Upload folder using huggingface_hub
Browse files- checkpoint-500/README.md +202 -0
- checkpoint-500/adapter_config.json +37 -0
- checkpoint-500/adapter_model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +24 -0
- checkpoint-500/tokenizer.model +3 -0
- checkpoint-500/tokenizer_config.json +45 -0
- checkpoint-500/trainer_state.json +1791 -0
- checkpoint-500/training_args.bin +3 -0
- merged/config.json +28 -0
- merged/generation_config.json +7 -0
- merged/model-00001-of-00003.safetensors +3 -0
- merged/model-00002-of-00003.safetensors +3 -0
- merged/model-00003-of-00003.safetensors +3 -0
- merged/model.safetensors.index.json +298 -0
- merged/special_tokens_map.json +24 -0
- merged/tokenizer.model +3 -0
- merged/tokenizer_config.json +45 -0
checkpoint-500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 3 |
+
library_name: peft
|
| 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 0.14.0
|
checkpoint-500/adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": null,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 16,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"down_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"v_proj"
|
| 33 |
+
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
+
}
|
checkpoint-500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0aa07d08ac132b8a6b3d7ec5e2df0b08dda8f17c39923194bb1c9314a01ee60
|
| 3 |
+
size 335604696
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ee74a626e2859141d1891a98ada7ce89093761d4510fa2ec697ff40c58f3bcb
|
| 3 |
+
size 170920532
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4ff8101529bba26ae271fa4ecf4767e935b1137eda10adff0aea10c49bd62f4
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f4fe8e328be6e10e053e14666b2e571c45c73d9a8291556b08910e3da67b3e6
|
| 3 |
+
size 1064
|
checkpoint-500/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-500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 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 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false,
|
| 44 |
+
"use_fast": true
|
| 45 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,1791 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004,
|
| 13 |
+
"grad_norm": 2.6788930892944336,
|
| 14 |
+
"learning_rate": 2.857142857142857e-05,
|
| 15 |
+
"loss": 4.0572,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008,
|
| 20 |
+
"grad_norm": 2.1637303829193115,
|
| 21 |
+
"learning_rate": 5.714285714285714e-05,
|
| 22 |
+
"loss": 4.0232,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012,
|
| 27 |
+
"grad_norm": 2.1258859634399414,
|
| 28 |
+
"learning_rate": 8.571428571428571e-05,
|
| 29 |
+
"loss": 3.9261,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.016,
|
| 34 |
+
"grad_norm": 2.0480237007141113,
|
| 35 |
+
"learning_rate": 0.00011428571428571428,
|
| 36 |
+
"loss": 3.4327,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 2.771353244781494,
|
| 42 |
+
"learning_rate": 0.00014285714285714287,
|
| 43 |
+
"loss": 3.2181,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.024,
|
| 48 |
+
"grad_norm": 4.0292840003967285,
|
| 49 |
+
"learning_rate": 0.00017142857142857143,
|
| 50 |
+
"loss": 2.8105,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.028,
|
| 55 |
+
"grad_norm": 2.4763782024383545,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 2.557,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.032,
|
| 62 |
+
"grad_norm": 3.077378749847412,
|
| 63 |
+
"learning_rate": 0.00019999164298554375,
|
| 64 |
+
"loss": 2.4899,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.036,
|
| 69 |
+
"grad_norm": 2.2943201065063477,
|
| 70 |
+
"learning_rate": 0.00019996657333896877,
|
| 71 |
+
"loss": 2.2044,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 1.5257244110107422,
|
| 77 |
+
"learning_rate": 0.00019992479525042303,
|
| 78 |
+
"loss": 2.1377,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.044,
|
| 83 |
+
"grad_norm": 2.646472930908203,
|
| 84 |
+
"learning_rate": 0.00019986631570270832,
|
| 85 |
+
"loss": 2.1691,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.048,
|
| 90 |
+
"grad_norm": 1.4800257682800293,
|
| 91 |
+
"learning_rate": 0.00019979114447011323,
|
| 92 |
+
"loss": 2.1081,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.052,
|
| 97 |
+
"grad_norm": 1.1242213249206543,
|
| 98 |
+
"learning_rate": 0.0001996992941167792,
|
| 99 |
+
"loss": 2.1417,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.056,
|
| 104 |
+
"grad_norm": 4.963758945465088,
|
| 105 |
+
"learning_rate": 0.00019959077999460095,
|
| 106 |
+
"loss": 2.1159,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"grad_norm": 0.9503554701805115,
|
| 112 |
+
"learning_rate": 0.00019946562024066014,
|
| 113 |
+
"loss": 2.0883,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.064,
|
| 118 |
+
"grad_norm": 0.941498339176178,
|
| 119 |
+
"learning_rate": 0.00019932383577419432,
|
| 120 |
+
"loss": 1.9921,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.068,
|
| 125 |
+
"grad_norm": 0.8340420722961426,
|
| 126 |
+
"learning_rate": 0.00019916545029310012,
|
| 127 |
+
"loss": 2.0157,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.072,
|
| 132 |
+
"grad_norm": 0.9049850106239319,
|
| 133 |
+
"learning_rate": 0.00019899049026997272,
|
| 134 |
+
"loss": 1.9313,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.076,
|
| 139 |
+
"grad_norm": 0.8044288158416748,
|
| 140 |
+
"learning_rate": 0.00019879898494768093,
|
| 141 |
+
"loss": 1.9204,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08,
|
| 146 |
+
"grad_norm": 0.659812867641449,
|
| 147 |
+
"learning_rate": 0.00019859096633447965,
|
| 148 |
+
"loss": 1.7439,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.084,
|
| 153 |
+
"grad_norm": 0.8015430569648743,
|
| 154 |
+
"learning_rate": 0.0001983664691986601,
|
| 155 |
+
"loss": 2.0801,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.088,
|
| 160 |
+
"grad_norm": 0.8872734904289246,
|
| 161 |
+
"learning_rate": 0.00019812553106273847,
|
| 162 |
+
"loss": 1.8559,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.092,
|
| 167 |
+
"grad_norm": 0.7351342439651489,
|
| 168 |
+
"learning_rate": 0.00019786819219718443,
|
| 169 |
+
"loss": 1.9224,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.096,
|
| 174 |
+
"grad_norm": 0.8413205146789551,
|
| 175 |
+
"learning_rate": 0.00019759449561369038,
|
| 176 |
+
"loss": 1.9007,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"grad_norm": 0.7147359251976013,
|
| 182 |
+
"learning_rate": 0.00019730448705798239,
|
| 183 |
+
"loss": 1.7427,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.104,
|
| 188 |
+
"grad_norm": 0.7019318342208862,
|
| 189 |
+
"learning_rate": 0.00019699821500217434,
|
| 190 |
+
"loss": 2.0314,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.108,
|
| 195 |
+
"grad_norm": 0.6427651047706604,
|
| 196 |
+
"learning_rate": 0.0001966757306366662,
|
| 197 |
+
"loss": 2.0035,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.112,
|
| 202 |
+
"grad_norm": 0.7367712259292603,
|
| 203 |
+
"learning_rate": 0.00019633708786158806,
|
| 204 |
+
"loss": 1.8773,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.116,
|
| 209 |
+
"grad_norm": 0.6351197361946106,
|
| 210 |
+
"learning_rate": 0.00019598234327779118,
|
| 211 |
+
"loss": 1.8856,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12,
|
| 216 |
+
"grad_norm": 0.7486622929573059,
|
| 217 |
+
"learning_rate": 0.00019561155617738797,
|
| 218 |
+
"loss": 1.9533,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.124,
|
| 223 |
+
"grad_norm": 0.6752346158027649,
|
| 224 |
+
"learning_rate": 0.00019522478853384155,
|
| 225 |
+
"loss": 1.8538,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.128,
|
| 230 |
+
"grad_norm": 0.6963580846786499,
|
| 231 |
+
"learning_rate": 0.00019482210499160765,
|
| 232 |
+
"loss": 1.6746,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.132,
|
| 237 |
+
"grad_norm": 0.749860405921936,
|
| 238 |
+
"learning_rate": 0.00019440357285533,
|
| 239 |
+
"loss": 1.8631,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.136,
|
| 244 |
+
"grad_norm": 0.7538766264915466,
|
| 245 |
+
"learning_rate": 0.00019396926207859084,
|
| 246 |
+
"loss": 1.9797,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"grad_norm": 0.7004328370094299,
|
| 252 |
+
"learning_rate": 0.000193519245252219,
|
| 253 |
+
"loss": 1.7575,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.144,
|
| 258 |
+
"grad_norm": 0.6718307137489319,
|
| 259 |
+
"learning_rate": 0.00019305359759215685,
|
| 260 |
+
"loss": 1.9175,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.148,
|
| 265 |
+
"grad_norm": 0.7772621512413025,
|
| 266 |
+
"learning_rate": 0.00019257239692688907,
|
| 267 |
+
"loss": 1.8359,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.152,
|
| 272 |
+
"grad_norm": 0.7804538607597351,
|
| 273 |
+
"learning_rate": 0.00019207572368443385,
|
| 274 |
+
"loss": 1.8289,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.156,
|
| 279 |
+
"grad_norm": 0.6580988168716431,
|
| 280 |
+
"learning_rate": 0.0001915636608789006,
|
| 281 |
+
"loss": 1.7915,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16,
|
| 286 |
+
"grad_norm": 0.7220495343208313,
|
| 287 |
+
"learning_rate": 0.0001910362940966147,
|
| 288 |
+
"loss": 1.9061,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.164,
|
| 293 |
+
"grad_norm": 0.5738845467567444,
|
| 294 |
+
"learning_rate": 0.00019049371148181253,
|
| 295 |
+
"loss": 1.8292,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.168,
|
| 300 |
+
"grad_norm": 0.6399781107902527,
|
| 301 |
+
"learning_rate": 0.00018993600372190932,
|
| 302 |
+
"loss": 1.7994,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.172,
|
| 307 |
+
"grad_norm": 0.7971667051315308,
|
| 308 |
+
"learning_rate": 0.00018936326403234125,
|
| 309 |
+
"loss": 1.9215,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.176,
|
| 314 |
+
"grad_norm": 0.7101048827171326,
|
| 315 |
+
"learning_rate": 0.00018877558814098561,
|
| 316 |
+
"loss": 1.7503,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"grad_norm": 0.7746285200119019,
|
| 322 |
+
"learning_rate": 0.0001881730742721608,
|
| 323 |
+
"loss": 1.8146,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.184,
|
| 328 |
+
"grad_norm": 0.6883628964424133,
|
| 329 |
+
"learning_rate": 0.0001875558231302091,
|
| 330 |
+
"loss": 1.7111,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.188,
|
| 335 |
+
"grad_norm": 0.7610198259353638,
|
| 336 |
+
"learning_rate": 0.00018692393788266479,
|
| 337 |
+
"loss": 1.679,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.192,
|
| 342 |
+
"grad_norm": 0.8225780129432678,
|
| 343 |
+
"learning_rate": 0.00018627752414301086,
|
| 344 |
+
"loss": 1.7223,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.196,
|
| 349 |
+
"grad_norm": 0.6937716603279114,
|
| 350 |
+
"learning_rate": 0.00018561668995302667,
|
| 351 |
+
"loss": 1.6544,
|
| 352 |
+
"step": 98
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2,
|
| 356 |
+
"grad_norm": 0.6846134066581726,
|
| 357 |
+
"learning_rate": 0.00018494154576472976,
|
| 358 |
+
"loss": 1.7601,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.204,
|
| 363 |
+
"grad_norm": 0.7952787280082703,
|
| 364 |
+
"learning_rate": 0.00018425220442191495,
|
| 365 |
+
"loss": 1.6013,
|
| 366 |
+
"step": 102
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.208,
|
| 370 |
+
"grad_norm": 0.8951203227043152,
|
| 371 |
+
"learning_rate": 0.00018354878114129367,
|
| 372 |
+
"loss": 1.8765,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.212,
|
| 377 |
+
"grad_norm": 0.8003262877464294,
|
| 378 |
+
"learning_rate": 0.00018283139349323634,
|
| 379 |
+
"loss": 1.6842,
|
| 380 |
+
"step": 106
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.216,
|
| 384 |
+
"grad_norm": 0.6088269948959351,
|
| 385 |
+
"learning_rate": 0.00018210016138212187,
|
| 386 |
+
"loss": 1.4961,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"grad_norm": 0.7331597208976746,
|
| 392 |
+
"learning_rate": 0.00018135520702629675,
|
| 393 |
+
"loss": 1.7553,
|
| 394 |
+
"step": 110
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.224,
|
| 398 |
+
"grad_norm": 0.8118029832839966,
|
| 399 |
+
"learning_rate": 0.00018059665493764743,
|
| 400 |
+
"loss": 1.7535,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.228,
|
| 405 |
+
"grad_norm": 0.735879123210907,
|
| 406 |
+
"learning_rate": 0.0001798246319007893,
|
| 407 |
+
"loss": 1.7167,
|
| 408 |
+
"step": 114
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.232,
|
| 412 |
+
"grad_norm": 0.8310593962669373,
|
| 413 |
+
"learning_rate": 0.00017903926695187595,
|
| 414 |
+
"loss": 1.5874,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.236,
|
| 419 |
+
"grad_norm": 0.7394288778305054,
|
| 420 |
+
"learning_rate": 0.00017824069135703198,
|
| 421 |
+
"loss": 1.5916,
|
| 422 |
+
"step": 118
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.24,
|
| 426 |
+
"grad_norm": 0.7554506659507751,
|
| 427 |
+
"learning_rate": 0.00017742903859041325,
|
| 428 |
+
"loss": 1.6571,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.244,
|
| 433 |
+
"grad_norm": 0.6930153965950012,
|
| 434 |
+
"learning_rate": 0.0001766044443118978,
|
| 435 |
+
"loss": 1.7444,
|
| 436 |
+
"step": 122
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.248,
|
| 440 |
+
"grad_norm": 0.8027361035346985,
|
| 441 |
+
"learning_rate": 0.0001757670463444118,
|
| 442 |
+
"loss": 1.6741,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.252,
|
| 447 |
+
"grad_norm": 0.902922511100769,
|
| 448 |
+
"learning_rate": 0.00017491698465089362,
|
| 449 |
+
"loss": 1.4208,
|
| 450 |
+
"step": 126
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.256,
|
| 454 |
+
"grad_norm": 1.6366736888885498,
|
| 455 |
+
"learning_rate": 0.00017405440131090048,
|
| 456 |
+
"loss": 1.8175,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26,
|
| 461 |
+
"grad_norm": 0.8488344550132751,
|
| 462 |
+
"learning_rate": 0.00017317944049686124,
|
| 463 |
+
"loss": 1.7101,
|
| 464 |
+
"step": 130
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.264,
|
| 468 |
+
"grad_norm": 0.822182834148407,
|
| 469 |
+
"learning_rate": 0.00017229224844997928,
|
| 470 |
+
"loss": 1.7928,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.268,
|
| 475 |
+
"grad_norm": 0.6915173530578613,
|
| 476 |
+
"learning_rate": 0.00017139297345578994,
|
| 477 |
+
"loss": 1.4227,
|
| 478 |
+
"step": 134
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.272,
|
| 482 |
+
"grad_norm": 0.7020794153213501,
|
| 483 |
+
"learning_rate": 0.00017048176581937563,
|
| 484 |
+
"loss": 1.5705,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.276,
|
| 489 |
+
"grad_norm": 0.8134623169898987,
|
| 490 |
+
"learning_rate": 0.0001695587778402442,
|
| 491 |
+
"loss": 1.707,
|
| 492 |
+
"step": 138
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.28,
|
| 496 |
+
"grad_norm": 0.8580635190010071,
|
| 497 |
+
"learning_rate": 0.0001686241637868734,
|
| 498 |
+
"loss": 1.6409,
|
| 499 |
+
"step": 140
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.284,
|
| 503 |
+
"grad_norm": 0.7832855582237244,
|
| 504 |
+
"learning_rate": 0.00016767807987092621,
|
| 505 |
+
"loss": 1.6571,
|
| 506 |
+
"step": 142
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.288,
|
| 510 |
+
"grad_norm": 0.7040796279907227,
|
| 511 |
+
"learning_rate": 0.00016672068422114196,
|
| 512 |
+
"loss": 1.6752,
|
| 513 |
+
"step": 144
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.292,
|
| 517 |
+
"grad_norm": 0.6851047873497009,
|
| 518 |
+
"learning_rate": 0.0001657521368569064,
|
| 519 |
+
"loss": 1.6308,
|
| 520 |
+
"step": 146
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.296,
|
| 524 |
+
"grad_norm": 0.6454576253890991,
|
| 525 |
+
"learning_rate": 0.00016477259966150588,
|
| 526 |
+
"loss": 1.62,
|
| 527 |
+
"step": 148
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3,
|
| 531 |
+
"grad_norm": 0.9445090889930725,
|
| 532 |
+
"learning_rate": 0.0001637822363550706,
|
| 533 |
+
"loss": 1.5146,
|
| 534 |
+
"step": 150
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.304,
|
| 538 |
+
"grad_norm": 0.8589845895767212,
|
| 539 |
+
"learning_rate": 0.00016278121246720987,
|
| 540 |
+
"loss": 1.6042,
|
| 541 |
+
"step": 152
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.308,
|
| 545 |
+
"grad_norm": 0.8403664827346802,
|
| 546 |
+
"learning_rate": 0.00016176969530934572,
|
| 547 |
+
"loss": 1.7251,
|
| 548 |
+
"step": 154
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.312,
|
| 552 |
+
"grad_norm": 0.758743166923523,
|
| 553 |
+
"learning_rate": 0.00016074785394674837,
|
| 554 |
+
"loss": 1.6135,
|
| 555 |
+
"step": 156
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.316,
|
| 559 |
+
"grad_norm": 0.8078017234802246,
|
| 560 |
+
"learning_rate": 0.00015971585917027862,
|
| 561 |
+
"loss": 1.5345,
|
| 562 |
+
"step": 158
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.32,
|
| 566 |
+
"grad_norm": 0.8423400521278381,
|
| 567 |
+
"learning_rate": 0.0001586738834678418,
|
| 568 |
+
"loss": 1.5991,
|
| 569 |
+
"step": 160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.324,
|
| 573 |
+
"grad_norm": 0.7609900236129761,
|
| 574 |
+
"learning_rate": 0.00015762210099555803,
|
| 575 |
+
"loss": 1.4574,
|
| 576 |
+
"step": 162
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.328,
|
| 580 |
+
"grad_norm": 0.7936549186706543,
|
| 581 |
+
"learning_rate": 0.00015656068754865387,
|
| 582 |
+
"loss": 1.5212,
|
| 583 |
+
"step": 164
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.332,
|
| 587 |
+
"grad_norm": 0.8465148210525513,
|
| 588 |
+
"learning_rate": 0.0001554898205320797,
|
| 589 |
+
"loss": 1.5272,
|
| 590 |
+
"step": 166
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.336,
|
| 594 |
+
"grad_norm": 0.8214313983917236,
|
| 595 |
+
"learning_rate": 0.00015440967893085828,
|
| 596 |
+
"loss": 1.4002,
|
| 597 |
+
"step": 168
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"grad_norm": 1.0386507511138916,
|
| 602 |
+
"learning_rate": 0.00015332044328016914,
|
| 603 |
+
"loss": 1.5952,
|
| 604 |
+
"step": 170
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.344,
|
| 608 |
+
"grad_norm": 0.9584160447120667,
|
| 609 |
+
"learning_rate": 0.00015222229563517385,
|
| 610 |
+
"loss": 1.7756,
|
| 611 |
+
"step": 172
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.348,
|
| 615 |
+
"grad_norm": 0.8221916556358337,
|
| 616 |
+
"learning_rate": 0.00015111541954058734,
|
| 617 |
+
"loss": 1.2855,
|
| 618 |
+
"step": 174
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.352,
|
| 622 |
+
"grad_norm": 0.8400780558586121,
|
| 623 |
+
"learning_rate": 0.00015000000000000001,
|
| 624 |
+
"loss": 1.6195,
|
| 625 |
+
"step": 176
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.356,
|
| 629 |
+
"grad_norm": 1.312400460243225,
|
| 630 |
+
"learning_rate": 0.00014887622344495643,
|
| 631 |
+
"loss": 1.5087,
|
| 632 |
+
"step": 178
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.36,
|
| 636 |
+
"grad_norm": 0.9566483497619629,
|
| 637 |
+
"learning_rate": 0.0001477442777037949,
|
| 638 |
+
"loss": 1.5742,
|
| 639 |
+
"step": 180
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.364,
|
| 643 |
+
"grad_norm": 0.8587402105331421,
|
| 644 |
+
"learning_rate": 0.0001466043519702539,
|
| 645 |
+
"loss": 1.741,
|
| 646 |
+
"step": 182
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.368,
|
| 650 |
+
"grad_norm": 0.8634321689605713,
|
| 651 |
+
"learning_rate": 0.00014545663677185006,
|
| 652 |
+
"loss": 1.5015,
|
| 653 |
+
"step": 184
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.372,
|
| 657 |
+
"grad_norm": 1.018045425415039,
|
| 658 |
+
"learning_rate": 0.00014430132393803352,
|
| 659 |
+
"loss": 1.592,
|
| 660 |
+
"step": 186
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.376,
|
| 664 |
+
"grad_norm": 0.8314984440803528,
|
| 665 |
+
"learning_rate": 0.00014313860656812536,
|
| 666 |
+
"loss": 1.3886,
|
| 667 |
+
"step": 188
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38,
|
| 671 |
+
"grad_norm": 0.783717691898346,
|
| 672 |
+
"learning_rate": 0.0001419686789990429,
|
| 673 |
+
"loss": 1.3943,
|
| 674 |
+
"step": 190
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.384,
|
| 678 |
+
"grad_norm": 1.0520801544189453,
|
| 679 |
+
"learning_rate": 0.00014079173677281837,
|
| 680 |
+
"loss": 1.4546,
|
| 681 |
+
"step": 192
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.388,
|
| 685 |
+
"grad_norm": 1.0584237575531006,
|
| 686 |
+
"learning_rate": 0.0001396079766039157,
|
| 687 |
+
"loss": 1.7287,
|
| 688 |
+
"step": 194
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.392,
|
| 692 |
+
"grad_norm": 0.8840407133102417,
|
| 693 |
+
"learning_rate": 0.00013841759634635178,
|
| 694 |
+
"loss": 1.3588,
|
| 695 |
+
"step": 196
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.396,
|
| 699 |
+
"grad_norm": 0.995851993560791,
|
| 700 |
+
"learning_rate": 0.00013722079496062702,
|
| 701 |
+
"loss": 1.4566,
|
| 702 |
+
"step": 198
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4,
|
| 706 |
+
"grad_norm": 0.8311200141906738,
|
| 707 |
+
"learning_rate": 0.00013601777248047105,
|
| 708 |
+
"loss": 1.4679,
|
| 709 |
+
"step": 200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.404,
|
| 713 |
+
"grad_norm": 1.1487723588943481,
|
| 714 |
+
"learning_rate": 0.00013480872997940905,
|
| 715 |
+
"loss": 1.4859,
|
| 716 |
+
"step": 202
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.408,
|
| 720 |
+
"grad_norm": 1.0271517038345337,
|
| 721 |
+
"learning_rate": 0.00013359386953715421,
|
| 722 |
+
"loss": 1.4812,
|
| 723 |
+
"step": 204
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.412,
|
| 727 |
+
"grad_norm": 0.9313080906867981,
|
| 728 |
+
"learning_rate": 0.00013237339420583212,
|
| 729 |
+
"loss": 1.2583,
|
| 730 |
+
"step": 206
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.416,
|
| 734 |
+
"grad_norm": 1.0934455394744873,
|
| 735 |
+
"learning_rate": 0.00013114750797604247,
|
| 736 |
+
"loss": 1.344,
|
| 737 |
+
"step": 208
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42,
|
| 741 |
+
"grad_norm": 0.9046192169189453,
|
| 742 |
+
"learning_rate": 0.00012991641574276418,
|
| 743 |
+
"loss": 1.4883,
|
| 744 |
+
"step": 210
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.424,
|
| 748 |
+
"grad_norm": 1.1089824438095093,
|
| 749 |
+
"learning_rate": 0.00012868032327110904,
|
| 750 |
+
"loss": 1.32,
|
| 751 |
+
"step": 212
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.428,
|
| 755 |
+
"grad_norm": 0.9256604313850403,
|
| 756 |
+
"learning_rate": 0.00012743943716193016,
|
| 757 |
+
"loss": 1.4668,
|
| 758 |
+
"step": 214
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.432,
|
| 762 |
+
"grad_norm": 0.9342580437660217,
|
| 763 |
+
"learning_rate": 0.0001261939648172906,
|
| 764 |
+
"loss": 1.5961,
|
| 765 |
+
"step": 216
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.436,
|
| 769 |
+
"grad_norm": 0.9283121824264526,
|
| 770 |
+
"learning_rate": 0.00012494411440579814,
|
| 771 |
+
"loss": 1.3257,
|
| 772 |
+
"step": 218
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.44,
|
| 776 |
+
"grad_norm": 1.032076358795166,
|
| 777 |
+
"learning_rate": 0.00012369009482781192,
|
| 778 |
+
"loss": 1.4502,
|
| 779 |
+
"step": 220
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.444,
|
| 783 |
+
"grad_norm": 0.9665339589118958,
|
| 784 |
+
"learning_rate": 0.00012243211568052677,
|
| 785 |
+
"loss": 1.1899,
|
| 786 |
+
"step": 222
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.448,
|
| 790 |
+
"grad_norm": 1.004429578781128,
|
| 791 |
+
"learning_rate": 0.0001211703872229411,
|
| 792 |
+
"loss": 1.3543,
|
| 793 |
+
"step": 224
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.452,
|
| 797 |
+
"grad_norm": 0.9309017062187195,
|
| 798 |
+
"learning_rate": 0.00011990512034071406,
|
| 799 |
+
"loss": 1.4476,
|
| 800 |
+
"step": 226
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.456,
|
| 804 |
+
"grad_norm": 1.1324740648269653,
|
| 805 |
+
"learning_rate": 0.00011863652651091823,
|
| 806 |
+
"loss": 1.3554,
|
| 807 |
+
"step": 228
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.46,
|
| 811 |
+
"grad_norm": 1.1737691164016724,
|
| 812 |
+
"learning_rate": 0.00011736481776669306,
|
| 813 |
+
"loss": 1.4122,
|
| 814 |
+
"step": 230
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.464,
|
| 818 |
+
"grad_norm": 0.9779687523841858,
|
| 819 |
+
"learning_rate": 0.00011609020666180575,
|
| 820 |
+
"loss": 1.2033,
|
| 821 |
+
"step": 232
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.468,
|
| 825 |
+
"grad_norm": 1.132530689239502,
|
| 826 |
+
"learning_rate": 0.0001148129062351249,
|
| 827 |
+
"loss": 1.3125,
|
| 828 |
+
"step": 234
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.472,
|
| 832 |
+
"grad_norm": 1.0582220554351807,
|
| 833 |
+
"learning_rate": 0.00011353312997501313,
|
| 834 |
+
"loss": 1.4083,
|
| 835 |
+
"step": 236
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.476,
|
| 839 |
+
"grad_norm": 1.100317120552063,
|
| 840 |
+
"learning_rate": 0.00011225109178364455,
|
| 841 |
+
"loss": 1.5247,
|
| 842 |
+
"step": 238
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.48,
|
| 846 |
+
"grad_norm": 0.9119705557823181,
|
| 847 |
+
"learning_rate": 0.00011096700594125318,
|
| 848 |
+
"loss": 1.39,
|
| 849 |
+
"step": 240
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.484,
|
| 853 |
+
"grad_norm": 0.9528422951698303,
|
| 854 |
+
"learning_rate": 0.00010968108707031792,
|
| 855 |
+
"loss": 1.1719,
|
| 856 |
+
"step": 242
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.488,
|
| 860 |
+
"grad_norm": 1.1193115711212158,
|
| 861 |
+
"learning_rate": 0.00010839355009969068,
|
| 862 |
+
"loss": 1.3211,
|
| 863 |
+
"step": 244
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.492,
|
| 867 |
+
"grad_norm": 1.3409603834152222,
|
| 868 |
+
"learning_rate": 0.00010710461022867302,
|
| 869 |
+
"loss": 1.3367,
|
| 870 |
+
"step": 246
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.496,
|
| 874 |
+
"grad_norm": 1.6449599266052246,
|
| 875 |
+
"learning_rate": 0.00010581448289104758,
|
| 876 |
+
"loss": 1.0548,
|
| 877 |
+
"step": 248
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5,
|
| 881 |
+
"grad_norm": 1.0316084623336792,
|
| 882 |
+
"learning_rate": 0.00010452338371907064,
|
| 883 |
+
"loss": 1.1945,
|
| 884 |
+
"step": 250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.504,
|
| 888 |
+
"grad_norm": 0.9953674674034119,
|
| 889 |
+
"learning_rate": 0.00010323152850743107,
|
| 890 |
+
"loss": 1.2618,
|
| 891 |
+
"step": 252
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.508,
|
| 895 |
+
"grad_norm": 0.8978606462478638,
|
| 896 |
+
"learning_rate": 0.00010193913317718244,
|
| 897 |
+
"loss": 1.1902,
|
| 898 |
+
"step": 254
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.512,
|
| 902 |
+
"grad_norm": 0.8899203538894653,
|
| 903 |
+
"learning_rate": 0.00010064641373965393,
|
| 904 |
+
"loss": 1.5724,
|
| 905 |
+
"step": 256
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.516,
|
| 909 |
+
"grad_norm": 0.9201542139053345,
|
| 910 |
+
"learning_rate": 9.935358626034606e-05,
|
| 911 |
+
"loss": 1.2819,
|
| 912 |
+
"step": 258
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.52,
|
| 916 |
+
"grad_norm": 0.9490768313407898,
|
| 917 |
+
"learning_rate": 9.806086682281758e-05,
|
| 918 |
+
"loss": 1.2958,
|
| 919 |
+
"step": 260
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.524,
|
| 923 |
+
"grad_norm": 1.0369281768798828,
|
| 924 |
+
"learning_rate": 9.676847149256895e-05,
|
| 925 |
+
"loss": 1.165,
|
| 926 |
+
"step": 262
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.528,
|
| 930 |
+
"grad_norm": 1.0459696054458618,
|
| 931 |
+
"learning_rate": 9.547661628092937e-05,
|
| 932 |
+
"loss": 1.1462,
|
| 933 |
+
"step": 264
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.532,
|
| 937 |
+
"grad_norm": 1.0801945924758911,
|
| 938 |
+
"learning_rate": 9.418551710895243e-05,
|
| 939 |
+
"loss": 1.3083,
|
| 940 |
+
"step": 266
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.536,
|
| 944 |
+
"grad_norm": 1.0541006326675415,
|
| 945 |
+
"learning_rate": 9.289538977132703e-05,
|
| 946 |
+
"loss": 1.3734,
|
| 947 |
+
"step": 268
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.54,
|
| 951 |
+
"grad_norm": 1.1310724020004272,
|
| 952 |
+
"learning_rate": 9.160644990030931e-05,
|
| 953 |
+
"loss": 1.3012,
|
| 954 |
+
"step": 270
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.544,
|
| 958 |
+
"grad_norm": 0.9250295162200928,
|
| 959 |
+
"learning_rate": 9.03189129296821e-05,
|
| 960 |
+
"loss": 0.9101,
|
| 961 |
+
"step": 272
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.548,
|
| 965 |
+
"grad_norm": 1.0503145456314087,
|
| 966 |
+
"learning_rate": 8.903299405874684e-05,
|
| 967 |
+
"loss": 1.2005,
|
| 968 |
+
"step": 274
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.552,
|
| 972 |
+
"grad_norm": 1.188832402229309,
|
| 973 |
+
"learning_rate": 8.774890821635548e-05,
|
| 974 |
+
"loss": 1.3463,
|
| 975 |
+
"step": 276
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.556,
|
| 979 |
+
"grad_norm": 1.2457951307296753,
|
| 980 |
+
"learning_rate": 8.646687002498692e-05,
|
| 981 |
+
"loss": 1.1548,
|
| 982 |
+
"step": 278
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.56,
|
| 986 |
+
"grad_norm": 1.0752447843551636,
|
| 987 |
+
"learning_rate": 8.518709376487515e-05,
|
| 988 |
+
"loss": 1.1081,
|
| 989 |
+
"step": 280
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.564,
|
| 993 |
+
"grad_norm": 1.0465664863586426,
|
| 994 |
+
"learning_rate": 8.390979333819426e-05,
|
| 995 |
+
"loss": 1.0964,
|
| 996 |
+
"step": 282
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.568,
|
| 1000 |
+
"grad_norm": 1.1226983070373535,
|
| 1001 |
+
"learning_rate": 8.263518223330697e-05,
|
| 1002 |
+
"loss": 1.1712,
|
| 1003 |
+
"step": 284
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.572,
|
| 1007 |
+
"grad_norm": 1.475192904472351,
|
| 1008 |
+
"learning_rate": 8.13634734890818e-05,
|
| 1009 |
+
"loss": 1.2109,
|
| 1010 |
+
"step": 286
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.576,
|
| 1014 |
+
"grad_norm": 1.2802696228027344,
|
| 1015 |
+
"learning_rate": 8.009487965928596e-05,
|
| 1016 |
+
"loss": 1.3174,
|
| 1017 |
+
"step": 288
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.58,
|
| 1021 |
+
"grad_norm": 1.0212256908416748,
|
| 1022 |
+
"learning_rate": 7.882961277705895e-05,
|
| 1023 |
+
"loss": 1.3373,
|
| 1024 |
+
"step": 290
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.584,
|
| 1028 |
+
"grad_norm": 1.0210835933685303,
|
| 1029 |
+
"learning_rate": 7.756788431947326e-05,
|
| 1030 |
+
"loss": 1.0587,
|
| 1031 |
+
"step": 292
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.588,
|
| 1035 |
+
"grad_norm": 1.03009831905365,
|
| 1036 |
+
"learning_rate": 7.630990517218808e-05,
|
| 1037 |
+
"loss": 1.1519,
|
| 1038 |
+
"step": 294
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.592,
|
| 1042 |
+
"grad_norm": 1.0977703332901,
|
| 1043 |
+
"learning_rate": 7.505588559420189e-05,
|
| 1044 |
+
"loss": 1.0765,
|
| 1045 |
+
"step": 296
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.596,
|
| 1049 |
+
"grad_norm": 1.040688395500183,
|
| 1050 |
+
"learning_rate": 7.380603518270941e-05,
|
| 1051 |
+
"loss": 1.0378,
|
| 1052 |
+
"step": 298
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6,
|
| 1056 |
+
"grad_norm": 1.4648557901382446,
|
| 1057 |
+
"learning_rate": 7.256056283806986e-05,
|
| 1058 |
+
"loss": 1.3358,
|
| 1059 |
+
"step": 300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.604,
|
| 1063 |
+
"grad_norm": 1.0665948390960693,
|
| 1064 |
+
"learning_rate": 7.131967672889101e-05,
|
| 1065 |
+
"loss": 1.3743,
|
| 1066 |
+
"step": 302
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.608,
|
| 1070 |
+
"grad_norm": 1.123956561088562,
|
| 1071 |
+
"learning_rate": 7.008358425723585e-05,
|
| 1072 |
+
"loss": 1.1218,
|
| 1073 |
+
"step": 304
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.612,
|
| 1077 |
+
"grad_norm": 1.0305341482162476,
|
| 1078 |
+
"learning_rate": 6.885249202395754e-05,
|
| 1079 |
+
"loss": 1.4106,
|
| 1080 |
+
"step": 306
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.616,
|
| 1084 |
+
"grad_norm": 1.0478438138961792,
|
| 1085 |
+
"learning_rate": 6.762660579416791e-05,
|
| 1086 |
+
"loss": 1.3295,
|
| 1087 |
+
"step": 308
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.62,
|
| 1091 |
+
"grad_norm": 1.03648042678833,
|
| 1092 |
+
"learning_rate": 6.640613046284581e-05,
|
| 1093 |
+
"loss": 1.2259,
|
| 1094 |
+
"step": 310
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.624,
|
| 1098 |
+
"grad_norm": 1.1469812393188477,
|
| 1099 |
+
"learning_rate": 6.519127002059095e-05,
|
| 1100 |
+
"loss": 1.2067,
|
| 1101 |
+
"step": 312
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.628,
|
| 1105 |
+
"grad_norm": 1.0658073425292969,
|
| 1106 |
+
"learning_rate": 6.398222751952899e-05,
|
| 1107 |
+
"loss": 1.1753,
|
| 1108 |
+
"step": 314
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.632,
|
| 1112 |
+
"grad_norm": 1.1740753650665283,
|
| 1113 |
+
"learning_rate": 6.277920503937303e-05,
|
| 1114 |
+
"loss": 1.0735,
|
| 1115 |
+
"step": 316
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.636,
|
| 1119 |
+
"grad_norm": 1.3712061643600464,
|
| 1120 |
+
"learning_rate": 6.158240365364823e-05,
|
| 1121 |
+
"loss": 1.1055,
|
| 1122 |
+
"step": 318
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.64,
|
| 1126 |
+
"grad_norm": 1.3711669445037842,
|
| 1127 |
+
"learning_rate": 6.039202339608432e-05,
|
| 1128 |
+
"loss": 0.9251,
|
| 1129 |
+
"step": 320
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.644,
|
| 1133 |
+
"grad_norm": 1.1360186338424683,
|
| 1134 |
+
"learning_rate": 5.920826322718165e-05,
|
| 1135 |
+
"loss": 1.1513,
|
| 1136 |
+
"step": 322
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.648,
|
| 1140 |
+
"grad_norm": 1.1550403833389282,
|
| 1141 |
+
"learning_rate": 5.80313210009571e-05,
|
| 1142 |
+
"loss": 0.7667,
|
| 1143 |
+
"step": 324
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.652,
|
| 1147 |
+
"grad_norm": 1.2344552278518677,
|
| 1148 |
+
"learning_rate": 5.6861393431874675e-05,
|
| 1149 |
+
"loss": 1.1123,
|
| 1150 |
+
"step": 326
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.656,
|
| 1154 |
+
"grad_norm": 1.0663491487503052,
|
| 1155 |
+
"learning_rate": 5.5698676061966515e-05,
|
| 1156 |
+
"loss": 1.1687,
|
| 1157 |
+
"step": 328
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.66,
|
| 1161 |
+
"grad_norm": 1.3150757551193237,
|
| 1162 |
+
"learning_rate": 5.4543363228149946e-05,
|
| 1163 |
+
"loss": 1.0538,
|
| 1164 |
+
"step": 330
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.664,
|
| 1168 |
+
"grad_norm": 1.2159111499786377,
|
| 1169 |
+
"learning_rate": 5.339564802974615e-05,
|
| 1170 |
+
"loss": 1.0246,
|
| 1171 |
+
"step": 332
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.668,
|
| 1175 |
+
"grad_norm": 1.1044658422470093,
|
| 1176 |
+
"learning_rate": 5.22557222962051e-05,
|
| 1177 |
+
"loss": 1.1401,
|
| 1178 |
+
"step": 334
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.672,
|
| 1182 |
+
"grad_norm": 1.152716040611267,
|
| 1183 |
+
"learning_rate": 5.112377655504359e-05,
|
| 1184 |
+
"loss": 1.0505,
|
| 1185 |
+
"step": 336
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.676,
|
| 1189 |
+
"grad_norm": 1.1883264780044556,
|
| 1190 |
+
"learning_rate": 5.000000000000002e-05,
|
| 1191 |
+
"loss": 1.1524,
|
| 1192 |
+
"step": 338
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.68,
|
| 1196 |
+
"grad_norm": 1.2339959144592285,
|
| 1197 |
+
"learning_rate": 4.888458045941269e-05,
|
| 1198 |
+
"loss": 1.1015,
|
| 1199 |
+
"step": 340
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.684,
|
| 1203 |
+
"grad_norm": 1.1014620065689087,
|
| 1204 |
+
"learning_rate": 4.777770436482617e-05,
|
| 1205 |
+
"loss": 1.1227,
|
| 1206 |
+
"step": 342
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.688,
|
| 1210 |
+
"grad_norm": 1.0251641273498535,
|
| 1211 |
+
"learning_rate": 4.66795567198309e-05,
|
| 1212 |
+
"loss": 1.1145,
|
| 1213 |
+
"step": 344
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.692,
|
| 1217 |
+
"grad_norm": 1.3105113506317139,
|
| 1218 |
+
"learning_rate": 4.559032106914173e-05,
|
| 1219 |
+
"loss": 1.2321,
|
| 1220 |
+
"step": 346
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.696,
|
| 1224 |
+
"grad_norm": 1.314314365386963,
|
| 1225 |
+
"learning_rate": 4.451017946792032e-05,
|
| 1226 |
+
"loss": 1.0897,
|
| 1227 |
+
"step": 348
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7,
|
| 1231 |
+
"grad_norm": 1.194879412651062,
|
| 1232 |
+
"learning_rate": 4.343931245134616e-05,
|
| 1233 |
+
"loss": 1.1422,
|
| 1234 |
+
"step": 350
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.704,
|
| 1238 |
+
"grad_norm": 1.1237996816635132,
|
| 1239 |
+
"learning_rate": 4.2377899004441966e-05,
|
| 1240 |
+
"loss": 1.0447,
|
| 1241 |
+
"step": 352
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.708,
|
| 1245 |
+
"grad_norm": 1.193502426147461,
|
| 1246 |
+
"learning_rate": 4.132611653215822e-05,
|
| 1247 |
+
"loss": 0.8471,
|
| 1248 |
+
"step": 354
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.712,
|
| 1252 |
+
"grad_norm": 1.0709404945373535,
|
| 1253 |
+
"learning_rate": 4.028414082972141e-05,
|
| 1254 |
+
"loss": 0.9889,
|
| 1255 |
+
"step": 356
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.716,
|
| 1259 |
+
"grad_norm": 1.1148098707199097,
|
| 1260 |
+
"learning_rate": 3.9252146053251636e-05,
|
| 1261 |
+
"loss": 1.2275,
|
| 1262 |
+
"step": 358
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.72,
|
| 1266 |
+
"grad_norm": 1.2912510633468628,
|
| 1267 |
+
"learning_rate": 3.8230304690654304e-05,
|
| 1268 |
+
"loss": 1.0965,
|
| 1269 |
+
"step": 360
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.724,
|
| 1273 |
+
"grad_norm": 1.2405377626419067,
|
| 1274 |
+
"learning_rate": 3.721878753279017e-05,
|
| 1275 |
+
"loss": 1.296,
|
| 1276 |
+
"step": 362
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.728,
|
| 1280 |
+
"grad_norm": 1.1991064548492432,
|
| 1281 |
+
"learning_rate": 3.621776364492939e-05,
|
| 1282 |
+
"loss": 1.0759,
|
| 1283 |
+
"step": 364
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.732,
|
| 1287 |
+
"grad_norm": 0.9793534874916077,
|
| 1288 |
+
"learning_rate": 3.522740033849411e-05,
|
| 1289 |
+
"loss": 0.8587,
|
| 1290 |
+
"step": 366
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.736,
|
| 1294 |
+
"grad_norm": 1.1337475776672363,
|
| 1295 |
+
"learning_rate": 3.424786314309365e-05,
|
| 1296 |
+
"loss": 0.7274,
|
| 1297 |
+
"step": 368
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.74,
|
| 1301 |
+
"grad_norm": 1.3411873579025269,
|
| 1302 |
+
"learning_rate": 3.3279315778858036e-05,
|
| 1303 |
+
"loss": 0.9668,
|
| 1304 |
+
"step": 370
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.744,
|
| 1308 |
+
"grad_norm": 1.331512451171875,
|
| 1309 |
+
"learning_rate": 3.2321920129073816e-05,
|
| 1310 |
+
"loss": 1.0782,
|
| 1311 |
+
"step": 372
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.748,
|
| 1315 |
+
"grad_norm": 1.1993547677993774,
|
| 1316 |
+
"learning_rate": 3.137583621312665e-05,
|
| 1317 |
+
"loss": 1.0403,
|
| 1318 |
+
"step": 374
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.752,
|
| 1322 |
+
"grad_norm": 1.4476321935653687,
|
| 1323 |
+
"learning_rate": 3.04412221597558e-05,
|
| 1324 |
+
"loss": 0.9,
|
| 1325 |
+
"step": 376
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.756,
|
| 1329 |
+
"grad_norm": 1.2879384756088257,
|
| 1330 |
+
"learning_rate": 2.9518234180624393e-05,
|
| 1331 |
+
"loss": 0.7182,
|
| 1332 |
+
"step": 378
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.76,
|
| 1336 |
+
"grad_norm": 1.4833335876464844,
|
| 1337 |
+
"learning_rate": 2.8607026544210114e-05,
|
| 1338 |
+
"loss": 0.9735,
|
| 1339 |
+
"step": 380
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.764,
|
| 1343 |
+
"grad_norm": 1.1914557218551636,
|
| 1344 |
+
"learning_rate": 2.770775155002071e-05,
|
| 1345 |
+
"loss": 0.9925,
|
| 1346 |
+
"step": 382
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.768,
|
| 1350 |
+
"grad_norm": 1.4587005376815796,
|
| 1351 |
+
"learning_rate": 2.6820559503138797e-05,
|
| 1352 |
+
"loss": 1.4029,
|
| 1353 |
+
"step": 384
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.772,
|
| 1357 |
+
"grad_norm": 1.3272329568862915,
|
| 1358 |
+
"learning_rate": 2.594559868909956e-05,
|
| 1359 |
+
"loss": 0.8871,
|
| 1360 |
+
"step": 386
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.776,
|
| 1364 |
+
"grad_norm": 1.326879858970642,
|
| 1365 |
+
"learning_rate": 2.50830153491064e-05,
|
| 1366 |
+
"loss": 0.745,
|
| 1367 |
+
"step": 388
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.78,
|
| 1371 |
+
"grad_norm": 1.3535796403884888,
|
| 1372 |
+
"learning_rate": 2.423295365558821e-05,
|
| 1373 |
+
"loss": 0.8069,
|
| 1374 |
+
"step": 390
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.784,
|
| 1378 |
+
"grad_norm": 1.1943892240524292,
|
| 1379 |
+
"learning_rate": 2.339555568810221e-05,
|
| 1380 |
+
"loss": 1.1725,
|
| 1381 |
+
"step": 392
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.788,
|
| 1385 |
+
"grad_norm": 1.2473647594451904,
|
| 1386 |
+
"learning_rate": 2.2570961409586754e-05,
|
| 1387 |
+
"loss": 0.9927,
|
| 1388 |
+
"step": 394
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.792,
|
| 1392 |
+
"grad_norm": 1.1211111545562744,
|
| 1393 |
+
"learning_rate": 2.1759308642968025e-05,
|
| 1394 |
+
"loss": 0.8283,
|
| 1395 |
+
"step": 396
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.796,
|
| 1399 |
+
"grad_norm": 1.2145154476165771,
|
| 1400 |
+
"learning_rate": 2.0960733048124083e-05,
|
| 1401 |
+
"loss": 0.9538,
|
| 1402 |
+
"step": 398
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8,
|
| 1406 |
+
"grad_norm": 1.3465194702148438,
|
| 1407 |
+
"learning_rate": 2.01753680992107e-05,
|
| 1408 |
+
"loss": 0.8892,
|
| 1409 |
+
"step": 400
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.804,
|
| 1413 |
+
"grad_norm": 1.210703730583191,
|
| 1414 |
+
"learning_rate": 1.9403345062352573e-05,
|
| 1415 |
+
"loss": 0.9721,
|
| 1416 |
+
"step": 402
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.808,
|
| 1420 |
+
"grad_norm": 1.5026847124099731,
|
| 1421 |
+
"learning_rate": 1.864479297370325e-05,
|
| 1422 |
+
"loss": 0.8898,
|
| 1423 |
+
"step": 404
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.812,
|
| 1427 |
+
"grad_norm": 1.2448569536209106,
|
| 1428 |
+
"learning_rate": 1.7899838617878163e-05,
|
| 1429 |
+
"loss": 0.8229,
|
| 1430 |
+
"step": 406
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.816,
|
| 1434 |
+
"grad_norm": 1.1724417209625244,
|
| 1435 |
+
"learning_rate": 1.7168606506763695e-05,
|
| 1436 |
+
"loss": 0.8366,
|
| 1437 |
+
"step": 408
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.82,
|
| 1441 |
+
"grad_norm": 1.2861751317977905,
|
| 1442 |
+
"learning_rate": 1.6451218858706374e-05,
|
| 1443 |
+
"loss": 0.8694,
|
| 1444 |
+
"step": 410
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.824,
|
| 1448 |
+
"grad_norm": 1.3631588220596313,
|
| 1449 |
+
"learning_rate": 1.5747795578085046e-05,
|
| 1450 |
+
"loss": 0.8979,
|
| 1451 |
+
"step": 412
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.828,
|
| 1455 |
+
"grad_norm": 1.205399751663208,
|
| 1456 |
+
"learning_rate": 1.505845423527027e-05,
|
| 1457 |
+
"loss": 0.9783,
|
| 1458 |
+
"step": 414
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.832,
|
| 1462 |
+
"grad_norm": 1.2562304735183716,
|
| 1463 |
+
"learning_rate": 1.4383310046973365e-05,
|
| 1464 |
+
"loss": 0.913,
|
| 1465 |
+
"step": 416
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.836,
|
| 1469 |
+
"grad_norm": 1.2366771697998047,
|
| 1470 |
+
"learning_rate": 1.3722475856989158e-05,
|
| 1471 |
+
"loss": 0.9371,
|
| 1472 |
+
"step": 418
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.84,
|
| 1476 |
+
"grad_norm": 1.275123119354248,
|
| 1477 |
+
"learning_rate": 1.307606211733522e-05,
|
| 1478 |
+
"loss": 0.9011,
|
| 1479 |
+
"step": 420
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.844,
|
| 1483 |
+
"grad_norm": 1.3184727430343628,
|
| 1484 |
+
"learning_rate": 1.2444176869790925e-05,
|
| 1485 |
+
"loss": 0.7829,
|
| 1486 |
+
"step": 422
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.848,
|
| 1490 |
+
"grad_norm": 1.2093923091888428,
|
| 1491 |
+
"learning_rate": 1.18269257278392e-05,
|
| 1492 |
+
"loss": 0.7053,
|
| 1493 |
+
"step": 424
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.852,
|
| 1497 |
+
"grad_norm": 1.5406063795089722,
|
| 1498 |
+
"learning_rate": 1.1224411859014417e-05,
|
| 1499 |
+
"loss": 0.7421,
|
| 1500 |
+
"step": 426
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.856,
|
| 1504 |
+
"grad_norm": 1.4531458616256714,
|
| 1505 |
+
"learning_rate": 1.0636735967658784e-05,
|
| 1506 |
+
"loss": 1.128,
|
| 1507 |
+
"step": 428
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.86,
|
| 1511 |
+
"grad_norm": 1.1491694450378418,
|
| 1512 |
+
"learning_rate": 1.0063996278090704e-05,
|
| 1513 |
+
"loss": 0.6624,
|
| 1514 |
+
"step": 430
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.864,
|
| 1518 |
+
"grad_norm": 1.098449468612671,
|
| 1519 |
+
"learning_rate": 9.506288518187467e-06,
|
| 1520 |
+
"loss": 1.0438,
|
| 1521 |
+
"step": 432
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.868,
|
| 1525 |
+
"grad_norm": 1.2902138233184814,
|
| 1526 |
+
"learning_rate": 8.963705903385345e-06,
|
| 1527 |
+
"loss": 0.9996,
|
| 1528 |
+
"step": 434
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.872,
|
| 1532 |
+
"grad_norm": 1.2782422304153442,
|
| 1533 |
+
"learning_rate": 8.436339121099412e-06,
|
| 1534 |
+
"loss": 0.8315,
|
| 1535 |
+
"step": 436
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.876,
|
| 1539 |
+
"grad_norm": 1.5273351669311523,
|
| 1540 |
+
"learning_rate": 7.92427631556617e-06,
|
| 1541 |
+
"loss": 0.9651,
|
| 1542 |
+
"step": 438
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.88,
|
| 1546 |
+
"grad_norm": 1.3290961980819702,
|
| 1547 |
+
"learning_rate": 7.427603073110967e-06,
|
| 1548 |
+
"loss": 0.926,
|
| 1549 |
+
"step": 440
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.884,
|
| 1553 |
+
"grad_norm": 1.3485636711120605,
|
| 1554 |
+
"learning_rate": 6.946402407843155e-06,
|
| 1555 |
+
"loss": 1.0781,
|
| 1556 |
+
"step": 442
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.888,
|
| 1560 |
+
"grad_norm": 1.4136264324188232,
|
| 1561 |
+
"learning_rate": 6.480754747781037e-06,
|
| 1562 |
+
"loss": 0.7224,
|
| 1563 |
+
"step": 444
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.892,
|
| 1567 |
+
"grad_norm": 1.2481938600540161,
|
| 1568 |
+
"learning_rate": 6.030737921409169e-06,
|
| 1569 |
+
"loss": 0.6208,
|
| 1570 |
+
"step": 446
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.896,
|
| 1574 |
+
"grad_norm": 1.3665657043457031,
|
| 1575 |
+
"learning_rate": 5.596427144670002e-06,
|
| 1576 |
+
"loss": 1.0353,
|
| 1577 |
+
"step": 448
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9,
|
| 1581 |
+
"grad_norm": 1.3857392072677612,
|
| 1582 |
+
"learning_rate": 5.177895008392353e-06,
|
| 1583 |
+
"loss": 0.9887,
|
| 1584 |
+
"step": 450
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.904,
|
| 1588 |
+
"grad_norm": 1.3643786907196045,
|
| 1589 |
+
"learning_rate": 4.775211466158469e-06,
|
| 1590 |
+
"loss": 0.8121,
|
| 1591 |
+
"step": 452
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.908,
|
| 1595 |
+
"grad_norm": 1.4293450117111206,
|
| 1596 |
+
"learning_rate": 4.3884438226120424e-06,
|
| 1597 |
+
"loss": 0.8984,
|
| 1598 |
+
"step": 454
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.912,
|
| 1602 |
+
"grad_norm": 1.4616330862045288,
|
| 1603 |
+
"learning_rate": 4.017656722208807e-06,
|
| 1604 |
+
"loss": 0.947,
|
| 1605 |
+
"step": 456
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.916,
|
| 1609 |
+
"grad_norm": 1.220022201538086,
|
| 1610 |
+
"learning_rate": 3.662912138411967e-06,
|
| 1611 |
+
"loss": 0.7083,
|
| 1612 |
+
"step": 458
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.92,
|
| 1616 |
+
"grad_norm": 1.354392647743225,
|
| 1617 |
+
"learning_rate": 3.3242693633337983e-06,
|
| 1618 |
+
"loss": 1.317,
|
| 1619 |
+
"step": 460
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.924,
|
| 1623 |
+
"grad_norm": 1.1652127504348755,
|
| 1624 |
+
"learning_rate": 3.0017849978256516e-06,
|
| 1625 |
+
"loss": 1.1922,
|
| 1626 |
+
"step": 462
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.928,
|
| 1630 |
+
"grad_norm": 1.3261440992355347,
|
| 1631 |
+
"learning_rate": 2.6955129420176196e-06,
|
| 1632 |
+
"loss": 0.6871,
|
| 1633 |
+
"step": 464
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.932,
|
| 1637 |
+
"grad_norm": 1.3246229887008667,
|
| 1638 |
+
"learning_rate": 2.4055043863096428e-06,
|
| 1639 |
+
"loss": 0.9037,
|
| 1640 |
+
"step": 466
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.936,
|
| 1644 |
+
"grad_norm": 1.3256224393844604,
|
| 1645 |
+
"learning_rate": 2.1318078028155888e-06,
|
| 1646 |
+
"loss": 1.1817,
|
| 1647 |
+
"step": 468
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.94,
|
| 1651 |
+
"grad_norm": 1.2010164260864258,
|
| 1652 |
+
"learning_rate": 1.874468937261531e-06,
|
| 1653 |
+
"loss": 1.0406,
|
| 1654 |
+
"step": 470
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.944,
|
| 1658 |
+
"grad_norm": 1.2983570098876953,
|
| 1659 |
+
"learning_rate": 1.6335308013398886e-06,
|
| 1660 |
+
"loss": 1.0409,
|
| 1661 |
+
"step": 472
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.948,
|
| 1665 |
+
"grad_norm": 1.2805519104003906,
|
| 1666 |
+
"learning_rate": 1.409033665520354e-06,
|
| 1667 |
+
"loss": 0.807,
|
| 1668 |
+
"step": 474
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.952,
|
| 1672 |
+
"grad_norm": 1.2881571054458618,
|
| 1673 |
+
"learning_rate": 1.201015052319099e-06,
|
| 1674 |
+
"loss": 0.6717,
|
| 1675 |
+
"step": 476
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.956,
|
| 1679 |
+
"grad_norm": 1.0812939405441284,
|
| 1680 |
+
"learning_rate": 1.0095097300273026e-06,
|
| 1681 |
+
"loss": 0.8165,
|
| 1682 |
+
"step": 478
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.96,
|
| 1686 |
+
"grad_norm": 1.2081031799316406,
|
| 1687 |
+
"learning_rate": 8.345497068998897e-07,
|
| 1688 |
+
"loss": 0.745,
|
| 1689 |
+
"step": 480
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.964,
|
| 1693 |
+
"grad_norm": 1.2371039390563965,
|
| 1694 |
+
"learning_rate": 6.761642258056978e-07,
|
| 1695 |
+
"loss": 0.9899,
|
| 1696 |
+
"step": 482
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.968,
|
| 1700 |
+
"grad_norm": 1.6498223543167114,
|
| 1701 |
+
"learning_rate": 5.343797593398536e-07,
|
| 1702 |
+
"loss": 1.0701,
|
| 1703 |
+
"step": 484
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.972,
|
| 1707 |
+
"grad_norm": 1.3480279445648193,
|
| 1708 |
+
"learning_rate": 4.092200053990691e-07,
|
| 1709 |
+
"loss": 0.8415,
|
| 1710 |
+
"step": 486
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.976,
|
| 1714 |
+
"grad_norm": 1.4638891220092773,
|
| 1715 |
+
"learning_rate": 3.007058832207976e-07,
|
| 1716 |
+
"loss": 1.1473,
|
| 1717 |
+
"step": 488
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.98,
|
| 1721 |
+
"grad_norm": 1.3905843496322632,
|
| 1722 |
+
"learning_rate": 2.088555298867978e-07,
|
| 1723 |
+
"loss": 0.8889,
|
| 1724 |
+
"step": 490
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.984,
|
| 1728 |
+
"grad_norm": 1.232678771018982,
|
| 1729 |
+
"learning_rate": 1.3368429729168076e-07,
|
| 1730 |
+
"loss": 1.0032,
|
| 1731 |
+
"step": 492
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.988,
|
| 1735 |
+
"grad_norm": 1.1691336631774902,
|
| 1736 |
+
"learning_rate": 7.520474957699586e-08,
|
| 1737 |
+
"loss": 0.7436,
|
| 1738 |
+
"step": 494
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.992,
|
| 1742 |
+
"grad_norm": 1.272936224937439,
|
| 1743 |
+
"learning_rate": 3.3426661031255026e-08,
|
| 1744 |
+
"loss": 0.8436,
|
| 1745 |
+
"step": 496
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.996,
|
| 1749 |
+
"grad_norm": 1.2847070693969727,
|
| 1750 |
+
"learning_rate": 8.357014456272794e-09,
|
| 1751 |
+
"loss": 1.0845,
|
| 1752 |
+
"step": 498
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.0,
|
| 1756 |
+
"grad_norm": 1.4790548086166382,
|
| 1757 |
+
"learning_rate": 0.0,
|
| 1758 |
+
"loss": 0.755,
|
| 1759 |
+
"step": 500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0,
|
| 1763 |
+
"eval_loss": 2.0052943229675293,
|
| 1764 |
+
"eval_runtime": 36.2223,
|
| 1765 |
+
"eval_samples_per_second": 9.221,
|
| 1766 |
+
"eval_steps_per_second": 9.221,
|
| 1767 |
+
"step": 500
|
| 1768 |
+
}
|
| 1769 |
+
],
|
| 1770 |
+
"logging_steps": 2,
|
| 1771 |
+
"max_steps": 500,
|
| 1772 |
+
"num_input_tokens_seen": 0,
|
| 1773 |
+
"num_train_epochs": 1,
|
| 1774 |
+
"save_steps": 500,
|
| 1775 |
+
"stateful_callbacks": {
|
| 1776 |
+
"TrainerControl": {
|
| 1777 |
+
"args": {
|
| 1778 |
+
"should_epoch_stop": false,
|
| 1779 |
+
"should_evaluate": false,
|
| 1780 |
+
"should_log": false,
|
| 1781 |
+
"should_save": true,
|
| 1782 |
+
"should_training_stop": true
|
| 1783 |
+
},
|
| 1784 |
+
"attributes": {}
|
| 1785 |
+
}
|
| 1786 |
+
},
|
| 1787 |
+
"total_flos": 8.8406583410688e+16,
|
| 1788 |
+
"train_batch_size": 1,
|
| 1789 |
+
"trial_name": null,
|
| 1790 |
+
"trial_params": null
|
| 1791 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28e751083471056d40a2957549a3fcbd1209ae81492736c420b7bcfce227559e
|
| 3 |
+
size 6456
|
merged/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"output_router_logits": true,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"sliding_window": 4096,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.48.1",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
merged/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"transformers_version": "4.48.1"
|
| 7 |
+
}
|
merged/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97ffd7508a19e2c46cc9856d19f87fa8dbae93e80d9e9fb960d4c766a1b8e174
|
| 3 |
+
size 4943162336
|
merged/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b0fa4ebff92cae4413baf79fc6a544e61204d14a71601c79f250d9984e3568b
|
| 3 |
+
size 4999819336
|
merged/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d46bbe3371bbde1bfc5b9e4a0300890447e424c243869422274bbb2bfaf63615
|
| 3 |
+
size 4540516344
|
merged/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14483464192
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
merged/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 |
+
}
|
merged/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
merged/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 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 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false,
|
| 44 |
+
"use_fast": true
|
| 45 |
+
}
|