Upload 12 files
Browse files- README.md +202 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +40 -0
- llm2vec_config.json +6 -0
- merges.txt +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +325 -0
- trainer_state.json +1701 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: Salesforce/codegen-350M-mono
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "CodeGenBiModel",
|
| 5 |
+
"parent_library": "llm2vec.models.codegen"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "Salesforce/codegen-350M-mono",
|
| 8 |
+
"bias": "none",
|
| 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": 32,
|
| 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": 16,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"qkv_proj",
|
| 27 |
+
"out_proj"
|
| 28 |
+
],
|
| 29 |
+
"task_type": null,
|
| 30 |
+
"use_dora": false,
|
| 31 |
+
"use_rslora": false
|
| 32 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92b709fcc94f0c05265a091c7a3738ef9c6176a5d45e74c528ed57c7f055f5d9
|
| 3 |
+
size 3941712
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
llm2vec_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pooling_mode": "mean",
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"doc_max_length": 400,
|
| 5 |
+
"skip_instruction": true
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"model_max_length": 2048,
|
| 321 |
+
"pad_token": "<|endoftext|>",
|
| 322 |
+
"return_token_type_ids": false,
|
| 323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
+
"unk_token": "<|endoftext|>"
|
| 325 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1701 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.471956224350206,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.022799817601459188,
|
| 13 |
+
"grad_norm": 2.5625,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 15 |
+
"loss": 4.9225,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.045599635202918376,
|
| 20 |
+
"grad_norm": 3.546875,
|
| 21 |
+
"learning_rate": 6.666666666666667e-05,
|
| 22 |
+
"loss": 2.1478,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06839945280437756,
|
| 27 |
+
"grad_norm": 1.8671875,
|
| 28 |
+
"learning_rate": 0.0001,
|
| 29 |
+
"loss": 0.6361,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09119927040583675,
|
| 34 |
+
"grad_norm": 1.46875,
|
| 35 |
+
"learning_rate": 0.00013333333333333334,
|
| 36 |
+
"loss": 0.467,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11399908800729594,
|
| 41 |
+
"grad_norm": 2.15625,
|
| 42 |
+
"learning_rate": 0.0001666666666666667,
|
| 43 |
+
"loss": 0.4381,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13679890560875513,
|
| 48 |
+
"grad_norm": 1.8203125,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.3365,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15959872321021432,
|
| 55 |
+
"grad_norm": 1.4765625,
|
| 56 |
+
"learning_rate": 0.00019988560970029743,
|
| 57 |
+
"loss": 0.3255,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1823985408116735,
|
| 62 |
+
"grad_norm": 1.40625,
|
| 63 |
+
"learning_rate": 0.00019977121940059484,
|
| 64 |
+
"loss": 0.2946,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2051983584131327,
|
| 69 |
+
"grad_norm": 1.1328125,
|
| 70 |
+
"learning_rate": 0.00019965682910089226,
|
| 71 |
+
"loss": 0.3023,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.22799817601459188,
|
| 76 |
+
"grad_norm": 1.1640625,
|
| 77 |
+
"learning_rate": 0.00019954243880118967,
|
| 78 |
+
"loss": 0.2708,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2507979936160511,
|
| 83 |
+
"grad_norm": 0.9921875,
|
| 84 |
+
"learning_rate": 0.0001994280485014871,
|
| 85 |
+
"loss": 0.3645,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27359781121751026,
|
| 90 |
+
"grad_norm": 0.82421875,
|
| 91 |
+
"learning_rate": 0.00019931365820178448,
|
| 92 |
+
"loss": 0.3072,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.29639762881896947,
|
| 97 |
+
"grad_norm": 1.2265625,
|
| 98 |
+
"learning_rate": 0.00019919926790208192,
|
| 99 |
+
"loss": 0.2891,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.31919744642042863,
|
| 104 |
+
"grad_norm": 2.015625,
|
| 105 |
+
"learning_rate": 0.00019908487760237934,
|
| 106 |
+
"loss": 0.2763,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.34199726402188785,
|
| 111 |
+
"grad_norm": 1.5078125,
|
| 112 |
+
"learning_rate": 0.00019897048730267673,
|
| 113 |
+
"loss": 0.2824,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.364797081623347,
|
| 118 |
+
"grad_norm": 1.4140625,
|
| 119 |
+
"learning_rate": 0.00019885609700297417,
|
| 120 |
+
"loss": 0.3007,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3875968992248062,
|
| 125 |
+
"grad_norm": 1.359375,
|
| 126 |
+
"learning_rate": 0.00019874170670327156,
|
| 127 |
+
"loss": 0.2955,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4103967168262654,
|
| 132 |
+
"grad_norm": 1.078125,
|
| 133 |
+
"learning_rate": 0.000198627316403569,
|
| 134 |
+
"loss": 0.2385,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4331965344277246,
|
| 139 |
+
"grad_norm": 0.97265625,
|
| 140 |
+
"learning_rate": 0.0001985129261038664,
|
| 141 |
+
"loss": 0.2461,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.45599635202918376,
|
| 146 |
+
"grad_norm": 1.421875,
|
| 147 |
+
"learning_rate": 0.0001983985358041638,
|
| 148 |
+
"loss": 0.2567,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.478796169630643,
|
| 153 |
+
"grad_norm": 1.25,
|
| 154 |
+
"learning_rate": 0.00019828414550446125,
|
| 155 |
+
"loss": 0.2189,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5015959872321022,
|
| 160 |
+
"grad_norm": 1.0703125,
|
| 161 |
+
"learning_rate": 0.00019816975520475864,
|
| 162 |
+
"loss": 0.272,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5243958048335613,
|
| 167 |
+
"grad_norm": 1.78125,
|
| 168 |
+
"learning_rate": 0.00019805536490505606,
|
| 169 |
+
"loss": 0.2615,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5471956224350205,
|
| 174 |
+
"grad_norm": 1.0859375,
|
| 175 |
+
"learning_rate": 0.00019794097460535347,
|
| 176 |
+
"loss": 0.2476,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5699954400364797,
|
| 181 |
+
"grad_norm": 1.328125,
|
| 182 |
+
"learning_rate": 0.0001978265843056509,
|
| 183 |
+
"loss": 0.2327,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5927952576379389,
|
| 188 |
+
"grad_norm": 1.1953125,
|
| 189 |
+
"learning_rate": 0.0001977121940059483,
|
| 190 |
+
"loss": 0.2664,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.615595075239398,
|
| 195 |
+
"grad_norm": 1.109375,
|
| 196 |
+
"learning_rate": 0.00019759780370624572,
|
| 197 |
+
"loss": 0.2266,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6383948928408573,
|
| 202 |
+
"grad_norm": 1.2265625,
|
| 203 |
+
"learning_rate": 0.00019748341340654314,
|
| 204 |
+
"loss": 0.2234,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6611947104423165,
|
| 209 |
+
"grad_norm": 1.1875,
|
| 210 |
+
"learning_rate": 0.00019736902310684055,
|
| 211 |
+
"loss": 0.2463,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6839945280437757,
|
| 216 |
+
"grad_norm": 1.265625,
|
| 217 |
+
"learning_rate": 0.00019725463280713797,
|
| 218 |
+
"loss": 0.2311,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7067943456452348,
|
| 223 |
+
"grad_norm": 1.09375,
|
| 224 |
+
"learning_rate": 0.00019714024250743536,
|
| 225 |
+
"loss": 0.2251,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.729594163246694,
|
| 230 |
+
"grad_norm": 1.046875,
|
| 231 |
+
"learning_rate": 0.0001970258522077328,
|
| 232 |
+
"loss": 0.2492,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7523939808481532,
|
| 237 |
+
"grad_norm": 1.3984375,
|
| 238 |
+
"learning_rate": 0.00019691146190803022,
|
| 239 |
+
"loss": 0.2554,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7751937984496124,
|
| 244 |
+
"grad_norm": 0.8125,
|
| 245 |
+
"learning_rate": 0.00019679707160832763,
|
| 246 |
+
"loss": 0.2384,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7979936160510716,
|
| 251 |
+
"grad_norm": 1.3125,
|
| 252 |
+
"learning_rate": 0.00019668268130862505,
|
| 253 |
+
"loss": 0.2583,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8207934336525308,
|
| 258 |
+
"grad_norm": 0.625,
|
| 259 |
+
"learning_rate": 0.00019656829100892244,
|
| 260 |
+
"loss": 0.2343,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.84359325125399,
|
| 265 |
+
"grad_norm": 1.0234375,
|
| 266 |
+
"learning_rate": 0.00019645390070921988,
|
| 267 |
+
"loss": 0.2193,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8663930688554492,
|
| 272 |
+
"grad_norm": 0.875,
|
| 273 |
+
"learning_rate": 0.00019633951040951727,
|
| 274 |
+
"loss": 0.2212,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8891928864569083,
|
| 279 |
+
"grad_norm": 1.578125,
|
| 280 |
+
"learning_rate": 0.00019622512010981468,
|
| 281 |
+
"loss": 0.2178,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9119927040583675,
|
| 286 |
+
"grad_norm": 0.8125,
|
| 287 |
+
"learning_rate": 0.00019611072981011213,
|
| 288 |
+
"loss": 0.2135,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9347925216598267,
|
| 293 |
+
"grad_norm": 0.92578125,
|
| 294 |
+
"learning_rate": 0.00019599633951040952,
|
| 295 |
+
"loss": 0.2522,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.957592339261286,
|
| 300 |
+
"grad_norm": 0.8828125,
|
| 301 |
+
"learning_rate": 0.00019588194921070696,
|
| 302 |
+
"loss": 0.2138,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9803921568627451,
|
| 307 |
+
"grad_norm": 1.3125,
|
| 308 |
+
"learning_rate": 0.00019576755891100435,
|
| 309 |
+
"loss": 0.2043,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.0031919744642044,
|
| 314 |
+
"grad_norm": 1.0546875,
|
| 315 |
+
"learning_rate": 0.00019565316861130177,
|
| 316 |
+
"loss": 0.1855,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.0259917920656634,
|
| 321 |
+
"grad_norm": 1.1796875,
|
| 322 |
+
"learning_rate": 0.00019553877831159918,
|
| 323 |
+
"loss": 0.2099,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.0487916096671226,
|
| 328 |
+
"grad_norm": 0.99609375,
|
| 329 |
+
"learning_rate": 0.0001954243880118966,
|
| 330 |
+
"loss": 0.2032,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0715914272685818,
|
| 335 |
+
"grad_norm": 0.91015625,
|
| 336 |
+
"learning_rate": 0.000195309997712194,
|
| 337 |
+
"loss": 0.1753,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.094391244870041,
|
| 342 |
+
"grad_norm": 1.359375,
|
| 343 |
+
"learning_rate": 0.00019519560741249143,
|
| 344 |
+
"loss": 0.1997,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.1171910624715002,
|
| 349 |
+
"grad_norm": 1.3203125,
|
| 350 |
+
"learning_rate": 0.00019508121711278885,
|
| 351 |
+
"loss": 0.2101,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.1399908800729595,
|
| 356 |
+
"grad_norm": 0.8046875,
|
| 357 |
+
"learning_rate": 0.00019496682681308626,
|
| 358 |
+
"loss": 0.1734,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.1627906976744187,
|
| 363 |
+
"grad_norm": 1.0078125,
|
| 364 |
+
"learning_rate": 0.00019485243651338368,
|
| 365 |
+
"loss": 0.1716,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.1855905152758779,
|
| 370 |
+
"grad_norm": 0.78515625,
|
| 371 |
+
"learning_rate": 0.0001947380462136811,
|
| 372 |
+
"loss": 0.1588,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.2083903328773369,
|
| 377 |
+
"grad_norm": 0.85546875,
|
| 378 |
+
"learning_rate": 0.0001946236559139785,
|
| 379 |
+
"loss": 0.166,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.231190150478796,
|
| 384 |
+
"grad_norm": 1.296875,
|
| 385 |
+
"learning_rate": 0.00019450926561427593,
|
| 386 |
+
"loss": 0.1514,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.2539899680802553,
|
| 391 |
+
"grad_norm": 1.3125,
|
| 392 |
+
"learning_rate": 0.00019439487531457334,
|
| 393 |
+
"loss": 0.2103,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.2767897856817145,
|
| 398 |
+
"grad_norm": 1.3984375,
|
| 399 |
+
"learning_rate": 0.00019428048501487076,
|
| 400 |
+
"loss": 0.185,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.2995896032831737,
|
| 405 |
+
"grad_norm": 1.1015625,
|
| 406 |
+
"learning_rate": 0.00019416609471516815,
|
| 407 |
+
"loss": 0.1498,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.322389420884633,
|
| 412 |
+
"grad_norm": 1.28125,
|
| 413 |
+
"learning_rate": 0.0001940517044154656,
|
| 414 |
+
"loss": 0.1706,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.3451892384860922,
|
| 419 |
+
"grad_norm": 1.515625,
|
| 420 |
+
"learning_rate": 0.00019393731411576298,
|
| 421 |
+
"loss": 0.1579,
|
| 422 |
+
"step": 2950
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.3679890560875512,
|
| 426 |
+
"grad_norm": 1.28125,
|
| 427 |
+
"learning_rate": 0.0001938229238160604,
|
| 428 |
+
"loss": 0.1777,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.3907888736890106,
|
| 433 |
+
"grad_norm": 0.734375,
|
| 434 |
+
"learning_rate": 0.00019370853351635784,
|
| 435 |
+
"loss": 0.168,
|
| 436 |
+
"step": 3050
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.4135886912904696,
|
| 440 |
+
"grad_norm": 0.5546875,
|
| 441 |
+
"learning_rate": 0.00019359414321665523,
|
| 442 |
+
"loss": 0.1325,
|
| 443 |
+
"step": 3100
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.4363885088919288,
|
| 447 |
+
"grad_norm": 0.4453125,
|
| 448 |
+
"learning_rate": 0.00019347975291695267,
|
| 449 |
+
"loss": 0.1483,
|
| 450 |
+
"step": 3150
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.459188326493388,
|
| 454 |
+
"grad_norm": 0.953125,
|
| 455 |
+
"learning_rate": 0.00019336536261725006,
|
| 456 |
+
"loss": 0.1424,
|
| 457 |
+
"step": 3200
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.4819881440948472,
|
| 461 |
+
"grad_norm": 1.03125,
|
| 462 |
+
"learning_rate": 0.00019325097231754748,
|
| 463 |
+
"loss": 0.1352,
|
| 464 |
+
"step": 3250
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.5047879616963065,
|
| 468 |
+
"grad_norm": 1.7421875,
|
| 469 |
+
"learning_rate": 0.0001931365820178449,
|
| 470 |
+
"loss": 0.1583,
|
| 471 |
+
"step": 3300
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.5275877792977655,
|
| 475 |
+
"grad_norm": 1.40625,
|
| 476 |
+
"learning_rate": 0.0001930221917181423,
|
| 477 |
+
"loss": 0.1496,
|
| 478 |
+
"step": 3350
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.550387596899225,
|
| 482 |
+
"grad_norm": 1.578125,
|
| 483 |
+
"learning_rate": 0.00019290780141843972,
|
| 484 |
+
"loss": 0.1551,
|
| 485 |
+
"step": 3400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.573187414500684,
|
| 489 |
+
"grad_norm": 0.59375,
|
| 490 |
+
"learning_rate": 0.00019279341111873714,
|
| 491 |
+
"loss": 0.1275,
|
| 492 |
+
"step": 3450
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.5959872321021433,
|
| 496 |
+
"grad_norm": 1.25,
|
| 497 |
+
"learning_rate": 0.00019267902081903456,
|
| 498 |
+
"loss": 0.1685,
|
| 499 |
+
"step": 3500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.6187870497036023,
|
| 503 |
+
"grad_norm": 1.171875,
|
| 504 |
+
"learning_rate": 0.00019256463051933197,
|
| 505 |
+
"loss": 0.1271,
|
| 506 |
+
"step": 3550
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.6415868673050615,
|
| 510 |
+
"grad_norm": 0.98828125,
|
| 511 |
+
"learning_rate": 0.0001924502402196294,
|
| 512 |
+
"loss": 0.1344,
|
| 513 |
+
"step": 3600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.6643866849065208,
|
| 517 |
+
"grad_norm": 0.72265625,
|
| 518 |
+
"learning_rate": 0.0001923358499199268,
|
| 519 |
+
"loss": 0.1516,
|
| 520 |
+
"step": 3650
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.68718650250798,
|
| 524 |
+
"grad_norm": 0.7109375,
|
| 525 |
+
"learning_rate": 0.00019222145962022422,
|
| 526 |
+
"loss": 0.1379,
|
| 527 |
+
"step": 3700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.7099863201094392,
|
| 531 |
+
"grad_norm": 0.37890625,
|
| 532 |
+
"learning_rate": 0.00019210706932052164,
|
| 533 |
+
"loss": 0.1396,
|
| 534 |
+
"step": 3750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.7327861377108982,
|
| 538 |
+
"grad_norm": 1.25,
|
| 539 |
+
"learning_rate": 0.00019199267902081902,
|
| 540 |
+
"loss": 0.1544,
|
| 541 |
+
"step": 3800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.7555859553123576,
|
| 545 |
+
"grad_norm": 1.390625,
|
| 546 |
+
"learning_rate": 0.00019187828872111647,
|
| 547 |
+
"loss": 0.1639,
|
| 548 |
+
"step": 3850
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.7783857729138166,
|
| 552 |
+
"grad_norm": 1.734375,
|
| 553 |
+
"learning_rate": 0.00019176389842141386,
|
| 554 |
+
"loss": 0.1473,
|
| 555 |
+
"step": 3900
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.8011855905152758,
|
| 559 |
+
"grad_norm": 0.9765625,
|
| 560 |
+
"learning_rate": 0.0001916495081217113,
|
| 561 |
+
"loss": 0.1606,
|
| 562 |
+
"step": 3950
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.823985408116735,
|
| 566 |
+
"grad_norm": 0.326171875,
|
| 567 |
+
"learning_rate": 0.00019153511782200872,
|
| 568 |
+
"loss": 0.155,
|
| 569 |
+
"step": 4000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.8467852257181943,
|
| 573 |
+
"grad_norm": 1.1171875,
|
| 574 |
+
"learning_rate": 0.0001914207275223061,
|
| 575 |
+
"loss": 0.1222,
|
| 576 |
+
"step": 4050
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.8695850433196535,
|
| 580 |
+
"grad_norm": 1.828125,
|
| 581 |
+
"learning_rate": 0.00019130633722260355,
|
| 582 |
+
"loss": 0.1476,
|
| 583 |
+
"step": 4100
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.8923848609211125,
|
| 587 |
+
"grad_norm": 0.67578125,
|
| 588 |
+
"learning_rate": 0.00019119194692290094,
|
| 589 |
+
"loss": 0.1358,
|
| 590 |
+
"step": 4150
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.915184678522572,
|
| 594 |
+
"grad_norm": 1.59375,
|
| 595 |
+
"learning_rate": 0.00019107755662319838,
|
| 596 |
+
"loss": 0.1439,
|
| 597 |
+
"step": 4200
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.937984496124031,
|
| 601 |
+
"grad_norm": 1.2109375,
|
| 602 |
+
"learning_rate": 0.00019096316632349577,
|
| 603 |
+
"loss": 0.1699,
|
| 604 |
+
"step": 4250
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.9607843137254903,
|
| 608 |
+
"grad_norm": 1.09375,
|
| 609 |
+
"learning_rate": 0.00019084877602379319,
|
| 610 |
+
"loss": 0.1364,
|
| 611 |
+
"step": 4300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.9835841313269493,
|
| 615 |
+
"grad_norm": 1.328125,
|
| 616 |
+
"learning_rate": 0.0001907343857240906,
|
| 617 |
+
"loss": 0.1242,
|
| 618 |
+
"step": 4350
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.0063839489284088,
|
| 622 |
+
"grad_norm": 1.6328125,
|
| 623 |
+
"learning_rate": 0.00019061999542438802,
|
| 624 |
+
"loss": 0.1146,
|
| 625 |
+
"step": 4400
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.0291837665298678,
|
| 629 |
+
"grad_norm": 0.9609375,
|
| 630 |
+
"learning_rate": 0.00019050560512468543,
|
| 631 |
+
"loss": 0.1327,
|
| 632 |
+
"step": 4450
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.0519835841313268,
|
| 636 |
+
"grad_norm": 1.0390625,
|
| 637 |
+
"learning_rate": 0.00019039121482498285,
|
| 638 |
+
"loss": 0.1278,
|
| 639 |
+
"step": 4500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.074783401732786,
|
| 643 |
+
"grad_norm": 1.484375,
|
| 644 |
+
"learning_rate": 0.00019027682452528027,
|
| 645 |
+
"loss": 0.1069,
|
| 646 |
+
"step": 4550
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.097583219334245,
|
| 650 |
+
"grad_norm": 1.3125,
|
| 651 |
+
"learning_rate": 0.00019016243422557768,
|
| 652 |
+
"loss": 0.1351,
|
| 653 |
+
"step": 4600
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.1203830369357046,
|
| 657 |
+
"grad_norm": 1.7421875,
|
| 658 |
+
"learning_rate": 0.0001900480439258751,
|
| 659 |
+
"loss": 0.1372,
|
| 660 |
+
"step": 4650
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.1431828545371636,
|
| 664 |
+
"grad_norm": 1.4140625,
|
| 665 |
+
"learning_rate": 0.0001899336536261725,
|
| 666 |
+
"loss": 0.1093,
|
| 667 |
+
"step": 4700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.165982672138623,
|
| 671 |
+
"grad_norm": 0.8046875,
|
| 672 |
+
"learning_rate": 0.00018981926332646993,
|
| 673 |
+
"loss": 0.1,
|
| 674 |
+
"step": 4750
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.188782489740082,
|
| 678 |
+
"grad_norm": 1.109375,
|
| 679 |
+
"learning_rate": 0.00018970487302676735,
|
| 680 |
+
"loss": 0.1016,
|
| 681 |
+
"step": 4800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.2115823073415415,
|
| 685 |
+
"grad_norm": 0.76953125,
|
| 686 |
+
"learning_rate": 0.00018959048272706473,
|
| 687 |
+
"loss": 0.0976,
|
| 688 |
+
"step": 4850
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.2343821249430005,
|
| 692 |
+
"grad_norm": 1.7734375,
|
| 693 |
+
"learning_rate": 0.00018947609242736218,
|
| 694 |
+
"loss": 0.1132,
|
| 695 |
+
"step": 4900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.2571819425444595,
|
| 699 |
+
"grad_norm": 1.0625,
|
| 700 |
+
"learning_rate": 0.00018936170212765957,
|
| 701 |
+
"loss": 0.1174,
|
| 702 |
+
"step": 4950
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.279981760145919,
|
| 706 |
+
"grad_norm": 1.59375,
|
| 707 |
+
"learning_rate": 0.000189247311827957,
|
| 708 |
+
"loss": 0.1191,
|
| 709 |
+
"step": 5000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.302781577747378,
|
| 713 |
+
"grad_norm": 0.7734375,
|
| 714 |
+
"learning_rate": 0.00018913292152825443,
|
| 715 |
+
"loss": 0.0933,
|
| 716 |
+
"step": 5050
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.3255813953488373,
|
| 720 |
+
"grad_norm": 1.3984375,
|
| 721 |
+
"learning_rate": 0.00018901853122855181,
|
| 722 |
+
"loss": 0.1065,
|
| 723 |
+
"step": 5100
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.3483812129502963,
|
| 727 |
+
"grad_norm": 0.8125,
|
| 728 |
+
"learning_rate": 0.00018890414092884926,
|
| 729 |
+
"loss": 0.0993,
|
| 730 |
+
"step": 5150
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.3711810305517558,
|
| 734 |
+
"grad_norm": 1.265625,
|
| 735 |
+
"learning_rate": 0.00018878975062914665,
|
| 736 |
+
"loss": 0.1179,
|
| 737 |
+
"step": 5200
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.3939808481532148,
|
| 741 |
+
"grad_norm": 0.8671875,
|
| 742 |
+
"learning_rate": 0.00018867536032944406,
|
| 743 |
+
"loss": 0.0982,
|
| 744 |
+
"step": 5250
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.4167806657546738,
|
| 748 |
+
"grad_norm": 1.203125,
|
| 749 |
+
"learning_rate": 0.00018856097002974148,
|
| 750 |
+
"loss": 0.0831,
|
| 751 |
+
"step": 5300
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.439580483356133,
|
| 755 |
+
"grad_norm": 0.9453125,
|
| 756 |
+
"learning_rate": 0.0001884465797300389,
|
| 757 |
+
"loss": 0.0943,
|
| 758 |
+
"step": 5350
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.462380300957592,
|
| 762 |
+
"grad_norm": 1.484375,
|
| 763 |
+
"learning_rate": 0.00018833218943033634,
|
| 764 |
+
"loss": 0.088,
|
| 765 |
+
"step": 5400
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.4851801185590516,
|
| 769 |
+
"grad_norm": 1.59375,
|
| 770 |
+
"learning_rate": 0.00018821779913063373,
|
| 771 |
+
"loss": 0.0952,
|
| 772 |
+
"step": 5450
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.5079799361605106,
|
| 776 |
+
"grad_norm": 1.7421875,
|
| 777 |
+
"learning_rate": 0.00018810340883093114,
|
| 778 |
+
"loss": 0.0952,
|
| 779 |
+
"step": 5500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.53077975376197,
|
| 783 |
+
"grad_norm": 0.76171875,
|
| 784 |
+
"learning_rate": 0.00018798901853122856,
|
| 785 |
+
"loss": 0.0901,
|
| 786 |
+
"step": 5550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.553579571363429,
|
| 790 |
+
"grad_norm": 0.58984375,
|
| 791 |
+
"learning_rate": 0.00018787462823152598,
|
| 792 |
+
"loss": 0.0989,
|
| 793 |
+
"step": 5600
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.576379388964888,
|
| 797 |
+
"grad_norm": 0.87890625,
|
| 798 |
+
"learning_rate": 0.0001877602379318234,
|
| 799 |
+
"loss": 0.0794,
|
| 800 |
+
"step": 5650
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.5991792065663475,
|
| 804 |
+
"grad_norm": 0.9921875,
|
| 805 |
+
"learning_rate": 0.0001876458476321208,
|
| 806 |
+
"loss": 0.1076,
|
| 807 |
+
"step": 5700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.621979024167807,
|
| 811 |
+
"grad_norm": 0.64453125,
|
| 812 |
+
"learning_rate": 0.00018753145733241822,
|
| 813 |
+
"loss": 0.0745,
|
| 814 |
+
"step": 5750
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.644778841769266,
|
| 818 |
+
"grad_norm": 0.6875,
|
| 819 |
+
"learning_rate": 0.00018741706703271564,
|
| 820 |
+
"loss": 0.0938,
|
| 821 |
+
"step": 5800
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.667578659370725,
|
| 825 |
+
"grad_norm": 0.478515625,
|
| 826 |
+
"learning_rate": 0.00018730267673301306,
|
| 827 |
+
"loss": 0.0888,
|
| 828 |
+
"step": 5850
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.6903784769721844,
|
| 832 |
+
"grad_norm": 0.98828125,
|
| 833 |
+
"learning_rate": 0.00018718828643331044,
|
| 834 |
+
"loss": 0.0836,
|
| 835 |
+
"step": 5900
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.7131782945736433,
|
| 839 |
+
"grad_norm": 0.53125,
|
| 840 |
+
"learning_rate": 0.0001870738961336079,
|
| 841 |
+
"loss": 0.0821,
|
| 842 |
+
"step": 5950
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.7359781121751023,
|
| 846 |
+
"grad_norm": 0.875,
|
| 847 |
+
"learning_rate": 0.0001869595058339053,
|
| 848 |
+
"loss": 0.1043,
|
| 849 |
+
"step": 6000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.7587779297765618,
|
| 853 |
+
"grad_norm": 0.32421875,
|
| 854 |
+
"learning_rate": 0.00018684511553420272,
|
| 855 |
+
"loss": 0.1005,
|
| 856 |
+
"step": 6050
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.781577747378021,
|
| 860 |
+
"grad_norm": 2.3125,
|
| 861 |
+
"learning_rate": 0.00018673072523450014,
|
| 862 |
+
"loss": 0.1028,
|
| 863 |
+
"step": 6100
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.80437756497948,
|
| 867 |
+
"grad_norm": 1.9453125,
|
| 868 |
+
"learning_rate": 0.00018661633493479752,
|
| 869 |
+
"loss": 0.1046,
|
| 870 |
+
"step": 6150
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.827177382580939,
|
| 874 |
+
"grad_norm": 0.875,
|
| 875 |
+
"learning_rate": 0.00018650194463509497,
|
| 876 |
+
"loss": 0.0964,
|
| 877 |
+
"step": 6200
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.8499772001823986,
|
| 881 |
+
"grad_norm": 1.421875,
|
| 882 |
+
"learning_rate": 0.00018638755433539236,
|
| 883 |
+
"loss": 0.0775,
|
| 884 |
+
"step": 6250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.8727770177838576,
|
| 888 |
+
"grad_norm": 0.75390625,
|
| 889 |
+
"learning_rate": 0.00018627316403568977,
|
| 890 |
+
"loss": 0.0963,
|
| 891 |
+
"step": 6300
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.895576835385317,
|
| 895 |
+
"grad_norm": 0.7421875,
|
| 896 |
+
"learning_rate": 0.0001861587737359872,
|
| 897 |
+
"loss": 0.0903,
|
| 898 |
+
"step": 6350
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.918376652986776,
|
| 902 |
+
"grad_norm": 1.078125,
|
| 903 |
+
"learning_rate": 0.0001860443834362846,
|
| 904 |
+
"loss": 0.0914,
|
| 905 |
+
"step": 6400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.9411764705882355,
|
| 909 |
+
"grad_norm": 1.2109375,
|
| 910 |
+
"learning_rate": 0.00018592999313658205,
|
| 911 |
+
"loss": 0.108,
|
| 912 |
+
"step": 6450
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.9639762881896945,
|
| 916 |
+
"grad_norm": 0.83203125,
|
| 917 |
+
"learning_rate": 0.00018581560283687944,
|
| 918 |
+
"loss": 0.0876,
|
| 919 |
+
"step": 6500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.9867761057911535,
|
| 923 |
+
"grad_norm": 0.73046875,
|
| 924 |
+
"learning_rate": 0.00018570121253717685,
|
| 925 |
+
"loss": 0.0834,
|
| 926 |
+
"step": 6550
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.009575923392613,
|
| 930 |
+
"grad_norm": 0.3828125,
|
| 931 |
+
"learning_rate": 0.00018558682223747427,
|
| 932 |
+
"loss": 0.0786,
|
| 933 |
+
"step": 6600
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.032375740994072,
|
| 937 |
+
"grad_norm": 1.2109375,
|
| 938 |
+
"learning_rate": 0.00018547243193777169,
|
| 939 |
+
"loss": 0.0803,
|
| 940 |
+
"step": 6650
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 3.0551755585955314,
|
| 944 |
+
"grad_norm": 1.59375,
|
| 945 |
+
"learning_rate": 0.0001853580416380691,
|
| 946 |
+
"loss": 0.0846,
|
| 947 |
+
"step": 6700
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.0779753761969904,
|
| 951 |
+
"grad_norm": 0.5234375,
|
| 952 |
+
"learning_rate": 0.00018524365133836652,
|
| 953 |
+
"loss": 0.0562,
|
| 954 |
+
"step": 6750
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.10077519379845,
|
| 958 |
+
"grad_norm": 1.9765625,
|
| 959 |
+
"learning_rate": 0.00018512926103866393,
|
| 960 |
+
"loss": 0.0934,
|
| 961 |
+
"step": 6800
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.123575011399909,
|
| 965 |
+
"grad_norm": 0.7578125,
|
| 966 |
+
"learning_rate": 0.00018501487073896135,
|
| 967 |
+
"loss": 0.0813,
|
| 968 |
+
"step": 6850
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.146374829001368,
|
| 972 |
+
"grad_norm": 1.171875,
|
| 973 |
+
"learning_rate": 0.00018490048043925877,
|
| 974 |
+
"loss": 0.0661,
|
| 975 |
+
"step": 6900
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.169174646602827,
|
| 979 |
+
"grad_norm": 0.5234375,
|
| 980 |
+
"learning_rate": 0.00018478609013955615,
|
| 981 |
+
"loss": 0.0589,
|
| 982 |
+
"step": 6950
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.191974464204286,
|
| 986 |
+
"grad_norm": 1.4609375,
|
| 987 |
+
"learning_rate": 0.0001846716998398536,
|
| 988 |
+
"loss": 0.0679,
|
| 989 |
+
"step": 7000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.2147742818057456,
|
| 993 |
+
"grad_norm": 1.515625,
|
| 994 |
+
"learning_rate": 0.000184557309540151,
|
| 995 |
+
"loss": 0.0564,
|
| 996 |
+
"step": 7050
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.2375740994072046,
|
| 1000 |
+
"grad_norm": 1.4453125,
|
| 1001 |
+
"learning_rate": 0.0001844429192404484,
|
| 1002 |
+
"loss": 0.0763,
|
| 1003 |
+
"step": 7100
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.260373917008664,
|
| 1007 |
+
"grad_norm": 1.953125,
|
| 1008 |
+
"learning_rate": 0.00018432852894074585,
|
| 1009 |
+
"loss": 0.0768,
|
| 1010 |
+
"step": 7150
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.283173734610123,
|
| 1014 |
+
"grad_norm": 0.56640625,
|
| 1015 |
+
"learning_rate": 0.00018421413864104323,
|
| 1016 |
+
"loss": 0.0686,
|
| 1017 |
+
"step": 7200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.305973552211582,
|
| 1021 |
+
"grad_norm": 1.0703125,
|
| 1022 |
+
"learning_rate": 0.00018409974834134068,
|
| 1023 |
+
"loss": 0.0638,
|
| 1024 |
+
"step": 7250
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.3287733698130415,
|
| 1028 |
+
"grad_norm": 0.275390625,
|
| 1029 |
+
"learning_rate": 0.00018398535804163807,
|
| 1030 |
+
"loss": 0.0643,
|
| 1031 |
+
"step": 7300
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.3515731874145005,
|
| 1035 |
+
"grad_norm": 0.8984375,
|
| 1036 |
+
"learning_rate": 0.00018387096774193548,
|
| 1037 |
+
"loss": 0.067,
|
| 1038 |
+
"step": 7350
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.37437300501596,
|
| 1042 |
+
"grad_norm": 1.28125,
|
| 1043 |
+
"learning_rate": 0.00018375657744223293,
|
| 1044 |
+
"loss": 0.0756,
|
| 1045 |
+
"step": 7400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.397172822617419,
|
| 1049 |
+
"grad_norm": 1.1640625,
|
| 1050 |
+
"learning_rate": 0.00018364218714253031,
|
| 1051 |
+
"loss": 0.0579,
|
| 1052 |
+
"step": 7450
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.4199726402188784,
|
| 1056 |
+
"grad_norm": 0.62890625,
|
| 1057 |
+
"learning_rate": 0.00018352779684282773,
|
| 1058 |
+
"loss": 0.0533,
|
| 1059 |
+
"step": 7500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.4427724578203374,
|
| 1063 |
+
"grad_norm": 0.62890625,
|
| 1064 |
+
"learning_rate": 0.00018341340654312515,
|
| 1065 |
+
"loss": 0.0569,
|
| 1066 |
+
"step": 7550
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.465572275421797,
|
| 1070 |
+
"grad_norm": 1.328125,
|
| 1071 |
+
"learning_rate": 0.00018329901624342256,
|
| 1072 |
+
"loss": 0.0593,
|
| 1073 |
+
"step": 7600
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.488372093023256,
|
| 1077 |
+
"grad_norm": 1.859375,
|
| 1078 |
+
"learning_rate": 0.00018318462594371998,
|
| 1079 |
+
"loss": 0.0664,
|
| 1080 |
+
"step": 7650
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.5111719106247152,
|
| 1084 |
+
"grad_norm": 1.109375,
|
| 1085 |
+
"learning_rate": 0.0001830702356440174,
|
| 1086 |
+
"loss": 0.0593,
|
| 1087 |
+
"step": 7700
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.5339717282261742,
|
| 1091 |
+
"grad_norm": 0.6640625,
|
| 1092 |
+
"learning_rate": 0.0001829558453443148,
|
| 1093 |
+
"loss": 0.063,
|
| 1094 |
+
"step": 7750
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.556771545827633,
|
| 1098 |
+
"grad_norm": 0.2333984375,
|
| 1099 |
+
"learning_rate": 0.00018284145504461223,
|
| 1100 |
+
"loss": 0.0553,
|
| 1101 |
+
"step": 7800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.5795713634290927,
|
| 1105 |
+
"grad_norm": 0.60546875,
|
| 1106 |
+
"learning_rate": 0.00018272706474490964,
|
| 1107 |
+
"loss": 0.0513,
|
| 1108 |
+
"step": 7850
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.6023711810305517,
|
| 1112 |
+
"grad_norm": 0.421875,
|
| 1113 |
+
"learning_rate": 0.00018261267444520706,
|
| 1114 |
+
"loss": 0.0678,
|
| 1115 |
+
"step": 7900
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.625170998632011,
|
| 1119 |
+
"grad_norm": 0.87890625,
|
| 1120 |
+
"learning_rate": 0.00018249828414550448,
|
| 1121 |
+
"loss": 0.0446,
|
| 1122 |
+
"step": 7950
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.64797081623347,
|
| 1126 |
+
"grad_norm": 0.6640625,
|
| 1127 |
+
"learning_rate": 0.0001823838938458019,
|
| 1128 |
+
"loss": 0.0588,
|
| 1129 |
+
"step": 8000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.6707706338349295,
|
| 1133 |
+
"grad_norm": 0.2734375,
|
| 1134 |
+
"learning_rate": 0.0001822695035460993,
|
| 1135 |
+
"loss": 0.0564,
|
| 1136 |
+
"step": 8050
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.6935704514363885,
|
| 1140 |
+
"grad_norm": 0.294921875,
|
| 1141 |
+
"learning_rate": 0.00018215511324639672,
|
| 1142 |
+
"loss": 0.0526,
|
| 1143 |
+
"step": 8100
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.7163702690378475,
|
| 1147 |
+
"grad_norm": 1.765625,
|
| 1148 |
+
"learning_rate": 0.0001820407229466941,
|
| 1149 |
+
"loss": 0.0609,
|
| 1150 |
+
"step": 8150
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.739170086639307,
|
| 1154 |
+
"grad_norm": 0.76953125,
|
| 1155 |
+
"learning_rate": 0.00018192633264699156,
|
| 1156 |
+
"loss": 0.0679,
|
| 1157 |
+
"step": 8200
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.761969904240766,
|
| 1161 |
+
"grad_norm": 0.48828125,
|
| 1162 |
+
"learning_rate": 0.00018181194234728894,
|
| 1163 |
+
"loss": 0.0638,
|
| 1164 |
+
"step": 8250
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.7847697218422254,
|
| 1168 |
+
"grad_norm": 0.9765625,
|
| 1169 |
+
"learning_rate": 0.0001816975520475864,
|
| 1170 |
+
"loss": 0.0647,
|
| 1171 |
+
"step": 8300
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.8075695394436844,
|
| 1175 |
+
"grad_norm": 0.84375,
|
| 1176 |
+
"learning_rate": 0.00018158316174788378,
|
| 1177 |
+
"loss": 0.0747,
|
| 1178 |
+
"step": 8350
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.830369357045144,
|
| 1182 |
+
"grad_norm": 0.53515625,
|
| 1183 |
+
"learning_rate": 0.0001814687714481812,
|
| 1184 |
+
"loss": 0.0586,
|
| 1185 |
+
"step": 8400
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.853169174646603,
|
| 1189 |
+
"grad_norm": 1.3828125,
|
| 1190 |
+
"learning_rate": 0.00018135438114847864,
|
| 1191 |
+
"loss": 0.0544,
|
| 1192 |
+
"step": 8450
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.875968992248062,
|
| 1196 |
+
"grad_norm": 1.1640625,
|
| 1197 |
+
"learning_rate": 0.00018123999084877602,
|
| 1198 |
+
"loss": 0.0644,
|
| 1199 |
+
"step": 8500
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.8987688098495212,
|
| 1203 |
+
"grad_norm": 0.94140625,
|
| 1204 |
+
"learning_rate": 0.00018112560054907344,
|
| 1205 |
+
"loss": 0.0559,
|
| 1206 |
+
"step": 8550
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.9215686274509802,
|
| 1210 |
+
"grad_norm": 0.72265625,
|
| 1211 |
+
"learning_rate": 0.00018101121024937086,
|
| 1212 |
+
"loss": 0.0608,
|
| 1213 |
+
"step": 8600
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.9443684450524397,
|
| 1217 |
+
"grad_norm": 1.578125,
|
| 1218 |
+
"learning_rate": 0.00018089681994966827,
|
| 1219 |
+
"loss": 0.0688,
|
| 1220 |
+
"step": 8650
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.9671682626538987,
|
| 1224 |
+
"grad_norm": 1.046875,
|
| 1225 |
+
"learning_rate": 0.0001807824296499657,
|
| 1226 |
+
"loss": 0.0614,
|
| 1227 |
+
"step": 8700
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.989968080255358,
|
| 1231 |
+
"grad_norm": 0.79296875,
|
| 1232 |
+
"learning_rate": 0.0001806680393502631,
|
| 1233 |
+
"loss": 0.0515,
|
| 1234 |
+
"step": 8750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 4.0127678978568175,
|
| 1238 |
+
"grad_norm": 1.046875,
|
| 1239 |
+
"learning_rate": 0.00018055364905056052,
|
| 1240 |
+
"loss": 0.0527,
|
| 1241 |
+
"step": 8800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.035567715458276,
|
| 1245 |
+
"grad_norm": 0.8515625,
|
| 1246 |
+
"learning_rate": 0.00018043925875085794,
|
| 1247 |
+
"loss": 0.0567,
|
| 1248 |
+
"step": 8850
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.0583675330597355,
|
| 1252 |
+
"grad_norm": 0.92578125,
|
| 1253 |
+
"learning_rate": 0.00018032486845115535,
|
| 1254 |
+
"loss": 0.0501,
|
| 1255 |
+
"step": 8900
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 4.081167350661195,
|
| 1259 |
+
"grad_norm": 1.109375,
|
| 1260 |
+
"learning_rate": 0.00018021047815145274,
|
| 1261 |
+
"loss": 0.0329,
|
| 1262 |
+
"step": 8950
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.1039671682626535,
|
| 1266 |
+
"grad_norm": 1.453125,
|
| 1267 |
+
"learning_rate": 0.00018009608785175019,
|
| 1268 |
+
"loss": 0.0615,
|
| 1269 |
+
"step": 9000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 4.126766985864113,
|
| 1273 |
+
"grad_norm": 0.32421875,
|
| 1274 |
+
"learning_rate": 0.0001799816975520476,
|
| 1275 |
+
"loss": 0.0471,
|
| 1276 |
+
"step": 9050
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 4.149566803465572,
|
| 1280 |
+
"grad_norm": 0.63671875,
|
| 1281 |
+
"learning_rate": 0.00017986730725234502,
|
| 1282 |
+
"loss": 0.0467,
|
| 1283 |
+
"step": 9100
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 4.172366621067032,
|
| 1287 |
+
"grad_norm": 0.462890625,
|
| 1288 |
+
"learning_rate": 0.00017975291695264243,
|
| 1289 |
+
"loss": 0.0381,
|
| 1290 |
+
"step": 9150
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.19516643866849,
|
| 1294 |
+
"grad_norm": 1.2890625,
|
| 1295 |
+
"learning_rate": 0.00017963852665293982,
|
| 1296 |
+
"loss": 0.0414,
|
| 1297 |
+
"step": 9200
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.21796625626995,
|
| 1301 |
+
"grad_norm": 0.66015625,
|
| 1302 |
+
"learning_rate": 0.00017952413635323727,
|
| 1303 |
+
"loss": 0.0412,
|
| 1304 |
+
"step": 9250
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.240766073871409,
|
| 1308 |
+
"grad_norm": 0.96875,
|
| 1309 |
+
"learning_rate": 0.00017940974605353465,
|
| 1310 |
+
"loss": 0.0492,
|
| 1311 |
+
"step": 9300
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 4.263565891472869,
|
| 1315 |
+
"grad_norm": 0.5703125,
|
| 1316 |
+
"learning_rate": 0.00017929535575383207,
|
| 1317 |
+
"loss": 0.0526,
|
| 1318 |
+
"step": 9350
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.286365709074327,
|
| 1322 |
+
"grad_norm": 0.51953125,
|
| 1323 |
+
"learning_rate": 0.0001791809654541295,
|
| 1324 |
+
"loss": 0.0403,
|
| 1325 |
+
"step": 9400
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.309165526675787,
|
| 1329 |
+
"grad_norm": 0.984375,
|
| 1330 |
+
"learning_rate": 0.0001790665751544269,
|
| 1331 |
+
"loss": 0.0415,
|
| 1332 |
+
"step": 9450
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.331965344277246,
|
| 1336 |
+
"grad_norm": 0.7734375,
|
| 1337 |
+
"learning_rate": 0.00017895218485472435,
|
| 1338 |
+
"loss": 0.04,
|
| 1339 |
+
"step": 9500
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.354765161878705,
|
| 1343 |
+
"grad_norm": 0.349609375,
|
| 1344 |
+
"learning_rate": 0.00017883779455502173,
|
| 1345 |
+
"loss": 0.0461,
|
| 1346 |
+
"step": 9550
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.377564979480164,
|
| 1350 |
+
"grad_norm": 0.7890625,
|
| 1351 |
+
"learning_rate": 0.00017872340425531915,
|
| 1352 |
+
"loss": 0.0499,
|
| 1353 |
+
"step": 9600
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.4003647970816235,
|
| 1357 |
+
"grad_norm": 0.416015625,
|
| 1358 |
+
"learning_rate": 0.00017860901395561657,
|
| 1359 |
+
"loss": 0.038,
|
| 1360 |
+
"step": 9650
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.423164614683083,
|
| 1364 |
+
"grad_norm": 0.84765625,
|
| 1365 |
+
"learning_rate": 0.00017849462365591398,
|
| 1366 |
+
"loss": 0.0383,
|
| 1367 |
+
"step": 9700
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 4.4459644322845415,
|
| 1371 |
+
"grad_norm": 0.9765625,
|
| 1372 |
+
"learning_rate": 0.00017838023335621143,
|
| 1373 |
+
"loss": 0.0385,
|
| 1374 |
+
"step": 9750
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.468764249886001,
|
| 1378 |
+
"grad_norm": 0.482421875,
|
| 1379 |
+
"learning_rate": 0.00017826584305650881,
|
| 1380 |
+
"loss": 0.0361,
|
| 1381 |
+
"step": 9800
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.49156406748746,
|
| 1385 |
+
"grad_norm": 0.73046875,
|
| 1386 |
+
"learning_rate": 0.00017815145275680623,
|
| 1387 |
+
"loss": 0.0485,
|
| 1388 |
+
"step": 9850
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 4.514363885088919,
|
| 1392 |
+
"grad_norm": 2.125,
|
| 1393 |
+
"learning_rate": 0.00017803706245710365,
|
| 1394 |
+
"loss": 0.0372,
|
| 1395 |
+
"step": 9900
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.537163702690378,
|
| 1399 |
+
"grad_norm": 0.451171875,
|
| 1400 |
+
"learning_rate": 0.00017792267215740106,
|
| 1401 |
+
"loss": 0.0433,
|
| 1402 |
+
"step": 9950
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.559963520291838,
|
| 1406 |
+
"grad_norm": 0.63671875,
|
| 1407 |
+
"learning_rate": 0.00017780828185769848,
|
| 1408 |
+
"loss": 0.0337,
|
| 1409 |
+
"step": 10000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 4.582763337893297,
|
| 1413 |
+
"grad_norm": 1.375,
|
| 1414 |
+
"learning_rate": 0.0001776938915579959,
|
| 1415 |
+
"loss": 0.0392,
|
| 1416 |
+
"step": 10050
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 4.605563155494756,
|
| 1420 |
+
"grad_norm": 0.8359375,
|
| 1421 |
+
"learning_rate": 0.0001775795012582933,
|
| 1422 |
+
"loss": 0.0404,
|
| 1423 |
+
"step": 10100
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 4.628362973096215,
|
| 1427 |
+
"grad_norm": 0.65234375,
|
| 1428 |
+
"learning_rate": 0.00017746511095859073,
|
| 1429 |
+
"loss": 0.0312,
|
| 1430 |
+
"step": 10150
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 4.651162790697675,
|
| 1434 |
+
"grad_norm": 0.609375,
|
| 1435 |
+
"learning_rate": 0.00017735072065888814,
|
| 1436 |
+
"loss": 0.0398,
|
| 1437 |
+
"step": 10200
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 4.673962608299133,
|
| 1441 |
+
"grad_norm": 0.45703125,
|
| 1442 |
+
"learning_rate": 0.00017723633035918553,
|
| 1443 |
+
"loss": 0.0386,
|
| 1444 |
+
"step": 10250
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 4.696762425900593,
|
| 1448 |
+
"grad_norm": 0.3828125,
|
| 1449 |
+
"learning_rate": 0.00017712194005948298,
|
| 1450 |
+
"loss": 0.0343,
|
| 1451 |
+
"step": 10300
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 4.719562243502052,
|
| 1455 |
+
"grad_norm": 0.921875,
|
| 1456 |
+
"learning_rate": 0.0001770075497597804,
|
| 1457 |
+
"loss": 0.0472,
|
| 1458 |
+
"step": 10350
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 4.7423620611035116,
|
| 1462 |
+
"grad_norm": 0.8984375,
|
| 1463 |
+
"learning_rate": 0.00017689315946007778,
|
| 1464 |
+
"loss": 0.042,
|
| 1465 |
+
"step": 10400
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 4.76516187870497,
|
| 1469 |
+
"grad_norm": 1.78125,
|
| 1470 |
+
"learning_rate": 0.00017677876916037522,
|
| 1471 |
+
"loss": 0.0412,
|
| 1472 |
+
"step": 10450
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 4.7879616963064295,
|
| 1476 |
+
"grad_norm": 0.5234375,
|
| 1477 |
+
"learning_rate": 0.0001766643788606726,
|
| 1478 |
+
"loss": 0.0432,
|
| 1479 |
+
"step": 10500
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 4.810761513907889,
|
| 1483 |
+
"grad_norm": 0.2265625,
|
| 1484 |
+
"learning_rate": 0.00017654998856097006,
|
| 1485 |
+
"loss": 0.0525,
|
| 1486 |
+
"step": 10550
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 4.8335613315093475,
|
| 1490 |
+
"grad_norm": 0.89453125,
|
| 1491 |
+
"learning_rate": 0.00017643559826126744,
|
| 1492 |
+
"loss": 0.0395,
|
| 1493 |
+
"step": 10600
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 4.856361149110807,
|
| 1497 |
+
"grad_norm": 1.0859375,
|
| 1498 |
+
"learning_rate": 0.00017632120796156486,
|
| 1499 |
+
"loss": 0.0387,
|
| 1500 |
+
"step": 10650
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 4.879160966712266,
|
| 1504 |
+
"grad_norm": 0.8671875,
|
| 1505 |
+
"learning_rate": 0.00017620681766186228,
|
| 1506 |
+
"loss": 0.041,
|
| 1507 |
+
"step": 10700
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 4.901960784313726,
|
| 1511 |
+
"grad_norm": 1.640625,
|
| 1512 |
+
"learning_rate": 0.0001760924273621597,
|
| 1513 |
+
"loss": 0.038,
|
| 1514 |
+
"step": 10750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 4.924760601915184,
|
| 1518 |
+
"grad_norm": 1.3125,
|
| 1519 |
+
"learning_rate": 0.0001759780370624571,
|
| 1520 |
+
"loss": 0.0448,
|
| 1521 |
+
"step": 10800
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.947560419516644,
|
| 1525 |
+
"grad_norm": 1.3046875,
|
| 1526 |
+
"learning_rate": 0.00017586364676275452,
|
| 1527 |
+
"loss": 0.0417,
|
| 1528 |
+
"step": 10850
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 4.970360237118103,
|
| 1532 |
+
"grad_norm": 0.423828125,
|
| 1533 |
+
"learning_rate": 0.00017574925646305194,
|
| 1534 |
+
"loss": 0.0393,
|
| 1535 |
+
"step": 10900
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 4.993160054719562,
|
| 1539 |
+
"grad_norm": 1.1171875,
|
| 1540 |
+
"learning_rate": 0.00017563486616334936,
|
| 1541 |
+
"loss": 0.0353,
|
| 1542 |
+
"step": 10950
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 5.015959872321021,
|
| 1546 |
+
"grad_norm": 0.421875,
|
| 1547 |
+
"learning_rate": 0.00017552047586364677,
|
| 1548 |
+
"loss": 0.0376,
|
| 1549 |
+
"step": 11000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 5.038759689922481,
|
| 1553 |
+
"grad_norm": 1.828125,
|
| 1554 |
+
"learning_rate": 0.0001754060855639442,
|
| 1555 |
+
"loss": 0.0388,
|
| 1556 |
+
"step": 11050
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 5.06155950752394,
|
| 1560 |
+
"grad_norm": 0.32421875,
|
| 1561 |
+
"learning_rate": 0.0001752916952642416,
|
| 1562 |
+
"loss": 0.0318,
|
| 1563 |
+
"step": 11100
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 5.084359325125399,
|
| 1567 |
+
"grad_norm": 1.0859375,
|
| 1568 |
+
"learning_rate": 0.00017517730496453902,
|
| 1569 |
+
"loss": 0.0251,
|
| 1570 |
+
"step": 11150
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 5.107159142726858,
|
| 1574 |
+
"grad_norm": 0.373046875,
|
| 1575 |
+
"learning_rate": 0.0001750629146648364,
|
| 1576 |
+
"loss": 0.0443,
|
| 1577 |
+
"step": 11200
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 5.1299589603283176,
|
| 1581 |
+
"grad_norm": 0.51171875,
|
| 1582 |
+
"learning_rate": 0.00017494852436513385,
|
| 1583 |
+
"loss": 0.0285,
|
| 1584 |
+
"step": 11250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 5.152758777929777,
|
| 1588 |
+
"grad_norm": 0.75,
|
| 1589 |
+
"learning_rate": 0.00017483413406543124,
|
| 1590 |
+
"loss": 0.0319,
|
| 1591 |
+
"step": 11300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 5.1755585955312355,
|
| 1595 |
+
"grad_norm": 0.375,
|
| 1596 |
+
"learning_rate": 0.00017471974376572869,
|
| 1597 |
+
"loss": 0.0292,
|
| 1598 |
+
"step": 11350
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 5.198358413132695,
|
| 1602 |
+
"grad_norm": 0.28515625,
|
| 1603 |
+
"learning_rate": 0.0001746053534660261,
|
| 1604 |
+
"loss": 0.0281,
|
| 1605 |
+
"step": 11400
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 5.221158230734154,
|
| 1609 |
+
"grad_norm": 0.361328125,
|
| 1610 |
+
"learning_rate": 0.0001744909631663235,
|
| 1611 |
+
"loss": 0.029,
|
| 1612 |
+
"step": 11450
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 5.243958048335613,
|
| 1616 |
+
"grad_norm": 0.265625,
|
| 1617 |
+
"learning_rate": 0.00017437657286662093,
|
| 1618 |
+
"loss": 0.0382,
|
| 1619 |
+
"step": 11500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 5.266757865937072,
|
| 1623 |
+
"grad_norm": 0.2177734375,
|
| 1624 |
+
"learning_rate": 0.00017426218256691832,
|
| 1625 |
+
"loss": 0.0328,
|
| 1626 |
+
"step": 11550
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 5.289557683538532,
|
| 1630 |
+
"grad_norm": 1.6015625,
|
| 1631 |
+
"learning_rate": 0.00017414779226721577,
|
| 1632 |
+
"loss": 0.03,
|
| 1633 |
+
"step": 11600
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 5.312357501139991,
|
| 1637 |
+
"grad_norm": 1.109375,
|
| 1638 |
+
"learning_rate": 0.00017403340196751315,
|
| 1639 |
+
"loss": 0.0251,
|
| 1640 |
+
"step": 11650
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 5.33515731874145,
|
| 1644 |
+
"grad_norm": 0.70703125,
|
| 1645 |
+
"learning_rate": 0.00017391901166781057,
|
| 1646 |
+
"loss": 0.0267,
|
| 1647 |
+
"step": 11700
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 5.357957136342909,
|
| 1651 |
+
"grad_norm": 0.6171875,
|
| 1652 |
+
"learning_rate": 0.000173804621368108,
|
| 1653 |
+
"loss": 0.0357,
|
| 1654 |
+
"step": 11750
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 5.380756953944369,
|
| 1658 |
+
"grad_norm": 1.6015625,
|
| 1659 |
+
"learning_rate": 0.0001736902310684054,
|
| 1660 |
+
"loss": 0.035,
|
| 1661 |
+
"step": 11800
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 5.403556771545827,
|
| 1665 |
+
"grad_norm": 0.5390625,
|
| 1666 |
+
"learning_rate": 0.00017357584076870282,
|
| 1667 |
+
"loss": 0.0235,
|
| 1668 |
+
"step": 11850
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 5.426356589147287,
|
| 1672 |
+
"grad_norm": 0.58984375,
|
| 1673 |
+
"learning_rate": 0.00017346145046900023,
|
| 1674 |
+
"loss": 0.0277,
|
| 1675 |
+
"step": 11900
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 5.449156406748746,
|
| 1679 |
+
"grad_norm": 0.78515625,
|
| 1680 |
+
"learning_rate": 0.00017334706016929765,
|
| 1681 |
+
"loss": 0.0294,
|
| 1682 |
+
"step": 11950
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 5.471956224350206,
|
| 1686 |
+
"grad_norm": 0.859375,
|
| 1687 |
+
"learning_rate": 0.00017323266986959507,
|
| 1688 |
+
"loss": 0.0245,
|
| 1689 |
+
"step": 12000
|
| 1690 |
+
}
|
| 1691 |
+
],
|
| 1692 |
+
"logging_steps": 50,
|
| 1693 |
+
"max_steps": 87720,
|
| 1694 |
+
"num_input_tokens_seen": 0,
|
| 1695 |
+
"num_train_epochs": 40,
|
| 1696 |
+
"save_steps": 200,
|
| 1697 |
+
"total_flos": 0.0,
|
| 1698 |
+
"train_batch_size": 128,
|
| 1699 |
+
"trial_name": null,
|
| 1700 |
+
"trial_params": null
|
| 1701 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80e666a165ed787f68e7fc7c360a7bd7a90e9c9f4cb849d4ea057d2d75b99e30
|
| 3 |
+
size 5240
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|