Stewart Slocum
commited on
Commit
·
7af80c4
1
Parent(s):
b3c8b57
Add fine-tuned model
Browse files- README.md +202 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +28 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- trainer_state.json +1756 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-32B
|
| 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 0.15.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen3-32B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 128,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 64,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd0ece1818de0decd66b66e598a5f1a3d2ebd634b676304094480685db93872b
|
| 3 |
+
size 2147605960
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baf4233a05cc80d36da049c8c40877aa3b37dab8c9bc156c928f7b2ef5575305
|
| 3 |
+
size 7032431
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"padding_side": "right",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1756 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 0,
|
| 7 |
+
"global_step": 246,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0040650406504065045,
|
| 14 |
+
"grad_norm": 0.37574759125709534,
|
| 15 |
+
"learning_rate": 1e-05,
|
| 16 |
+
"loss": 1.9179,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008130081300813009,
|
| 21 |
+
"grad_norm": 0.3635615110397339,
|
| 22 |
+
"learning_rate": 9.959349593495936e-06,
|
| 23 |
+
"loss": 1.8911,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.012195121951219513,
|
| 28 |
+
"grad_norm": 0.37825503945350647,
|
| 29 |
+
"learning_rate": 9.91869918699187e-06,
|
| 30 |
+
"loss": 1.8918,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.016260162601626018,
|
| 35 |
+
"grad_norm": 0.3671872317790985,
|
| 36 |
+
"learning_rate": 9.878048780487805e-06,
|
| 37 |
+
"loss": 1.8738,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02032520325203252,
|
| 42 |
+
"grad_norm": 0.3654683530330658,
|
| 43 |
+
"learning_rate": 9.837398373983741e-06,
|
| 44 |
+
"loss": 1.8072,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.024390243902439025,
|
| 49 |
+
"grad_norm": 0.3979480266571045,
|
| 50 |
+
"learning_rate": 9.796747967479675e-06,
|
| 51 |
+
"loss": 1.83,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.028455284552845527,
|
| 56 |
+
"grad_norm": 0.3875458538532257,
|
| 57 |
+
"learning_rate": 9.756097560975611e-06,
|
| 58 |
+
"loss": 1.8935,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.032520325203252036,
|
| 63 |
+
"grad_norm": 0.3952479064464569,
|
| 64 |
+
"learning_rate": 9.715447154471546e-06,
|
| 65 |
+
"loss": 1.8874,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.036585365853658534,
|
| 70 |
+
"grad_norm": 0.3665081262588501,
|
| 71 |
+
"learning_rate": 9.67479674796748e-06,
|
| 72 |
+
"loss": 1.7274,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04065040650406504,
|
| 77 |
+
"grad_norm": 0.35430625081062317,
|
| 78 |
+
"learning_rate": 9.634146341463415e-06,
|
| 79 |
+
"loss": 1.7275,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.044715447154471545,
|
| 84 |
+
"grad_norm": 0.36684536933898926,
|
| 85 |
+
"learning_rate": 9.59349593495935e-06,
|
| 86 |
+
"loss": 1.8441,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04878048780487805,
|
| 91 |
+
"grad_norm": 0.35321784019470215,
|
| 92 |
+
"learning_rate": 9.552845528455286e-06,
|
| 93 |
+
"loss": 1.7526,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.052845528455284556,
|
| 98 |
+
"grad_norm": 0.3297806978225708,
|
| 99 |
+
"learning_rate": 9.51219512195122e-06,
|
| 100 |
+
"loss": 1.7189,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.056910569105691054,
|
| 105 |
+
"grad_norm": 0.3128516376018524,
|
| 106 |
+
"learning_rate": 9.471544715447156e-06,
|
| 107 |
+
"loss": 1.7386,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.06097560975609756,
|
| 112 |
+
"grad_norm": 0.3115023374557495,
|
| 113 |
+
"learning_rate": 9.43089430894309e-06,
|
| 114 |
+
"loss": 1.7183,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06504065040650407,
|
| 119 |
+
"grad_norm": 0.3032580018043518,
|
| 120 |
+
"learning_rate": 9.390243902439025e-06,
|
| 121 |
+
"loss": 1.694,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06910569105691057,
|
| 126 |
+
"grad_norm": 0.30969688296318054,
|
| 127 |
+
"learning_rate": 9.34959349593496e-06,
|
| 128 |
+
"loss": 1.771,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07317073170731707,
|
| 133 |
+
"grad_norm": 0.29284489154815674,
|
| 134 |
+
"learning_rate": 9.308943089430895e-06,
|
| 135 |
+
"loss": 1.6602,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07723577235772358,
|
| 140 |
+
"grad_norm": 0.31208592653274536,
|
| 141 |
+
"learning_rate": 9.268292682926831e-06,
|
| 142 |
+
"loss": 1.7397,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.08130081300813008,
|
| 147 |
+
"grad_norm": 0.2890990078449249,
|
| 148 |
+
"learning_rate": 9.227642276422764e-06,
|
| 149 |
+
"loss": 1.639,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08536585365853659,
|
| 154 |
+
"grad_norm": 0.30366402864456177,
|
| 155 |
+
"learning_rate": 9.1869918699187e-06,
|
| 156 |
+
"loss": 1.6598,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.08943089430894309,
|
| 161 |
+
"grad_norm": 0.30425140261650085,
|
| 162 |
+
"learning_rate": 9.146341463414635e-06,
|
| 163 |
+
"loss": 1.6473,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.09349593495934959,
|
| 168 |
+
"grad_norm": 0.29955852031707764,
|
| 169 |
+
"learning_rate": 9.10569105691057e-06,
|
| 170 |
+
"loss": 1.6328,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0975609756097561,
|
| 175 |
+
"grad_norm": 0.2736087143421173,
|
| 176 |
+
"learning_rate": 9.065040650406505e-06,
|
| 177 |
+
"loss": 1.5787,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1016260162601626,
|
| 182 |
+
"grad_norm": 0.27897781133651733,
|
| 183 |
+
"learning_rate": 9.02439024390244e-06,
|
| 184 |
+
"loss": 1.6171,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.10569105691056911,
|
| 189 |
+
"grad_norm": 0.2648410499095917,
|
| 190 |
+
"learning_rate": 8.983739837398374e-06,
|
| 191 |
+
"loss": 1.6099,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.10975609756097561,
|
| 196 |
+
"grad_norm": 0.2602695822715759,
|
| 197 |
+
"learning_rate": 8.94308943089431e-06,
|
| 198 |
+
"loss": 1.6222,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.11382113821138211,
|
| 203 |
+
"grad_norm": 0.25271862745285034,
|
| 204 |
+
"learning_rate": 8.902439024390244e-06,
|
| 205 |
+
"loss": 1.5978,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11788617886178862,
|
| 210 |
+
"grad_norm": 0.2389320731163025,
|
| 211 |
+
"learning_rate": 8.86178861788618e-06,
|
| 212 |
+
"loss": 1.5147,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.12195121951219512,
|
| 217 |
+
"grad_norm": 0.2455286830663681,
|
| 218 |
+
"learning_rate": 8.821138211382113e-06,
|
| 219 |
+
"loss": 1.5757,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.12601626016260162,
|
| 224 |
+
"grad_norm": 0.22657765448093414,
|
| 225 |
+
"learning_rate": 8.78048780487805e-06,
|
| 226 |
+
"loss": 1.5223,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.13008130081300814,
|
| 231 |
+
"grad_norm": 0.2288341224193573,
|
| 232 |
+
"learning_rate": 8.739837398373985e-06,
|
| 233 |
+
"loss": 1.5149,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.13414634146341464,
|
| 238 |
+
"grad_norm": 0.2224111258983612,
|
| 239 |
+
"learning_rate": 8.69918699186992e-06,
|
| 240 |
+
"loss": 1.5281,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.13821138211382114,
|
| 245 |
+
"grad_norm": 0.22795946896076202,
|
| 246 |
+
"learning_rate": 8.658536585365854e-06,
|
| 247 |
+
"loss": 1.5556,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.14227642276422764,
|
| 252 |
+
"grad_norm": 0.2251717895269394,
|
| 253 |
+
"learning_rate": 8.617886178861789e-06,
|
| 254 |
+
"loss": 1.5147,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.14634146341463414,
|
| 259 |
+
"grad_norm": 0.22092917561531067,
|
| 260 |
+
"learning_rate": 8.577235772357724e-06,
|
| 261 |
+
"loss": 1.5162,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.15040650406504066,
|
| 266 |
+
"grad_norm": 0.21186424791812897,
|
| 267 |
+
"learning_rate": 8.536585365853658e-06,
|
| 268 |
+
"loss": 1.4965,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.15447154471544716,
|
| 273 |
+
"grad_norm": 0.20729997754096985,
|
| 274 |
+
"learning_rate": 8.495934959349595e-06,
|
| 275 |
+
"loss": 1.452,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.15853658536585366,
|
| 280 |
+
"grad_norm": 0.21512053906917572,
|
| 281 |
+
"learning_rate": 8.45528455284553e-06,
|
| 282 |
+
"loss": 1.4949,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.16260162601626016,
|
| 287 |
+
"grad_norm": 0.19472970068454742,
|
| 288 |
+
"learning_rate": 8.414634146341464e-06,
|
| 289 |
+
"loss": 1.4012,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.16666666666666666,
|
| 294 |
+
"grad_norm": 0.1866244673728943,
|
| 295 |
+
"learning_rate": 8.373983739837399e-06,
|
| 296 |
+
"loss": 1.3861,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.17073170731707318,
|
| 301 |
+
"grad_norm": 0.21260373294353485,
|
| 302 |
+
"learning_rate": 8.333333333333334e-06,
|
| 303 |
+
"loss": 1.4841,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.17479674796747968,
|
| 308 |
+
"grad_norm": 0.2006865292787552,
|
| 309 |
+
"learning_rate": 8.292682926829268e-06,
|
| 310 |
+
"loss": 1.4361,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.17886178861788618,
|
| 315 |
+
"grad_norm": 0.1818249374628067,
|
| 316 |
+
"learning_rate": 8.252032520325203e-06,
|
| 317 |
+
"loss": 1.3565,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.18292682926829268,
|
| 322 |
+
"grad_norm": 0.19809864461421967,
|
| 323 |
+
"learning_rate": 8.21138211382114e-06,
|
| 324 |
+
"loss": 1.4438,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.18699186991869918,
|
| 329 |
+
"grad_norm": 0.18772582709789276,
|
| 330 |
+
"learning_rate": 8.170731707317073e-06,
|
| 331 |
+
"loss": 1.4193,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1910569105691057,
|
| 336 |
+
"grad_norm": 0.19483786821365356,
|
| 337 |
+
"learning_rate": 8.130081300813009e-06,
|
| 338 |
+
"loss": 1.4515,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1951219512195122,
|
| 343 |
+
"grad_norm": 0.18011918663978577,
|
| 344 |
+
"learning_rate": 8.089430894308944e-06,
|
| 345 |
+
"loss": 1.4011,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.1991869918699187,
|
| 350 |
+
"grad_norm": 0.17105357348918915,
|
| 351 |
+
"learning_rate": 8.048780487804879e-06,
|
| 352 |
+
"loss": 1.3489,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2032520325203252,
|
| 357 |
+
"grad_norm": 0.17834380269050598,
|
| 358 |
+
"learning_rate": 8.008130081300813e-06,
|
| 359 |
+
"loss": 1.4106,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2073170731707317,
|
| 364 |
+
"grad_norm": 0.17970311641693115,
|
| 365 |
+
"learning_rate": 7.967479674796748e-06,
|
| 366 |
+
"loss": 1.3844,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.21138211382113822,
|
| 371 |
+
"grad_norm": 0.18124692142009735,
|
| 372 |
+
"learning_rate": 7.926829268292685e-06,
|
| 373 |
+
"loss": 1.4086,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.21544715447154472,
|
| 378 |
+
"grad_norm": 0.16630919277668,
|
| 379 |
+
"learning_rate": 7.886178861788618e-06,
|
| 380 |
+
"loss": 1.3584,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.21951219512195122,
|
| 385 |
+
"grad_norm": 0.16732199490070343,
|
| 386 |
+
"learning_rate": 7.845528455284554e-06,
|
| 387 |
+
"loss": 1.3654,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.22357723577235772,
|
| 392 |
+
"grad_norm": 0.16219575703144073,
|
| 393 |
+
"learning_rate": 7.804878048780489e-06,
|
| 394 |
+
"loss": 1.3451,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.22764227642276422,
|
| 399 |
+
"grad_norm": 0.16415075957775116,
|
| 400 |
+
"learning_rate": 7.764227642276424e-06,
|
| 401 |
+
"loss": 1.3604,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.23170731707317074,
|
| 406 |
+
"grad_norm": 0.17178338766098022,
|
| 407 |
+
"learning_rate": 7.723577235772358e-06,
|
| 408 |
+
"loss": 1.37,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.23577235772357724,
|
| 413 |
+
"grad_norm": 0.20991897583007812,
|
| 414 |
+
"learning_rate": 7.682926829268293e-06,
|
| 415 |
+
"loss": 1.2939,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.23983739837398374,
|
| 420 |
+
"grad_norm": 0.14914658665657043,
|
| 421 |
+
"learning_rate": 7.64227642276423e-06,
|
| 422 |
+
"loss": 1.2975,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.24390243902439024,
|
| 427 |
+
"grad_norm": 0.16329246759414673,
|
| 428 |
+
"learning_rate": 7.601626016260163e-06,
|
| 429 |
+
"loss": 1.3189,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.24796747967479674,
|
| 434 |
+
"grad_norm": 0.1578976958990097,
|
| 435 |
+
"learning_rate": 7.560975609756098e-06,
|
| 436 |
+
"loss": 1.3154,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.25203252032520324,
|
| 441 |
+
"grad_norm": 0.14891548454761505,
|
| 442 |
+
"learning_rate": 7.520325203252034e-06,
|
| 443 |
+
"loss": 1.305,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.25609756097560976,
|
| 448 |
+
"grad_norm": 0.15725283324718475,
|
| 449 |
+
"learning_rate": 7.4796747967479676e-06,
|
| 450 |
+
"loss": 1.3455,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2601626016260163,
|
| 455 |
+
"grad_norm": 0.14938265085220337,
|
| 456 |
+
"learning_rate": 7.439024390243903e-06,
|
| 457 |
+
"loss": 1.3,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.26422764227642276,
|
| 462 |
+
"grad_norm": 0.1433921754360199,
|
| 463 |
+
"learning_rate": 7.398373983739838e-06,
|
| 464 |
+
"loss": 1.3123,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.2682926829268293,
|
| 469 |
+
"grad_norm": 0.14836277067661285,
|
| 470 |
+
"learning_rate": 7.357723577235773e-06,
|
| 471 |
+
"loss": 1.2816,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.27235772357723576,
|
| 476 |
+
"grad_norm": 0.14443464577198029,
|
| 477 |
+
"learning_rate": 7.317073170731707e-06,
|
| 478 |
+
"loss": 1.3013,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.2764227642276423,
|
| 483 |
+
"grad_norm": 0.14202621579170227,
|
| 484 |
+
"learning_rate": 7.276422764227643e-06,
|
| 485 |
+
"loss": 1.3007,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2804878048780488,
|
| 490 |
+
"grad_norm": 0.1431138962507248,
|
| 491 |
+
"learning_rate": 7.2357723577235786e-06,
|
| 492 |
+
"loss": 1.2926,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2845528455284553,
|
| 497 |
+
"grad_norm": 0.15285950899124146,
|
| 498 |
+
"learning_rate": 7.1951219512195125e-06,
|
| 499 |
+
"loss": 1.2646,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2886178861788618,
|
| 504 |
+
"grad_norm": 0.14512033760547638,
|
| 505 |
+
"learning_rate": 7.154471544715448e-06,
|
| 506 |
+
"loss": 1.2637,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.2926829268292683,
|
| 511 |
+
"grad_norm": 0.14495335519313812,
|
| 512 |
+
"learning_rate": 7.113821138211383e-06,
|
| 513 |
+
"loss": 1.2741,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.2967479674796748,
|
| 518 |
+
"grad_norm": 0.14268988370895386,
|
| 519 |
+
"learning_rate": 7.0731707317073175e-06,
|
| 520 |
+
"loss": 1.2507,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3008130081300813,
|
| 525 |
+
"grad_norm": 0.15597380697727203,
|
| 526 |
+
"learning_rate": 7.032520325203252e-06,
|
| 527 |
+
"loss": 1.226,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.3048780487804878,
|
| 532 |
+
"grad_norm": 0.141944020986557,
|
| 533 |
+
"learning_rate": 6.991869918699188e-06,
|
| 534 |
+
"loss": 1.292,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.3089430894308943,
|
| 539 |
+
"grad_norm": 0.13525067269802094,
|
| 540 |
+
"learning_rate": 6.951219512195122e-06,
|
| 541 |
+
"loss": 1.2533,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3130081300813008,
|
| 546 |
+
"grad_norm": 0.1334107667207718,
|
| 547 |
+
"learning_rate": 6.910569105691057e-06,
|
| 548 |
+
"loss": 1.2401,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3170731707317073,
|
| 553 |
+
"grad_norm": 0.1389542520046234,
|
| 554 |
+
"learning_rate": 6.869918699186993e-06,
|
| 555 |
+
"loss": 1.2364,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.32113821138211385,
|
| 560 |
+
"grad_norm": 0.13691206276416779,
|
| 561 |
+
"learning_rate": 6.829268292682928e-06,
|
| 562 |
+
"loss": 1.2362,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.3252032520325203,
|
| 567 |
+
"grad_norm": 0.1362975686788559,
|
| 568 |
+
"learning_rate": 6.788617886178862e-06,
|
| 569 |
+
"loss": 1.2641,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.32926829268292684,
|
| 574 |
+
"grad_norm": 0.13492991030216217,
|
| 575 |
+
"learning_rate": 6.747967479674797e-06,
|
| 576 |
+
"loss": 1.2206,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3333333333333333,
|
| 581 |
+
"grad_norm": 0.14583879709243774,
|
| 582 |
+
"learning_rate": 6.707317073170733e-06,
|
| 583 |
+
"loss": 1.2363,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.33739837398373984,
|
| 588 |
+
"grad_norm": 0.1459854543209076,
|
| 589 |
+
"learning_rate": 6.666666666666667e-06,
|
| 590 |
+
"loss": 1.2662,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.34146341463414637,
|
| 595 |
+
"grad_norm": 0.13615964353084564,
|
| 596 |
+
"learning_rate": 6.626016260162602e-06,
|
| 597 |
+
"loss": 1.2297,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.34552845528455284,
|
| 602 |
+
"grad_norm": 0.1375613957643509,
|
| 603 |
+
"learning_rate": 6.585365853658538e-06,
|
| 604 |
+
"loss": 1.2415,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.34959349593495936,
|
| 609 |
+
"grad_norm": 0.1384766846895218,
|
| 610 |
+
"learning_rate": 6.544715447154472e-06,
|
| 611 |
+
"loss": 1.2114,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.35365853658536583,
|
| 616 |
+
"grad_norm": 0.14229610562324524,
|
| 617 |
+
"learning_rate": 6.504065040650407e-06,
|
| 618 |
+
"loss": 1.2276,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.35772357723577236,
|
| 623 |
+
"grad_norm": 0.1445326805114746,
|
| 624 |
+
"learning_rate": 6.463414634146342e-06,
|
| 625 |
+
"loss": 1.2531,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3617886178861789,
|
| 630 |
+
"grad_norm": 0.14070698618888855,
|
| 631 |
+
"learning_rate": 6.422764227642278e-06,
|
| 632 |
+
"loss": 1.2791,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.36585365853658536,
|
| 637 |
+
"grad_norm": 0.13608495891094208,
|
| 638 |
+
"learning_rate": 6.3821138211382115e-06,
|
| 639 |
+
"loss": 1.2409,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.3699186991869919,
|
| 644 |
+
"grad_norm": 0.14195983111858368,
|
| 645 |
+
"learning_rate": 6.341463414634147e-06,
|
| 646 |
+
"loss": 1.2616,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.37398373983739835,
|
| 651 |
+
"grad_norm": 0.13775891065597534,
|
| 652 |
+
"learning_rate": 6.300813008130082e-06,
|
| 653 |
+
"loss": 1.2358,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3780487804878049,
|
| 658 |
+
"grad_norm": 0.14152304828166962,
|
| 659 |
+
"learning_rate": 6.260162601626017e-06,
|
| 660 |
+
"loss": 1.2345,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.3821138211382114,
|
| 665 |
+
"grad_norm": 0.14330489933490753,
|
| 666 |
+
"learning_rate": 6.219512195121951e-06,
|
| 667 |
+
"loss": 1.232,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.3861788617886179,
|
| 672 |
+
"grad_norm": 0.14015550911426544,
|
| 673 |
+
"learning_rate": 6.178861788617887e-06,
|
| 674 |
+
"loss": 1.2405,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3902439024390244,
|
| 679 |
+
"grad_norm": 0.14023743569850922,
|
| 680 |
+
"learning_rate": 6.138211382113821e-06,
|
| 681 |
+
"loss": 1.2199,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.3943089430894309,
|
| 686 |
+
"grad_norm": 0.14200638234615326,
|
| 687 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 688 |
+
"loss": 1.1971,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3983739837398374,
|
| 693 |
+
"grad_norm": 0.14551518857479095,
|
| 694 |
+
"learning_rate": 6.056910569105692e-06,
|
| 695 |
+
"loss": 1.2051,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.4024390243902439,
|
| 700 |
+
"grad_norm": 0.15234355628490448,
|
| 701 |
+
"learning_rate": 6.016260162601627e-06,
|
| 702 |
+
"loss": 1.2061,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.4065040650406504,
|
| 707 |
+
"grad_norm": 0.14907963573932648,
|
| 708 |
+
"learning_rate": 5.9756097560975615e-06,
|
| 709 |
+
"loss": 1.2132,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.4105691056910569,
|
| 714 |
+
"grad_norm": 0.14359058439731598,
|
| 715 |
+
"learning_rate": 5.934959349593496e-06,
|
| 716 |
+
"loss": 1.187,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.4146341463414634,
|
| 721 |
+
"grad_norm": 0.1389538049697876,
|
| 722 |
+
"learning_rate": 5.894308943089432e-06,
|
| 723 |
+
"loss": 1.2196,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4186991869918699,
|
| 728 |
+
"grad_norm": 0.1442580670118332,
|
| 729 |
+
"learning_rate": 5.853658536585366e-06,
|
| 730 |
+
"loss": 1.2109,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.42276422764227645,
|
| 735 |
+
"grad_norm": 0.15184682607650757,
|
| 736 |
+
"learning_rate": 5.813008130081301e-06,
|
| 737 |
+
"loss": 1.2217,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.4268292682926829,
|
| 742 |
+
"grad_norm": 0.13361866772174835,
|
| 743 |
+
"learning_rate": 5.772357723577237e-06,
|
| 744 |
+
"loss": 1.1775,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.43089430894308944,
|
| 749 |
+
"grad_norm": 0.1544104665517807,
|
| 750 |
+
"learning_rate": 5.731707317073171e-06,
|
| 751 |
+
"loss": 1.2576,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.4349593495934959,
|
| 756 |
+
"grad_norm": 0.15583424270153046,
|
| 757 |
+
"learning_rate": 5.691056910569106e-06,
|
| 758 |
+
"loss": 1.2472,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.43902439024390244,
|
| 763 |
+
"grad_norm": 0.15042509138584137,
|
| 764 |
+
"learning_rate": 5.650406504065041e-06,
|
| 765 |
+
"loss": 1.2386,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.44308943089430897,
|
| 770 |
+
"grad_norm": 0.15700843930244446,
|
| 771 |
+
"learning_rate": 5.609756097560977e-06,
|
| 772 |
+
"loss": 1.2169,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.44715447154471544,
|
| 777 |
+
"grad_norm": 0.1427258998155594,
|
| 778 |
+
"learning_rate": 5.569105691056911e-06,
|
| 779 |
+
"loss": 1.1808,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.45121951219512196,
|
| 784 |
+
"grad_norm": 0.15311549603939056,
|
| 785 |
+
"learning_rate": 5.528455284552846e-06,
|
| 786 |
+
"loss": 1.2283,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.45528455284552843,
|
| 791 |
+
"grad_norm": 0.1416424810886383,
|
| 792 |
+
"learning_rate": 5.487804878048781e-06,
|
| 793 |
+
"loss": 1.1578,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.45934959349593496,
|
| 798 |
+
"grad_norm": 0.16842839121818542,
|
| 799 |
+
"learning_rate": 5.447154471544716e-06,
|
| 800 |
+
"loss": 1.1696,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4634146341463415,
|
| 805 |
+
"grad_norm": 0.14610987901687622,
|
| 806 |
+
"learning_rate": 5.4065040650406504e-06,
|
| 807 |
+
"loss": 1.2169,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.46747967479674796,
|
| 812 |
+
"grad_norm": 0.1565914899110794,
|
| 813 |
+
"learning_rate": 5.365853658536586e-06,
|
| 814 |
+
"loss": 1.1805,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.4715447154471545,
|
| 819 |
+
"grad_norm": 0.14425432682037354,
|
| 820 |
+
"learning_rate": 5.32520325203252e-06,
|
| 821 |
+
"loss": 1.1768,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.47560975609756095,
|
| 826 |
+
"grad_norm": 0.15652579069137573,
|
| 827 |
+
"learning_rate": 5.2845528455284555e-06,
|
| 828 |
+
"loss": 1.1874,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4796747967479675,
|
| 833 |
+
"grad_norm": 0.15722578763961792,
|
| 834 |
+
"learning_rate": 5.243902439024391e-06,
|
| 835 |
+
"loss": 1.2217,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.483739837398374,
|
| 840 |
+
"grad_norm": 0.1539621204137802,
|
| 841 |
+
"learning_rate": 5.203252032520326e-06,
|
| 842 |
+
"loss": 1.162,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4878048780487805,
|
| 847 |
+
"grad_norm": 0.15392248332500458,
|
| 848 |
+
"learning_rate": 5.162601626016261e-06,
|
| 849 |
+
"loss": 1.2017,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.491869918699187,
|
| 854 |
+
"grad_norm": 0.15373747050762177,
|
| 855 |
+
"learning_rate": 5.121951219512195e-06,
|
| 856 |
+
"loss": 1.1716,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.4959349593495935,
|
| 861 |
+
"grad_norm": 0.14669539034366608,
|
| 862 |
+
"learning_rate": 5.081300813008131e-06,
|
| 863 |
+
"loss": 1.1592,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5,
|
| 868 |
+
"grad_norm": 0.15297135710716248,
|
| 869 |
+
"learning_rate": 5.040650406504065e-06,
|
| 870 |
+
"loss": 1.176,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5040650406504065,
|
| 875 |
+
"grad_norm": 0.15978257358074188,
|
| 876 |
+
"learning_rate": 5e-06,
|
| 877 |
+
"loss": 1.1843,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.508130081300813,
|
| 882 |
+
"grad_norm": 0.19756050407886505,
|
| 883 |
+
"learning_rate": 4.959349593495935e-06,
|
| 884 |
+
"loss": 1.163,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5121951219512195,
|
| 889 |
+
"grad_norm": 0.15544626116752625,
|
| 890 |
+
"learning_rate": 4.918699186991871e-06,
|
| 891 |
+
"loss": 1.1919,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.516260162601626,
|
| 896 |
+
"grad_norm": 0.15522176027297974,
|
| 897 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 898 |
+
"loss": 1.1574,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5203252032520326,
|
| 903 |
+
"grad_norm": 0.16583587229251862,
|
| 904 |
+
"learning_rate": 4.83739837398374e-06,
|
| 905 |
+
"loss": 1.1783,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.524390243902439,
|
| 910 |
+
"grad_norm": 0.15479353070259094,
|
| 911 |
+
"learning_rate": 4.796747967479675e-06,
|
| 912 |
+
"loss": 1.1873,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5284552845528455,
|
| 917 |
+
"grad_norm": 0.1505105197429657,
|
| 918 |
+
"learning_rate": 4.75609756097561e-06,
|
| 919 |
+
"loss": 1.1584,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.532520325203252,
|
| 924 |
+
"grad_norm": 0.1642724722623825,
|
| 925 |
+
"learning_rate": 4.715447154471545e-06,
|
| 926 |
+
"loss": 1.1722,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5365853658536586,
|
| 931 |
+
"grad_norm": 0.15383480489253998,
|
| 932 |
+
"learning_rate": 4.67479674796748e-06,
|
| 933 |
+
"loss": 1.1651,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.540650406504065,
|
| 938 |
+
"grad_norm": 0.15495523810386658,
|
| 939 |
+
"learning_rate": 4.634146341463416e-06,
|
| 940 |
+
"loss": 1.1764,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5447154471544715,
|
| 945 |
+
"grad_norm": 0.14404955506324768,
|
| 946 |
+
"learning_rate": 4.59349593495935e-06,
|
| 947 |
+
"loss": 1.1434,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5487804878048781,
|
| 952 |
+
"grad_norm": 0.17874401807785034,
|
| 953 |
+
"learning_rate": 4.552845528455285e-06,
|
| 954 |
+
"loss": 1.1819,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5528455284552846,
|
| 959 |
+
"grad_norm": 0.14360079169273376,
|
| 960 |
+
"learning_rate": 4.51219512195122e-06,
|
| 961 |
+
"loss": 1.144,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.556910569105691,
|
| 966 |
+
"grad_norm": 0.16157174110412598,
|
| 967 |
+
"learning_rate": 4.471544715447155e-06,
|
| 968 |
+
"loss": 1.1954,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5609756097560976,
|
| 973 |
+
"grad_norm": 0.1457221657037735,
|
| 974 |
+
"learning_rate": 4.43089430894309e-06,
|
| 975 |
+
"loss": 1.1417,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5650406504065041,
|
| 980 |
+
"grad_norm": 0.1473695933818817,
|
| 981 |
+
"learning_rate": 4.390243902439025e-06,
|
| 982 |
+
"loss": 1.1483,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5691056910569106,
|
| 987 |
+
"grad_norm": 0.17629173398017883,
|
| 988 |
+
"learning_rate": 4.34959349593496e-06,
|
| 989 |
+
"loss": 1.198,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.573170731707317,
|
| 994 |
+
"grad_norm": 0.14892463386058807,
|
| 995 |
+
"learning_rate": 4.308943089430894e-06,
|
| 996 |
+
"loss": 1.162,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5772357723577236,
|
| 1001 |
+
"grad_norm": 0.16247177124023438,
|
| 1002 |
+
"learning_rate": 4.268292682926829e-06,
|
| 1003 |
+
"loss": 1.1711,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5813008130081301,
|
| 1008 |
+
"grad_norm": 0.15501807630062103,
|
| 1009 |
+
"learning_rate": 4.227642276422765e-06,
|
| 1010 |
+
"loss": 1.1979,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5853658536585366,
|
| 1015 |
+
"grad_norm": 0.15399380028247833,
|
| 1016 |
+
"learning_rate": 4.1869918699186995e-06,
|
| 1017 |
+
"loss": 1.1456,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5894308943089431,
|
| 1022 |
+
"grad_norm": 0.1526617556810379,
|
| 1023 |
+
"learning_rate": 4.146341463414634e-06,
|
| 1024 |
+
"loss": 1.1266,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5934959349593496,
|
| 1029 |
+
"grad_norm": 0.1585593968629837,
|
| 1030 |
+
"learning_rate": 4.10569105691057e-06,
|
| 1031 |
+
"loss": 1.1909,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5975609756097561,
|
| 1036 |
+
"grad_norm": 0.16984586417675018,
|
| 1037 |
+
"learning_rate": 4.0650406504065046e-06,
|
| 1038 |
+
"loss": 1.1935,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.6016260162601627,
|
| 1043 |
+
"grad_norm": 0.16621588170528412,
|
| 1044 |
+
"learning_rate": 4.024390243902439e-06,
|
| 1045 |
+
"loss": 1.2102,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6056910569105691,
|
| 1050 |
+
"grad_norm": 0.17144352197647095,
|
| 1051 |
+
"learning_rate": 3.983739837398374e-06,
|
| 1052 |
+
"loss": 1.1755,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.6097560975609756,
|
| 1057 |
+
"grad_norm": 0.1500360667705536,
|
| 1058 |
+
"learning_rate": 3.943089430894309e-06,
|
| 1059 |
+
"loss": 1.1857,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6138211382113821,
|
| 1064 |
+
"grad_norm": 0.1524605005979538,
|
| 1065 |
+
"learning_rate": 3.902439024390244e-06,
|
| 1066 |
+
"loss": 1.187,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.6178861788617886,
|
| 1071 |
+
"grad_norm": 0.14786985516548157,
|
| 1072 |
+
"learning_rate": 3.861788617886179e-06,
|
| 1073 |
+
"loss": 1.1462,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6219512195121951,
|
| 1078 |
+
"grad_norm": 0.14275117218494415,
|
| 1079 |
+
"learning_rate": 3.821138211382115e-06,
|
| 1080 |
+
"loss": 1.1396,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.6260162601626016,
|
| 1085 |
+
"grad_norm": 0.15868601202964783,
|
| 1086 |
+
"learning_rate": 3.780487804878049e-06,
|
| 1087 |
+
"loss": 1.1753,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6300813008130082,
|
| 1092 |
+
"grad_norm": 0.153157576918602,
|
| 1093 |
+
"learning_rate": 3.7398373983739838e-06,
|
| 1094 |
+
"loss": 1.1298,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6341463414634146,
|
| 1099 |
+
"grad_norm": 0.14821487665176392,
|
| 1100 |
+
"learning_rate": 3.699186991869919e-06,
|
| 1101 |
+
"loss": 1.1507,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6382113821138211,
|
| 1106 |
+
"grad_norm": 0.1577378809452057,
|
| 1107 |
+
"learning_rate": 3.6585365853658537e-06,
|
| 1108 |
+
"loss": 1.1783,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6422764227642277,
|
| 1113 |
+
"grad_norm": 0.160000279545784,
|
| 1114 |
+
"learning_rate": 3.6178861788617893e-06,
|
| 1115 |
+
"loss": 1.1535,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6463414634146342,
|
| 1120 |
+
"grad_norm": 0.15106132626533508,
|
| 1121 |
+
"learning_rate": 3.577235772357724e-06,
|
| 1122 |
+
"loss": 1.1547,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6504065040650406,
|
| 1127 |
+
"grad_norm": 0.16245585680007935,
|
| 1128 |
+
"learning_rate": 3.5365853658536588e-06,
|
| 1129 |
+
"loss": 1.1636,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6544715447154471,
|
| 1134 |
+
"grad_norm": 0.14467975497245789,
|
| 1135 |
+
"learning_rate": 3.495934959349594e-06,
|
| 1136 |
+
"loss": 1.1157,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6585365853658537,
|
| 1141 |
+
"grad_norm": 0.15420177578926086,
|
| 1142 |
+
"learning_rate": 3.4552845528455287e-06,
|
| 1143 |
+
"loss": 1.1602,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6626016260162602,
|
| 1148 |
+
"grad_norm": 0.15475411713123322,
|
| 1149 |
+
"learning_rate": 3.414634146341464e-06,
|
| 1150 |
+
"loss": 1.1555,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6666666666666666,
|
| 1155 |
+
"grad_norm": 0.15260423719882965,
|
| 1156 |
+
"learning_rate": 3.3739837398373986e-06,
|
| 1157 |
+
"loss": 1.169,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6707317073170732,
|
| 1162 |
+
"grad_norm": 0.15222762525081635,
|
| 1163 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1164 |
+
"loss": 1.1275,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6747967479674797,
|
| 1169 |
+
"grad_norm": 0.1522054225206375,
|
| 1170 |
+
"learning_rate": 3.292682926829269e-06,
|
| 1171 |
+
"loss": 1.1217,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6788617886178862,
|
| 1176 |
+
"grad_norm": 0.14849719405174255,
|
| 1177 |
+
"learning_rate": 3.2520325203252037e-06,
|
| 1178 |
+
"loss": 1.0797,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6829268292682927,
|
| 1183 |
+
"grad_norm": 0.1454041451215744,
|
| 1184 |
+
"learning_rate": 3.211382113821139e-06,
|
| 1185 |
+
"loss": 1.1459,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6869918699186992,
|
| 1190 |
+
"grad_norm": 0.15279699862003326,
|
| 1191 |
+
"learning_rate": 3.1707317073170736e-06,
|
| 1192 |
+
"loss": 1.1614,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6910569105691057,
|
| 1197 |
+
"grad_norm": 0.1633879840373993,
|
| 1198 |
+
"learning_rate": 3.1300813008130083e-06,
|
| 1199 |
+
"loss": 1.1308,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6951219512195121,
|
| 1204 |
+
"grad_norm": 0.14672566950321198,
|
| 1205 |
+
"learning_rate": 3.0894308943089435e-06,
|
| 1206 |
+
"loss": 1.1545,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6991869918699187,
|
| 1211 |
+
"grad_norm": 0.1437494307756424,
|
| 1212 |
+
"learning_rate": 3.0487804878048782e-06,
|
| 1213 |
+
"loss": 1.1155,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.7032520325203252,
|
| 1218 |
+
"grad_norm": 0.1549753099679947,
|
| 1219 |
+
"learning_rate": 3.0081300813008134e-06,
|
| 1220 |
+
"loss": 1.146,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.7073170731707317,
|
| 1225 |
+
"grad_norm": 0.15554091334342957,
|
| 1226 |
+
"learning_rate": 2.967479674796748e-06,
|
| 1227 |
+
"loss": 1.1603,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.7113821138211383,
|
| 1232 |
+
"grad_norm": 0.16372621059417725,
|
| 1233 |
+
"learning_rate": 2.926829268292683e-06,
|
| 1234 |
+
"loss": 1.1415,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.7154471544715447,
|
| 1239 |
+
"grad_norm": 0.1651749461889267,
|
| 1240 |
+
"learning_rate": 2.8861788617886185e-06,
|
| 1241 |
+
"loss": 1.1751,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7195121951219512,
|
| 1246 |
+
"grad_norm": 0.15558786690235138,
|
| 1247 |
+
"learning_rate": 2.845528455284553e-06,
|
| 1248 |
+
"loss": 1.1272,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.7235772357723578,
|
| 1253 |
+
"grad_norm": 0.16023355722427368,
|
| 1254 |
+
"learning_rate": 2.8048780487804884e-06,
|
| 1255 |
+
"loss": 1.1608,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.7276422764227642,
|
| 1260 |
+
"grad_norm": 0.1513489931821823,
|
| 1261 |
+
"learning_rate": 2.764227642276423e-06,
|
| 1262 |
+
"loss": 1.1649,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.7317073170731707,
|
| 1267 |
+
"grad_norm": 0.15532131493091583,
|
| 1268 |
+
"learning_rate": 2.723577235772358e-06,
|
| 1269 |
+
"loss": 1.1219,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.7357723577235772,
|
| 1274 |
+
"grad_norm": 0.14749093353748322,
|
| 1275 |
+
"learning_rate": 2.682926829268293e-06,
|
| 1276 |
+
"loss": 1.1156,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7398373983739838,
|
| 1281 |
+
"grad_norm": 0.1486608237028122,
|
| 1282 |
+
"learning_rate": 2.6422764227642278e-06,
|
| 1283 |
+
"loss": 1.1273,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7439024390243902,
|
| 1288 |
+
"grad_norm": 0.1560998260974884,
|
| 1289 |
+
"learning_rate": 2.601626016260163e-06,
|
| 1290 |
+
"loss": 1.1316,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7479674796747967,
|
| 1295 |
+
"grad_norm": 0.27837422490119934,
|
| 1296 |
+
"learning_rate": 2.5609756097560977e-06,
|
| 1297 |
+
"loss": 1.1488,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7520325203252033,
|
| 1302 |
+
"grad_norm": 0.15026023983955383,
|
| 1303 |
+
"learning_rate": 2.5203252032520324e-06,
|
| 1304 |
+
"loss": 1.1695,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7560975609756098,
|
| 1309 |
+
"grad_norm": 0.1622571498155594,
|
| 1310 |
+
"learning_rate": 2.4796747967479676e-06,
|
| 1311 |
+
"loss": 1.2141,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7601626016260162,
|
| 1316 |
+
"grad_norm": 0.14364777505397797,
|
| 1317 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 1318 |
+
"loss": 1.1094,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7642276422764228,
|
| 1323 |
+
"grad_norm": 0.16454081237316132,
|
| 1324 |
+
"learning_rate": 2.3983739837398375e-06,
|
| 1325 |
+
"loss": 1.1308,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7682926829268293,
|
| 1330 |
+
"grad_norm": 0.14899757504463196,
|
| 1331 |
+
"learning_rate": 2.3577235772357727e-06,
|
| 1332 |
+
"loss": 1.143,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7723577235772358,
|
| 1337 |
+
"grad_norm": 0.14920292794704437,
|
| 1338 |
+
"learning_rate": 2.317073170731708e-06,
|
| 1339 |
+
"loss": 1.1597,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7764227642276422,
|
| 1344 |
+
"grad_norm": 0.15899574756622314,
|
| 1345 |
+
"learning_rate": 2.2764227642276426e-06,
|
| 1346 |
+
"loss": 1.1513,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7804878048780488,
|
| 1351 |
+
"grad_norm": 0.14869162440299988,
|
| 1352 |
+
"learning_rate": 2.2357723577235773e-06,
|
| 1353 |
+
"loss": 1.1326,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7845528455284553,
|
| 1358 |
+
"grad_norm": 0.16438134014606476,
|
| 1359 |
+
"learning_rate": 2.1951219512195125e-06,
|
| 1360 |
+
"loss": 1.1394,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.7886178861788617,
|
| 1365 |
+
"grad_norm": 0.14691002666950226,
|
| 1366 |
+
"learning_rate": 2.154471544715447e-06,
|
| 1367 |
+
"loss": 1.1069,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7926829268292683,
|
| 1372 |
+
"grad_norm": 0.1594485491514206,
|
| 1373 |
+
"learning_rate": 2.1138211382113824e-06,
|
| 1374 |
+
"loss": 1.1613,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7967479674796748,
|
| 1379 |
+
"grad_norm": 0.15907639265060425,
|
| 1380 |
+
"learning_rate": 2.073170731707317e-06,
|
| 1381 |
+
"loss": 1.129,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.8008130081300813,
|
| 1386 |
+
"grad_norm": 0.16430595517158508,
|
| 1387 |
+
"learning_rate": 2.0325203252032523e-06,
|
| 1388 |
+
"loss": 1.1479,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.8048780487804879,
|
| 1393 |
+
"grad_norm": 0.14952394366264343,
|
| 1394 |
+
"learning_rate": 1.991869918699187e-06,
|
| 1395 |
+
"loss": 1.1419,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.8089430894308943,
|
| 1400 |
+
"grad_norm": 0.16877399384975433,
|
| 1401 |
+
"learning_rate": 1.951219512195122e-06,
|
| 1402 |
+
"loss": 1.1632,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.8130081300813008,
|
| 1407 |
+
"grad_norm": 0.15305615961551666,
|
| 1408 |
+
"learning_rate": 1.9105691056910574e-06,
|
| 1409 |
+
"loss": 1.1035,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.8170731707317073,
|
| 1414 |
+
"grad_norm": 0.15920433402061462,
|
| 1415 |
+
"learning_rate": 1.8699186991869919e-06,
|
| 1416 |
+
"loss": 1.1133,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.8211382113821138,
|
| 1421 |
+
"grad_norm": 0.1496686041355133,
|
| 1422 |
+
"learning_rate": 1.8292682926829268e-06,
|
| 1423 |
+
"loss": 1.1317,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.8252032520325203,
|
| 1428 |
+
"grad_norm": 0.16935904324054718,
|
| 1429 |
+
"learning_rate": 1.788617886178862e-06,
|
| 1430 |
+
"loss": 1.1223,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.8292682926829268,
|
| 1435 |
+
"grad_norm": 0.15048307180404663,
|
| 1436 |
+
"learning_rate": 1.747967479674797e-06,
|
| 1437 |
+
"loss": 1.1048,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.8333333333333334,
|
| 1442 |
+
"grad_norm": 0.1464565545320511,
|
| 1443 |
+
"learning_rate": 1.707317073170732e-06,
|
| 1444 |
+
"loss": 1.1099,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.8373983739837398,
|
| 1449 |
+
"grad_norm": 0.1460927128791809,
|
| 1450 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 1451 |
+
"loss": 1.0934,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.8414634146341463,
|
| 1456 |
+
"grad_norm": 0.15281639993190765,
|
| 1457 |
+
"learning_rate": 1.6260162601626018e-06,
|
| 1458 |
+
"loss": 1.1199,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8455284552845529,
|
| 1463 |
+
"grad_norm": 0.2008025050163269,
|
| 1464 |
+
"learning_rate": 1.5853658536585368e-06,
|
| 1465 |
+
"loss": 1.2044,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8495934959349594,
|
| 1470 |
+
"grad_norm": 0.15971218049526215,
|
| 1471 |
+
"learning_rate": 1.5447154471544717e-06,
|
| 1472 |
+
"loss": 1.15,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8536585365853658,
|
| 1477 |
+
"grad_norm": 0.1761285811662674,
|
| 1478 |
+
"learning_rate": 1.5040650406504067e-06,
|
| 1479 |
+
"loss": 1.1328,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8577235772357723,
|
| 1484 |
+
"grad_norm": 0.16200976073741913,
|
| 1485 |
+
"learning_rate": 1.4634146341463414e-06,
|
| 1486 |
+
"loss": 1.1091,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.8617886178861789,
|
| 1491 |
+
"grad_norm": 0.15674898028373718,
|
| 1492 |
+
"learning_rate": 1.4227642276422766e-06,
|
| 1493 |
+
"loss": 1.125,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8658536585365854,
|
| 1498 |
+
"grad_norm": 0.15859454870224,
|
| 1499 |
+
"learning_rate": 1.3821138211382116e-06,
|
| 1500 |
+
"loss": 1.1583,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8699186991869918,
|
| 1505 |
+
"grad_norm": 0.15535226464271545,
|
| 1506 |
+
"learning_rate": 1.3414634146341465e-06,
|
| 1507 |
+
"loss": 1.0963,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8739837398373984,
|
| 1512 |
+
"grad_norm": 0.1512589156627655,
|
| 1513 |
+
"learning_rate": 1.3008130081300815e-06,
|
| 1514 |
+
"loss": 1.1534,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8780487804878049,
|
| 1519 |
+
"grad_norm": 0.1450413465499878,
|
| 1520 |
+
"learning_rate": 1.2601626016260162e-06,
|
| 1521 |
+
"loss": 1.1121,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8821138211382114,
|
| 1526 |
+
"grad_norm": 0.1688557267189026,
|
| 1527 |
+
"learning_rate": 1.2195121951219514e-06,
|
| 1528 |
+
"loss": 1.1493,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.8861788617886179,
|
| 1533 |
+
"grad_norm": 0.15116536617279053,
|
| 1534 |
+
"learning_rate": 1.1788617886178863e-06,
|
| 1535 |
+
"loss": 1.1484,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.8902439024390244,
|
| 1540 |
+
"grad_norm": 0.16531287133693695,
|
| 1541 |
+
"learning_rate": 1.1382113821138213e-06,
|
| 1542 |
+
"loss": 1.1693,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.8943089430894309,
|
| 1547 |
+
"grad_norm": 0.15921427309513092,
|
| 1548 |
+
"learning_rate": 1.0975609756097562e-06,
|
| 1549 |
+
"loss": 1.1083,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.8983739837398373,
|
| 1554 |
+
"grad_norm": 0.17713923752307892,
|
| 1555 |
+
"learning_rate": 1.0569105691056912e-06,
|
| 1556 |
+
"loss": 1.1362,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.9024390243902439,
|
| 1561 |
+
"grad_norm": 0.1571284383535385,
|
| 1562 |
+
"learning_rate": 1.0162601626016261e-06,
|
| 1563 |
+
"loss": 1.1253,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.9065040650406504,
|
| 1568 |
+
"grad_norm": 0.14652420580387115,
|
| 1569 |
+
"learning_rate": 9.75609756097561e-07,
|
| 1570 |
+
"loss": 1.1311,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.9105691056910569,
|
| 1575 |
+
"grad_norm": 0.15918847918510437,
|
| 1576 |
+
"learning_rate": 9.349593495934959e-07,
|
| 1577 |
+
"loss": 1.1378,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.9146341463414634,
|
| 1582 |
+
"grad_norm": 0.16262595355510712,
|
| 1583 |
+
"learning_rate": 8.94308943089431e-07,
|
| 1584 |
+
"loss": 1.1348,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.9186991869918699,
|
| 1589 |
+
"grad_norm": 0.1511622965335846,
|
| 1590 |
+
"learning_rate": 8.53658536585366e-07,
|
| 1591 |
+
"loss": 1.1396,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.9227642276422764,
|
| 1596 |
+
"grad_norm": 0.1463434100151062,
|
| 1597 |
+
"learning_rate": 8.130081300813009e-07,
|
| 1598 |
+
"loss": 1.1218,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.926829268292683,
|
| 1603 |
+
"grad_norm": 0.15269097685813904,
|
| 1604 |
+
"learning_rate": 7.723577235772359e-07,
|
| 1605 |
+
"loss": 1.1409,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.9308943089430894,
|
| 1610 |
+
"grad_norm": 0.14281761646270752,
|
| 1611 |
+
"learning_rate": 7.317073170731707e-07,
|
| 1612 |
+
"loss": 1.1259,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.9349593495934959,
|
| 1617 |
+
"grad_norm": 0.1497596651315689,
|
| 1618 |
+
"learning_rate": 6.910569105691058e-07,
|
| 1619 |
+
"loss": 1.1158,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.9390243902439024,
|
| 1624 |
+
"grad_norm": 0.14198538661003113,
|
| 1625 |
+
"learning_rate": 6.504065040650407e-07,
|
| 1626 |
+
"loss": 1.1221,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.943089430894309,
|
| 1631 |
+
"grad_norm": 0.1596405953168869,
|
| 1632 |
+
"learning_rate": 6.097560975609757e-07,
|
| 1633 |
+
"loss": 1.1569,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.9471544715447154,
|
| 1638 |
+
"grad_norm": 0.14457373321056366,
|
| 1639 |
+
"learning_rate": 5.691056910569106e-07,
|
| 1640 |
+
"loss": 1.1292,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9512195121951219,
|
| 1645 |
+
"grad_norm": 0.15270555019378662,
|
| 1646 |
+
"learning_rate": 5.284552845528456e-07,
|
| 1647 |
+
"loss": 1.0797,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9552845528455285,
|
| 1652 |
+
"grad_norm": 0.1524428278207779,
|
| 1653 |
+
"learning_rate": 4.878048780487805e-07,
|
| 1654 |
+
"loss": 1.1426,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.959349593495935,
|
| 1659 |
+
"grad_norm": 0.14316333830356598,
|
| 1660 |
+
"learning_rate": 4.471544715447155e-07,
|
| 1661 |
+
"loss": 1.1174,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9634146341463414,
|
| 1666 |
+
"grad_norm": 0.14907851815223694,
|
| 1667 |
+
"learning_rate": 4.0650406504065046e-07,
|
| 1668 |
+
"loss": 1.1392,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.967479674796748,
|
| 1673 |
+
"grad_norm": 0.162221759557724,
|
| 1674 |
+
"learning_rate": 3.6585365853658536e-07,
|
| 1675 |
+
"loss": 1.1253,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9715447154471545,
|
| 1680 |
+
"grad_norm": 0.1450115293264389,
|
| 1681 |
+
"learning_rate": 3.2520325203252037e-07,
|
| 1682 |
+
"loss": 1.1174,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.975609756097561,
|
| 1687 |
+
"grad_norm": 0.14495380222797394,
|
| 1688 |
+
"learning_rate": 2.845528455284553e-07,
|
| 1689 |
+
"loss": 1.0811,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.9796747967479674,
|
| 1694 |
+
"grad_norm": 0.170689195394516,
|
| 1695 |
+
"learning_rate": 2.439024390243903e-07,
|
| 1696 |
+
"loss": 1.1634,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.983739837398374,
|
| 1701 |
+
"grad_norm": 0.15047703683376312,
|
| 1702 |
+
"learning_rate": 2.0325203252032523e-07,
|
| 1703 |
+
"loss": 1.1165,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.9878048780487805,
|
| 1708 |
+
"grad_norm": 0.14652645587921143,
|
| 1709 |
+
"learning_rate": 1.6260162601626018e-07,
|
| 1710 |
+
"loss": 1.1168,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.991869918699187,
|
| 1715 |
+
"grad_norm": 0.1450301855802536,
|
| 1716 |
+
"learning_rate": 1.2195121951219514e-07,
|
| 1717 |
+
"loss": 1.1167,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.9959349593495935,
|
| 1722 |
+
"grad_norm": 0.16407828032970428,
|
| 1723 |
+
"learning_rate": 8.130081300813009e-08,
|
| 1724 |
+
"loss": 1.1345,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.0,
|
| 1729 |
+
"grad_norm": 0.14291557669639587,
|
| 1730 |
+
"learning_rate": 4.0650406504065046e-08,
|
| 1731 |
+
"loss": 1.0985,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
}
|
| 1734 |
+
],
|
| 1735 |
+
"logging_steps": 1.0,
|
| 1736 |
+
"max_steps": 246,
|
| 1737 |
+
"num_input_tokens_seen": 0,
|
| 1738 |
+
"num_train_epochs": 1,
|
| 1739 |
+
"save_steps": 0,
|
| 1740 |
+
"stateful_callbacks": {
|
| 1741 |
+
"TrainerControl": {
|
| 1742 |
+
"args": {
|
| 1743 |
+
"should_epoch_stop": false,
|
| 1744 |
+
"should_evaluate": false,
|
| 1745 |
+
"should_log": false,
|
| 1746 |
+
"should_save": true,
|
| 1747 |
+
"should_training_stop": true
|
| 1748 |
+
},
|
| 1749 |
+
"attributes": {}
|
| 1750 |
+
}
|
| 1751 |
+
},
|
| 1752 |
+
"total_flos": 3.6102723928798e+17,
|
| 1753 |
+
"train_batch_size": 1,
|
| 1754 |
+
"trial_name": null,
|
| 1755 |
+
"trial_params": null
|
| 1756 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|