Upload folder using huggingface_hub
Browse files- README.md +208 -0
- adapter_config.json +50 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- trainer_state.json +1754 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/DeepSeek-OCR
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:./deepseek_ocr
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
- unsloth
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- 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. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
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).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.18.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "DeepseekOCRForCausalLM",
|
| 7 |
+
"parent_library": "transformers_modules.deepseek_ocr.modeling_deepseekocr",
|
| 8 |
+
"unsloth_fixed": true
|
| 9 |
+
},
|
| 10 |
+
"base_model_name_or_path": "unsloth/DeepSeek-OCR",
|
| 11 |
+
"bias": "none",
|
| 12 |
+
"corda_config": null,
|
| 13 |
+
"ensure_weight_tying": false,
|
| 14 |
+
"eva_config": null,
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": false,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": true,
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 16,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0.05,
|
| 26 |
+
"megatron_config": null,
|
| 27 |
+
"megatron_core": "megatron.core",
|
| 28 |
+
"modules_to_save": null,
|
| 29 |
+
"peft_type": "LORA",
|
| 30 |
+
"peft_version": "0.18.0",
|
| 31 |
+
"qalora_group_size": 16,
|
| 32 |
+
"r": 16,
|
| 33 |
+
"rank_pattern": {},
|
| 34 |
+
"revision": null,
|
| 35 |
+
"target_modules": [
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"down_proj",
|
| 40 |
+
"o_proj",
|
| 41 |
+
"k_proj",
|
| 42 |
+
"up_proj"
|
| 43 |
+
],
|
| 44 |
+
"target_parameters": null,
|
| 45 |
+
"task_type": "CAUSAL_LM",
|
| 46 |
+
"trainable_token_indices": null,
|
| 47 |
+
"use_dora": false,
|
| 48 |
+
"use_qalora": false,
|
| 49 |
+
"use_rslora": false
|
| 50 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8735a7e748c4dbd37bf0ba53cd50beb4c7fa5b399fe79c9f0cfa34247ad42fdf
|
| 3 |
+
size 310662536
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:000c9c28f96addd0d6da09158a5d8fdebf4b237f7161c75b28c5654c2cfa4e55
|
| 3 |
+
size 162452055
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ad25a511bee3332dbed17a70bf3df04eb9aefe047f2ca66f0b3a4e2f5c412ab
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:830f1d36edab13214ac6df2f6ab157c3d7d466ad075f3415bcdbe0e363c167d7
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|User|>",
|
| 4 |
+
"<|Assistant|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<｜▁pad▁｜>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
}
|
| 27 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1754 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1200,
|
| 3 |
+
"best_metric": 0.14440582692623138,
|
| 4 |
+
"best_model_checkpoint": "./outputs/checkpoint-1200",
|
| 5 |
+
"epoch": 0.9962640099626401,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 1200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004151100041511001,
|
| 14 |
+
"grad_norm": 0.7003103494644165,
|
| 15 |
+
"learning_rate": 0.00016,
|
| 16 |
+
"loss": 0.7739,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008302200083022002,
|
| 21 |
+
"grad_norm": 0.2718559503555298,
|
| 22 |
+
"learning_rate": 0.00019933333333333334,
|
| 23 |
+
"loss": 0.4629,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008302200083022002,
|
| 28 |
+
"eval_loss": 0.38488370180130005,
|
| 29 |
+
"eval_runtime": 191.3755,
|
| 30 |
+
"eval_samples_per_second": 4.703,
|
| 31 |
+
"eval_steps_per_second": 2.351,
|
| 32 |
+
"step": 10
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.012453300124533,
|
| 36 |
+
"grad_norm": 0.14381290972232819,
|
| 37 |
+
"learning_rate": 0.00019850000000000003,
|
| 38 |
+
"loss": 0.3145,
|
| 39 |
+
"step": 15
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.016604400166044003,
|
| 43 |
+
"grad_norm": 0.19169217348098755,
|
| 44 |
+
"learning_rate": 0.00019766666666666666,
|
| 45 |
+
"loss": 0.2939,
|
| 46 |
+
"step": 20
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.020755500207555,
|
| 50 |
+
"grad_norm": 0.14952002465724945,
|
| 51 |
+
"learning_rate": 0.00019683333333333334,
|
| 52 |
+
"loss": 0.2497,
|
| 53 |
+
"step": 25
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.024906600249066,
|
| 57 |
+
"grad_norm": 0.14751273393630981,
|
| 58 |
+
"learning_rate": 0.000196,
|
| 59 |
+
"loss": 0.232,
|
| 60 |
+
"step": 30
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.029057700290577002,
|
| 64 |
+
"grad_norm": 0.14557640254497528,
|
| 65 |
+
"learning_rate": 0.00019516666666666668,
|
| 66 |
+
"loss": 0.2456,
|
| 67 |
+
"step": 35
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.033208800332088007,
|
| 71 |
+
"grad_norm": 0.13989262282848358,
|
| 72 |
+
"learning_rate": 0.00019433333333333333,
|
| 73 |
+
"loss": 0.2252,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.037359900373599,
|
| 78 |
+
"grad_norm": 0.15823808312416077,
|
| 79 |
+
"learning_rate": 0.00019350000000000001,
|
| 80 |
+
"loss": 0.2263,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04151100041511,
|
| 85 |
+
"grad_norm": 0.14398093521595,
|
| 86 |
+
"learning_rate": 0.0001926666666666667,
|
| 87 |
+
"loss": 0.2162,
|
| 88 |
+
"step": 50
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.045662100456621,
|
| 92 |
+
"grad_norm": 0.12337611615657806,
|
| 93 |
+
"learning_rate": 0.00019183333333333333,
|
| 94 |
+
"loss": 0.2065,
|
| 95 |
+
"step": 55
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.049813200498132,
|
| 99 |
+
"grad_norm": 0.1576000601053238,
|
| 100 |
+
"learning_rate": 0.000191,
|
| 101 |
+
"loss": 0.2067,
|
| 102 |
+
"step": 60
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.053964300539643004,
|
| 106 |
+
"grad_norm": 0.13802748918533325,
|
| 107 |
+
"learning_rate": 0.00019016666666666666,
|
| 108 |
+
"loss": 0.2055,
|
| 109 |
+
"step": 65
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.058115400581154004,
|
| 113 |
+
"grad_norm": 0.12468370050191879,
|
| 114 |
+
"learning_rate": 0.00018933333333333335,
|
| 115 |
+
"loss": 0.1899,
|
| 116 |
+
"step": 70
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.062266500622665005,
|
| 120 |
+
"grad_norm": 0.13926441967487335,
|
| 121 |
+
"learning_rate": 0.0001885,
|
| 122 |
+
"loss": 0.2005,
|
| 123 |
+
"step": 75
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06641760066417601,
|
| 127 |
+
"grad_norm": 0.12755008041858673,
|
| 128 |
+
"learning_rate": 0.00018766666666666668,
|
| 129 |
+
"loss": 0.1843,
|
| 130 |
+
"step": 80
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.070568700705687,
|
| 134 |
+
"grad_norm": 0.11908452957868576,
|
| 135 |
+
"learning_rate": 0.00018683333333333334,
|
| 136 |
+
"loss": 0.195,
|
| 137 |
+
"step": 85
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.074719800747198,
|
| 141 |
+
"grad_norm": 0.10701552778482437,
|
| 142 |
+
"learning_rate": 0.00018600000000000002,
|
| 143 |
+
"loss": 0.1864,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.07887090078870901,
|
| 148 |
+
"grad_norm": 0.12250486761331558,
|
| 149 |
+
"learning_rate": 0.00018516666666666668,
|
| 150 |
+
"loss": 0.1953,
|
| 151 |
+
"step": 95
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.08302200083022,
|
| 155 |
+
"grad_norm": 0.14064641296863556,
|
| 156 |
+
"learning_rate": 0.00018433333333333333,
|
| 157 |
+
"loss": 0.1809,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.08717310087173101,
|
| 162 |
+
"grad_norm": 0.12372340261936188,
|
| 163 |
+
"learning_rate": 0.00018350000000000002,
|
| 164 |
+
"loss": 0.178,
|
| 165 |
+
"step": 105
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.091324200913242,
|
| 169 |
+
"grad_norm": 0.089394710958004,
|
| 170 |
+
"learning_rate": 0.00018266666666666667,
|
| 171 |
+
"loss": 0.1641,
|
| 172 |
+
"step": 110
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.09547530095475301,
|
| 176 |
+
"grad_norm": 0.11845199763774872,
|
| 177 |
+
"learning_rate": 0.00018183333333333335,
|
| 178 |
+
"loss": 0.1914,
|
| 179 |
+
"step": 115
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.099626400996264,
|
| 183 |
+
"grad_norm": 0.10505373775959015,
|
| 184 |
+
"learning_rate": 0.000181,
|
| 185 |
+
"loss": 0.2002,
|
| 186 |
+
"step": 120
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.10377750103777501,
|
| 190 |
+
"grad_norm": 0.11983006447553635,
|
| 191 |
+
"learning_rate": 0.0001801666666666667,
|
| 192 |
+
"loss": 0.178,
|
| 193 |
+
"step": 125
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.10792860107928601,
|
| 197 |
+
"grad_norm": 0.14301978051662445,
|
| 198 |
+
"learning_rate": 0.00017933333333333332,
|
| 199 |
+
"loss": 0.1838,
|
| 200 |
+
"step": 130
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.11207970112079702,
|
| 204 |
+
"grad_norm": 0.11357705295085907,
|
| 205 |
+
"learning_rate": 0.0001785,
|
| 206 |
+
"loss": 0.1758,
|
| 207 |
+
"step": 135
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.11623080116230801,
|
| 211 |
+
"grad_norm": 0.11982124298810959,
|
| 212 |
+
"learning_rate": 0.00017766666666666666,
|
| 213 |
+
"loss": 0.1838,
|
| 214 |
+
"step": 140
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.12038190120381902,
|
| 218 |
+
"grad_norm": 0.10831739008426666,
|
| 219 |
+
"learning_rate": 0.00017683333333333334,
|
| 220 |
+
"loss": 0.1844,
|
| 221 |
+
"step": 145
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.12453300124533001,
|
| 225 |
+
"grad_norm": 0.1307750791311264,
|
| 226 |
+
"learning_rate": 0.00017600000000000002,
|
| 227 |
+
"loss": 0.1682,
|
| 228 |
+
"step": 150
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.12868410128684102,
|
| 232 |
+
"grad_norm": 0.11941725760698318,
|
| 233 |
+
"learning_rate": 0.00017516666666666668,
|
| 234 |
+
"loss": 0.1817,
|
| 235 |
+
"step": 155
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.13283520132835203,
|
| 239 |
+
"grad_norm": 0.11858333647251129,
|
| 240 |
+
"learning_rate": 0.00017433333333333336,
|
| 241 |
+
"loss": 0.1755,
|
| 242 |
+
"step": 160
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.136986301369863,
|
| 246 |
+
"grad_norm": 0.148487389087677,
|
| 247 |
+
"learning_rate": 0.00017350000000000002,
|
| 248 |
+
"loss": 0.1737,
|
| 249 |
+
"step": 165
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.141137401411374,
|
| 253 |
+
"grad_norm": 0.09661240875720978,
|
| 254 |
+
"learning_rate": 0.00017266666666666667,
|
| 255 |
+
"loss": 0.1711,
|
| 256 |
+
"step": 170
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.14528850145288502,
|
| 260 |
+
"grad_norm": 0.11982620507478714,
|
| 261 |
+
"learning_rate": 0.00017183333333333333,
|
| 262 |
+
"loss": 0.1761,
|
| 263 |
+
"step": 175
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.149439601494396,
|
| 267 |
+
"grad_norm": 0.13303467631340027,
|
| 268 |
+
"learning_rate": 0.000171,
|
| 269 |
+
"loss": 0.1852,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.153590701535907,
|
| 274 |
+
"grad_norm": 0.17849081754684448,
|
| 275 |
+
"learning_rate": 0.00017016666666666666,
|
| 276 |
+
"loss": 0.175,
|
| 277 |
+
"step": 185
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.15774180157741802,
|
| 281 |
+
"grad_norm": 0.1439221203327179,
|
| 282 |
+
"learning_rate": 0.00016933333333333335,
|
| 283 |
+
"loss": 0.1829,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.16189290161892902,
|
| 288 |
+
"grad_norm": 0.10196991264820099,
|
| 289 |
+
"learning_rate": 0.0001685,
|
| 290 |
+
"loss": 0.1806,
|
| 291 |
+
"step": 195
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.16604400166044,
|
| 295 |
+
"grad_norm": 0.08456692099571228,
|
| 296 |
+
"learning_rate": 0.00016766666666666669,
|
| 297 |
+
"loss": 0.1654,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.170195101701951,
|
| 302 |
+
"grad_norm": 0.11249461770057678,
|
| 303 |
+
"learning_rate": 0.00016683333333333334,
|
| 304 |
+
"loss": 0.1742,
|
| 305 |
+
"step": 205
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.17434620174346202,
|
| 309 |
+
"grad_norm": 0.13056688010692596,
|
| 310 |
+
"learning_rate": 0.000166,
|
| 311 |
+
"loss": 0.1638,
|
| 312 |
+
"step": 210
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.17849730178497303,
|
| 316 |
+
"grad_norm": 0.11072465032339096,
|
| 317 |
+
"learning_rate": 0.00016516666666666668,
|
| 318 |
+
"loss": 0.174,
|
| 319 |
+
"step": 215
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.182648401826484,
|
| 323 |
+
"grad_norm": 0.1256282925605774,
|
| 324 |
+
"learning_rate": 0.00016433333333333333,
|
| 325 |
+
"loss": 0.1787,
|
| 326 |
+
"step": 220
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.18679950186799502,
|
| 330 |
+
"grad_norm": 0.11549237370491028,
|
| 331 |
+
"learning_rate": 0.00016350000000000002,
|
| 332 |
+
"loss": 0.158,
|
| 333 |
+
"step": 225
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.19095060190950602,
|
| 337 |
+
"grad_norm": 0.1422484964132309,
|
| 338 |
+
"learning_rate": 0.00016266666666666667,
|
| 339 |
+
"loss": 0.1763,
|
| 340 |
+
"step": 230
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.19510170195101703,
|
| 344 |
+
"grad_norm": 0.15041838586330414,
|
| 345 |
+
"learning_rate": 0.00016183333333333335,
|
| 346 |
+
"loss": 0.1724,
|
| 347 |
+
"step": 235
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.199252801992528,
|
| 351 |
+
"grad_norm": 0.15117141604423523,
|
| 352 |
+
"learning_rate": 0.000161,
|
| 353 |
+
"loss": 0.1748,
|
| 354 |
+
"step": 240
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.20340390203403902,
|
| 358 |
+
"grad_norm": 0.13535872101783752,
|
| 359 |
+
"learning_rate": 0.00016016666666666667,
|
| 360 |
+
"loss": 0.1639,
|
| 361 |
+
"step": 245
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.20755500207555003,
|
| 365 |
+
"grad_norm": 0.11507098376750946,
|
| 366 |
+
"learning_rate": 0.00015933333333333332,
|
| 367 |
+
"loss": 0.1707,
|
| 368 |
+
"step": 250
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.21170610211706103,
|
| 372 |
+
"grad_norm": 0.1293431520462036,
|
| 373 |
+
"learning_rate": 0.0001585,
|
| 374 |
+
"loss": 0.1549,
|
| 375 |
+
"step": 255
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.21585720215857201,
|
| 379 |
+
"grad_norm": 0.11451301723718643,
|
| 380 |
+
"learning_rate": 0.00015766666666666669,
|
| 381 |
+
"loss": 0.169,
|
| 382 |
+
"step": 260
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.22000830220008302,
|
| 386 |
+
"grad_norm": 0.12253163754940033,
|
| 387 |
+
"learning_rate": 0.00015683333333333334,
|
| 388 |
+
"loss": 0.1622,
|
| 389 |
+
"step": 265
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.22415940224159403,
|
| 393 |
+
"grad_norm": 0.12956801056861877,
|
| 394 |
+
"learning_rate": 0.00015600000000000002,
|
| 395 |
+
"loss": 0.1682,
|
| 396 |
+
"step": 270
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.228310502283105,
|
| 400 |
+
"grad_norm": 0.13183289766311646,
|
| 401 |
+
"learning_rate": 0.00015516666666666668,
|
| 402 |
+
"loss": 0.173,
|
| 403 |
+
"step": 275
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.23246160232461602,
|
| 407 |
+
"grad_norm": 0.10935479402542114,
|
| 408 |
+
"learning_rate": 0.00015433333333333334,
|
| 409 |
+
"loss": 0.1655,
|
| 410 |
+
"step": 280
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.23661270236612703,
|
| 414 |
+
"grad_norm": 0.12317913770675659,
|
| 415 |
+
"learning_rate": 0.0001535,
|
| 416 |
+
"loss": 0.1737,
|
| 417 |
+
"step": 285
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.24076380240763803,
|
| 421 |
+
"grad_norm": 0.11220147460699081,
|
| 422 |
+
"learning_rate": 0.00015266666666666667,
|
| 423 |
+
"loss": 0.1629,
|
| 424 |
+
"step": 290
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.244914902449149,
|
| 428 |
+
"grad_norm": 0.13465231657028198,
|
| 429 |
+
"learning_rate": 0.00015183333333333333,
|
| 430 |
+
"loss": 0.1662,
|
| 431 |
+
"step": 295
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.24906600249066002,
|
| 435 |
+
"grad_norm": 0.11543688923120499,
|
| 436 |
+
"learning_rate": 0.000151,
|
| 437 |
+
"loss": 0.1696,
|
| 438 |
+
"step": 300
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.253217102532171,
|
| 442 |
+
"grad_norm": 0.11491172760725021,
|
| 443 |
+
"learning_rate": 0.00015016666666666667,
|
| 444 |
+
"loss": 0.1658,
|
| 445 |
+
"step": 305
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.25736820257368204,
|
| 449 |
+
"grad_norm": 0.12188146263360977,
|
| 450 |
+
"learning_rate": 0.00014933333333333335,
|
| 451 |
+
"loss": 0.1658,
|
| 452 |
+
"step": 310
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.261519302615193,
|
| 456 |
+
"grad_norm": 0.12088894098997116,
|
| 457 |
+
"learning_rate": 0.0001485,
|
| 458 |
+
"loss": 0.1784,
|
| 459 |
+
"step": 315
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.26567040265670405,
|
| 463 |
+
"grad_norm": 0.12337731570005417,
|
| 464 |
+
"learning_rate": 0.00014766666666666666,
|
| 465 |
+
"loss": 0.166,
|
| 466 |
+
"step": 320
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.26982150269821503,
|
| 470 |
+
"grad_norm": 0.1168065220117569,
|
| 471 |
+
"learning_rate": 0.00014683333333333334,
|
| 472 |
+
"loss": 0.1673,
|
| 473 |
+
"step": 325
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.273972602739726,
|
| 477 |
+
"grad_norm": 0.11037846654653549,
|
| 478 |
+
"learning_rate": 0.000146,
|
| 479 |
+
"loss": 0.1593,
|
| 480 |
+
"step": 330
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.27812370278123705,
|
| 484 |
+
"grad_norm": 0.1385302096605301,
|
| 485 |
+
"learning_rate": 0.00014516666666666668,
|
| 486 |
+
"loss": 0.1711,
|
| 487 |
+
"step": 335
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.282274802822748,
|
| 491 |
+
"grad_norm": 0.12126076221466064,
|
| 492 |
+
"learning_rate": 0.00014433333333333334,
|
| 493 |
+
"loss": 0.1672,
|
| 494 |
+
"step": 340
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.286425902864259,
|
| 498 |
+
"grad_norm": 0.13003192842006683,
|
| 499 |
+
"learning_rate": 0.00014350000000000002,
|
| 500 |
+
"loss": 0.1856,
|
| 501 |
+
"step": 345
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.29057700290577004,
|
| 505 |
+
"grad_norm": 0.11907174438238144,
|
| 506 |
+
"learning_rate": 0.00014266666666666667,
|
| 507 |
+
"loss": 0.1626,
|
| 508 |
+
"step": 350
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.294728102947281,
|
| 512 |
+
"grad_norm": 0.1277119666337967,
|
| 513 |
+
"learning_rate": 0.00014183333333333333,
|
| 514 |
+
"loss": 0.1546,
|
| 515 |
+
"step": 355
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.298879202988792,
|
| 519 |
+
"grad_norm": 0.09578083455562592,
|
| 520 |
+
"learning_rate": 0.000141,
|
| 521 |
+
"loss": 0.1581,
|
| 522 |
+
"step": 360
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.30303030303030304,
|
| 526 |
+
"grad_norm": 0.14650468528270721,
|
| 527 |
+
"learning_rate": 0.00014016666666666667,
|
| 528 |
+
"loss": 0.155,
|
| 529 |
+
"step": 365
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.307181403071814,
|
| 533 |
+
"grad_norm": 0.09313970804214478,
|
| 534 |
+
"learning_rate": 0.00013933333333333335,
|
| 535 |
+
"loss": 0.1538,
|
| 536 |
+
"step": 370
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.31133250311332505,
|
| 540 |
+
"grad_norm": 0.12291823327541351,
|
| 541 |
+
"learning_rate": 0.0001385,
|
| 542 |
+
"loss": 0.1618,
|
| 543 |
+
"step": 375
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.31548360315483603,
|
| 547 |
+
"grad_norm": 0.15737979114055634,
|
| 548 |
+
"learning_rate": 0.0001376666666666667,
|
| 549 |
+
"loss": 0.1489,
|
| 550 |
+
"step": 380
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.319634703196347,
|
| 554 |
+
"grad_norm": 0.1407833844423294,
|
| 555 |
+
"learning_rate": 0.00013683333333333334,
|
| 556 |
+
"loss": 0.1667,
|
| 557 |
+
"step": 385
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.32378580323785805,
|
| 561 |
+
"grad_norm": 0.11220885813236237,
|
| 562 |
+
"learning_rate": 0.00013600000000000003,
|
| 563 |
+
"loss": 0.1612,
|
| 564 |
+
"step": 390
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.32793690327936903,
|
| 568 |
+
"grad_norm": 0.11603619903326035,
|
| 569 |
+
"learning_rate": 0.00013516666666666665,
|
| 570 |
+
"loss": 0.1512,
|
| 571 |
+
"step": 395
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.33208800332088,
|
| 575 |
+
"grad_norm": 0.1272398978471756,
|
| 576 |
+
"learning_rate": 0.00013433333333333334,
|
| 577 |
+
"loss": 0.1698,
|
| 578 |
+
"step": 400
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.33623910336239105,
|
| 582 |
+
"grad_norm": 0.09472394734621048,
|
| 583 |
+
"learning_rate": 0.0001335,
|
| 584 |
+
"loss": 0.1383,
|
| 585 |
+
"step": 405
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.340390203403902,
|
| 589 |
+
"grad_norm": 0.14773984253406525,
|
| 590 |
+
"learning_rate": 0.00013266666666666667,
|
| 591 |
+
"loss": 0.1448,
|
| 592 |
+
"step": 410
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.34454130344541306,
|
| 596 |
+
"grad_norm": 0.12423422932624817,
|
| 597 |
+
"learning_rate": 0.00013183333333333333,
|
| 598 |
+
"loss": 0.1592,
|
| 599 |
+
"step": 415
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.34869240348692404,
|
| 603 |
+
"grad_norm": 0.09750059992074966,
|
| 604 |
+
"learning_rate": 0.000131,
|
| 605 |
+
"loss": 0.1547,
|
| 606 |
+
"step": 420
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.352843503528435,
|
| 610 |
+
"grad_norm": 0.15196076035499573,
|
| 611 |
+
"learning_rate": 0.00013016666666666667,
|
| 612 |
+
"loss": 0.1454,
|
| 613 |
+
"step": 425
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.35699460356994606,
|
| 617 |
+
"grad_norm": 0.13726986944675446,
|
| 618 |
+
"learning_rate": 0.00012933333333333332,
|
| 619 |
+
"loss": 0.1671,
|
| 620 |
+
"step": 430
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.36114570361145704,
|
| 624 |
+
"grad_norm": 0.13060466945171356,
|
| 625 |
+
"learning_rate": 0.0001285,
|
| 626 |
+
"loss": 0.1547,
|
| 627 |
+
"step": 435
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.365296803652968,
|
| 631 |
+
"grad_norm": 0.12362024933099747,
|
| 632 |
+
"learning_rate": 0.00012766666666666666,
|
| 633 |
+
"loss": 0.1616,
|
| 634 |
+
"step": 440
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.36944790369447905,
|
| 638 |
+
"grad_norm": 0.1080276295542717,
|
| 639 |
+
"learning_rate": 0.00012683333333333334,
|
| 640 |
+
"loss": 0.1564,
|
| 641 |
+
"step": 445
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.37359900373599003,
|
| 645 |
+
"grad_norm": 0.11262942105531693,
|
| 646 |
+
"learning_rate": 0.000126,
|
| 647 |
+
"loss": 0.1604,
|
| 648 |
+
"step": 450
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.377750103777501,
|
| 652 |
+
"grad_norm": 0.13379591703414917,
|
| 653 |
+
"learning_rate": 0.00012516666666666668,
|
| 654 |
+
"loss": 0.157,
|
| 655 |
+
"step": 455
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.38190120381901205,
|
| 659 |
+
"grad_norm": 0.12742692232131958,
|
| 660 |
+
"learning_rate": 0.00012433333333333334,
|
| 661 |
+
"loss": 0.1579,
|
| 662 |
+
"step": 460
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.386052303860523,
|
| 666 |
+
"grad_norm": 0.10482796281576157,
|
| 667 |
+
"learning_rate": 0.00012350000000000002,
|
| 668 |
+
"loss": 0.1528,
|
| 669 |
+
"step": 465
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.39020340390203406,
|
| 673 |
+
"grad_norm": 0.12541286647319794,
|
| 674 |
+
"learning_rate": 0.00012266666666666668,
|
| 675 |
+
"loss": 0.1498,
|
| 676 |
+
"step": 470
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.39435450394354504,
|
| 680 |
+
"grad_norm": 0.15082834661006927,
|
| 681 |
+
"learning_rate": 0.00012183333333333333,
|
| 682 |
+
"loss": 0.1402,
|
| 683 |
+
"step": 475
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.398505603985056,
|
| 687 |
+
"grad_norm": 0.11872395128011703,
|
| 688 |
+
"learning_rate": 0.000121,
|
| 689 |
+
"loss": 0.1613,
|
| 690 |
+
"step": 480
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.40265670402656706,
|
| 694 |
+
"grad_norm": 0.12806229293346405,
|
| 695 |
+
"learning_rate": 0.00012016666666666667,
|
| 696 |
+
"loss": 0.1467,
|
| 697 |
+
"step": 485
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.40680780406807804,
|
| 701 |
+
"grad_norm": 0.11704318970441818,
|
| 702 |
+
"learning_rate": 0.00011933333333333334,
|
| 703 |
+
"loss": 0.1536,
|
| 704 |
+
"step": 490
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.410958904109589,
|
| 708 |
+
"grad_norm": 0.11440624296665192,
|
| 709 |
+
"learning_rate": 0.00011850000000000001,
|
| 710 |
+
"loss": 0.1488,
|
| 711 |
+
"step": 495
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.41511000415110005,
|
| 715 |
+
"grad_norm": 0.1284865289926529,
|
| 716 |
+
"learning_rate": 0.00011766666666666668,
|
| 717 |
+
"loss": 0.1479,
|
| 718 |
+
"step": 500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.41926110419261103,
|
| 722 |
+
"grad_norm": 0.1310071051120758,
|
| 723 |
+
"learning_rate": 0.00011683333333333333,
|
| 724 |
+
"loss": 0.1638,
|
| 725 |
+
"step": 505
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.42341220423412207,
|
| 729 |
+
"grad_norm": 0.14244677126407623,
|
| 730 |
+
"learning_rate": 0.000116,
|
| 731 |
+
"loss": 0.166,
|
| 732 |
+
"step": 510
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.42756330427563305,
|
| 736 |
+
"grad_norm": 0.12084666639566422,
|
| 737 |
+
"learning_rate": 0.00011516666666666667,
|
| 738 |
+
"loss": 0.1521,
|
| 739 |
+
"step": 515
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.43171440431714403,
|
| 743 |
+
"grad_norm": 0.13859711587429047,
|
| 744 |
+
"learning_rate": 0.00011433333333333334,
|
| 745 |
+
"loss": 0.1575,
|
| 746 |
+
"step": 520
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.43586550435865506,
|
| 750 |
+
"grad_norm": 0.14870645105838776,
|
| 751 |
+
"learning_rate": 0.00011350000000000001,
|
| 752 |
+
"loss": 0.1599,
|
| 753 |
+
"step": 525
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.44001660440016604,
|
| 757 |
+
"grad_norm": 0.12018068134784698,
|
| 758 |
+
"learning_rate": 0.00011266666666666668,
|
| 759 |
+
"loss": 0.1648,
|
| 760 |
+
"step": 530
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.444167704441677,
|
| 764 |
+
"grad_norm": 0.120558962225914,
|
| 765 |
+
"learning_rate": 0.00011183333333333335,
|
| 766 |
+
"loss": 0.154,
|
| 767 |
+
"step": 535
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.44831880448318806,
|
| 771 |
+
"grad_norm": 0.11315838992595673,
|
| 772 |
+
"learning_rate": 0.00011100000000000001,
|
| 773 |
+
"loss": 0.1465,
|
| 774 |
+
"step": 540
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.45246990452469904,
|
| 778 |
+
"grad_norm": 0.1233653798699379,
|
| 779 |
+
"learning_rate": 0.00011016666666666666,
|
| 780 |
+
"loss": 0.1389,
|
| 781 |
+
"step": 545
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.45662100456621,
|
| 785 |
+
"grad_norm": 0.12076210975646973,
|
| 786 |
+
"learning_rate": 0.00010933333333333333,
|
| 787 |
+
"loss": 0.1575,
|
| 788 |
+
"step": 550
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.46077210460772106,
|
| 792 |
+
"grad_norm": 0.11424656212329865,
|
| 793 |
+
"learning_rate": 0.00010850000000000001,
|
| 794 |
+
"loss": 0.1542,
|
| 795 |
+
"step": 555
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.46492320464923204,
|
| 799 |
+
"grad_norm": 0.11583676189184189,
|
| 800 |
+
"learning_rate": 0.00010766666666666668,
|
| 801 |
+
"loss": 0.1626,
|
| 802 |
+
"step": 560
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.46907430469074307,
|
| 806 |
+
"grad_norm": 0.12343718856573105,
|
| 807 |
+
"learning_rate": 0.00010683333333333335,
|
| 808 |
+
"loss": 0.1394,
|
| 809 |
+
"step": 565
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.47322540473225405,
|
| 813 |
+
"grad_norm": 0.12574954330921173,
|
| 814 |
+
"learning_rate": 0.00010600000000000002,
|
| 815 |
+
"loss": 0.1402,
|
| 816 |
+
"step": 570
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.47737650477376503,
|
| 820 |
+
"grad_norm": 0.13551151752471924,
|
| 821 |
+
"learning_rate": 0.00010516666666666668,
|
| 822 |
+
"loss": 0.1598,
|
| 823 |
+
"step": 575
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.48152760481527607,
|
| 827 |
+
"grad_norm": 0.12537416815757751,
|
| 828 |
+
"learning_rate": 0.00010433333333333333,
|
| 829 |
+
"loss": 0.1588,
|
| 830 |
+
"step": 580
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.48567870485678705,
|
| 834 |
+
"grad_norm": 0.13128598034381866,
|
| 835 |
+
"learning_rate": 0.0001035,
|
| 836 |
+
"loss": 0.143,
|
| 837 |
+
"step": 585
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.489829804898298,
|
| 841 |
+
"grad_norm": 0.11566058546304703,
|
| 842 |
+
"learning_rate": 0.00010266666666666666,
|
| 843 |
+
"loss": 0.1608,
|
| 844 |
+
"step": 590
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.49398090493980906,
|
| 848 |
+
"grad_norm": 0.11678820848464966,
|
| 849 |
+
"learning_rate": 0.00010183333333333333,
|
| 850 |
+
"loss": 0.1505,
|
| 851 |
+
"step": 595
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.49813200498132004,
|
| 855 |
+
"grad_norm": 0.12501274049282074,
|
| 856 |
+
"learning_rate": 0.000101,
|
| 857 |
+
"loss": 0.161,
|
| 858 |
+
"step": 600
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.49813200498132004,
|
| 862 |
+
"eval_loss": 0.15276095271110535,
|
| 863 |
+
"eval_runtime": 185.8767,
|
| 864 |
+
"eval_samples_per_second": 4.842,
|
| 865 |
+
"eval_steps_per_second": 2.421,
|
| 866 |
+
"step": 600
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.502283105022831,
|
| 870 |
+
"grad_norm": 0.10359059274196625,
|
| 871 |
+
"learning_rate": 0.00010016666666666667,
|
| 872 |
+
"loss": 0.1498,
|
| 873 |
+
"step": 605
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.506434205064342,
|
| 877 |
+
"grad_norm": 0.12891648709774017,
|
| 878 |
+
"learning_rate": 9.933333333333334e-05,
|
| 879 |
+
"loss": 0.1565,
|
| 880 |
+
"step": 610
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.5105853051058531,
|
| 884 |
+
"grad_norm": 0.1454884111881256,
|
| 885 |
+
"learning_rate": 9.850000000000001e-05,
|
| 886 |
+
"loss": 0.1422,
|
| 887 |
+
"step": 615
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.5147364051473641,
|
| 891 |
+
"grad_norm": 0.12548445165157318,
|
| 892 |
+
"learning_rate": 9.766666666666668e-05,
|
| 893 |
+
"loss": 0.176,
|
| 894 |
+
"step": 620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.518887505188875,
|
| 898 |
+
"grad_norm": 0.11389490962028503,
|
| 899 |
+
"learning_rate": 9.683333333333335e-05,
|
| 900 |
+
"loss": 0.152,
|
| 901 |
+
"step": 625
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.523038605230386,
|
| 905 |
+
"grad_norm": 0.13731062412261963,
|
| 906 |
+
"learning_rate": 9.6e-05,
|
| 907 |
+
"loss": 0.1438,
|
| 908 |
+
"step": 630
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.527189705271897,
|
| 912 |
+
"grad_norm": 0.10833003371953964,
|
| 913 |
+
"learning_rate": 9.516666666666667e-05,
|
| 914 |
+
"loss": 0.136,
|
| 915 |
+
"step": 635
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5313408053134081,
|
| 919 |
+
"grad_norm": 0.13331717252731323,
|
| 920 |
+
"learning_rate": 9.433333333333334e-05,
|
| 921 |
+
"loss": 0.1515,
|
| 922 |
+
"step": 640
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.5354919053549191,
|
| 926 |
+
"grad_norm": 0.11971119791269302,
|
| 927 |
+
"learning_rate": 9.350000000000001e-05,
|
| 928 |
+
"loss": 0.1608,
|
| 929 |
+
"step": 645
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.5396430053964301,
|
| 933 |
+
"grad_norm": 0.12283340841531754,
|
| 934 |
+
"learning_rate": 9.266666666666666e-05,
|
| 935 |
+
"loss": 0.1478,
|
| 936 |
+
"step": 650
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.543794105437941,
|
| 940 |
+
"grad_norm": 0.18648238480091095,
|
| 941 |
+
"learning_rate": 9.183333333333333e-05,
|
| 942 |
+
"loss": 0.1578,
|
| 943 |
+
"step": 655
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.547945205479452,
|
| 947 |
+
"grad_norm": 0.1412057876586914,
|
| 948 |
+
"learning_rate": 9.1e-05,
|
| 949 |
+
"loss": 0.1396,
|
| 950 |
+
"step": 660
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.552096305520963,
|
| 954 |
+
"grad_norm": 0.14734192192554474,
|
| 955 |
+
"learning_rate": 9.016666666666667e-05,
|
| 956 |
+
"loss": 0.1571,
|
| 957 |
+
"step": 665
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.5562474055624741,
|
| 961 |
+
"grad_norm": 0.10538703948259354,
|
| 962 |
+
"learning_rate": 8.933333333333334e-05,
|
| 963 |
+
"loss": 0.1641,
|
| 964 |
+
"step": 670
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.5603985056039851,
|
| 968 |
+
"grad_norm": 0.12703998386859894,
|
| 969 |
+
"learning_rate": 8.850000000000001e-05,
|
| 970 |
+
"loss": 0.1559,
|
| 971 |
+
"step": 675
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.564549605645496,
|
| 975 |
+
"grad_norm": 0.12684640288352966,
|
| 976 |
+
"learning_rate": 8.766666666666668e-05,
|
| 977 |
+
"loss": 0.1537,
|
| 978 |
+
"step": 680
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.568700705687007,
|
| 982 |
+
"grad_norm": 0.1368802934885025,
|
| 983 |
+
"learning_rate": 8.683333333333333e-05,
|
| 984 |
+
"loss": 0.1554,
|
| 985 |
+
"step": 685
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.572851805728518,
|
| 989 |
+
"grad_norm": 0.12192381918430328,
|
| 990 |
+
"learning_rate": 8.6e-05,
|
| 991 |
+
"loss": 0.1698,
|
| 992 |
+
"step": 690
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.5770029057700291,
|
| 996 |
+
"grad_norm": 0.09523618221282959,
|
| 997 |
+
"learning_rate": 8.516666666666667e-05,
|
| 998 |
+
"loss": 0.1362,
|
| 999 |
+
"step": 695
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.5811540058115401,
|
| 1003 |
+
"grad_norm": 0.12437159568071365,
|
| 1004 |
+
"learning_rate": 8.433333333333334e-05,
|
| 1005 |
+
"loss": 0.1526,
|
| 1006 |
+
"step": 700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.5853051058530511,
|
| 1010 |
+
"grad_norm": 0.12487108260393143,
|
| 1011 |
+
"learning_rate": 8.35e-05,
|
| 1012 |
+
"loss": 0.1362,
|
| 1013 |
+
"step": 705
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.589456205894562,
|
| 1017 |
+
"grad_norm": 0.10976472496986389,
|
| 1018 |
+
"learning_rate": 8.266666666666667e-05,
|
| 1019 |
+
"loss": 0.1516,
|
| 1020 |
+
"step": 710
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.593607305936073,
|
| 1024 |
+
"grad_norm": 0.11062753945589066,
|
| 1025 |
+
"learning_rate": 8.183333333333333e-05,
|
| 1026 |
+
"loss": 0.1486,
|
| 1027 |
+
"step": 715
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.597758405977584,
|
| 1031 |
+
"grad_norm": 0.1419171243906021,
|
| 1032 |
+
"learning_rate": 8.1e-05,
|
| 1033 |
+
"loss": 0.1558,
|
| 1034 |
+
"step": 720
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.6019095060190951,
|
| 1038 |
+
"grad_norm": 0.11999824643135071,
|
| 1039 |
+
"learning_rate": 8.016666666666667e-05,
|
| 1040 |
+
"loss": 0.1365,
|
| 1041 |
+
"step": 725
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.6060606060606061,
|
| 1045 |
+
"grad_norm": 0.12366942316293716,
|
| 1046 |
+
"learning_rate": 7.933333333333334e-05,
|
| 1047 |
+
"loss": 0.1594,
|
| 1048 |
+
"step": 730
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.6102117061021171,
|
| 1052 |
+
"grad_norm": 0.12560267746448517,
|
| 1053 |
+
"learning_rate": 7.850000000000001e-05,
|
| 1054 |
+
"loss": 0.1469,
|
| 1055 |
+
"step": 735
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.614362806143628,
|
| 1059 |
+
"grad_norm": 0.12089208513498306,
|
| 1060 |
+
"learning_rate": 7.766666666666667e-05,
|
| 1061 |
+
"loss": 0.1557,
|
| 1062 |
+
"step": 740
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.618513906185139,
|
| 1066 |
+
"grad_norm": 0.1430719494819641,
|
| 1067 |
+
"learning_rate": 7.683333333333334e-05,
|
| 1068 |
+
"loss": 0.1423,
|
| 1069 |
+
"step": 745
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.6226650062266501,
|
| 1073 |
+
"grad_norm": 0.13126327097415924,
|
| 1074 |
+
"learning_rate": 7.6e-05,
|
| 1075 |
+
"loss": 0.1468,
|
| 1076 |
+
"step": 750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.6268161062681611,
|
| 1080 |
+
"grad_norm": 0.09532318264245987,
|
| 1081 |
+
"learning_rate": 7.516666666666667e-05,
|
| 1082 |
+
"loss": 0.1449,
|
| 1083 |
+
"step": 755
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.6309672063096721,
|
| 1087 |
+
"grad_norm": 0.12227542698383331,
|
| 1088 |
+
"learning_rate": 7.433333333333333e-05,
|
| 1089 |
+
"loss": 0.1544,
|
| 1090 |
+
"step": 760
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.635118306351183,
|
| 1094 |
+
"grad_norm": 0.14084969460964203,
|
| 1095 |
+
"learning_rate": 7.35e-05,
|
| 1096 |
+
"loss": 0.1488,
|
| 1097 |
+
"step": 765
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.639269406392694,
|
| 1101 |
+
"grad_norm": 0.12827131152153015,
|
| 1102 |
+
"learning_rate": 7.266666666666667e-05,
|
| 1103 |
+
"loss": 0.1447,
|
| 1104 |
+
"step": 770
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.6434205064342051,
|
| 1108 |
+
"grad_norm": 0.14061811566352844,
|
| 1109 |
+
"learning_rate": 7.183333333333334e-05,
|
| 1110 |
+
"loss": 0.1428,
|
| 1111 |
+
"step": 775
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.6475716064757161,
|
| 1115 |
+
"grad_norm": 0.14365419745445251,
|
| 1116 |
+
"learning_rate": 7.1e-05,
|
| 1117 |
+
"loss": 0.1574,
|
| 1118 |
+
"step": 780
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.6517227065172271,
|
| 1122 |
+
"grad_norm": 0.11606994271278381,
|
| 1123 |
+
"learning_rate": 7.016666666666667e-05,
|
| 1124 |
+
"loss": 0.146,
|
| 1125 |
+
"step": 785
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.6558738065587381,
|
| 1129 |
+
"grad_norm": 0.12274261564016342,
|
| 1130 |
+
"learning_rate": 6.933333333333334e-05,
|
| 1131 |
+
"loss": 0.1369,
|
| 1132 |
+
"step": 790
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.660024906600249,
|
| 1136 |
+
"grad_norm": 0.11611846834421158,
|
| 1137 |
+
"learning_rate": 6.850000000000001e-05,
|
| 1138 |
+
"loss": 0.1557,
|
| 1139 |
+
"step": 795
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.66417600664176,
|
| 1143 |
+
"grad_norm": 0.13420958817005157,
|
| 1144 |
+
"learning_rate": 6.766666666666667e-05,
|
| 1145 |
+
"loss": 0.1491,
|
| 1146 |
+
"step": 800
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.66417600664176,
|
| 1150 |
+
"eval_loss": 0.14878682792186737,
|
| 1151 |
+
"eval_runtime": 186.9396,
|
| 1152 |
+
"eval_samples_per_second": 4.814,
|
| 1153 |
+
"eval_steps_per_second": 2.407,
|
| 1154 |
+
"step": 800
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.6683271066832711,
|
| 1158 |
+
"grad_norm": 0.12904717028141022,
|
| 1159 |
+
"learning_rate": 6.683333333333334e-05,
|
| 1160 |
+
"loss": 0.153,
|
| 1161 |
+
"step": 805
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.6724782067247821,
|
| 1165 |
+
"grad_norm": 0.12883269786834717,
|
| 1166 |
+
"learning_rate": 6.6e-05,
|
| 1167 |
+
"loss": 0.1455,
|
| 1168 |
+
"step": 810
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.6766293067662931,
|
| 1172 |
+
"grad_norm": 0.15537196397781372,
|
| 1173 |
+
"learning_rate": 6.516666666666666e-05,
|
| 1174 |
+
"loss": 0.1564,
|
| 1175 |
+
"step": 815
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.680780406807804,
|
| 1179 |
+
"grad_norm": 0.12396696209907532,
|
| 1180 |
+
"learning_rate": 6.433333333333333e-05,
|
| 1181 |
+
"loss": 0.1458,
|
| 1182 |
+
"step": 820
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.684931506849315,
|
| 1186 |
+
"grad_norm": 0.15211425721645355,
|
| 1187 |
+
"learning_rate": 6.35e-05,
|
| 1188 |
+
"loss": 0.1424,
|
| 1189 |
+
"step": 825
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.6890826068908261,
|
| 1193 |
+
"grad_norm": 0.12306790798902512,
|
| 1194 |
+
"learning_rate": 6.266666666666667e-05,
|
| 1195 |
+
"loss": 0.1418,
|
| 1196 |
+
"step": 830
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.6932337069323371,
|
| 1200 |
+
"grad_norm": 0.13135729730129242,
|
| 1201 |
+
"learning_rate": 6.183333333333334e-05,
|
| 1202 |
+
"loss": 0.1329,
|
| 1203 |
+
"step": 835
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.6973848069738481,
|
| 1207 |
+
"grad_norm": 0.1494913101196289,
|
| 1208 |
+
"learning_rate": 6.1e-05,
|
| 1209 |
+
"loss": 0.1518,
|
| 1210 |
+
"step": 840
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.7015359070153591,
|
| 1214 |
+
"grad_norm": 0.10251809656620026,
|
| 1215 |
+
"learning_rate": 6.0166666666666674e-05,
|
| 1216 |
+
"loss": 0.135,
|
| 1217 |
+
"step": 845
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.70568700705687,
|
| 1221 |
+
"grad_norm": 0.10936664044857025,
|
| 1222 |
+
"learning_rate": 5.9333333333333343e-05,
|
| 1223 |
+
"loss": 0.1498,
|
| 1224 |
+
"step": 850
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.709838107098381,
|
| 1228 |
+
"grad_norm": 0.14118026196956635,
|
| 1229 |
+
"learning_rate": 5.85e-05,
|
| 1230 |
+
"loss": 0.1549,
|
| 1231 |
+
"step": 855
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.7139892071398921,
|
| 1235 |
+
"grad_norm": 0.12029966711997986,
|
| 1236 |
+
"learning_rate": 5.766666666666667e-05,
|
| 1237 |
+
"loss": 0.1279,
|
| 1238 |
+
"step": 860
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.7181403071814031,
|
| 1242 |
+
"grad_norm": 0.13987119495868683,
|
| 1243 |
+
"learning_rate": 5.683333333333334e-05,
|
| 1244 |
+
"loss": 0.1311,
|
| 1245 |
+
"step": 865
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.7222914072229141,
|
| 1249 |
+
"grad_norm": 0.14721432328224182,
|
| 1250 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 1251 |
+
"loss": 0.1539,
|
| 1252 |
+
"step": 870
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.726442507264425,
|
| 1256 |
+
"grad_norm": 0.12505626678466797,
|
| 1257 |
+
"learning_rate": 5.516666666666667e-05,
|
| 1258 |
+
"loss": 0.1479,
|
| 1259 |
+
"step": 875
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.730593607305936,
|
| 1263 |
+
"grad_norm": 0.13287393748760223,
|
| 1264 |
+
"learning_rate": 5.433333333333334e-05,
|
| 1265 |
+
"loss": 0.1586,
|
| 1266 |
+
"step": 880
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.7347447073474471,
|
| 1270 |
+
"grad_norm": 0.10323189944028854,
|
| 1271 |
+
"learning_rate": 5.3500000000000006e-05,
|
| 1272 |
+
"loss": 0.1401,
|
| 1273 |
+
"step": 885
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.7388958073889581,
|
| 1277 |
+
"grad_norm": 0.12466787546873093,
|
| 1278 |
+
"learning_rate": 5.266666666666666e-05,
|
| 1279 |
+
"loss": 0.1428,
|
| 1280 |
+
"step": 890
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.7430469074304691,
|
| 1284 |
+
"grad_norm": 0.13881418108940125,
|
| 1285 |
+
"learning_rate": 5.183333333333333e-05,
|
| 1286 |
+
"loss": 0.1471,
|
| 1287 |
+
"step": 895
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.7471980074719801,
|
| 1291 |
+
"grad_norm": 0.1371707320213318,
|
| 1292 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 1293 |
+
"loss": 0.1508,
|
| 1294 |
+
"step": 900
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.751349107513491,
|
| 1298 |
+
"grad_norm": 0.13635429739952087,
|
| 1299 |
+
"learning_rate": 5.0166666666666675e-05,
|
| 1300 |
+
"loss": 0.147,
|
| 1301 |
+
"step": 905
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.755500207555002,
|
| 1305 |
+
"grad_norm": 0.126560777425766,
|
| 1306 |
+
"learning_rate": 4.933333333333334e-05,
|
| 1307 |
+
"loss": 0.1365,
|
| 1308 |
+
"step": 910
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.7596513075965131,
|
| 1312 |
+
"grad_norm": 0.10843600332736969,
|
| 1313 |
+
"learning_rate": 4.85e-05,
|
| 1314 |
+
"loss": 0.1471,
|
| 1315 |
+
"step": 915
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.7638024076380241,
|
| 1319 |
+
"grad_norm": 0.13791149854660034,
|
| 1320 |
+
"learning_rate": 4.766666666666667e-05,
|
| 1321 |
+
"loss": 0.1511,
|
| 1322 |
+
"step": 920
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.7679535076795351,
|
| 1326 |
+
"grad_norm": 0.12029317021369934,
|
| 1327 |
+
"learning_rate": 4.683333333333334e-05,
|
| 1328 |
+
"loss": 0.1492,
|
| 1329 |
+
"step": 925
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.772104607721046,
|
| 1333 |
+
"grad_norm": 0.08313252031803131,
|
| 1334 |
+
"learning_rate": 4.600000000000001e-05,
|
| 1335 |
+
"loss": 0.1422,
|
| 1336 |
+
"step": 930
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.776255707762557,
|
| 1340 |
+
"grad_norm": 0.09343947470188141,
|
| 1341 |
+
"learning_rate": 4.516666666666667e-05,
|
| 1342 |
+
"loss": 0.1467,
|
| 1343 |
+
"step": 935
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.7804068078040681,
|
| 1347 |
+
"grad_norm": 0.11305926740169525,
|
| 1348 |
+
"learning_rate": 4.433333333333334e-05,
|
| 1349 |
+
"loss": 0.143,
|
| 1350 |
+
"step": 940
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.7845579078455791,
|
| 1354 |
+
"grad_norm": 0.12202338129281998,
|
| 1355 |
+
"learning_rate": 4.35e-05,
|
| 1356 |
+
"loss": 0.1382,
|
| 1357 |
+
"step": 945
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.7887090078870901,
|
| 1361 |
+
"grad_norm": 0.13653194904327393,
|
| 1362 |
+
"learning_rate": 4.266666666666667e-05,
|
| 1363 |
+
"loss": 0.1248,
|
| 1364 |
+
"step": 950
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.7928601079286011,
|
| 1368 |
+
"grad_norm": 0.1358615607023239,
|
| 1369 |
+
"learning_rate": 4.183333333333334e-05,
|
| 1370 |
+
"loss": 0.1528,
|
| 1371 |
+
"step": 955
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.797011207970112,
|
| 1375 |
+
"grad_norm": 0.13426993787288666,
|
| 1376 |
+
"learning_rate": 4.1e-05,
|
| 1377 |
+
"loss": 0.1511,
|
| 1378 |
+
"step": 960
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.801162308011623,
|
| 1382 |
+
"grad_norm": 0.08840786665678024,
|
| 1383 |
+
"learning_rate": 4.016666666666667e-05,
|
| 1384 |
+
"loss": 0.147,
|
| 1385 |
+
"step": 965
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.8053134080531341,
|
| 1389 |
+
"grad_norm": 0.10167238861322403,
|
| 1390 |
+
"learning_rate": 3.933333333333333e-05,
|
| 1391 |
+
"loss": 0.124,
|
| 1392 |
+
"step": 970
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.8094645080946451,
|
| 1396 |
+
"grad_norm": 0.15286456048488617,
|
| 1397 |
+
"learning_rate": 3.85e-05,
|
| 1398 |
+
"loss": 0.1388,
|
| 1399 |
+
"step": 975
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.8136156081361561,
|
| 1403 |
+
"grad_norm": 0.12808531522750854,
|
| 1404 |
+
"learning_rate": 3.766666666666667e-05,
|
| 1405 |
+
"loss": 0.1312,
|
| 1406 |
+
"step": 980
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.8177667081776671,
|
| 1410 |
+
"grad_norm": 0.11656677722930908,
|
| 1411 |
+
"learning_rate": 3.683333333333334e-05,
|
| 1412 |
+
"loss": 0.1479,
|
| 1413 |
+
"step": 985
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.821917808219178,
|
| 1417 |
+
"grad_norm": 0.10321146994829178,
|
| 1418 |
+
"learning_rate": 3.6e-05,
|
| 1419 |
+
"loss": 0.1233,
|
| 1420 |
+
"step": 990
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.8260689082606891,
|
| 1424 |
+
"grad_norm": 0.14637711644172668,
|
| 1425 |
+
"learning_rate": 3.516666666666667e-05,
|
| 1426 |
+
"loss": 0.1381,
|
| 1427 |
+
"step": 995
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.8302200083022001,
|
| 1431 |
+
"grad_norm": 0.11799775063991547,
|
| 1432 |
+
"learning_rate": 3.433333333333333e-05,
|
| 1433 |
+
"loss": 0.1371,
|
| 1434 |
+
"step": 1000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.8302200083022001,
|
| 1438 |
+
"eval_loss": 0.14595866203308105,
|
| 1439 |
+
"eval_runtime": 186.6793,
|
| 1440 |
+
"eval_samples_per_second": 4.821,
|
| 1441 |
+
"eval_steps_per_second": 2.411,
|
| 1442 |
+
"step": 1000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.8343711083437111,
|
| 1446 |
+
"grad_norm": 0.056576840579509735,
|
| 1447 |
+
"learning_rate": 3.35e-05,
|
| 1448 |
+
"loss": 0.1278,
|
| 1449 |
+
"step": 1005
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.8385222083852221,
|
| 1453 |
+
"grad_norm": 0.12720656394958496,
|
| 1454 |
+
"learning_rate": 3.266666666666667e-05,
|
| 1455 |
+
"loss": 0.1467,
|
| 1456 |
+
"step": 1010
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.842673308426733,
|
| 1460 |
+
"grad_norm": 0.1243145540356636,
|
| 1461 |
+
"learning_rate": 3.183333333333334e-05,
|
| 1462 |
+
"loss": 0.1404,
|
| 1463 |
+
"step": 1015
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.8468244084682441,
|
| 1467 |
+
"grad_norm": 0.12584663927555084,
|
| 1468 |
+
"learning_rate": 3.1e-05,
|
| 1469 |
+
"loss": 0.1511,
|
| 1470 |
+
"step": 1020
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.8509755085097551,
|
| 1474 |
+
"grad_norm": 0.14398354291915894,
|
| 1475 |
+
"learning_rate": 3.016666666666667e-05,
|
| 1476 |
+
"loss": 0.1435,
|
| 1477 |
+
"step": 1025
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.8551266085512661,
|
| 1481 |
+
"grad_norm": 0.17242616415023804,
|
| 1482 |
+
"learning_rate": 2.9333333333333336e-05,
|
| 1483 |
+
"loss": 0.1524,
|
| 1484 |
+
"step": 1030
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.8592777085927771,
|
| 1488 |
+
"grad_norm": 0.11134395748376846,
|
| 1489 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 1490 |
+
"loss": 0.1406,
|
| 1491 |
+
"step": 1035
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.8634288086342881,
|
| 1495 |
+
"grad_norm": 0.13715781271457672,
|
| 1496 |
+
"learning_rate": 2.7666666666666667e-05,
|
| 1497 |
+
"loss": 0.1504,
|
| 1498 |
+
"step": 1040
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.867579908675799,
|
| 1502 |
+
"grad_norm": 0.13127276301383972,
|
| 1503 |
+
"learning_rate": 2.6833333333333333e-05,
|
| 1504 |
+
"loss": 0.1465,
|
| 1505 |
+
"step": 1045
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.8717310087173101,
|
| 1509 |
+
"grad_norm": 0.1410035789012909,
|
| 1510 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 1511 |
+
"loss": 0.1289,
|
| 1512 |
+
"step": 1050
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.8758821087588211,
|
| 1516 |
+
"grad_norm": 0.1502102166414261,
|
| 1517 |
+
"learning_rate": 2.5166666666666667e-05,
|
| 1518 |
+
"loss": 0.1367,
|
| 1519 |
+
"step": 1055
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.8800332088003321,
|
| 1523 |
+
"grad_norm": 0.12710800766944885,
|
| 1524 |
+
"learning_rate": 2.4333333333333336e-05,
|
| 1525 |
+
"loss": 0.135,
|
| 1526 |
+
"step": 1060
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.8841843088418431,
|
| 1530 |
+
"grad_norm": 0.1329444795846939,
|
| 1531 |
+
"learning_rate": 2.35e-05,
|
| 1532 |
+
"loss": 0.1315,
|
| 1533 |
+
"step": 1065
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.888335408883354,
|
| 1537 |
+
"grad_norm": 0.12778909504413605,
|
| 1538 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 1539 |
+
"loss": 0.1541,
|
| 1540 |
+
"step": 1070
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.8924865089248651,
|
| 1544 |
+
"grad_norm": 0.12005715072154999,
|
| 1545 |
+
"learning_rate": 2.1833333333333333e-05,
|
| 1546 |
+
"loss": 0.151,
|
| 1547 |
+
"step": 1075
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.8966376089663761,
|
| 1551 |
+
"grad_norm": 0.08895500004291534,
|
| 1552 |
+
"learning_rate": 2.1e-05,
|
| 1553 |
+
"loss": 0.1387,
|
| 1554 |
+
"step": 1080
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.9007887090078871,
|
| 1558 |
+
"grad_norm": 0.12626707553863525,
|
| 1559 |
+
"learning_rate": 2.0166666666666668e-05,
|
| 1560 |
+
"loss": 0.149,
|
| 1561 |
+
"step": 1085
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.9049398090493981,
|
| 1565 |
+
"grad_norm": 0.13254553079605103,
|
| 1566 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 1567 |
+
"loss": 0.1414,
|
| 1568 |
+
"step": 1090
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.9090909090909091,
|
| 1572 |
+
"grad_norm": 0.1267685890197754,
|
| 1573 |
+
"learning_rate": 1.85e-05,
|
| 1574 |
+
"loss": 0.1647,
|
| 1575 |
+
"step": 1095
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.91324200913242,
|
| 1579 |
+
"grad_norm": 0.12603411078453064,
|
| 1580 |
+
"learning_rate": 1.7666666666666668e-05,
|
| 1581 |
+
"loss": 0.1407,
|
| 1582 |
+
"step": 1100
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.9173931091739311,
|
| 1586 |
+
"grad_norm": 0.172598734498024,
|
| 1587 |
+
"learning_rate": 1.6833333333333334e-05,
|
| 1588 |
+
"loss": 0.1435,
|
| 1589 |
+
"step": 1105
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.9215442092154421,
|
| 1593 |
+
"grad_norm": 0.143843412399292,
|
| 1594 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1595 |
+
"loss": 0.1517,
|
| 1596 |
+
"step": 1110
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.9256953092569531,
|
| 1600 |
+
"grad_norm": 0.14932668209075928,
|
| 1601 |
+
"learning_rate": 1.5166666666666668e-05,
|
| 1602 |
+
"loss": 0.1528,
|
| 1603 |
+
"step": 1115
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.9298464092984641,
|
| 1607 |
+
"grad_norm": 0.1127849742770195,
|
| 1608 |
+
"learning_rate": 1.4333333333333334e-05,
|
| 1609 |
+
"loss": 0.1355,
|
| 1610 |
+
"step": 1120
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.933997509339975,
|
| 1614 |
+
"grad_norm": 0.1379147619009018,
|
| 1615 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 1616 |
+
"loss": 0.1505,
|
| 1617 |
+
"step": 1125
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.9381486093814861,
|
| 1621 |
+
"grad_norm": 0.11335213482379913,
|
| 1622 |
+
"learning_rate": 1.2666666666666668e-05,
|
| 1623 |
+
"loss": 0.1517,
|
| 1624 |
+
"step": 1130
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.9422997094229971,
|
| 1628 |
+
"grad_norm": 0.13676024973392487,
|
| 1629 |
+
"learning_rate": 1.1833333333333334e-05,
|
| 1630 |
+
"loss": 0.1487,
|
| 1631 |
+
"step": 1135
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.9464508094645081,
|
| 1635 |
+
"grad_norm": 0.11180838197469711,
|
| 1636 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 1637 |
+
"loss": 0.124,
|
| 1638 |
+
"step": 1140
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.9506019095060191,
|
| 1642 |
+
"grad_norm": 0.13548138737678528,
|
| 1643 |
+
"learning_rate": 1.0166666666666667e-05,
|
| 1644 |
+
"loss": 0.1496,
|
| 1645 |
+
"step": 1145
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.9547530095475301,
|
| 1649 |
+
"grad_norm": 0.1309673935174942,
|
| 1650 |
+
"learning_rate": 9.333333333333334e-06,
|
| 1651 |
+
"loss": 0.1315,
|
| 1652 |
+
"step": 1150
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.958904109589041,
|
| 1656 |
+
"grad_norm": 0.11803894490003586,
|
| 1657 |
+
"learning_rate": 8.500000000000002e-06,
|
| 1658 |
+
"loss": 0.1609,
|
| 1659 |
+
"step": 1155
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.9630552096305521,
|
| 1663 |
+
"grad_norm": 0.12026551365852356,
|
| 1664 |
+
"learning_rate": 7.666666666666667e-06,
|
| 1665 |
+
"loss": 0.145,
|
| 1666 |
+
"step": 1160
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.9672063096720631,
|
| 1670 |
+
"grad_norm": 0.14298652112483978,
|
| 1671 |
+
"learning_rate": 6.833333333333333e-06,
|
| 1672 |
+
"loss": 0.154,
|
| 1673 |
+
"step": 1165
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.9713574097135741,
|
| 1677 |
+
"grad_norm": 0.13830389082431793,
|
| 1678 |
+
"learning_rate": 6e-06,
|
| 1679 |
+
"loss": 0.1373,
|
| 1680 |
+
"step": 1170
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.9755085097550851,
|
| 1684 |
+
"grad_norm": 0.1225619986653328,
|
| 1685 |
+
"learning_rate": 5.166666666666667e-06,
|
| 1686 |
+
"loss": 0.1522,
|
| 1687 |
+
"step": 1175
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.979659609796596,
|
| 1691 |
+
"grad_norm": 0.1404723823070526,
|
| 1692 |
+
"learning_rate": 4.333333333333334e-06,
|
| 1693 |
+
"loss": 0.1517,
|
| 1694 |
+
"step": 1180
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.9838107098381071,
|
| 1698 |
+
"grad_norm": 0.12082472443580627,
|
| 1699 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 1700 |
+
"loss": 0.1503,
|
| 1701 |
+
"step": 1185
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.9879618098796181,
|
| 1705 |
+
"grad_norm": 0.09916210919618607,
|
| 1706 |
+
"learning_rate": 2.666666666666667e-06,
|
| 1707 |
+
"loss": 0.1369,
|
| 1708 |
+
"step": 1190
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.9921129099211291,
|
| 1712 |
+
"grad_norm": 0.13724960386753082,
|
| 1713 |
+
"learning_rate": 1.8333333333333335e-06,
|
| 1714 |
+
"loss": 0.1304,
|
| 1715 |
+
"step": 1195
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.9962640099626401,
|
| 1719 |
+
"grad_norm": 0.13304875791072845,
|
| 1720 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1721 |
+
"loss": 0.1429,
|
| 1722 |
+
"step": 1200
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.9962640099626401,
|
| 1726 |
+
"eval_loss": 0.14440582692623138,
|
| 1727 |
+
"eval_runtime": 186.846,
|
| 1728 |
+
"eval_samples_per_second": 4.817,
|
| 1729 |
+
"eval_steps_per_second": 2.408,
|
| 1730 |
+
"step": 1200
|
| 1731 |
+
}
|
| 1732 |
+
],
|
| 1733 |
+
"logging_steps": 5,
|
| 1734 |
+
"max_steps": 1205,
|
| 1735 |
+
"num_input_tokens_seen": 0,
|
| 1736 |
+
"num_train_epochs": 1,
|
| 1737 |
+
"save_steps": 200,
|
| 1738 |
+
"stateful_callbacks": {
|
| 1739 |
+
"TrainerControl": {
|
| 1740 |
+
"args": {
|
| 1741 |
+
"should_epoch_stop": false,
|
| 1742 |
+
"should_evaluate": false,
|
| 1743 |
+
"should_log": false,
|
| 1744 |
+
"should_save": true,
|
| 1745 |
+
"should_training_stop": false
|
| 1746 |
+
},
|
| 1747 |
+
"attributes": {}
|
| 1748 |
+
}
|
| 1749 |
+
},
|
| 1750 |
+
"total_flos": 1.0590193691259955e+18,
|
| 1751 |
+
"train_batch_size": 10,
|
| 1752 |
+
"trial_name": null,
|
| 1753 |
+
"trial_params": null
|
| 1754 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d3c9c56184f5d8d7b68e83a22f6d77f9526e1012e8aa88632b3d7e2fb11870a
|
| 3 |
+
size 5713
|