Upload folder using huggingface_hub
Browse files- README.md +204 -0
- adapter_config.json +29 -0
- adapter_model.bin +3 -0
- qwen.tiktoken +0 -0
- special_tokens_map.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +1060 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: Qwen/Qwen-VL-Chat
|
| 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 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.8.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen-VL-Chat",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"w1",
|
| 23 |
+
"w2",
|
| 24 |
+
"c_attn",
|
| 25 |
+
"attn.c_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0319d03f0427062c389ce636d4c0304a58c64b304caa32bb3c800097c0cf7631
|
| 3 |
+
size 224482573
|
qwen.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "<|endoftext|>"
|
| 3 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": [
|
| 4 |
+
"Qwen/Qwen-VL-Chat--tokenization_qwen.QWenTokenizer",
|
| 5 |
+
null
|
| 6 |
+
]
|
| 7 |
+
},
|
| 8 |
+
"clean_up_tokenization_spaces": true,
|
| 9 |
+
"model_max_length": 1500,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"tokenizer_class": "QWenTokenizer"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1060 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8706070780754089,
|
| 3 |
+
"best_model_checkpoint": "ckpt/origin/pedes_rewrite/checkpoint-104",
|
| 4 |
+
"epoch": 5.804651162790698,
|
| 5 |
+
"eval_steps": 13,
|
| 6 |
+
"global_step": 156,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 14 |
+
"loss": 1.8602,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 6.666666666666667e-05,
|
| 20 |
+
"loss": 1.8321,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 0.0001,
|
| 26 |
+
"loss": 1.8243,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 9.999626433348663e-05,
|
| 32 |
+
"loss": 1.8373,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 9.998505789215469e-05,
|
| 38 |
+
"loss": 1.7732,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.22,
|
| 43 |
+
"learning_rate": 9.996638235054528e-05,
|
| 44 |
+
"loss": 1.7818,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"learning_rate": 9.994024049928221e-05,
|
| 50 |
+
"loss": 1.6944,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3,
|
| 55 |
+
"learning_rate": 9.990663624465504e-05,
|
| 56 |
+
"loss": 1.6106,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.33,
|
| 61 |
+
"learning_rate": 9.986557460803527e-05,
|
| 62 |
+
"loss": 1.6462,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.37,
|
| 67 |
+
"learning_rate": 9.981706172512619e-05,
|
| 68 |
+
"loss": 1.6212,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.41,
|
| 73 |
+
"learning_rate": 9.976110484504588e-05,
|
| 74 |
+
"loss": 1.6387,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.45,
|
| 79 |
+
"learning_rate": 9.969771232924403e-05,
|
| 80 |
+
"loss": 1.6043,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.48,
|
| 85 |
+
"learning_rate": 9.962689365025259e-05,
|
| 86 |
+
"loss": 1.5568,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.48,
|
| 91 |
+
"eval_loss": 1.5163209438323975,
|
| 92 |
+
"eval_runtime": 34.871,
|
| 93 |
+
"eval_samples_per_second": 1.434,
|
| 94 |
+
"eval_steps_per_second": 1.434,
|
| 95 |
+
"step": 13
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.52,
|
| 99 |
+
"learning_rate": 9.954865939027028e-05,
|
| 100 |
+
"loss": 1.4951,
|
| 101 |
+
"step": 14
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.56,
|
| 105 |
+
"learning_rate": 9.946302123958131e-05,
|
| 106 |
+
"loss": 1.4334,
|
| 107 |
+
"step": 15
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"learning_rate": 9.936999199480853e-05,
|
| 112 |
+
"loss": 1.4054,
|
| 113 |
+
"step": 16
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.63,
|
| 117 |
+
"learning_rate": 9.926958555700134e-05,
|
| 118 |
+
"loss": 1.4458,
|
| 119 |
+
"step": 17
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.67,
|
| 123 |
+
"learning_rate": 9.916181692955842e-05,
|
| 124 |
+
"loss": 1.3881,
|
| 125 |
+
"step": 18
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.71,
|
| 129 |
+
"learning_rate": 9.90467022159859e-05,
|
| 130 |
+
"loss": 1.3585,
|
| 131 |
+
"step": 19
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.74,
|
| 135 |
+
"learning_rate": 9.892425861749099e-05,
|
| 136 |
+
"loss": 1.3459,
|
| 137 |
+
"step": 20
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.78,
|
| 141 |
+
"learning_rate": 9.879450443041171e-05,
|
| 142 |
+
"loss": 1.3004,
|
| 143 |
+
"step": 21
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.82,
|
| 147 |
+
"learning_rate": 9.865745904348295e-05,
|
| 148 |
+
"loss": 1.2611,
|
| 149 |
+
"step": 22
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.86,
|
| 153 |
+
"learning_rate": 9.851314293493923e-05,
|
| 154 |
+
"loss": 1.3038,
|
| 155 |
+
"step": 23
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.89,
|
| 159 |
+
"learning_rate": 9.836157766945466e-05,
|
| 160 |
+
"loss": 1.2547,
|
| 161 |
+
"step": 24
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.93,
|
| 165 |
+
"learning_rate": 9.820278589492076e-05,
|
| 166 |
+
"loss": 1.2802,
|
| 167 |
+
"step": 25
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.97,
|
| 171 |
+
"learning_rate": 9.803679133906209e-05,
|
| 172 |
+
"loss": 1.1729,
|
| 173 |
+
"step": 26
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.97,
|
| 177 |
+
"eval_loss": 1.2355083227157593,
|
| 178 |
+
"eval_runtime": 34.8406,
|
| 179 |
+
"eval_samples_per_second": 1.435,
|
| 180 |
+
"eval_steps_per_second": 1.435,
|
| 181 |
+
"step": 26
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.0,
|
| 185 |
+
"learning_rate": 9.786361880589083e-05,
|
| 186 |
+
"loss": 1.2083,
|
| 187 |
+
"step": 27
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.04,
|
| 191 |
+
"learning_rate": 9.768329417200028e-05,
|
| 192 |
+
"loss": 1.1907,
|
| 193 |
+
"step": 28
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.08,
|
| 197 |
+
"learning_rate": 9.749584438269832e-05,
|
| 198 |
+
"loss": 1.1546,
|
| 199 |
+
"step": 29
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.12,
|
| 203 |
+
"learning_rate": 9.730129744798095e-05,
|
| 204 |
+
"loss": 1.1084,
|
| 205 |
+
"step": 30
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.15,
|
| 209 |
+
"learning_rate": 9.709968243834698e-05,
|
| 210 |
+
"loss": 1.112,
|
| 211 |
+
"step": 31
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.19,
|
| 215 |
+
"learning_rate": 9.689102948045397e-05,
|
| 216 |
+
"loss": 1.0599,
|
| 217 |
+
"step": 32
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.23,
|
| 221 |
+
"learning_rate": 9.667536975261667e-05,
|
| 222 |
+
"loss": 1.0952,
|
| 223 |
+
"step": 33
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.27,
|
| 227 |
+
"learning_rate": 9.6452735480148e-05,
|
| 228 |
+
"loss": 1.1067,
|
| 229 |
+
"step": 34
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.3,
|
| 233 |
+
"learning_rate": 9.622315993054383e-05,
|
| 234 |
+
"loss": 1.0152,
|
| 235 |
+
"step": 35
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.34,
|
| 239 |
+
"learning_rate": 9.598667740851187e-05,
|
| 240 |
+
"loss": 1.0704,
|
| 241 |
+
"step": 36
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.38,
|
| 245 |
+
"learning_rate": 9.574332325084563e-05,
|
| 246 |
+
"loss": 1.031,
|
| 247 |
+
"step": 37
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.41,
|
| 251 |
+
"learning_rate": 9.549313382114426e-05,
|
| 252 |
+
"loss": 1.0216,
|
| 253 |
+
"step": 38
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.45,
|
| 257 |
+
"learning_rate": 9.523614650437876e-05,
|
| 258 |
+
"loss": 1.0242,
|
| 259 |
+
"step": 39
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.45,
|
| 263 |
+
"eval_loss": 1.0572456121444702,
|
| 264 |
+
"eval_runtime": 34.7485,
|
| 265 |
+
"eval_samples_per_second": 1.439,
|
| 266 |
+
"eval_steps_per_second": 1.439,
|
| 267 |
+
"step": 39
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.49,
|
| 271 |
+
"learning_rate": 9.497239970130562e-05,
|
| 272 |
+
"loss": 0.9805,
|
| 273 |
+
"step": 40
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.53,
|
| 277 |
+
"learning_rate": 9.470193282272886e-05,
|
| 278 |
+
"loss": 0.9745,
|
| 279 |
+
"step": 41
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.56,
|
| 283 |
+
"learning_rate": 9.442478628361098e-05,
|
| 284 |
+
"loss": 0.9749,
|
| 285 |
+
"step": 42
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.6,
|
| 289 |
+
"learning_rate": 9.414100149703373e-05,
|
| 290 |
+
"loss": 0.9916,
|
| 291 |
+
"step": 43
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.64,
|
| 295 |
+
"learning_rate": 9.385062086801013e-05,
|
| 296 |
+
"loss": 0.9389,
|
| 297 |
+
"step": 44
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.67,
|
| 301 |
+
"learning_rate": 9.355368778714784e-05,
|
| 302 |
+
"loss": 0.9721,
|
| 303 |
+
"step": 45
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.71,
|
| 307 |
+
"learning_rate": 9.325024662416552e-05,
|
| 308 |
+
"loss": 0.9278,
|
| 309 |
+
"step": 46
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.75,
|
| 313 |
+
"learning_rate": 9.294034272126287e-05,
|
| 314 |
+
"loss": 0.922,
|
| 315 |
+
"step": 47
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.79,
|
| 319 |
+
"learning_rate": 9.262402238634515e-05,
|
| 320 |
+
"loss": 0.9192,
|
| 321 |
+
"step": 48
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.82,
|
| 325 |
+
"learning_rate": 9.230133288610366e-05,
|
| 326 |
+
"loss": 0.9203,
|
| 327 |
+
"step": 49
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.86,
|
| 331 |
+
"learning_rate": 9.197232243895284e-05,
|
| 332 |
+
"loss": 0.9317,
|
| 333 |
+
"step": 50
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.9,
|
| 337 |
+
"learning_rate": 9.163704020782507e-05,
|
| 338 |
+
"loss": 0.9355,
|
| 339 |
+
"step": 51
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.93,
|
| 343 |
+
"learning_rate": 9.129553629282448e-05,
|
| 344 |
+
"loss": 0.9027,
|
| 345 |
+
"step": 52
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.93,
|
| 349 |
+
"eval_loss": 0.9721283912658691,
|
| 350 |
+
"eval_runtime": 34.6767,
|
| 351 |
+
"eval_samples_per_second": 1.442,
|
| 352 |
+
"eval_steps_per_second": 1.442,
|
| 353 |
+
"step": 52
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.97,
|
| 357 |
+
"learning_rate": 9.094786172374066e-05,
|
| 358 |
+
"loss": 0.9358,
|
| 359 |
+
"step": 53
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.01,
|
| 363 |
+
"learning_rate": 9.059406845242342e-05,
|
| 364 |
+
"loss": 0.8565,
|
| 365 |
+
"step": 54
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.05,
|
| 369 |
+
"learning_rate": 9.02342093450198e-05,
|
| 370 |
+
"loss": 0.8217,
|
| 371 |
+
"step": 55
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.08,
|
| 375 |
+
"learning_rate": 8.986833817407449e-05,
|
| 376 |
+
"loss": 0.8717,
|
| 377 |
+
"step": 56
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.12,
|
| 381 |
+
"learning_rate": 8.949650961049478e-05,
|
| 382 |
+
"loss": 0.8637,
|
| 383 |
+
"step": 57
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.16,
|
| 387 |
+
"learning_rate": 8.911877921538117e-05,
|
| 388 |
+
"loss": 0.8261,
|
| 389 |
+
"step": 58
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.2,
|
| 393 |
+
"learning_rate": 8.87352034317252e-05,
|
| 394 |
+
"loss": 0.7963,
|
| 395 |
+
"step": 59
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.23,
|
| 399 |
+
"learning_rate": 8.834583957597529e-05,
|
| 400 |
+
"loss": 0.8731,
|
| 401 |
+
"step": 60
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.27,
|
| 405 |
+
"learning_rate": 8.795074582947214e-05,
|
| 406 |
+
"loss": 0.8759,
|
| 407 |
+
"step": 61
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.31,
|
| 411 |
+
"learning_rate": 8.754998122975489e-05,
|
| 412 |
+
"loss": 0.8333,
|
| 413 |
+
"step": 62
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.34,
|
| 417 |
+
"learning_rate": 8.714360566173931e-05,
|
| 418 |
+
"loss": 0.7972,
|
| 419 |
+
"step": 63
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.38,
|
| 423 |
+
"learning_rate": 8.673167984876949e-05,
|
| 424 |
+
"loss": 0.8378,
|
| 425 |
+
"step": 64
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.42,
|
| 429 |
+
"learning_rate": 8.631426534354403e-05,
|
| 430 |
+
"loss": 0.8188,
|
| 431 |
+
"step": 65
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.42,
|
| 435 |
+
"eval_loss": 0.9200485944747925,
|
| 436 |
+
"eval_runtime": 34.696,
|
| 437 |
+
"eval_samples_per_second": 1.441,
|
| 438 |
+
"eval_steps_per_second": 1.441,
|
| 439 |
+
"step": 65
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.46,
|
| 443 |
+
"learning_rate": 8.58914245189185e-05,
|
| 444 |
+
"loss": 0.774,
|
| 445 |
+
"step": 66
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.49,
|
| 449 |
+
"learning_rate": 8.546322055858526e-05,
|
| 450 |
+
"loss": 0.8312,
|
| 451 |
+
"step": 67
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.53,
|
| 455 |
+
"learning_rate": 8.502971744763215e-05,
|
| 456 |
+
"loss": 0.8011,
|
| 457 |
+
"step": 68
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.57,
|
| 461 |
+
"learning_rate": 8.459097996298137e-05,
|
| 462 |
+
"loss": 0.7958,
|
| 463 |
+
"step": 69
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.6,
|
| 467 |
+
"learning_rate": 8.414707366371007e-05,
|
| 468 |
+
"loss": 0.7647,
|
| 469 |
+
"step": 70
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.64,
|
| 473 |
+
"learning_rate": 8.369806488125418e-05,
|
| 474 |
+
"loss": 0.8322,
|
| 475 |
+
"step": 71
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.68,
|
| 479 |
+
"learning_rate": 8.324402070949658e-05,
|
| 480 |
+
"loss": 0.7983,
|
| 481 |
+
"step": 72
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.72,
|
| 485 |
+
"learning_rate": 8.278500899474163e-05,
|
| 486 |
+
"loss": 0.7903,
|
| 487 |
+
"step": 73
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.75,
|
| 491 |
+
"learning_rate": 8.232109832557696e-05,
|
| 492 |
+
"loss": 0.765,
|
| 493 |
+
"step": 74
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.79,
|
| 497 |
+
"learning_rate": 8.185235802262469e-05,
|
| 498 |
+
"loss": 0.7847,
|
| 499 |
+
"step": 75
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.83,
|
| 503 |
+
"learning_rate": 8.137885812818295e-05,
|
| 504 |
+
"loss": 0.7789,
|
| 505 |
+
"step": 76
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.87,
|
| 509 |
+
"learning_rate": 8.09006693957597e-05,
|
| 510 |
+
"loss": 0.7802,
|
| 511 |
+
"step": 77
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.9,
|
| 515 |
+
"learning_rate": 8.041786327950036e-05,
|
| 516 |
+
"loss": 0.7535,
|
| 517 |
+
"step": 78
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.9,
|
| 521 |
+
"eval_loss": 0.8959811925888062,
|
| 522 |
+
"eval_runtime": 34.7154,
|
| 523 |
+
"eval_samples_per_second": 1.44,
|
| 524 |
+
"eval_steps_per_second": 1.44,
|
| 525 |
+
"step": 78
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.94,
|
| 529 |
+
"learning_rate": 7.993051192351057e-05,
|
| 530 |
+
"loss": 0.7877,
|
| 531 |
+
"step": 79
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.98,
|
| 535 |
+
"learning_rate": 7.943868815107594e-05,
|
| 536 |
+
"loss": 0.7804,
|
| 537 |
+
"step": 80
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.01,
|
| 541 |
+
"learning_rate": 7.894246545378037e-05,
|
| 542 |
+
"loss": 0.7512,
|
| 543 |
+
"step": 81
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.05,
|
| 547 |
+
"learning_rate": 7.844191798052438e-05,
|
| 548 |
+
"loss": 0.713,
|
| 549 |
+
"step": 82
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.09,
|
| 553 |
+
"learning_rate": 7.793712052644535e-05,
|
| 554 |
+
"loss": 0.7655,
|
| 555 |
+
"step": 83
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.13,
|
| 559 |
+
"learning_rate": 7.742814852174112e-05,
|
| 560 |
+
"loss": 0.6954,
|
| 561 |
+
"step": 84
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.16,
|
| 565 |
+
"learning_rate": 7.691507802039862e-05,
|
| 566 |
+
"loss": 0.7137,
|
| 567 |
+
"step": 85
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.2,
|
| 571 |
+
"learning_rate": 7.639798568882947e-05,
|
| 572 |
+
"loss": 0.7439,
|
| 573 |
+
"step": 86
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.24,
|
| 577 |
+
"learning_rate": 7.587694879441401e-05,
|
| 578 |
+
"loss": 0.7458,
|
| 579 |
+
"step": 87
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.27,
|
| 583 |
+
"learning_rate": 7.535204519395538e-05,
|
| 584 |
+
"loss": 0.7443,
|
| 585 |
+
"step": 88
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.31,
|
| 589 |
+
"learning_rate": 7.482335332204568e-05,
|
| 590 |
+
"loss": 0.7162,
|
| 591 |
+
"step": 89
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.35,
|
| 595 |
+
"learning_rate": 7.429095217934577e-05,
|
| 596 |
+
"loss": 0.7134,
|
| 597 |
+
"step": 90
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.39,
|
| 601 |
+
"learning_rate": 7.375492132078052e-05,
|
| 602 |
+
"loss": 0.7311,
|
| 603 |
+
"step": 91
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.39,
|
| 607 |
+
"eval_loss": 0.8750792741775513,
|
| 608 |
+
"eval_runtime": 34.7072,
|
| 609 |
+
"eval_samples_per_second": 1.441,
|
| 610 |
+
"eval_steps_per_second": 1.441,
|
| 611 |
+
"step": 91
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.42,
|
| 615 |
+
"learning_rate": 7.321534084365102e-05,
|
| 616 |
+
"loss": 0.6978,
|
| 617 |
+
"step": 92
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.46,
|
| 621 |
+
"learning_rate": 7.267229137566607e-05,
|
| 622 |
+
"loss": 0.7277,
|
| 623 |
+
"step": 93
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 3.5,
|
| 627 |
+
"learning_rate": 7.212585406289418e-05,
|
| 628 |
+
"loss": 0.7412,
|
| 629 |
+
"step": 94
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.53,
|
| 633 |
+
"learning_rate": 7.157611055763819e-05,
|
| 634 |
+
"loss": 0.6875,
|
| 635 |
+
"step": 95
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 3.57,
|
| 639 |
+
"learning_rate": 7.102314300623426e-05,
|
| 640 |
+
"loss": 0.68,
|
| 641 |
+
"step": 96
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.61,
|
| 645 |
+
"learning_rate": 7.046703403677695e-05,
|
| 646 |
+
"loss": 0.6764,
|
| 647 |
+
"step": 97
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 3.65,
|
| 651 |
+
"learning_rate": 6.990786674677245e-05,
|
| 652 |
+
"loss": 0.675,
|
| 653 |
+
"step": 98
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.68,
|
| 657 |
+
"learning_rate": 6.934572469072162e-05,
|
| 658 |
+
"loss": 0.7028,
|
| 659 |
+
"step": 99
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.72,
|
| 663 |
+
"learning_rate": 6.878069186763465e-05,
|
| 664 |
+
"loss": 0.6985,
|
| 665 |
+
"step": 100
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.76,
|
| 669 |
+
"learning_rate": 6.821285270847934e-05,
|
| 670 |
+
"loss": 0.7309,
|
| 671 |
+
"step": 101
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 3.8,
|
| 675 |
+
"learning_rate": 6.764229206356498e-05,
|
| 676 |
+
"loss": 0.6851,
|
| 677 |
+
"step": 102
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.83,
|
| 681 |
+
"learning_rate": 6.70690951898634e-05,
|
| 682 |
+
"loss": 0.6568,
|
| 683 |
+
"step": 103
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.87,
|
| 687 |
+
"learning_rate": 6.649334773826924e-05,
|
| 688 |
+
"loss": 0.6845,
|
| 689 |
+
"step": 104
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.87,
|
| 693 |
+
"eval_loss": 0.8706070780754089,
|
| 694 |
+
"eval_runtime": 34.6892,
|
| 695 |
+
"eval_samples_per_second": 1.441,
|
| 696 |
+
"eval_steps_per_second": 1.441,
|
| 697 |
+
"step": 104
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.91,
|
| 701 |
+
"learning_rate": 6.591513574080151e-05,
|
| 702 |
+
"loss": 0.6993,
|
| 703 |
+
"step": 105
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.94,
|
| 707 |
+
"learning_rate": 6.533454559774807e-05,
|
| 708 |
+
"loss": 0.6635,
|
| 709 |
+
"step": 106
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.98,
|
| 713 |
+
"learning_rate": 6.475166406475515e-05,
|
| 714 |
+
"loss": 0.7059,
|
| 715 |
+
"step": 107
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 4.02,
|
| 719 |
+
"learning_rate": 6.41665782398637e-05,
|
| 720 |
+
"loss": 0.6543,
|
| 721 |
+
"step": 108
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 4.06,
|
| 725 |
+
"learning_rate": 6.357937555049464e-05,
|
| 726 |
+
"loss": 0.6807,
|
| 727 |
+
"step": 109
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 4.09,
|
| 731 |
+
"learning_rate": 6.299014374038493e-05,
|
| 732 |
+
"loss": 0.6573,
|
| 733 |
+
"step": 110
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.13,
|
| 737 |
+
"learning_rate": 6.239897085647623e-05,
|
| 738 |
+
"loss": 0.6481,
|
| 739 |
+
"step": 111
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 4.17,
|
| 743 |
+
"learning_rate": 6.180594523575838e-05,
|
| 744 |
+
"loss": 0.6209,
|
| 745 |
+
"step": 112
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 4.2,
|
| 749 |
+
"learning_rate": 6.121115549206949e-05,
|
| 750 |
+
"loss": 0.6125,
|
| 751 |
+
"step": 113
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.24,
|
| 755 |
+
"learning_rate": 6.061469050285469e-05,
|
| 756 |
+
"loss": 0.6703,
|
| 757 |
+
"step": 114
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 4.28,
|
| 761 |
+
"learning_rate": 6.001663939588542e-05,
|
| 762 |
+
"loss": 0.6821,
|
| 763 |
+
"step": 115
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 4.32,
|
| 767 |
+
"learning_rate": 5.941709153594146e-05,
|
| 768 |
+
"loss": 0.6885,
|
| 769 |
+
"step": 116
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 4.35,
|
| 773 |
+
"learning_rate": 5.881613651145732e-05,
|
| 774 |
+
"loss": 0.6598,
|
| 775 |
+
"step": 117
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 4.35,
|
| 779 |
+
"eval_loss": 0.8761024475097656,
|
| 780 |
+
"eval_runtime": 34.7313,
|
| 781 |
+
"eval_samples_per_second": 1.44,
|
| 782 |
+
"eval_steps_per_second": 1.44,
|
| 783 |
+
"step": 117
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.39,
|
| 787 |
+
"learning_rate": 5.821386412113545e-05,
|
| 788 |
+
"loss": 0.6081,
|
| 789 |
+
"step": 118
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 4.43,
|
| 793 |
+
"learning_rate": 5.761036436052788e-05,
|
| 794 |
+
"loss": 0.6263,
|
| 795 |
+
"step": 119
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 4.47,
|
| 799 |
+
"learning_rate": 5.700572740858847e-05,
|
| 800 |
+
"loss": 0.6068,
|
| 801 |
+
"step": 120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.5,
|
| 805 |
+
"learning_rate": 5.640004361419776e-05,
|
| 806 |
+
"loss": 0.626,
|
| 807 |
+
"step": 121
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.54,
|
| 811 |
+
"learning_rate": 5.579340348266251e-05,
|
| 812 |
+
"loss": 0.6514,
|
| 813 |
+
"step": 122
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.58,
|
| 817 |
+
"learning_rate": 5.518589766219172e-05,
|
| 818 |
+
"loss": 0.6156,
|
| 819 |
+
"step": 123
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.61,
|
| 823 |
+
"learning_rate": 5.4577616930351385e-05,
|
| 824 |
+
"loss": 0.6637,
|
| 825 |
+
"step": 124
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.65,
|
| 829 |
+
"learning_rate": 5.396865218049995e-05,
|
| 830 |
+
"loss": 0.6058,
|
| 831 |
+
"step": 125
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 4.69,
|
| 835 |
+
"learning_rate": 5.3359094408206345e-05,
|
| 836 |
+
"loss": 0.6208,
|
| 837 |
+
"step": 126
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.73,
|
| 841 |
+
"learning_rate": 5.27490346976529e-05,
|
| 842 |
+
"loss": 0.6259,
|
| 843 |
+
"step": 127
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.76,
|
| 847 |
+
"learning_rate": 5.21385642080249e-05,
|
| 848 |
+
"loss": 0.6001,
|
| 849 |
+
"step": 128
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.8,
|
| 853 |
+
"learning_rate": 5.152777415988894e-05,
|
| 854 |
+
"loss": 0.6447,
|
| 855 |
+
"step": 129
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.84,
|
| 859 |
+
"learning_rate": 5.0916755821562237e-05,
|
| 860 |
+
"loss": 0.5753,
|
| 861 |
+
"step": 130
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.84,
|
| 865 |
+
"eval_loss": 0.8741121888160706,
|
| 866 |
+
"eval_runtime": 34.7416,
|
| 867 |
+
"eval_samples_per_second": 1.439,
|
| 868 |
+
"eval_steps_per_second": 1.439,
|
| 869 |
+
"step": 130
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 4.87,
|
| 873 |
+
"learning_rate": 5.030560049547458e-05,
|
| 874 |
+
"loss": 0.6011,
|
| 875 |
+
"step": 131
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 4.91,
|
| 879 |
+
"learning_rate": 4.969439950452543e-05,
|
| 880 |
+
"loss": 0.6303,
|
| 881 |
+
"step": 132
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 4.95,
|
| 885 |
+
"learning_rate": 4.908324417843778e-05,
|
| 886 |
+
"loss": 0.6238,
|
| 887 |
+
"step": 133
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 4.99,
|
| 891 |
+
"learning_rate": 4.847222584011106e-05,
|
| 892 |
+
"loss": 0.623,
|
| 893 |
+
"step": 134
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 5.02,
|
| 897 |
+
"learning_rate": 4.7861435791975126e-05,
|
| 898 |
+
"loss": 0.5594,
|
| 899 |
+
"step": 135
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 5.06,
|
| 903 |
+
"learning_rate": 4.72509653023471e-05,
|
| 904 |
+
"loss": 0.5714,
|
| 905 |
+
"step": 136
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 5.1,
|
| 909 |
+
"learning_rate": 4.664090559179367e-05,
|
| 910 |
+
"loss": 0.6115,
|
| 911 |
+
"step": 137
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 5.13,
|
| 915 |
+
"learning_rate": 4.603134781950006e-05,
|
| 916 |
+
"loss": 0.5987,
|
| 917 |
+
"step": 138
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 5.17,
|
| 921 |
+
"learning_rate": 4.542238306964863e-05,
|
| 922 |
+
"loss": 0.5588,
|
| 923 |
+
"step": 139
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 5.21,
|
| 927 |
+
"learning_rate": 4.4814102337808293e-05,
|
| 928 |
+
"loss": 0.5612,
|
| 929 |
+
"step": 140
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 5.25,
|
| 933 |
+
"learning_rate": 4.420659651733751e-05,
|
| 934 |
+
"loss": 0.5595,
|
| 935 |
+
"step": 141
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 5.28,
|
| 939 |
+
"learning_rate": 4.359995638580226e-05,
|
| 940 |
+
"loss": 0.5534,
|
| 941 |
+
"step": 142
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 5.32,
|
| 945 |
+
"learning_rate": 4.2994272591411556e-05,
|
| 946 |
+
"loss": 0.5499,
|
| 947 |
+
"step": 143
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 5.32,
|
| 951 |
+
"eval_loss": 0.897064745426178,
|
| 952 |
+
"eval_runtime": 34.7112,
|
| 953 |
+
"eval_samples_per_second": 1.44,
|
| 954 |
+
"eval_steps_per_second": 1.44,
|
| 955 |
+
"step": 143
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 5.36,
|
| 959 |
+
"learning_rate": 4.238963563947212e-05,
|
| 960 |
+
"loss": 0.5902,
|
| 961 |
+
"step": 144
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 5.4,
|
| 965 |
+
"learning_rate": 4.178613587886455e-05,
|
| 966 |
+
"loss": 0.5371,
|
| 967 |
+
"step": 145
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 5.43,
|
| 971 |
+
"learning_rate": 4.118386348854269e-05,
|
| 972 |
+
"loss": 0.5798,
|
| 973 |
+
"step": 146
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 5.47,
|
| 977 |
+
"learning_rate": 4.0582908464058556e-05,
|
| 978 |
+
"loss": 0.5681,
|
| 979 |
+
"step": 147
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 5.51,
|
| 983 |
+
"learning_rate": 3.998336060411459e-05,
|
| 984 |
+
"loss": 0.5851,
|
| 985 |
+
"step": 148
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 5.54,
|
| 989 |
+
"learning_rate": 3.938530949714533e-05,
|
| 990 |
+
"loss": 0.5849,
|
| 991 |
+
"step": 149
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 5.58,
|
| 995 |
+
"learning_rate": 3.878884450793053e-05,
|
| 996 |
+
"loss": 0.5968,
|
| 997 |
+
"step": 150
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 5.62,
|
| 1001 |
+
"learning_rate": 3.819405476424163e-05,
|
| 1002 |
+
"loss": 0.5533,
|
| 1003 |
+
"step": 151
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 5.66,
|
| 1007 |
+
"learning_rate": 3.7601029143523764e-05,
|
| 1008 |
+
"loss": 0.5724,
|
| 1009 |
+
"step": 152
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 5.69,
|
| 1013 |
+
"learning_rate": 3.700985625961507e-05,
|
| 1014 |
+
"loss": 0.5314,
|
| 1015 |
+
"step": 153
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 5.73,
|
| 1019 |
+
"learning_rate": 3.642062444950537e-05,
|
| 1020 |
+
"loss": 0.5572,
|
| 1021 |
+
"step": 154
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 5.77,
|
| 1025 |
+
"learning_rate": 3.5833421760136324e-05,
|
| 1026 |
+
"loss": 0.5895,
|
| 1027 |
+
"step": 155
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 5.8,
|
| 1031 |
+
"learning_rate": 3.524833593524487e-05,
|
| 1032 |
+
"loss": 0.5349,
|
| 1033 |
+
"step": 156
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 5.8,
|
| 1037 |
+
"eval_loss": 0.8920581936836243,
|
| 1038 |
+
"eval_runtime": 34.8827,
|
| 1039 |
+
"eval_samples_per_second": 1.433,
|
| 1040 |
+
"eval_steps_per_second": 1.433,
|
| 1041 |
+
"step": 156
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 5.8,
|
| 1045 |
+
"step": 156,
|
| 1046 |
+
"total_flos": 6.16421344002048e+17,
|
| 1047 |
+
"train_loss": 0.8834368617106707,
|
| 1048 |
+
"train_runtime": 13302.0563,
|
| 1049 |
+
"train_samples_per_second": 0.97,
|
| 1050 |
+
"train_steps_per_second": 0.02
|
| 1051 |
+
}
|
| 1052 |
+
],
|
| 1053 |
+
"logging_steps": 1.0,
|
| 1054 |
+
"max_steps": 260,
|
| 1055 |
+
"num_train_epochs": 10,
|
| 1056 |
+
"save_steps": 26,
|
| 1057 |
+
"total_flos": 6.16421344002048e+17,
|
| 1058 |
+
"trial_name": null,
|
| 1059 |
+
"trial_params": null
|
| 1060 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20749b17efd5cd3db2b04f603da56809d745b209c5e70c3f56eab55478d9da3c
|
| 3 |
+
size 4155
|