1.2+cu118
|
| 152 |
+
- Datasets 2.15.0
|
| 153 |
+
- Tokenizers 0.15.0
|
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 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_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 sha256:3863c09db8a8ee37f6c92e820fd3918dba26368631f34bba226156413c6f68bd
|
| 3 |
+
size 50573978
|
checkpoint-128/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-128/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 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-128/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:528e075df49b7bbd123228a3b95349c09b3e4aff529a6761814d25530514b3ec
|
| 3 |
+
size 50503848
|
checkpoint-128/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2662bde842785223ccfc20324eb816ad2974916f34f883ea7c17e0bfd3e93bd
|
| 3 |
+
size 202035450
|
checkpoint-128/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e46048a3692b100b154cf7c38df5e2ce5c28c9c56bbbf5e17fe2196b8374656f
|
| 3 |
+
size 14244
|
checkpoint-128/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:968a6dcbda34982ad43f2af2e04e5edf94e043c521201e71b1583695497d18e0
|
| 3 |
+
size 1064
|
checkpoint-128/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-128/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-128/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false,
|
| 43 |
+
"use_fast": true
|
| 44 |
+
}
|
checkpoint-128/trainer_state.json
ADDED
|
@@ -0,0 +1,1053 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 8,
|
| 6 |
+
"global_step": 128,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.5859375,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 3.9295,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 3.907318115234375,
|
| 21 |
+
"eval_runtime": 1.2713,
|
| 22 |
+
"eval_samples_per_second": 11.012,
|
| 23 |
+
"eval_steps_per_second": 5.506,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 0.5078125,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 3.805,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09,
|
| 35 |
+
"grad_norm": 0.63671875,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 3.8521,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"grad_norm": 0.609375,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 3.8947,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"grad_norm": 0.546875,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 3.6494,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19,
|
| 56 |
+
"grad_norm": 0.50390625,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 3.6457,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22,
|
| 63 |
+
"grad_norm": 0.640625,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 3.967,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25,
|
| 70 |
+
"grad_norm": 0.494140625,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 3.5364,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25,
|
| 77 |
+
"eval_loss": 3.6198840141296387,
|
| 78 |
+
"eval_runtime": 1.2681,
|
| 79 |
+
"eval_samples_per_second": 11.04,
|
| 80 |
+
"eval_steps_per_second": 5.52,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.28,
|
| 85 |
+
"grad_norm": 0.51171875,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 3.5216,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.31,
|
| 92 |
+
"grad_norm": 0.6171875,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 3.677,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.34,
|
| 99 |
+
"grad_norm": 0.734375,
|
| 100 |
+
"learning_rate": 0.00019996456111234527,
|
| 101 |
+
"loss": 3.058,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.38,
|
| 106 |
+
"grad_norm": 0.66796875,
|
| 107 |
+
"learning_rate": 0.0001998582695676762,
|
| 108 |
+
"loss": 3.1333,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.41,
|
| 113 |
+
"grad_norm": 0.8359375,
|
| 114 |
+
"learning_rate": 0.000199681200703075,
|
| 115 |
+
"loss": 3.38,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.44,
|
| 120 |
+
"grad_norm": 0.62109375,
|
| 121 |
+
"learning_rate": 0.00019943348002101371,
|
| 122 |
+
"loss": 3.1371,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.47,
|
| 127 |
+
"grad_norm": 0.65625,
|
| 128 |
+
"learning_rate": 0.00019911528310040074,
|
| 129 |
+
"loss": 3.1479,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5,
|
| 134 |
+
"grad_norm": 0.6484375,
|
| 135 |
+
"learning_rate": 0.00019872683547213446,
|
| 136 |
+
"loss": 3.263,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5,
|
| 141 |
+
"eval_loss": 3.1820719242095947,
|
| 142 |
+
"eval_runtime": 1.2692,
|
| 143 |
+
"eval_samples_per_second": 11.031,
|
| 144 |
+
"eval_steps_per_second": 5.515,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.53,
|
| 149 |
+
"grad_norm": 0.53125,
|
| 150 |
+
"learning_rate": 0.00019826841245925212,
|
| 151 |
+
"loss": 2.9833,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.56,
|
| 156 |
+
"grad_norm": 0.5703125,
|
| 157 |
+
"learning_rate": 0.00019774033898178667,
|
| 158 |
+
"loss": 3.0787,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.59,
|
| 163 |
+
"grad_norm": 0.71484375,
|
| 164 |
+
"learning_rate": 0.00019714298932647098,
|
| 165 |
+
"loss": 3.4132,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.62,
|
| 170 |
+
"grad_norm": 0.73046875,
|
| 171 |
+
"learning_rate": 0.0001964767868814516,
|
| 172 |
+
"loss": 2.7304,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.66,
|
| 177 |
+
"grad_norm": 0.55078125,
|
| 178 |
+
"learning_rate": 0.00019574220383620055,
|
| 179 |
+
"loss": 3.0116,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.69,
|
| 184 |
+
"grad_norm": 0.6171875,
|
| 185 |
+
"learning_rate": 0.00019493976084683813,
|
| 186 |
+
"loss": 2.9474,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"grad_norm": 0.61328125,
|
| 192 |
+
"learning_rate": 0.00019407002666710336,
|
| 193 |
+
"loss": 2.9415,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"grad_norm": 0.6328125,
|
| 199 |
+
"learning_rate": 0.00019313361774523385,
|
| 200 |
+
"loss": 2.798,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.75,
|
| 205 |
+
"eval_loss": 2.896176815032959,
|
| 206 |
+
"eval_runtime": 1.2765,
|
| 207 |
+
"eval_samples_per_second": 10.967,
|
| 208 |
+
"eval_steps_per_second": 5.484,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"grad_norm": 0.8046875,
|
| 214 |
+
"learning_rate": 0.00019213119778704128,
|
| 215 |
+
"loss": 3.2157,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.81,
|
| 220 |
+
"grad_norm": 0.7109375,
|
| 221 |
+
"learning_rate": 0.00019106347728549135,
|
| 222 |
+
"loss": 3.0666,
|
| 223 |
+
"step": 26
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.84,
|
| 227 |
+
"grad_norm": 0.59765625,
|
| 228 |
+
"learning_rate": 0.00018993121301712193,
|
| 229 |
+
"loss": 2.8219,
|
| 230 |
+
"step": 27
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.88,
|
| 234 |
+
"grad_norm": 0.75390625,
|
| 235 |
+
"learning_rate": 0.00018873520750565718,
|
| 236 |
+
"loss": 3.1164,
|
| 237 |
+
"step": 28
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.91,
|
| 241 |
+
"grad_norm": 0.67578125,
|
| 242 |
+
"learning_rate": 0.00018747630845319612,
|
| 243 |
+
"loss": 2.7154,
|
| 244 |
+
"step": 29
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.94,
|
| 248 |
+
"grad_norm": 0.625,
|
| 249 |
+
"learning_rate": 0.0001861554081393806,
|
| 250 |
+
"loss": 2.7395,
|
| 251 |
+
"step": 30
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.97,
|
| 255 |
+
"grad_norm": 0.8125,
|
| 256 |
+
"learning_rate": 0.0001847734427889671,
|
| 257 |
+
"loss": 2.8282,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.0,
|
| 262 |
+
"grad_norm": 0.86328125,
|
| 263 |
+
"learning_rate": 0.0001833313919082515,
|
| 264 |
+
"loss": 2.7787,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.0,
|
| 269 |
+
"eval_loss": 2.67726731300354,
|
| 270 |
+
"eval_runtime": 1.2769,
|
| 271 |
+
"eval_samples_per_second": 10.964,
|
| 272 |
+
"eval_steps_per_second": 5.482,
|
| 273 |
+
"step": 32
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.03,
|
| 277 |
+
"grad_norm": 0.703125,
|
| 278 |
+
"learning_rate": 0.0001818302775908169,
|
| 279 |
+
"loss": 2.5957,
|
| 280 |
+
"step": 33
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.06,
|
| 284 |
+
"grad_norm": 0.76953125,
|
| 285 |
+
"learning_rate": 0.00018027116379309638,
|
| 286 |
+
"loss": 2.7011,
|
| 287 |
+
"step": 34
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.09,
|
| 291 |
+
"grad_norm": 0.84765625,
|
| 292 |
+
"learning_rate": 0.00017865515558026428,
|
| 293 |
+
"loss": 2.6043,
|
| 294 |
+
"step": 35
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.12,
|
| 298 |
+
"grad_norm": 0.984375,
|
| 299 |
+
"learning_rate": 0.00017698339834299061,
|
| 300 |
+
"loss": 2.8607,
|
| 301 |
+
"step": 36
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.16,
|
| 305 |
+
"grad_norm": 0.7578125,
|
| 306 |
+
"learning_rate": 0.00017525707698561385,
|
| 307 |
+
"loss": 2.5949,
|
| 308 |
+
"step": 37
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.19,
|
| 312 |
+
"grad_norm": 0.94921875,
|
| 313 |
+
"learning_rate": 0.00017347741508630672,
|
| 314 |
+
"loss": 2.7476,
|
| 315 |
+
"step": 38
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.22,
|
| 319 |
+
"grad_norm": 0.88671875,
|
| 320 |
+
"learning_rate": 0.00017164567402983152,
|
| 321 |
+
"loss": 2.7991,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.25,
|
| 326 |
+
"grad_norm": 0.8671875,
|
| 327 |
+
"learning_rate": 0.0001697631521134985,
|
| 328 |
+
"loss": 2.5959,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.25,
|
| 333 |
+
"eval_loss": 2.5505764484405518,
|
| 334 |
+
"eval_runtime": 1.2761,
|
| 335 |
+
"eval_samples_per_second": 10.971,
|
| 336 |
+
"eval_steps_per_second": 5.486,
|
| 337 |
+
"step": 40
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.28,
|
| 341 |
+
"grad_norm": 0.984375,
|
| 342 |
+
"learning_rate": 0.00016783118362696163,
|
| 343 |
+
"loss": 2.5342,
|
| 344 |
+
"step": 41
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"grad_norm": 0.921875,
|
| 349 |
+
"learning_rate": 0.00016585113790650388,
|
| 350 |
+
"loss": 2.4969,
|
| 351 |
+
"step": 42
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.34,
|
| 355 |
+
"grad_norm": 1.125,
|
| 356 |
+
"learning_rate": 0.00016382441836448202,
|
| 357 |
+
"loss": 2.5723,
|
| 358 |
+
"step": 43
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.38,
|
| 362 |
+
"grad_norm": 1.015625,
|
| 363 |
+
"learning_rate": 0.0001617524614946192,
|
| 364 |
+
"loss": 2.6166,
|
| 365 |
+
"step": 44
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.41,
|
| 369 |
+
"grad_norm": 0.98828125,
|
| 370 |
+
"learning_rate": 0.00015963673585385016,
|
| 371 |
+
"loss": 2.4574,
|
| 372 |
+
"step": 45
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.44,
|
| 376 |
+
"grad_norm": 0.94921875,
|
| 377 |
+
"learning_rate": 0.0001574787410214407,
|
| 378 |
+
"loss": 2.5074,
|
| 379 |
+
"step": 46
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.47,
|
| 383 |
+
"grad_norm": 0.953125,
|
| 384 |
+
"learning_rate": 0.00015528000653611935,
|
| 385 |
+
"loss": 2.5394,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.5,
|
| 390 |
+
"grad_norm": 0.828125,
|
| 391 |
+
"learning_rate": 0.00015304209081197425,
|
| 392 |
+
"loss": 2.4793,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5,
|
| 397 |
+
"eval_loss": 2.495466470718384,
|
| 398 |
+
"eval_runtime": 1.2814,
|
| 399 |
+
"eval_samples_per_second": 10.926,
|
| 400 |
+
"eval_steps_per_second": 5.463,
|
| 401 |
+
"step": 48
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.53,
|
| 405 |
+
"grad_norm": 0.921875,
|
| 406 |
+
"learning_rate": 0.000150766580033884,
|
| 407 |
+
"loss": 2.2909,
|
| 408 |
+
"step": 49
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.56,
|
| 412 |
+
"grad_norm": 0.74609375,
|
| 413 |
+
"learning_rate": 0.00014845508703326504,
|
| 414 |
+
"loss": 2.3424,
|
| 415 |
+
"step": 50
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.59,
|
| 419 |
+
"grad_norm": 0.87890625,
|
| 420 |
+
"learning_rate": 0.0001461092501449326,
|
| 421 |
+
"loss": 2.506,
|
| 422 |
+
"step": 51
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.62,
|
| 426 |
+
"grad_norm": 0.7890625,
|
| 427 |
+
"learning_rate": 0.00014373073204588556,
|
| 428 |
+
"loss": 2.4829,
|
| 429 |
+
"step": 52
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.66,
|
| 433 |
+
"grad_norm": 0.984375,
|
| 434 |
+
"learning_rate": 0.00014132121857683783,
|
| 435 |
+
"loss": 2.481,
|
| 436 |
+
"step": 53
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.69,
|
| 440 |
+
"grad_norm": 0.9296875,
|
| 441 |
+
"learning_rate": 0.00013888241754733208,
|
| 442 |
+
"loss": 2.5512,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.72,
|
| 447 |
+
"grad_norm": 0.7890625,
|
| 448 |
+
"learning_rate": 0.00013641605752528224,
|
| 449 |
+
"loss": 2.5405,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.75,
|
| 454 |
+
"grad_norm": 0.95703125,
|
| 455 |
+
"learning_rate": 0.00013392388661180303,
|
| 456 |
+
"loss": 2.5221,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.75,
|
| 461 |
+
"eval_loss": 2.461298704147339,
|
| 462 |
+
"eval_runtime": 1.28,
|
| 463 |
+
"eval_samples_per_second": 10.937,
|
| 464 |
+
"eval_steps_per_second": 5.469,
|
| 465 |
+
"step": 56
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.78,
|
| 469 |
+
"grad_norm": 0.98046875,
|
| 470 |
+
"learning_rate": 0.0001314076712021949,
|
| 471 |
+
"loss": 2.5646,
|
| 472 |
+
"step": 57
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.81,
|
| 476 |
+
"grad_norm": 0.8125,
|
| 477 |
+
"learning_rate": 0.0001288691947339621,
|
| 478 |
+
"loss": 2.5079,
|
| 479 |
+
"step": 58
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.84,
|
| 483 |
+
"grad_norm": 0.8125,
|
| 484 |
+
"learning_rate": 0.00012631025642275212,
|
| 485 |
+
"loss": 2.4743,
|
| 486 |
+
"step": 59
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.88,
|
| 490 |
+
"grad_norm": 0.60546875,
|
| 491 |
+
"learning_rate": 0.0001237326699871115,
|
| 492 |
+
"loss": 2.3103,
|
| 493 |
+
"step": 60
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.91,
|
| 497 |
+
"grad_norm": 0.80859375,
|
| 498 |
+
"learning_rate": 0.00012113826236296244,
|
| 499 |
+
"loss": 2.4229,
|
| 500 |
+
"step": 61
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.94,
|
| 504 |
+
"grad_norm": 0.671875,
|
| 505 |
+
"learning_rate": 0.00011852887240871145,
|
| 506 |
+
"loss": 2.2709,
|
| 507 |
+
"step": 62
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.97,
|
| 511 |
+
"grad_norm": 0.8203125,
|
| 512 |
+
"learning_rate": 0.00011590634960190721,
|
| 513 |
+
"loss": 2.4868,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.0,
|
| 518 |
+
"grad_norm": 0.62109375,
|
| 519 |
+
"learning_rate": 0.00011327255272837221,
|
| 520 |
+
"loss": 2.4384,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0,
|
| 525 |
+
"eval_loss": 2.4055111408233643,
|
| 526 |
+
"eval_runtime": 1.2798,
|
| 527 |
+
"eval_samples_per_second": 10.94,
|
| 528 |
+
"eval_steps_per_second": 5.47,
|
| 529 |
+
"step": 64
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.03,
|
| 533 |
+
"grad_norm": 0.6328125,
|
| 534 |
+
"learning_rate": 0.00011062934856473655,
|
| 535 |
+
"loss": 2.3671,
|
| 536 |
+
"step": 65
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.06,
|
| 540 |
+
"grad_norm": 0.69140625,
|
| 541 |
+
"learning_rate": 0.00010797861055530831,
|
| 542 |
+
"loss": 2.3381,
|
| 543 |
+
"step": 66
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.09,
|
| 547 |
+
"grad_norm": 0.671875,
|
| 548 |
+
"learning_rate": 0.00010532221748421787,
|
| 549 |
+
"loss": 2.2134,
|
| 550 |
+
"step": 67
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.12,
|
| 554 |
+
"grad_norm": 0.7890625,
|
| 555 |
+
"learning_rate": 0.00010266205214377748,
|
| 556 |
+
"loss": 2.2687,
|
| 557 |
+
"step": 68
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.16,
|
| 561 |
+
"grad_norm": 0.75,
|
| 562 |
+
"learning_rate": 0.0001,
|
| 563 |
+
"loss": 2.4273,
|
| 564 |
+
"step": 69
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.19,
|
| 568 |
+
"grad_norm": 0.8671875,
|
| 569 |
+
"learning_rate": 9.733794785622253e-05,
|
| 570 |
+
"loss": 2.4439,
|
| 571 |
+
"step": 70
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.22,
|
| 575 |
+
"grad_norm": 0.953125,
|
| 576 |
+
"learning_rate": 9.467778251578217e-05,
|
| 577 |
+
"loss": 2.6631,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.25,
|
| 582 |
+
"grad_norm": 0.78125,
|
| 583 |
+
"learning_rate": 9.202138944469168e-05,
|
| 584 |
+
"loss": 2.295,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.25,
|
| 589 |
+
"eval_loss": 2.3922784328460693,
|
| 590 |
+
"eval_runtime": 1.282,
|
| 591 |
+
"eval_samples_per_second": 10.921,
|
| 592 |
+
"eval_steps_per_second": 5.46,
|
| 593 |
+
"step": 72
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.28,
|
| 597 |
+
"grad_norm": 0.734375,
|
| 598 |
+
"learning_rate": 8.937065143526347e-05,
|
| 599 |
+
"loss": 2.4963,
|
| 600 |
+
"step": 73
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.31,
|
| 604 |
+
"grad_norm": 0.68359375,
|
| 605 |
+
"learning_rate": 8.672744727162781e-05,
|
| 606 |
+
"loss": 2.4274,
|
| 607 |
+
"step": 74
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.34,
|
| 611 |
+
"grad_norm": 0.9765625,
|
| 612 |
+
"learning_rate": 8.409365039809281e-05,
|
| 613 |
+
"loss": 2.4988,
|
| 614 |
+
"step": 75
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.38,
|
| 618 |
+
"grad_norm": 0.75390625,
|
| 619 |
+
"learning_rate": 8.147112759128859e-05,
|
| 620 |
+
"loss": 2.2886,
|
| 621 |
+
"step": 76
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.41,
|
| 625 |
+
"grad_norm": 0.80078125,
|
| 626 |
+
"learning_rate": 7.886173763703757e-05,
|
| 627 |
+
"loss": 2.1944,
|
| 628 |
+
"step": 77
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.44,
|
| 632 |
+
"grad_norm": 0.8828125,
|
| 633 |
+
"learning_rate": 7.626733001288851e-05,
|
| 634 |
+
"loss": 2.3283,
|
| 635 |
+
"step": 78
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.47,
|
| 639 |
+
"grad_norm": 0.82421875,
|
| 640 |
+
"learning_rate": 7.368974357724789e-05,
|
| 641 |
+
"loss": 2.3855,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.5,
|
| 646 |
+
"grad_norm": 0.7890625,
|
| 647 |
+
"learning_rate": 7.113080526603792e-05,
|
| 648 |
+
"loss": 2.3943,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.5,
|
| 653 |
+
"eval_loss": 2.386228084564209,
|
| 654 |
+
"eval_runtime": 1.2835,
|
| 655 |
+
"eval_samples_per_second": 10.908,
|
| 656 |
+
"eval_steps_per_second": 5.454,
|
| 657 |
+
"step": 80
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.53,
|
| 661 |
+
"grad_norm": 0.94921875,
|
| 662 |
+
"learning_rate": 6.859232879780515e-05,
|
| 663 |
+
"loss": 2.2725,
|
| 664 |
+
"step": 81
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.56,
|
| 668 |
+
"grad_norm": 0.75,
|
| 669 |
+
"learning_rate": 6.607611338819697e-05,
|
| 670 |
+
"loss": 2.1989,
|
| 671 |
+
"step": 82
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.59,
|
| 675 |
+
"grad_norm": 0.703125,
|
| 676 |
+
"learning_rate": 6.358394247471778e-05,
|
| 677 |
+
"loss": 2.1219,
|
| 678 |
+
"step": 83
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.62,
|
| 682 |
+
"grad_norm": 1.0390625,
|
| 683 |
+
"learning_rate": 6.111758245266794e-05,
|
| 684 |
+
"loss": 2.3478,
|
| 685 |
+
"step": 84
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.66,
|
| 689 |
+
"grad_norm": 0.78125,
|
| 690 |
+
"learning_rate": 5.867878142316221e-05,
|
| 691 |
+
"loss": 2.4196,
|
| 692 |
+
"step": 85
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.69,
|
| 696 |
+
"grad_norm": 0.6796875,
|
| 697 |
+
"learning_rate": 5.626926795411447e-05,
|
| 698 |
+
"loss": 2.1882,
|
| 699 |
+
"step": 86
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.72,
|
| 703 |
+
"grad_norm": 0.8203125,
|
| 704 |
+
"learning_rate": 5.38907498550674e-05,
|
| 705 |
+
"loss": 2.4703,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.75,
|
| 710 |
+
"grad_norm": 0.8671875,
|
| 711 |
+
"learning_rate": 5.1544912966734994e-05,
|
| 712 |
+
"loss": 2.2398,
|
| 713 |
+
"step": 88
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.75,
|
| 717 |
+
"eval_loss": 2.3605105876922607,
|
| 718 |
+
"eval_runtime": 1.2887,
|
| 719 |
+
"eval_samples_per_second": 10.864,
|
| 720 |
+
"eval_steps_per_second": 5.432,
|
| 721 |
+
"step": 88
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.78,
|
| 725 |
+
"grad_norm": 0.81640625,
|
| 726 |
+
"learning_rate": 4.9233419966116036e-05,
|
| 727 |
+
"loss": 2.2939,
|
| 728 |
+
"step": 89
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.81,
|
| 732 |
+
"grad_norm": 1.0234375,
|
| 733 |
+
"learning_rate": 4.695790918802576e-05,
|
| 734 |
+
"loss": 2.2835,
|
| 735 |
+
"step": 90
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.84,
|
| 739 |
+
"grad_norm": 0.85546875,
|
| 740 |
+
"learning_rate": 4.47199934638807e-05,
|
| 741 |
+
"loss": 2.3145,
|
| 742 |
+
"step": 91
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.88,
|
| 746 |
+
"grad_norm": 0.5546875,
|
| 747 |
+
"learning_rate": 4.252125897855932e-05,
|
| 748 |
+
"loss": 2.2521,
|
| 749 |
+
"step": 92
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.91,
|
| 753 |
+
"grad_norm": 0.76953125,
|
| 754 |
+
"learning_rate": 4.036326414614985e-05,
|
| 755 |
+
"loss": 2.377,
|
| 756 |
+
"step": 93
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.94,
|
| 760 |
+
"grad_norm": 0.78125,
|
| 761 |
+
"learning_rate": 3.824753850538082e-05,
|
| 762 |
+
"loss": 2.4343,
|
| 763 |
+
"step": 94
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.97,
|
| 767 |
+
"grad_norm": 0.8046875,
|
| 768 |
+
"learning_rate": 3.617558163551802e-05,
|
| 769 |
+
"loss": 2.2051,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.0,
|
| 774 |
+
"grad_norm": 0.88671875,
|
| 775 |
+
"learning_rate": 3.414886209349615e-05,
|
| 776 |
+
"loss": 2.2693,
|
| 777 |
+
"step": 96
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.0,
|
| 781 |
+
"eval_loss": 2.3525888919830322,
|
| 782 |
+
"eval_runtime": 1.2821,
|
| 783 |
+
"eval_samples_per_second": 10.919,
|
| 784 |
+
"eval_steps_per_second": 5.46,
|
| 785 |
+
"step": 96
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.03,
|
| 789 |
+
"grad_norm": 0.74609375,
|
| 790 |
+
"learning_rate": 3.216881637303839e-05,
|
| 791 |
+
"loss": 2.5048,
|
| 792 |
+
"step": 97
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 3.06,
|
| 796 |
+
"grad_norm": 0.95703125,
|
| 797 |
+
"learning_rate": 3.0236847886501542e-05,
|
| 798 |
+
"loss": 2.3404,
|
| 799 |
+
"step": 98
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 3.09,
|
| 803 |
+
"grad_norm": 0.69140625,
|
| 804 |
+
"learning_rate": 2.8354325970168484e-05,
|
| 805 |
+
"loss": 2.3147,
|
| 806 |
+
"step": 99
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.12,
|
| 810 |
+
"grad_norm": 0.765625,
|
| 811 |
+
"learning_rate": 2.6522584913693294e-05,
|
| 812 |
+
"loss": 2.448,
|
| 813 |
+
"step": 100
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.16,
|
| 817 |
+
"grad_norm": 0.671875,
|
| 818 |
+
"learning_rate": 2.4742923014386156e-05,
|
| 819 |
+
"loss": 2.2212,
|
| 820 |
+
"step": 101
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.19,
|
| 824 |
+
"grad_norm": 0.625,
|
| 825 |
+
"learning_rate": 2.301660165700936e-05,
|
| 826 |
+
"loss": 2.3427,
|
| 827 |
+
"step": 102
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.22,
|
| 831 |
+
"grad_norm": 0.6484375,
|
| 832 |
+
"learning_rate": 2.1344844419735755e-05,
|
| 833 |
+
"loss": 2.1,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.25,
|
| 838 |
+
"grad_norm": 0.73046875,
|
| 839 |
+
"learning_rate": 1.9728836206903656e-05,
|
| 840 |
+
"loss": 2.425,
|
| 841 |
+
"step": 104
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.25,
|
| 845 |
+
"eval_loss": 2.3470816612243652,
|
| 846 |
+
"eval_runtime": 1.2874,
|
| 847 |
+
"eval_samples_per_second": 10.875,
|
| 848 |
+
"eval_steps_per_second": 5.437,
|
| 849 |
+
"step": 104
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.28,
|
| 853 |
+
"grad_norm": 0.734375,
|
| 854 |
+
"learning_rate": 1.8169722409183097e-05,
|
| 855 |
+
"loss": 2.2268,
|
| 856 |
+
"step": 105
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.31,
|
| 860 |
+
"grad_norm": 0.8359375,
|
| 861 |
+
"learning_rate": 1.6668608091748495e-05,
|
| 862 |
+
"loss": 2.3695,
|
| 863 |
+
"step": 106
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.34,
|
| 867 |
+
"grad_norm": 0.58203125,
|
| 868 |
+
"learning_rate": 1.522655721103291e-05,
|
| 869 |
+
"loss": 2.1864,
|
| 870 |
+
"step": 107
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.38,
|
| 874 |
+
"grad_norm": 0.5703125,
|
| 875 |
+
"learning_rate": 1.3844591860619383e-05,
|
| 876 |
+
"loss": 2.2613,
|
| 877 |
+
"step": 108
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 3.41,
|
| 881 |
+
"grad_norm": 0.7265625,
|
| 882 |
+
"learning_rate": 1.2523691546803873e-05,
|
| 883 |
+
"loss": 2.2771,
|
| 884 |
+
"step": 109
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.44,
|
| 888 |
+
"grad_norm": 0.59765625,
|
| 889 |
+
"learning_rate": 1.1264792494342857e-05,
|
| 890 |
+
"loss": 2.2056,
|
| 891 |
+
"step": 110
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 3.47,
|
| 895 |
+
"grad_norm": 0.6875,
|
| 896 |
+
"learning_rate": 1.0068786982878087e-05,
|
| 897 |
+
"loss": 2.4039,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 3.5,
|
| 902 |
+
"grad_norm": 0.77734375,
|
| 903 |
+
"learning_rate": 8.936522714508678e-06,
|
| 904 |
+
"loss": 2.2857,
|
| 905 |
+
"step": 112
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.5,
|
| 909 |
+
"eval_loss": 2.3467748165130615,
|
| 910 |
+
"eval_runtime": 1.2808,
|
| 911 |
+
"eval_samples_per_second": 10.931,
|
| 912 |
+
"eval_steps_per_second": 5.466,
|
| 913 |
+
"step": 112
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.53,
|
| 917 |
+
"grad_norm": 0.671875,
|
| 918 |
+
"learning_rate": 7.868802212958703e-06,
|
| 919 |
+
"loss": 2.257,
|
| 920 |
+
"step": 113
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.56,
|
| 924 |
+
"grad_norm": 1.21875,
|
| 925 |
+
"learning_rate": 6.866382254766157e-06,
|
| 926 |
+
"loss": 2.4278,
|
| 927 |
+
"step": 114
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.59,
|
| 931 |
+
"grad_norm": 0.859375,
|
| 932 |
+
"learning_rate": 5.929973332896677e-06,
|
| 933 |
+
"loss": 2.2232,
|
| 934 |
+
"step": 115
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.62,
|
| 938 |
+
"grad_norm": 0.66015625,
|
| 939 |
+
"learning_rate": 5.060239153161872e-06,
|
| 940 |
+
"loss": 2.225,
|
| 941 |
+
"step": 116
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.66,
|
| 945 |
+
"grad_norm": 0.6875,
|
| 946 |
+
"learning_rate": 4.257796163799455e-06,
|
| 947 |
+
"loss": 2.2133,
|
| 948 |
+
"step": 117
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.69,
|
| 952 |
+
"grad_norm": 0.8671875,
|
| 953 |
+
"learning_rate": 3.5232131185484076e-06,
|
| 954 |
+
"loss": 2.2191,
|
| 955 |
+
"step": 118
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.72,
|
| 959 |
+
"grad_norm": 0.77734375,
|
| 960 |
+
"learning_rate": 2.857010673529015e-06,
|
| 961 |
+
"loss": 2.0715,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 3.75,
|
| 966 |
+
"grad_norm": 0.72265625,
|
| 967 |
+
"learning_rate": 2.259661018213333e-06,
|
| 968 |
+
"loss": 2.2448,
|
| 969 |
+
"step": 120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.75,
|
| 973 |
+
"eval_loss": 2.3450927734375,
|
| 974 |
+
"eval_runtime": 1.2817,
|
| 975 |
+
"eval_samples_per_second": 10.923,
|
| 976 |
+
"eval_steps_per_second": 5.461,
|
| 977 |
+
"step": 120
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.78,
|
| 981 |
+
"grad_norm": 0.62109375,
|
| 982 |
+
"learning_rate": 1.7315875407479032e-06,
|
| 983 |
+
"loss": 2.1337,
|
| 984 |
+
"step": 121
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.81,
|
| 988 |
+
"grad_norm": 0.765625,
|
| 989 |
+
"learning_rate": 1.2731645278655445e-06,
|
| 990 |
+
"loss": 2.4334,
|
| 991 |
+
"step": 122
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 3.84,
|
| 995 |
+
"grad_norm": 0.73828125,
|
| 996 |
+
"learning_rate": 8.847168995992916e-07,
|
| 997 |
+
"loss": 2.3989,
|
| 998 |
+
"step": 123
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.88,
|
| 1002 |
+
"grad_norm": 0.71484375,
|
| 1003 |
+
"learning_rate": 5.665199789862907e-07,
|
| 1004 |
+
"loss": 2.3509,
|
| 1005 |
+
"step": 124
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.91,
|
| 1009 |
+
"grad_norm": 0.78125,
|
| 1010 |
+
"learning_rate": 3.1879929692498757e-07,
|
| 1011 |
+
"loss": 2.3366,
|
| 1012 |
+
"step": 125
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 3.94,
|
| 1016 |
+
"grad_norm": 0.625,
|
| 1017 |
+
"learning_rate": 1.4173043232380557e-07,
|
| 1018 |
+
"loss": 2.071,
|
| 1019 |
+
"step": 126
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.97,
|
| 1023 |
+
"grad_norm": 0.6015625,
|
| 1024 |
+
"learning_rate": 3.5438887654737355e-08,
|
| 1025 |
+
"loss": 2.2108,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 4.0,
|
| 1030 |
+
"grad_norm": 0.7578125,
|
| 1031 |
+
"learning_rate": 0.0,
|
| 1032 |
+
"loss": 2.1836,
|
| 1033 |
+
"step": 128
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.0,
|
| 1037 |
+
"eval_loss": 2.3465805053710938,
|
| 1038 |
+
"eval_runtime": 1.2864,
|
| 1039 |
+
"eval_samples_per_second": 10.883,
|
| 1040 |
+
"eval_steps_per_second": 5.441,
|
| 1041 |
+
"step": 128
|
| 1042 |
+
}
|
| 1043 |
+
],
|
| 1044 |
+
"logging_steps": 1,
|
| 1045 |
+
"max_steps": 128,
|
| 1046 |
+
"num_input_tokens_seen": 0,
|
| 1047 |
+
"num_train_epochs": 4,
|
| 1048 |
+
"save_steps": 32,
|
| 1049 |
+
"total_flos": 2.6669324546605056e+16,
|
| 1050 |
+
"train_batch_size": 2,
|
| 1051 |
+
"trial_name": null,
|
| 1052 |
+
"trial_params": null
|
| 1053 |
+
}
|
checkpoint-128/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
|
| 3 |
+
size 5816
|
checkpoint-32/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-32/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 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-32/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec430d847c06078c87671f113c67363bf58b51f662fe0c2c9aac1aea9197c05e
|
| 3 |
+
size 50503848
|
checkpoint-32/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2dcfc1311f5586ce9bc6ab8405e3706e4dcb6ef0050771e2c9bbe97b1fc7874
|
| 3 |
+
size 202035450
|
checkpoint-32/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fba88830bbf3f3a231c5f7c643ca357bcc703c4a14675504974ab2e003369a61
|
| 3 |
+
size 14244
|
checkpoint-32/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73fa7fed0c0930926a3524b49ae450b78da12282a81cf57d30f2d1a4044247d8
|
| 3 |
+
size 1064
|
checkpoint-32/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-32/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-32/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false,
|
| 43 |
+
"use_fast": true
|
| 44 |
+
}
|
checkpoint-32/trainer_state.json
ADDED
|
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 8,
|
| 6 |
+
"global_step": 32,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.5859375,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 3.9295,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 3.907318115234375,
|
| 21 |
+
"eval_runtime": 1.2713,
|
| 22 |
+
"eval_samples_per_second": 11.012,
|
| 23 |
+
"eval_steps_per_second": 5.506,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 0.5078125,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 3.805,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09,
|
| 35 |
+
"grad_norm": 0.63671875,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 3.8521,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"grad_norm": 0.609375,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 3.8947,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"grad_norm": 0.546875,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 3.6494,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19,
|
| 56 |
+
"grad_norm": 0.50390625,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 3.6457,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22,
|
| 63 |
+
"grad_norm": 0.640625,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 3.967,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25,
|
| 70 |
+
"grad_norm": 0.494140625,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 3.5364,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25,
|
| 77 |
+
"eval_loss": 3.6198840141296387,
|
| 78 |
+
"eval_runtime": 1.2681,
|
| 79 |
+
"eval_samples_per_second": 11.04,
|
| 80 |
+
"eval_steps_per_second": 5.52,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.28,
|
| 85 |
+
"grad_norm": 0.51171875,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 3.5216,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.31,
|
| 92 |
+
"grad_norm": 0.6171875,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 3.677,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.34,
|
| 99 |
+
"grad_norm": 0.734375,
|
| 100 |
+
"learning_rate": 0.00019996456111234527,
|
| 101 |
+
"loss": 3.058,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.38,
|
| 106 |
+
"grad_norm": 0.66796875,
|
| 107 |
+
"learning_rate": 0.0001998582695676762,
|
| 108 |
+
"loss": 3.1333,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.41,
|
| 113 |
+
"grad_norm": 0.8359375,
|
| 114 |
+
"learning_rate": 0.000199681200703075,
|
| 115 |
+
"loss": 3.38,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.44,
|
| 120 |
+
"grad_norm": 0.62109375,
|
| 121 |
+
"learning_rate": 0.00019943348002101371,
|
| 122 |
+
"loss": 3.1371,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.47,
|
| 127 |
+
"grad_norm": 0.65625,
|
| 128 |
+
"learning_rate": 0.00019911528310040074,
|
| 129 |
+
"loss": 3.1479,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5,
|
| 134 |
+
"grad_norm": 0.6484375,
|
| 135 |
+
"learning_rate": 0.00019872683547213446,
|
| 136 |
+
"loss": 3.263,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5,
|
| 141 |
+
"eval_loss": 3.1820719242095947,
|
| 142 |
+
"eval_runtime": 1.2692,
|
| 143 |
+
"eval_samples_per_second": 11.031,
|
| 144 |
+
"eval_steps_per_second": 5.515,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.53,
|
| 149 |
+
"grad_norm": 0.53125,
|
| 150 |
+
"learning_rate": 0.00019826841245925212,
|
| 151 |
+
"loss": 2.9833,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.56,
|
| 156 |
+
"grad_norm": 0.5703125,
|
| 157 |
+
"learning_rate": 0.00019774033898178667,
|
| 158 |
+
"loss": 3.0787,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.59,
|
| 163 |
+
"grad_norm": 0.71484375,
|
| 164 |
+
"learning_rate": 0.00019714298932647098,
|
| 165 |
+
"loss": 3.4132,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.62,
|
| 170 |
+
"grad_norm": 0.73046875,
|
| 171 |
+
"learning_rate": 0.0001964767868814516,
|
| 172 |
+
"loss": 2.7304,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.66,
|
| 177 |
+
"grad_norm": 0.55078125,
|
| 178 |
+
"learning_rate": 0.00019574220383620055,
|
| 179 |
+
"loss": 3.0116,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.69,
|
| 184 |
+
"grad_norm": 0.6171875,
|
| 185 |
+
"learning_rate": 0.00019493976084683813,
|
| 186 |
+
"loss": 2.9474,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"grad_norm": 0.61328125,
|
| 192 |
+
"learning_rate": 0.00019407002666710336,
|
| 193 |
+
"loss": 2.9415,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"grad_norm": 0.6328125,
|
| 199 |
+
"learning_rate": 0.00019313361774523385,
|
| 200 |
+
"loss": 2.798,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.75,
|
| 205 |
+
"eval_loss": 2.896176815032959,
|
| 206 |
+
"eval_runtime": 1.2765,
|
| 207 |
+
"eval_samples_per_second": 10.967,
|
| 208 |
+
"eval_steps_per_second": 5.484,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"grad_norm": 0.8046875,
|
| 214 |
+
"learning_rate": 0.00019213119778704128,
|
| 215 |
+
"loss": 3.2157,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.81,
|
| 220 |
+
"grad_norm": 0.7109375,
|
| 221 |
+
"learning_rate": 0.00019106347728549135,
|
| 222 |
+
"loss": 3.0666,
|
| 223 |
+
"step": 26
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.84,
|
| 227 |
+
"grad_norm": 0.59765625,
|
| 228 |
+
"learning_rate": 0.00018993121301712193,
|
| 229 |
+
"loss": 2.8219,
|
| 230 |
+
"step": 27
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.88,
|
| 234 |
+
"grad_norm": 0.75390625,
|
| 235 |
+
"learning_rate": 0.00018873520750565718,
|
| 236 |
+
"loss": 3.1164,
|
| 237 |
+
"step": 28
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.91,
|
| 241 |
+
"grad_norm": 0.67578125,
|
| 242 |
+
"learning_rate": 0.00018747630845319612,
|
| 243 |
+
"loss": 2.7154,
|
| 244 |
+
"step": 29
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.94,
|
| 248 |
+
"grad_norm": 0.625,
|
| 249 |
+
"learning_rate": 0.0001861554081393806,
|
| 250 |
+
"loss": 2.7395,
|
| 251 |
+
"step": 30
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.97,
|
| 255 |
+
"grad_norm": 0.8125,
|
| 256 |
+
"learning_rate": 0.0001847734427889671,
|
| 257 |
+
"loss": 2.8282,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.0,
|
| 262 |
+
"grad_norm": 0.86328125,
|
| 263 |
+
"learning_rate": 0.0001833313919082515,
|
| 264 |
+
"loss": 2.7787,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.0,
|
| 269 |
+
"eval_loss": 2.67726731300354,
|
| 270 |
+
"eval_runtime": 1.2769,
|
| 271 |
+
"eval_samples_per_second": 10.964,
|
| 272 |
+
"eval_steps_per_second": 5.482,
|
| 273 |
+
"step": 32
|
| 274 |
+
}
|
| 275 |
+
],
|
| 276 |
+
"logging_steps": 1,
|
| 277 |
+
"max_steps": 128,
|
| 278 |
+
"num_input_tokens_seen": 0,
|
| 279 |
+
"num_train_epochs": 4,
|
| 280 |
+
"save_steps": 32,
|
| 281 |
+
"total_flos": 6667331136651264.0,
|
| 282 |
+
"train_batch_size": 2,
|
| 283 |
+
"trial_name": null,
|
| 284 |
+
"trial_params": null
|
| 285 |
+
}
|
checkpoint-32/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
|
| 3 |
+
size 5816
|
checkpoint-64/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-64/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 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-64/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:478e962adcf5cf2208e94455da60f82ca1058e1b9684714f9c16065ef2896b84
|
| 3 |
+
size 50503848
|
checkpoint-64/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f7fae12b68510716cf6c13d76435aadee62c6caf362f7880a7604a4378d4478
|
| 3 |
+
size 202035450
|
checkpoint-64/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:926ec53b6c5e5969c7a9dedbcd5e4c4ff81ecd6859afd62f93fd8684f6ac758d
|
| 3 |
+
size 14244
|
checkpoint-64/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc2f121208237af7a1af0cb966f4edc3bb705d4fe4813c302cf1425b7f9228d4
|
| 3 |
+
size 1064
|
checkpoint-64/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-64/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-64/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false,
|
| 43 |
+
"use_fast": true
|
| 44 |
+
}
|
checkpoint-64/trainer_state.json
ADDED
|
@@ -0,0 +1,541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 8,
|
| 6 |
+
"global_step": 64,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.5859375,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 3.9295,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 3.907318115234375,
|
| 21 |
+
"eval_runtime": 1.2713,
|
| 22 |
+
"eval_samples_per_second": 11.012,
|
| 23 |
+
"eval_steps_per_second": 5.506,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 0.5078125,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 3.805,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09,
|
| 35 |
+
"grad_norm": 0.63671875,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 3.8521,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"grad_norm": 0.609375,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 3.8947,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"grad_norm": 0.546875,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 3.6494,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19,
|
| 56 |
+
"grad_norm": 0.50390625,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 3.6457,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22,
|
| 63 |
+
"grad_norm": 0.640625,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 3.967,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25,
|
| 70 |
+
"grad_norm": 0.494140625,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 3.5364,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25,
|
| 77 |
+
"eval_loss": 3.6198840141296387,
|
| 78 |
+
"eval_runtime": 1.2681,
|
| 79 |
+
"eval_samples_per_second": 11.04,
|
| 80 |
+
"eval_steps_per_second": 5.52,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.28,
|
| 85 |
+
"grad_norm": 0.51171875,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 3.5216,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.31,
|
| 92 |
+
"grad_norm": 0.6171875,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 3.677,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.34,
|
| 99 |
+
"grad_norm": 0.734375,
|
| 100 |
+
"learning_rate": 0.00019996456111234527,
|
| 101 |
+
"loss": 3.058,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.38,
|
| 106 |
+
"grad_norm": 0.66796875,
|
| 107 |
+
"learning_rate": 0.0001998582695676762,
|
| 108 |
+
"loss": 3.1333,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.41,
|
| 113 |
+
"grad_norm": 0.8359375,
|
| 114 |
+
"learning_rate": 0.000199681200703075,
|
| 115 |
+
"loss": 3.38,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.44,
|
| 120 |
+
"grad_norm": 0.62109375,
|
| 121 |
+
"learning_rate": 0.00019943348002101371,
|
| 122 |
+
"loss": 3.1371,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.47,
|
| 127 |
+
"grad_norm": 0.65625,
|
| 128 |
+
"learning_rate": 0.00019911528310040074,
|
| 129 |
+
"loss": 3.1479,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5,
|
| 134 |
+
"grad_norm": 0.6484375,
|
| 135 |
+
"learning_rate": 0.00019872683547213446,
|
| 136 |
+
"loss": 3.263,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5,
|
| 141 |
+
"eval_loss": 3.1820719242095947,
|
| 142 |
+
"eval_runtime": 1.2692,
|
| 143 |
+
"eval_samples_per_second": 11.031,
|
| 144 |
+
"eval_steps_per_second": 5.515,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.53,
|
| 149 |
+
"grad_norm": 0.53125,
|
| 150 |
+
"learning_rate": 0.00019826841245925212,
|
| 151 |
+
"loss": 2.9833,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.56,
|
| 156 |
+
"grad_norm": 0.5703125,
|
| 157 |
+
"learning_rate": 0.00019774033898178667,
|
| 158 |
+
"loss": 3.0787,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.59,
|
| 163 |
+
"grad_norm": 0.71484375,
|
| 164 |
+
"learning_rate": 0.00019714298932647098,
|
| 165 |
+
"loss": 3.4132,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.62,
|
| 170 |
+
"grad_norm": 0.73046875,
|
| 171 |
+
"learning_rate": 0.0001964767868814516,
|
| 172 |
+
"loss": 2.7304,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.66,
|
| 177 |
+
"grad_norm": 0.55078125,
|
| 178 |
+
"learning_rate": 0.00019574220383620055,
|
| 179 |
+
"loss": 3.0116,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.69,
|
| 184 |
+
"grad_norm": 0.6171875,
|
| 185 |
+
"learning_rate": 0.00019493976084683813,
|
| 186 |
+
"loss": 2.9474,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"grad_norm": 0.61328125,
|
| 192 |
+
"learning_rate": 0.00019407002666710336,
|
| 193 |
+
"loss": 2.9415,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"grad_norm": 0.6328125,
|
| 199 |
+
"learning_rate": 0.00019313361774523385,
|
| 200 |
+
"loss": 2.798,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.75,
|
| 205 |
+
"eval_loss": 2.896176815032959,
|
| 206 |
+
"eval_runtime": 1.2765,
|
| 207 |
+
"eval_samples_per_second": 10.967,
|
| 208 |
+
"eval_steps_per_second": 5.484,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"grad_norm": 0.8046875,
|
| 214 |
+
"learning_rate": 0.00019213119778704128,
|
| 215 |
+
"loss": 3.2157,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.81,
|
| 220 |
+
"grad_norm": 0.7109375,
|
| 221 |
+
"learning_rate": 0.00019106347728549135,
|
| 222 |
+
"loss": 3.0666,
|
| 223 |
+
"step": 26
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.84,
|
| 227 |
+
"grad_norm": 0.59765625,
|
| 228 |
+
"learning_rate": 0.00018993121301712193,
|
| 229 |
+
"loss": 2.8219,
|
| 230 |
+
"step": 27
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.88,
|
| 234 |
+
"grad_norm": 0.75390625,
|
| 235 |
+
"learning_rate": 0.00018873520750565718,
|
| 236 |
+
"loss": 3.1164,
|
| 237 |
+
"step": 28
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.91,
|
| 241 |
+
"grad_norm": 0.67578125,
|
| 242 |
+
"learning_rate": 0.00018747630845319612,
|
| 243 |
+
"loss": 2.7154,
|
| 244 |
+
"step": 29
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.94,
|
| 248 |
+
"grad_norm": 0.625,
|
| 249 |
+
"learning_rate": 0.0001861554081393806,
|
| 250 |
+
"loss": 2.7395,
|
| 251 |
+
"step": 30
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.97,
|
| 255 |
+
"grad_norm": 0.8125,
|
| 256 |
+
"learning_rate": 0.0001847734427889671,
|
| 257 |
+
"loss": 2.8282,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.0,
|
| 262 |
+
"grad_norm": 0.86328125,
|
| 263 |
+
"learning_rate": 0.0001833313919082515,
|
| 264 |
+
"loss": 2.7787,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.0,
|
| 269 |
+
"eval_loss": 2.67726731300354,
|
| 270 |
+
"eval_runtime": 1.2769,
|
| 271 |
+
"eval_samples_per_second": 10.964,
|
| 272 |
+
"eval_steps_per_second": 5.482,
|
| 273 |
+
"step": 32
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.03,
|
| 277 |
+
"grad_norm": 0.703125,
|
| 278 |
+
"learning_rate": 0.0001818302775908169,
|
| 279 |
+
"loss": 2.5957,
|
| 280 |
+
"step": 33
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.06,
|
| 284 |
+
"grad_norm": 0.76953125,
|
| 285 |
+
"learning_rate": 0.00018027116379309638,
|
| 286 |
+
"loss": 2.7011,
|
| 287 |
+
"step": 34
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.09,
|
| 291 |
+
"grad_norm": 0.84765625,
|
| 292 |
+
"learning_rate": 0.00017865515558026428,
|
| 293 |
+
"loss": 2.6043,
|
| 294 |
+
"step": 35
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.12,
|
| 298 |
+
"grad_norm": 0.984375,
|
| 299 |
+
"learning_rate": 0.00017698339834299061,
|
| 300 |
+
"loss": 2.8607,
|
| 301 |
+
"step": 36
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.16,
|
| 305 |
+
"grad_norm": 0.7578125,
|
| 306 |
+
"learning_rate": 0.00017525707698561385,
|
| 307 |
+
"loss": 2.5949,
|
| 308 |
+
"step": 37
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.19,
|
| 312 |
+
"grad_norm": 0.94921875,
|
| 313 |
+
"learning_rate": 0.00017347741508630672,
|
| 314 |
+
"loss": 2.7476,
|
| 315 |
+
"step": 38
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.22,
|
| 319 |
+
"grad_norm": 0.88671875,
|
| 320 |
+
"learning_rate": 0.00017164567402983152,
|
| 321 |
+
"loss": 2.7991,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.25,
|
| 326 |
+
"grad_norm": 0.8671875,
|
| 327 |
+
"learning_rate": 0.0001697631521134985,
|
| 328 |
+
"loss": 2.5959,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.25,
|
| 333 |
+
"eval_loss": 2.5505764484405518,
|
| 334 |
+
"eval_runtime": 1.2761,
|
| 335 |
+
"eval_samples_per_second": 10.971,
|
| 336 |
+
"eval_steps_per_second": 5.486,
|
| 337 |
+
"step": 40
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.28,
|
| 341 |
+
"grad_norm": 0.984375,
|
| 342 |
+
"learning_rate": 0.00016783118362696163,
|
| 343 |
+
"loss": 2.5342,
|
| 344 |
+
"step": 41
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"grad_norm": 0.921875,
|
| 349 |
+
"learning_rate": 0.00016585113790650388,
|
| 350 |
+
"loss": 2.4969,
|
| 351 |
+
"step": 42
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.34,
|
| 355 |
+
"grad_norm": 1.125,
|
| 356 |
+
"learning_rate": 0.00016382441836448202,
|
| 357 |
+
"loss": 2.5723,
|
| 358 |
+
"step": 43
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.38,
|
| 362 |
+
"grad_norm": 1.015625,
|
| 363 |
+
"learning_rate": 0.0001617524614946192,
|
| 364 |
+
"loss": 2.6166,
|
| 365 |
+
"step": 44
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.41,
|
| 369 |
+
"grad_norm": 0.98828125,
|
| 370 |
+
"learning_rate": 0.00015963673585385016,
|
| 371 |
+
"loss": 2.4574,
|
| 372 |
+
"step": 45
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.44,
|
| 376 |
+
"grad_norm": 0.94921875,
|
| 377 |
+
"learning_rate": 0.0001574787410214407,
|
| 378 |
+
"loss": 2.5074,
|
| 379 |
+
"step": 46
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.47,
|
| 383 |
+
"grad_norm": 0.953125,
|
| 384 |
+
"learning_rate": 0.00015528000653611935,
|
| 385 |
+
"loss": 2.5394,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.5,
|
| 390 |
+
"grad_norm": 0.828125,
|
| 391 |
+
"learning_rate": 0.00015304209081197425,
|
| 392 |
+
"loss": 2.4793,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5,
|
| 397 |
+
"eval_loss": 2.495466470718384,
|
| 398 |
+
"eval_runtime": 1.2814,
|
| 399 |
+
"eval_samples_per_second": 10.926,
|
| 400 |
+
"eval_steps_per_second": 5.463,
|
| 401 |
+
"step": 48
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.53,
|
| 405 |
+
"grad_norm": 0.921875,
|
| 406 |
+
"learning_rate": 0.000150766580033884,
|
| 407 |
+
"loss": 2.2909,
|
| 408 |
+
"step": 49
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.56,
|
| 412 |
+
"grad_norm": 0.74609375,
|
| 413 |
+
"learning_rate": 0.00014845508703326504,
|
| 414 |
+
"loss": 2.3424,
|
| 415 |
+
"step": 50
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.59,
|
| 419 |
+
"grad_norm": 0.87890625,
|
| 420 |
+
"learning_rate": 0.0001461092501449326,
|
| 421 |
+
"loss": 2.506,
|
| 422 |
+
"step": 51
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.62,
|
| 426 |
+
"grad_norm": 0.7890625,
|
| 427 |
+
"learning_rate": 0.00014373073204588556,
|
| 428 |
+
"loss": 2.4829,
|
| 429 |
+
"step": 52
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.66,
|
| 433 |
+
"grad_norm": 0.984375,
|
| 434 |
+
"learning_rate": 0.00014132121857683783,
|
| 435 |
+
"loss": 2.481,
|
| 436 |
+
"step": 53
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.69,
|
| 440 |
+
"grad_norm": 0.9296875,
|
| 441 |
+
"learning_rate": 0.00013888241754733208,
|
| 442 |
+
"loss": 2.5512,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.72,
|
| 447 |
+
"grad_norm": 0.7890625,
|
| 448 |
+
"learning_rate": 0.00013641605752528224,
|
| 449 |
+
"loss": 2.5405,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.75,
|
| 454 |
+
"grad_norm": 0.95703125,
|
| 455 |
+
"learning_rate": 0.00013392388661180303,
|
| 456 |
+
"loss": 2.5221,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.75,
|
| 461 |
+
"eval_loss": 2.461298704147339,
|
| 462 |
+
"eval_runtime": 1.28,
|
| 463 |
+
"eval_samples_per_second": 10.937,
|
| 464 |
+
"eval_steps_per_second": 5.469,
|
| 465 |
+
"step": 56
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.78,
|
| 469 |
+
"grad_norm": 0.98046875,
|
| 470 |
+
"learning_rate": 0.0001314076712021949,
|
| 471 |
+
"loss": 2.5646,
|
| 472 |
+
"step": 57
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.81,
|
| 476 |
+
"grad_norm": 0.8125,
|
| 477 |
+
"learning_rate": 0.0001288691947339621,
|
| 478 |
+
"loss": 2.5079,
|
| 479 |
+
"step": 58
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.84,
|
| 483 |
+
"grad_norm": 0.8125,
|
| 484 |
+
"learning_rate": 0.00012631025642275212,
|
| 485 |
+
"loss": 2.4743,
|
| 486 |
+
"step": 59
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.88,
|
| 490 |
+
"grad_norm": 0.60546875,
|
| 491 |
+
"learning_rate": 0.0001237326699871115,
|
| 492 |
+
"loss": 2.3103,
|
| 493 |
+
"step": 60
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.91,
|
| 497 |
+
"grad_norm": 0.80859375,
|
| 498 |
+
"learning_rate": 0.00012113826236296244,
|
| 499 |
+
"loss": 2.4229,
|
| 500 |
+
"step": 61
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.94,
|
| 504 |
+
"grad_norm": 0.671875,
|
| 505 |
+
"learning_rate": 0.00011852887240871145,
|
| 506 |
+
"loss": 2.2709,
|
| 507 |
+
"step": 62
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.97,
|
| 511 |
+
"grad_norm": 0.8203125,
|
| 512 |
+
"learning_rate": 0.00011590634960190721,
|
| 513 |
+
"loss": 2.4868,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.0,
|
| 518 |
+
"grad_norm": 0.62109375,
|
| 519 |
+
"learning_rate": 0.00011327255272837221,
|
| 520 |
+
"loss": 2.4384,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0,
|
| 525 |
+
"eval_loss": 2.4055111408233643,
|
| 526 |
+
"eval_runtime": 1.2798,
|
| 527 |
+
"eval_samples_per_second": 10.94,
|
| 528 |
+
"eval_steps_per_second": 5.47,
|
| 529 |
+
"step": 64
|
| 530 |
+
}
|
| 531 |
+
],
|
| 532 |
+
"logging_steps": 1,
|
| 533 |
+
"max_steps": 128,
|
| 534 |
+
"num_input_tokens_seen": 0,
|
| 535 |
+
"num_train_epochs": 4,
|
| 536 |
+
"save_steps": 32,
|
| 537 |
+
"total_flos": 1.3334662273302528e+16,
|
| 538 |
+
"train_batch_size": 2,
|
| 539 |
+
"trial_name": null,
|
| 540 |
+
"trial_params": null
|
| 541 |
+
}
|
checkpoint-64/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
|
| 3 |
+
size 5816
|
checkpoint-96/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-96/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 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-96/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7f91dafd56822f172630cecc2b2e1daa597fdbbad4c82963c27fc7d9324b236
|
| 3 |
+
size 50503848
|
checkpoint-96/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:201f8255e7b843a6dce3b0a0f20c92b3051e4c17064d38df3bcda3aea4710751
|
| 3 |
+
size 202035450
|
checkpoint-96/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cdd17d0d9f68ae884a6c41c42875839a612f5c867257621410c8670377c4664
|
| 3 |
+
size 14244
|
checkpoint-96/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b76c8662d73a5a13047466dda569fd16697d4a2a715b2ad8f3567f25cfa42c3
|
| 3 |
+
size 1064
|
checkpoint-96/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-96/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-96/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false,
|
| 43 |
+
"use_fast": true
|
| 44 |
+
}
|
checkpoint-96/trainer_state.json
ADDED
|
@@ -0,0 +1,797 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 8,
|
| 6 |
+
"global_step": 96,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.5859375,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 3.9295,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 3.907318115234375,
|
| 21 |
+
"eval_runtime": 1.2713,
|
| 22 |
+
"eval_samples_per_second": 11.012,
|
| 23 |
+
"eval_steps_per_second": 5.506,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 0.5078125,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 3.805,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09,
|
| 35 |
+
"grad_norm": 0.63671875,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 3.8521,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"grad_norm": 0.609375,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 3.8947,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"grad_norm": 0.546875,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 3.6494,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19,
|
| 56 |
+
"grad_norm": 0.50390625,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 3.6457,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22,
|
| 63 |
+
"grad_norm": 0.640625,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 3.967,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25,
|
| 70 |
+
"grad_norm": 0.494140625,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 3.5364,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25,
|
| 77 |
+
"eval_loss": 3.6198840141296387,
|
| 78 |
+
"eval_runtime": 1.2681,
|
| 79 |
+
"eval_samples_per_second": 11.04,
|
| 80 |
+
"eval_steps_per_second": 5.52,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.28,
|
| 85 |
+
"grad_norm": 0.51171875,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 3.5216,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.31,
|
| 92 |
+
"grad_norm": 0.6171875,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 3.677,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.34,
|
| 99 |
+
"grad_norm": 0.734375,
|
| 100 |
+
"learning_rate": 0.00019996456111234527,
|
| 101 |
+
"loss": 3.058,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.38,
|
| 106 |
+
"grad_norm": 0.66796875,
|
| 107 |
+
"learning_rate": 0.0001998582695676762,
|
| 108 |
+
"loss": 3.1333,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.41,
|
| 113 |
+
"grad_norm": 0.8359375,
|
| 114 |
+
"learning_rate": 0.000199681200703075,
|
| 115 |
+
"loss": 3.38,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.44,
|
| 120 |
+
"grad_norm": 0.62109375,
|
| 121 |
+
"learning_rate": 0.00019943348002101371,
|
| 122 |
+
"loss": 3.1371,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.47,
|
| 127 |
+
"grad_norm": 0.65625,
|
| 128 |
+
"learning_rate": 0.00019911528310040074,
|
| 129 |
+
"loss": 3.1479,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5,
|
| 134 |
+
"grad_norm": 0.6484375,
|
| 135 |
+
"learning_rate": 0.00019872683547213446,
|
| 136 |
+
"loss": 3.263,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5,
|
| 141 |
+
"eval_loss": 3.1820719242095947,
|
| 142 |
+
"eval_runtime": 1.2692,
|
| 143 |
+
"eval_samples_per_second": 11.031,
|
| 144 |
+
"eval_steps_per_second": 5.515,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.53,
|
| 149 |
+
"grad_norm": 0.53125,
|
| 150 |
+
"learning_rate": 0.00019826841245925212,
|
| 151 |
+
"loss": 2.9833,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.56,
|
| 156 |
+
"grad_norm": 0.5703125,
|
| 157 |
+
"learning_rate": 0.00019774033898178667,
|
| 158 |
+
"loss": 3.0787,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.59,
|
| 163 |
+
"grad_norm": 0.71484375,
|
| 164 |
+
"learning_rate": 0.00019714298932647098,
|
| 165 |
+
"loss": 3.4132,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.62,
|
| 170 |
+
"grad_norm": 0.73046875,
|
| 171 |
+
"learning_rate": 0.0001964767868814516,
|
| 172 |
+
"loss": 2.7304,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.66,
|
| 177 |
+
"grad_norm": 0.55078125,
|
| 178 |
+
"learning_rate": 0.00019574220383620055,
|
| 179 |
+
"loss": 3.0116,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.69,
|
| 184 |
+
"grad_norm": 0.6171875,
|
| 185 |
+
"learning_rate": 0.00019493976084683813,
|
| 186 |
+
"loss": 2.9474,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"grad_norm": 0.61328125,
|
| 192 |
+
"learning_rate": 0.00019407002666710336,
|
| 193 |
+
"loss": 2.9415,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.75,
|
| 198 |
+
"grad_norm": 0.6328125,
|
| 199 |
+
"learning_rate": 0.00019313361774523385,
|
| 200 |
+
"loss": 2.798,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.75,
|
| 205 |
+
"eval_loss": 2.896176815032959,
|
| 206 |
+
"eval_runtime": 1.2765,
|
| 207 |
+
"eval_samples_per_second": 10.967,
|
| 208 |
+
"eval_steps_per_second": 5.484,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.78,
|
| 213 |
+
"grad_norm": 0.8046875,
|
| 214 |
+
"learning_rate": 0.00019213119778704128,
|
| 215 |
+
"loss": 3.2157,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.81,
|
| 220 |
+
"grad_norm": 0.7109375,
|
| 221 |
+
"learning_rate": 0.00019106347728549135,
|
| 222 |
+
"loss": 3.0666,
|
| 223 |
+
"step": 26
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.84,
|
| 227 |
+
"grad_norm": 0.59765625,
|
| 228 |
+
"learning_rate": 0.00018993121301712193,
|
| 229 |
+
"loss": 2.8219,
|
| 230 |
+
"step": 27
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.88,
|
| 234 |
+
"grad_norm": 0.75390625,
|
| 235 |
+
"learning_rate": 0.00018873520750565718,
|
| 236 |
+
"loss": 3.1164,
|
| 237 |
+
"step": 28
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.91,
|
| 241 |
+
"grad_norm": 0.67578125,
|
| 242 |
+
"learning_rate": 0.00018747630845319612,
|
| 243 |
+
"loss": 2.7154,
|
| 244 |
+
"step": 29
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.94,
|
| 248 |
+
"grad_norm": 0.625,
|
| 249 |
+
"learning_rate": 0.0001861554081393806,
|
| 250 |
+
"loss": 2.7395,
|
| 251 |
+
"step": 30
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.97,
|
| 255 |
+
"grad_norm": 0.8125,
|
| 256 |
+
"learning_rate": 0.0001847734427889671,
|
| 257 |
+
"loss": 2.8282,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.0,
|
| 262 |
+
"grad_norm": 0.86328125,
|
| 263 |
+
"learning_rate": 0.0001833313919082515,
|
| 264 |
+
"loss": 2.7787,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.0,
|
| 269 |
+
"eval_loss": 2.67726731300354,
|
| 270 |
+
"eval_runtime": 1.2769,
|
| 271 |
+
"eval_samples_per_second": 10.964,
|
| 272 |
+
"eval_steps_per_second": 5.482,
|
| 273 |
+
"step": 32
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.03,
|
| 277 |
+
"grad_norm": 0.703125,
|
| 278 |
+
"learning_rate": 0.0001818302775908169,
|
| 279 |
+
"loss": 2.5957,
|
| 280 |
+
"step": 33
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.06,
|
| 284 |
+
"grad_norm": 0.76953125,
|
| 285 |
+
"learning_rate": 0.00018027116379309638,
|
| 286 |
+
"loss": 2.7011,
|
| 287 |
+
"step": 34
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.09,
|
| 291 |
+
"grad_norm": 0.84765625,
|
| 292 |
+
"learning_rate": 0.00017865515558026428,
|
| 293 |
+
"loss": 2.6043,
|
| 294 |
+
"step": 35
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.12,
|
| 298 |
+
"grad_norm": 0.984375,
|
| 299 |
+
"learning_rate": 0.00017698339834299061,
|
| 300 |
+
"loss": 2.8607,
|
| 301 |
+
"step": 36
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.16,
|
| 305 |
+
"grad_norm": 0.7578125,
|
| 306 |
+
"learning_rate": 0.00017525707698561385,
|
| 307 |
+
"loss": 2.5949,
|
| 308 |
+
"step": 37
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.19,
|
| 312 |
+
"grad_norm": 0.94921875,
|
| 313 |
+
"learning_rate": 0.00017347741508630672,
|
| 314 |
+
"loss": 2.7476,
|
| 315 |
+
"step": 38
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.22,
|
| 319 |
+
"grad_norm": 0.88671875,
|
| 320 |
+
"learning_rate": 0.00017164567402983152,
|
| 321 |
+
"loss": 2.7991,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.25,
|
| 326 |
+
"grad_norm": 0.8671875,
|
| 327 |
+
"learning_rate": 0.0001697631521134985,
|
| 328 |
+
"loss": 2.5959,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.25,
|
| 333 |
+
"eval_loss": 2.5505764484405518,
|
| 334 |
+
"eval_runtime": 1.2761,
|
| 335 |
+
"eval_samples_per_second": 10.971,
|
| 336 |
+
"eval_steps_per_second": 5.486,
|
| 337 |
+
"step": 40
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.28,
|
| 341 |
+
"grad_norm": 0.984375,
|
| 342 |
+
"learning_rate": 0.00016783118362696163,
|
| 343 |
+
"loss": 2.5342,
|
| 344 |
+
"step": 41
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"grad_norm": 0.921875,
|
| 349 |
+
"learning_rate": 0.00016585113790650388,
|
| 350 |
+
"loss": 2.4969,
|
| 351 |
+
"step": 42
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.34,
|
| 355 |
+
"grad_norm": 1.125,
|
| 356 |
+
"learning_rate": 0.00016382441836448202,
|
| 357 |
+
"loss": 2.5723,
|
| 358 |
+
"step": 43
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.38,
|
| 362 |
+
"grad_norm": 1.015625,
|
| 363 |
+
"learning_rate": 0.0001617524614946192,
|
| 364 |
+
"loss": 2.6166,
|
| 365 |
+
"step": 44
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.41,
|
| 369 |
+
"grad_norm": 0.98828125,
|
| 370 |
+
"learning_rate": 0.00015963673585385016,
|
| 371 |
+
"loss": 2.4574,
|
| 372 |
+
"step": 45
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.44,
|
| 376 |
+
"grad_norm": 0.94921875,
|
| 377 |
+
"learning_rate": 0.0001574787410214407,
|
| 378 |
+
"loss": 2.5074,
|
| 379 |
+
"step": 46
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.47,
|
| 383 |
+
"grad_norm": 0.953125,
|
| 384 |
+
"learning_rate": 0.00015528000653611935,
|
| 385 |
+
"loss": 2.5394,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.5,
|
| 390 |
+
"grad_norm": 0.828125,
|
| 391 |
+
"learning_rate": 0.00015304209081197425,
|
| 392 |
+
"loss": 2.4793,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5,
|
| 397 |
+
"eval_loss": 2.495466470718384,
|
| 398 |
+
"eval_runtime": 1.2814,
|
| 399 |
+
"eval_samples_per_second": 10.926,
|
| 400 |
+
"eval_steps_per_second": 5.463,
|
| 401 |
+
"step": 48
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.53,
|
| 405 |
+
"grad_norm": 0.921875,
|
| 406 |
+
"learning_rate": 0.000150766580033884,
|
| 407 |
+
"loss": 2.2909,
|
| 408 |
+
"step": 49
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.56,
|
| 412 |
+
"grad_norm": 0.74609375,
|
| 413 |
+
"learning_rate": 0.00014845508703326504,
|
| 414 |
+
"loss": 2.3424,
|
| 415 |
+
"step": 50
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.59,
|
| 419 |
+
"grad_norm": 0.87890625,
|
| 420 |
+
"learning_rate": 0.0001461092501449326,
|
| 421 |
+
"loss": 2.506,
|
| 422 |
+
"step": 51
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.62,
|
| 426 |
+
"grad_norm": 0.7890625,
|
| 427 |
+
"learning_rate": 0.00014373073204588556,
|
| 428 |
+
"loss": 2.4829,
|
| 429 |
+
"step": 52
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.66,
|
| 433 |
+
"grad_norm": 0.984375,
|
| 434 |
+
"learning_rate": 0.00014132121857683783,
|
| 435 |
+
"loss": 2.481,
|
| 436 |
+
"step": 53
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.69,
|
| 440 |
+
"grad_norm": 0.9296875,
|
| 441 |
+
"learning_rate": 0.00013888241754733208,
|
| 442 |
+
"loss": 2.5512,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.72,
|
| 447 |
+
"grad_norm": 0.7890625,
|
| 448 |
+
"learning_rate": 0.00013641605752528224,
|
| 449 |
+
"loss": 2.5405,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.75,
|
| 454 |
+
"grad_norm": 0.95703125,
|
| 455 |
+
"learning_rate": 0.00013392388661180303,
|
| 456 |
+
"loss": 2.5221,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.75,
|
| 461 |
+
"eval_loss": 2.461298704147339,
|
| 462 |
+
"eval_runtime": 1.28,
|
| 463 |
+
"eval_samples_per_second": 10.937,
|
| 464 |
+
"eval_steps_per_second": 5.469,
|
| 465 |
+
"step": 56
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.78,
|
| 469 |
+
"grad_norm": 0.98046875,
|
| 470 |
+
"learning_rate": 0.0001314076712021949,
|
| 471 |
+
"loss": 2.5646,
|
| 472 |
+
"step": 57
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.81,
|
| 476 |
+
"grad_norm": 0.8125,
|
| 477 |
+
"learning_rate": 0.0001288691947339621,
|
| 478 |
+
"loss": 2.5079,
|
| 479 |
+
"step": 58
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.84,
|
| 483 |
+
"grad_norm": 0.8125,
|
| 484 |
+
"learning_rate": 0.00012631025642275212,
|
| 485 |
+
"loss": 2.4743,
|
| 486 |
+
"step": 59
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.88,
|
| 490 |
+
"grad_norm": 0.60546875,
|
| 491 |
+
"learning_rate": 0.0001237326699871115,
|
| 492 |
+
"loss": 2.3103,
|
| 493 |
+
"step": 60
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.91,
|
| 497 |
+
"grad_norm": 0.80859375,
|
| 498 |
+
"learning_rate": 0.00012113826236296244,
|
| 499 |
+
"loss": 2.4229,
|
| 500 |
+
"step": 61
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.94,
|
| 504 |
+
"grad_norm": 0.671875,
|
| 505 |
+
"learning_rate": 0.00011852887240871145,
|
| 506 |
+
"loss": 2.2709,
|
| 507 |
+
"step": 62
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.97,
|
| 511 |
+
"grad_norm": 0.8203125,
|
| 512 |
+
"learning_rate": 0.00011590634960190721,
|
| 513 |
+
"loss": 2.4868,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.0,
|
| 518 |
+
"grad_norm": 0.62109375,
|
| 519 |
+
"learning_rate": 0.00011327255272837221,
|
| 520 |
+
"loss": 2.4384,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0,
|
| 525 |
+
"eval_loss": 2.4055111408233643,
|
| 526 |
+
"eval_runtime": 1.2798,
|
| 527 |
+
"eval_samples_per_second": 10.94,
|
| 528 |
+
"eval_steps_per_second": 5.47,
|
| 529 |
+
"step": 64
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.03,
|
| 533 |
+
"grad_norm": 0.6328125,
|
| 534 |
+
"learning_rate": 0.00011062934856473655,
|
| 535 |
+
"loss": 2.3671,
|
| 536 |
+
"step": 65
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.06,
|
| 540 |
+
"grad_norm": 0.69140625,
|
| 541 |
+
"learning_rate": 0.00010797861055530831,
|
| 542 |
+
"loss": 2.3381,
|
| 543 |
+
"step": 66
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.09,
|
| 547 |
+
"grad_norm": 0.671875,
|
| 548 |
+
"learning_rate": 0.00010532221748421787,
|
| 549 |
+
"loss": 2.2134,
|
| 550 |
+
"step": 67
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.12,
|
| 554 |
+
"grad_norm": 0.7890625,
|
| 555 |
+
"learning_rate": 0.00010266205214377748,
|
| 556 |
+
"loss": 2.2687,
|
| 557 |
+
"step": 68
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.16,
|
| 561 |
+
"grad_norm": 0.75,
|
| 562 |
+
"learning_rate": 0.0001,
|
| 563 |
+
"loss": 2.4273,
|
| 564 |
+
"step": 69
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.19,
|
| 568 |
+
"grad_norm": 0.8671875,
|
| 569 |
+
"learning_rate": 9.733794785622253e-05,
|
| 570 |
+
"loss": 2.4439,
|
| 571 |
+
"step": 70
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.22,
|
| 575 |
+
"grad_norm": 0.953125,
|
| 576 |
+
"learning_rate": 9.467778251578217e-05,
|
| 577 |
+
"loss": 2.6631,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.25,
|
| 582 |
+
"grad_norm": 0.78125,
|
| 583 |
+
"learning_rate": 9.202138944469168e-05,
|
| 584 |
+
"loss": 2.295,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.25,
|
| 589 |
+
"eval_loss": 2.3922784328460693,
|
| 590 |
+
"eval_runtime": 1.282,
|
| 591 |
+
"eval_samples_per_second": 10.921,
|
| 592 |
+
"eval_steps_per_second": 5.46,
|
| 593 |
+
"step": 72
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.28,
|
| 597 |
+
"grad_norm": 0.734375,
|
| 598 |
+
"learning_rate": 8.937065143526347e-05,
|
| 599 |
+
"loss": 2.4963,
|
| 600 |
+
"step": 73
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.31,
|
| 604 |
+
"grad_norm": 0.68359375,
|
| 605 |
+
"learning_rate": 8.672744727162781e-05,
|
| 606 |
+
"loss": 2.4274,
|
| 607 |
+
"step": 74
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.34,
|
| 611 |
+
"grad_norm": 0.9765625,
|
| 612 |
+
"learning_rate": 8.409365039809281e-05,
|
| 613 |
+
"loss": 2.4988,
|
| 614 |
+
"step": 75
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.38,
|
| 618 |
+
"grad_norm": 0.75390625,
|
| 619 |
+
"learning_rate": 8.147112759128859e-05,
|
| 620 |
+
"loss": 2.2886,
|
| 621 |
+
"step": 76
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.41,
|
| 625 |
+
"grad_norm": 0.80078125,
|
| 626 |
+
"learning_rate": 7.886173763703757e-05,
|
| 627 |
+
"loss": 2.1944,
|
| 628 |
+
"step": 77
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.44,
|
| 632 |
+
"grad_norm": 0.8828125,
|
| 633 |
+
"learning_rate": 7.626733001288851e-05,
|
| 634 |
+
"loss": 2.3283,
|
| 635 |
+
"step": 78
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.47,
|
| 639 |
+
"grad_norm": 0.82421875,
|
| 640 |
+
"learning_rate": 7.368974357724789e-05,
|
| 641 |
+
"loss": 2.3855,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.5,
|
| 646 |
+
"grad_norm": 0.7890625,
|
| 647 |
+
"learning_rate": 7.113080526603792e-05,
|
| 648 |
+
"loss": 2.3943,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.5,
|
| 653 |
+
"eval_loss": 2.386228084564209,
|
| 654 |
+
"eval_runtime": 1.2835,
|
| 655 |
+
"eval_samples_per_second": 10.908,
|
| 656 |
+
"eval_steps_per_second": 5.454,
|
| 657 |
+
"step": 80
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.53,
|
| 661 |
+
"grad_norm": 0.94921875,
|
| 662 |
+
"learning_rate": 6.859232879780515e-05,
|
| 663 |
+
"loss": 2.2725,
|
| 664 |
+
"step": 81
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.56,
|
| 668 |
+
"grad_norm": 0.75,
|
| 669 |
+
"learning_rate": 6.607611338819697e-05,
|
| 670 |
+
"loss": 2.1989,
|
| 671 |
+
"step": 82
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.59,
|
| 675 |
+
"grad_norm": 0.703125,
|
| 676 |
+
"learning_rate": 6.358394247471778e-05,
|
| 677 |
+
"loss": 2.1219,
|
| 678 |
+
"step": 83
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.62,
|
| 682 |
+
"grad_norm": 1.0390625,
|
| 683 |
+
"learning_rate": 6.111758245266794e-05,
|
| 684 |
+
"loss": 2.3478,
|
| 685 |
+
"step": 84
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.66,
|
| 689 |
+
"grad_norm": 0.78125,
|
| 690 |
+
"learning_rate": 5.867878142316221e-05,
|
| 691 |
+
"loss": 2.4196,
|
| 692 |
+
"step": 85
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.69,
|
| 696 |
+
"grad_norm": 0.6796875,
|
| 697 |
+
"learning_rate": 5.626926795411447e-05,
|
| 698 |
+
"loss": 2.1882,
|
| 699 |
+
"step": 86
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.72,
|
| 703 |
+
"grad_norm": 0.8203125,
|
| 704 |
+
"learning_rate": 5.38907498550674e-05,
|
| 705 |
+
"loss": 2.4703,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.75,
|
| 710 |
+
"grad_norm": 0.8671875,
|
| 711 |
+
"learning_rate": 5.1544912966734994e-05,
|
| 712 |
+
"loss": 2.2398,
|
| 713 |
+
"step": 88
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.75,
|
| 717 |
+
"eval_loss": 2.3605105876922607,
|
| 718 |
+
"eval_runtime": 1.2887,
|
| 719 |
+
"eval_samples_per_second": 10.864,
|
| 720 |
+
"eval_steps_per_second": 5.432,
|
| 721 |
+
"step": 88
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.78,
|
| 725 |
+
"grad_norm": 0.81640625,
|
| 726 |
+
"learning_rate": 4.9233419966116036e-05,
|
| 727 |
+
"loss": 2.2939,
|
| 728 |
+
"step": 89
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.81,
|
| 732 |
+
"grad_norm": 1.0234375,
|
| 733 |
+
"learning_rate": 4.695790918802576e-05,
|
| 734 |
+
"loss": 2.2835,
|
| 735 |
+
"step": 90
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.84,
|
| 739 |
+
"grad_norm": 0.85546875,
|
| 740 |
+
"learning_rate": 4.47199934638807e-05,
|
| 741 |
+
"loss": 2.3145,
|
| 742 |
+
"step": 91
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.88,
|
| 746 |
+
"grad_norm": 0.5546875,
|
| 747 |
+
"learning_rate": 4.252125897855932e-05,
|
| 748 |
+
"loss": 2.2521,
|
| 749 |
+
"step": 92
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.91,
|
| 753 |
+
"grad_norm": 0.76953125,
|
| 754 |
+
"learning_rate": 4.036326414614985e-05,
|
| 755 |
+
"loss": 2.377,
|
| 756 |
+
"step": 93
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.94,
|
| 760 |
+
"grad_norm": 0.78125,
|
| 761 |
+
"learning_rate": 3.824753850538082e-05,
|
| 762 |
+
"loss": 2.4343,
|
| 763 |
+
"step": 94
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.97,
|
| 767 |
+
"grad_norm": 0.8046875,
|
| 768 |
+
"learning_rate": 3.617558163551802e-05,
|
| 769 |
+
"loss": 2.2051,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.0,
|
| 774 |
+
"grad_norm": 0.88671875,
|
| 775 |
+
"learning_rate": 3.414886209349615e-05,
|
| 776 |
+
"loss": 2.2693,
|
| 777 |
+
"step": 96
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.0,
|
| 781 |
+
"eval_loss": 2.3525888919830322,
|
| 782 |
+
"eval_runtime": 1.2821,
|
| 783 |
+
"eval_samples_per_second": 10.919,
|
| 784 |
+
"eval_steps_per_second": 5.46,
|
| 785 |
+
"step": 96
|
| 786 |
+
}
|
| 787 |
+
],
|
| 788 |
+
"logging_steps": 1,
|
| 789 |
+
"max_steps": 128,
|
| 790 |
+
"num_input_tokens_seen": 0,
|
| 791 |
+
"num_train_epochs": 4,
|
| 792 |
+
"save_steps": 32,
|
| 793 |
+
"total_flos": 2.000199340995379e+16,
|
| 794 |
+
"train_batch_size": 2,
|
| 795 |
+
"trial_name": null,
|
| 796 |
+
"trial_params": null
|
| 797 |
+
}
|
checkpoint-96/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
|
| 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": true,
|
| 22 |
+
"_load_in_8bit": false,
|
| 23 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 24 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
| 25 |
+
"bnb_4bit_quant_type": "nf4",
|
| 26 |
+
"bnb_4bit_use_double_quant": true,
|
| 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": true,
|
| 32 |
+
"load_in_8bit": false,
|
| 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": "4.40.0.dev0",
|
| 41 |
+
"use_cache": false,
|
| 42 |
+
"vocab_size": 32000
|
| 43 |
+
}
|
runs/Apr30_02-51-48_663ec5cd7167/events.out.tfevents.1714445508.663ec5cd7167.5280.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bac99fef0086cdfda4f010adba206b97074810136dff597980b02f3f4736af
|
| 3 |
+
size 37468
|
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 |
+
}
|