Training in progress, epoch 5, checkpoint
Browse files- checkpoint-189/README.md +219 -0
- checkpoint-189/adapter_config.json +28 -0
- checkpoint-189/adapter_model.safetensors +3 -0
- checkpoint-189/optimizer.pt +3 -0
- checkpoint-189/rng_state.pth +3 -0
- checkpoint-189/scheduler.pt +3 -0
- checkpoint-189/trainer_state.json +1217 -0
- checkpoint-189/training_args.bin +3 -0
checkpoint-189/README.md
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: yentinglin/Taiwan-LLM-7B-v2.0-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 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 22 |
+
- **Model type:** [More Information Needed]
|
| 23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 24 |
+
- **License:** [More Information Needed]
|
| 25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 26 |
+
|
| 27 |
+
### Model Sources [optional]
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** [More Information Needed]
|
| 32 |
+
- **Paper [optional]:** [More Information Needed]
|
| 33 |
+
- **Demo [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
## Uses
|
| 36 |
+
|
| 37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 38 |
+
|
| 39 |
+
### Direct Use
|
| 40 |
+
|
| 41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 42 |
+
|
| 43 |
+
[More Information Needed]
|
| 44 |
+
|
| 45 |
+
### Downstream Use [optional]
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Out-of-Scope Use
|
| 52 |
+
|
| 53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
## Bias, Risks, and Limitations
|
| 58 |
+
|
| 59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
### Recommendations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 66 |
+
|
| 67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 68 |
+
|
| 69 |
+
## How to Get Started with the Model
|
| 70 |
+
|
| 71 |
+
Use the code below to get started with the model.
|
| 72 |
+
|
| 73 |
+
[More Information Needed]
|
| 74 |
+
|
| 75 |
+
## Training Details
|
| 76 |
+
|
| 77 |
+
### Training Data
|
| 78 |
+
|
| 79 |
+
<!-- This should link to a Data 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. -->
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
### Training Procedure
|
| 84 |
+
|
| 85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 86 |
+
|
| 87 |
+
#### Preprocessing [optional]
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
#### Training Hyperparameters
|
| 93 |
+
|
| 94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 95 |
+
|
| 96 |
+
#### Speeds, Sizes, Times [optional]
|
| 97 |
+
|
| 98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 99 |
+
|
| 100 |
+
[More Information Needed]
|
| 101 |
+
|
| 102 |
+
## Evaluation
|
| 103 |
+
|
| 104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 105 |
+
|
| 106 |
+
### Testing Data, Factors & Metrics
|
| 107 |
+
|
| 108 |
+
#### Testing Data
|
| 109 |
+
|
| 110 |
+
<!-- This should link to a Data Card if possible. -->
|
| 111 |
+
|
| 112 |
+
[More Information Needed]
|
| 113 |
+
|
| 114 |
+
#### Factors
|
| 115 |
+
|
| 116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Metrics
|
| 121 |
+
|
| 122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
### Results
|
| 127 |
+
|
| 128 |
+
[More Information Needed]
|
| 129 |
+
|
| 130 |
+
#### Summary
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
## Model Examination [optional]
|
| 135 |
+
|
| 136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
## Environmental Impact
|
| 141 |
+
|
| 142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 143 |
+
|
| 144 |
+
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).
|
| 145 |
+
|
| 146 |
+
- **Hardware Type:** [More Information Needed]
|
| 147 |
+
- **Hours used:** [More Information Needed]
|
| 148 |
+
- **Cloud Provider:** [More Information Needed]
|
| 149 |
+
- **Compute Region:** [More Information Needed]
|
| 150 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 151 |
+
|
| 152 |
+
## Technical Specifications [optional]
|
| 153 |
+
|
| 154 |
+
### Model Architecture and Objective
|
| 155 |
+
|
| 156 |
+
[More Information Needed]
|
| 157 |
+
|
| 158 |
+
### Compute Infrastructure
|
| 159 |
+
|
| 160 |
+
[More Information Needed]
|
| 161 |
+
|
| 162 |
+
#### Hardware
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
#### Software
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
## Citation [optional]
|
| 171 |
+
|
| 172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 173 |
+
|
| 174 |
+
**BibTeX:**
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
**APA:**
|
| 179 |
+
|
| 180 |
+
[More Information Needed]
|
| 181 |
+
|
| 182 |
+
## Glossary [optional]
|
| 183 |
+
|
| 184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## More Information [optional]
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
## Model Card Authors [optional]
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Model Card Contact
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
## Training procedure
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
+
- quant_method: bitsandbytes
|
| 206 |
+
- load_in_8bit: False
|
| 207 |
+
- load_in_4bit: True
|
| 208 |
+
- llm_int8_threshold: 6.0
|
| 209 |
+
- llm_int8_skip_modules: None
|
| 210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
+
- llm_int8_has_fp16_weight: False
|
| 212 |
+
- bnb_4bit_quant_type: nf4
|
| 213 |
+
- bnb_4bit_use_double_quant: True
|
| 214 |
+
- bnb_4bit_compute_dtype: float16
|
| 215 |
+
|
| 216 |
+
### Framework versions
|
| 217 |
+
|
| 218 |
+
|
| 219 |
+
- PEFT 0.6.0
|
checkpoint-189/adapter_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.075,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"up_proj",
|
| 21 |
+
"down_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"q_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM"
|
| 28 |
+
}
|
checkpoint-189/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c1a563d806306f6283679f0e1c975d82d0a661aa4a9196881ebed11ec6a8fef
|
| 3 |
+
size 159967880
|
checkpoint-189/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1a7ce47e0466f9a093d1928c27aac6e8e1656061fca50a09b59920b85f22a8
|
| 3 |
+
size 320084037
|
checkpoint-189/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ff0f99f0b51c51a3980c22b48595ede40878bf663cb28680406994f6908fc8b
|
| 3 |
+
size 14575
|
checkpoint-189/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7906fc8f93db36c6762b0c0a281695891ee2069123b9da6a1b62b1cdabd459e7
|
| 3 |
+
size 627
|
checkpoint-189/trainer_state.json
ADDED
|
@@ -0,0 +1,1217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.995967741935484,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 189,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 4.2505,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"eval_loss": 4.052073955535889,
|
| 20 |
+
"eval_runtime": 60.4806,
|
| 21 |
+
"eval_samples_per_second": 4.134,
|
| 22 |
+
"eval_steps_per_second": 4.134,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06,
|
| 27 |
+
"learning_rate": 0.0001,
|
| 28 |
+
"loss": 4.2141,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.1,
|
| 33 |
+
"learning_rate": 0.00015,
|
| 34 |
+
"loss": 4.0033,
|
| 35 |
+
"step": 3
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.13,
|
| 39 |
+
"learning_rate": 0.0002,
|
| 40 |
+
"loss": 3.9023,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.16,
|
| 45 |
+
"learning_rate": 0.00025,
|
| 46 |
+
"loss": 4.0955,
|
| 47 |
+
"step": 5
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.19,
|
| 51 |
+
"learning_rate": 0.0003,
|
| 52 |
+
"loss": 3.8902,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.23,
|
| 57 |
+
"learning_rate": 0.00035,
|
| 58 |
+
"loss": 3.9076,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.26,
|
| 63 |
+
"learning_rate": 0.0004,
|
| 64 |
+
"loss": 3.7008,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.29,
|
| 69 |
+
"learning_rate": 0.00045000000000000004,
|
| 70 |
+
"loss": 3.7071,
|
| 71 |
+
"step": 9
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.32,
|
| 75 |
+
"learning_rate": 0.0005,
|
| 76 |
+
"loss": 3.6304,
|
| 77 |
+
"step": 10
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.35,
|
| 81 |
+
"learning_rate": 0.0004999782204181027,
|
| 82 |
+
"loss": 3.6851,
|
| 83 |
+
"step": 11
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.39,
|
| 87 |
+
"learning_rate": 0.0004999128854672123,
|
| 88 |
+
"loss": 3.4864,
|
| 89 |
+
"step": 12
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.42,
|
| 93 |
+
"learning_rate": 0.000499804006531072,
|
| 94 |
+
"loss": 3.3743,
|
| 95 |
+
"step": 13
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.45,
|
| 99 |
+
"learning_rate": 0.0004996516025803834,
|
| 100 |
+
"loss": 3.2944,
|
| 101 |
+
"step": 14
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.48,
|
| 105 |
+
"learning_rate": 0.0004994557001695014,
|
| 106 |
+
"loss": 3.1978,
|
| 107 |
+
"step": 15
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.52,
|
| 111 |
+
"learning_rate": 0.0004992163334318065,
|
| 112 |
+
"loss": 3.0865,
|
| 113 |
+
"step": 16
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.55,
|
| 117 |
+
"learning_rate": 0.0004989335440737586,
|
| 118 |
+
"loss": 3.0893,
|
| 119 |
+
"step": 17
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.58,
|
| 123 |
+
"learning_rate": 0.0004986073813676296,
|
| 124 |
+
"loss": 2.9218,
|
| 125 |
+
"step": 18
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.61,
|
| 129 |
+
"learning_rate": 0.0004982379021429183,
|
| 130 |
+
"loss": 2.8753,
|
| 131 |
+
"step": 19
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.65,
|
| 135 |
+
"learning_rate": 0.0004978251707764492,
|
| 136 |
+
"loss": 2.7118,
|
| 137 |
+
"step": 20
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.68,
|
| 141 |
+
"learning_rate": 0.0004973692591811548,
|
| 142 |
+
"loss": 2.6693,
|
| 143 |
+
"step": 21
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.71,
|
| 147 |
+
"learning_rate": 0.0004968702467935468,
|
| 148 |
+
"loss": 2.474,
|
| 149 |
+
"step": 22
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.74,
|
| 153 |
+
"learning_rate": 0.0004963282205598744,
|
| 154 |
+
"loss": 2.3912,
|
| 155 |
+
"step": 23
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.77,
|
| 159 |
+
"learning_rate": 0.0004957432749209755,
|
| 160 |
+
"loss": 2.2401,
|
| 161 |
+
"step": 24
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.81,
|
| 165 |
+
"learning_rate": 0.0004951155117958217,
|
| 166 |
+
"loss": 2.1461,
|
| 167 |
+
"step": 25
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.81,
|
| 171 |
+
"eval_loss": 2.080416202545166,
|
| 172 |
+
"eval_runtime": 61.4527,
|
| 173 |
+
"eval_samples_per_second": 4.068,
|
| 174 |
+
"eval_steps_per_second": 4.068,
|
| 175 |
+
"step": 25
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.84,
|
| 179 |
+
"learning_rate": 0.0004944450405637602,
|
| 180 |
+
"loss": 2.1114,
|
| 181 |
+
"step": 26
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.87,
|
| 185 |
+
"learning_rate": 0.0004937319780454559,
|
| 186 |
+
"loss": 1.8994,
|
| 187 |
+
"step": 27
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.9,
|
| 191 |
+
"learning_rate": 0.0004929764484825369,
|
| 192 |
+
"loss": 2.0342,
|
| 193 |
+
"step": 28
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.94,
|
| 197 |
+
"learning_rate": 0.0004921785835159472,
|
| 198 |
+
"loss": 2.0333,
|
| 199 |
+
"step": 29
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.97,
|
| 203 |
+
"learning_rate": 0.0004913385221630097,
|
| 204 |
+
"loss": 1.8424,
|
| 205 |
+
"step": 30
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.0,
|
| 209 |
+
"learning_rate": 0.0004904564107932048,
|
| 210 |
+
"loss": 1.7993,
|
| 211 |
+
"step": 31
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.01,
|
| 215 |
+
"learning_rate": 0.000489532403102667,
|
| 216 |
+
"loss": 1.7643,
|
| 217 |
+
"step": 32
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.04,
|
| 221 |
+
"learning_rate": 0.0004885666600874058,
|
| 222 |
+
"loss": 1.8718,
|
| 223 |
+
"step": 33
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.07,
|
| 227 |
+
"learning_rate": 0.00048755935001525374,
|
| 228 |
+
"loss": 1.7178,
|
| 229 |
+
"step": 34
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.11,
|
| 233 |
+
"learning_rate": 0.0004865106483965487,
|
| 234 |
+
"loss": 1.7185,
|
| 235 |
+
"step": 35
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.14,
|
| 239 |
+
"learning_rate": 0.0004854207379535529,
|
| 240 |
+
"loss": 1.7702,
|
| 241 |
+
"step": 36
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.17,
|
| 245 |
+
"learning_rate": 0.00048428980858861636,
|
| 246 |
+
"loss": 1.7089,
|
| 247 |
+
"step": 37
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.2,
|
| 251 |
+
"learning_rate": 0.00048311805735108893,
|
| 252 |
+
"loss": 1.6515,
|
| 253 |
+
"step": 38
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.24,
|
| 257 |
+
"learning_rate": 0.000481905688402987,
|
| 258 |
+
"loss": 1.7014,
|
| 259 |
+
"step": 39
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.27,
|
| 263 |
+
"learning_rate": 0.0004806529129834207,
|
| 264 |
+
"loss": 1.5697,
|
| 265 |
+
"step": 40
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.3,
|
| 269 |
+
"learning_rate": 0.0004793599493717891,
|
| 270 |
+
"loss": 1.6295,
|
| 271 |
+
"step": 41
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.33,
|
| 275 |
+
"learning_rate": 0.00047802702284974695,
|
| 276 |
+
"loss": 1.4599,
|
| 277 |
+
"step": 42
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.36,
|
| 281 |
+
"learning_rate": 0.0004766543656619532,
|
| 282 |
+
"loss": 1.5082,
|
| 283 |
+
"step": 43
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.4,
|
| 287 |
+
"learning_rate": 0.00047524221697560476,
|
| 288 |
+
"loss": 1.4499,
|
| 289 |
+
"step": 44
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.43,
|
| 293 |
+
"learning_rate": 0.00047379082283876563,
|
| 294 |
+
"loss": 1.432,
|
| 295 |
+
"step": 45
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.46,
|
| 299 |
+
"learning_rate": 0.0004723004361374953,
|
| 300 |
+
"loss": 1.4362,
|
| 301 |
+
"step": 46
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.49,
|
| 305 |
+
"learning_rate": 0.0004707713165517877,
|
| 306 |
+
"loss": 1.4588,
|
| 307 |
+
"step": 47
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.53,
|
| 311 |
+
"learning_rate": 0.0004692037305103247,
|
| 312 |
+
"loss": 1.4489,
|
| 313 |
+
"step": 48
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.56,
|
| 317 |
+
"learning_rate": 0.0004675979511440549,
|
| 318 |
+
"loss": 1.3382,
|
| 319 |
+
"step": 49
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.59,
|
| 323 |
+
"learning_rate": 0.00046595425823860404,
|
| 324 |
+
"loss": 1.3896,
|
| 325 |
+
"step": 50
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.59,
|
| 329 |
+
"eval_loss": 1.4752908945083618,
|
| 330 |
+
"eval_runtime": 61.5879,
|
| 331 |
+
"eval_samples_per_second": 4.059,
|
| 332 |
+
"eval_steps_per_second": 4.059,
|
| 333 |
+
"step": 50
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.62,
|
| 337 |
+
"learning_rate": 0.0004642729381855262,
|
| 338 |
+
"loss": 1.3671,
|
| 339 |
+
"step": 51
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.66,
|
| 343 |
+
"learning_rate": 0.0004625542839324036,
|
| 344 |
+
"loss": 1.3629,
|
| 345 |
+
"step": 52
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.69,
|
| 349 |
+
"learning_rate": 0.00046079859493180467,
|
| 350 |
+
"loss": 1.3171,
|
| 351 |
+
"step": 53
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.72,
|
| 355 |
+
"learning_rate": 0.00045900617708910854,
|
| 356 |
+
"loss": 1.4639,
|
| 357 |
+
"step": 54
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.75,
|
| 361 |
+
"learning_rate": 0.0004571773427092047,
|
| 362 |
+
"loss": 1.3031,
|
| 363 |
+
"step": 55
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.78,
|
| 367 |
+
"learning_rate": 0.00045531241044207836,
|
| 368 |
+
"loss": 1.3329,
|
| 369 |
+
"step": 56
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.82,
|
| 373 |
+
"learning_rate": 0.00045341170522729,
|
| 374 |
+
"loss": 1.3298,
|
| 375 |
+
"step": 57
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.85,
|
| 379 |
+
"learning_rate": 0.00045147555823735875,
|
| 380 |
+
"loss": 1.3794,
|
| 381 |
+
"step": 58
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.88,
|
| 385 |
+
"learning_rate": 0.00044950430682005996,
|
| 386 |
+
"loss": 1.3068,
|
| 387 |
+
"step": 59
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.91,
|
| 391 |
+
"learning_rate": 0.00044749829443964704,
|
| 392 |
+
"loss": 1.3701,
|
| 393 |
+
"step": 60
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.95,
|
| 397 |
+
"learning_rate": 0.0004454578706170075,
|
| 398 |
+
"loss": 1.2326,
|
| 399 |
+
"step": 61
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.98,
|
| 403 |
+
"learning_rate": 0.0004433833908687633,
|
| 404 |
+
"loss": 1.1632,
|
| 405 |
+
"step": 62
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.01,
|
| 409 |
+
"learning_rate": 0.00044127521664532704,
|
| 410 |
+
"loss": 1.3177,
|
| 411 |
+
"step": 63
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.02,
|
| 415 |
+
"learning_rate": 0.000439133715267924,
|
| 416 |
+
"loss": 1.2388,
|
| 417 |
+
"step": 64
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.06,
|
| 421 |
+
"learning_rate": 0.0004369592598645911,
|
| 422 |
+
"loss": 1.162,
|
| 423 |
+
"step": 65
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.09,
|
| 427 |
+
"learning_rate": 0.00043475222930516476,
|
| 428 |
+
"loss": 1.2373,
|
| 429 |
+
"step": 66
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.12,
|
| 433 |
+
"learning_rate": 0.0004325130081352675,
|
| 434 |
+
"loss": 1.2125,
|
| 435 |
+
"step": 67
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.15,
|
| 439 |
+
"learning_rate": 0.00043024198650930625,
|
| 440 |
+
"loss": 1.2374,
|
| 441 |
+
"step": 68
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.19,
|
| 445 |
+
"learning_rate": 0.0004279395601224928,
|
| 446 |
+
"loss": 1.2134,
|
| 447 |
+
"step": 69
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.22,
|
| 451 |
+
"learning_rate": 0.0004256061301418996,
|
| 452 |
+
"loss": 1.2564,
|
| 453 |
+
"step": 70
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.25,
|
| 457 |
+
"learning_rate": 0.00042324210313656173,
|
| 458 |
+
"loss": 1.1408,
|
| 459 |
+
"step": 71
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.28,
|
| 463 |
+
"learning_rate": 0.00042084789100663714,
|
| 464 |
+
"loss": 1.1333,
|
| 465 |
+
"step": 72
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.31,
|
| 469 |
+
"learning_rate": 0.0004184239109116393,
|
| 470 |
+
"loss": 1.1668,
|
| 471 |
+
"step": 73
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.35,
|
| 475 |
+
"learning_rate": 0.0004159705851977521,
|
| 476 |
+
"loss": 1.1727,
|
| 477 |
+
"step": 74
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.38,
|
| 481 |
+
"learning_rate": 0.0004159705851977521,
|
| 482 |
+
"loss": 1.2477,
|
| 483 |
+
"step": 75
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.38,
|
| 487 |
+
"eval_loss": 1.3385169506072998,
|
| 488 |
+
"eval_runtime": 61.3886,
|
| 489 |
+
"eval_samples_per_second": 4.072,
|
| 490 |
+
"eval_steps_per_second": 4.072,
|
| 491 |
+
"step": 75
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.41,
|
| 495 |
+
"learning_rate": 0.0004134883413242421,
|
| 496 |
+
"loss": 1.149,
|
| 497 |
+
"step": 76
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.44,
|
| 501 |
+
"learning_rate": 0.0004109776117889789,
|
| 502 |
+
"loss": 1.2062,
|
| 503 |
+
"step": 77
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.48,
|
| 507 |
+
"learning_rate": 0.00040843883405307905,
|
| 508 |
+
"loss": 1.1129,
|
| 509 |
+
"step": 78
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.51,
|
| 513 |
+
"learning_rate": 0.0004058724504646834,
|
| 514 |
+
"loss": 1.162,
|
| 515 |
+
"step": 79
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.54,
|
| 519 |
+
"learning_rate": 0.00040327890818188427,
|
| 520 |
+
"loss": 1.0549,
|
| 521 |
+
"step": 80
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.57,
|
| 525 |
+
"learning_rate": 0.00040327890818188427,
|
| 526 |
+
"loss": 2.1276,
|
| 527 |
+
"step": 81
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.6,
|
| 531 |
+
"learning_rate": 0.00040327890818188427,
|
| 532 |
+
"loss": 1.173,
|
| 533 |
+
"step": 82
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.64,
|
| 537 |
+
"learning_rate": 0.0004006586590948141,
|
| 538 |
+
"loss": 1.1439,
|
| 539 |
+
"step": 83
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.67,
|
| 543 |
+
"learning_rate": 0.0004006586590948141,
|
| 544 |
+
"loss": 1.4863,
|
| 545 |
+
"step": 84
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.7,
|
| 549 |
+
"learning_rate": 0.0004006586590948141,
|
| 550 |
+
"loss": 1.819,
|
| 551 |
+
"step": 85
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.73,
|
| 555 |
+
"learning_rate": 0.0004006586590948141,
|
| 556 |
+
"loss": 1.5314,
|
| 557 |
+
"step": 86
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.77,
|
| 561 |
+
"learning_rate": 0.0004006586590948141,
|
| 562 |
+
"loss": 1.2033,
|
| 563 |
+
"step": 87
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.8,
|
| 567 |
+
"learning_rate": 0.0004006586590948141,
|
| 568 |
+
"loss": 1.9072,
|
| 569 |
+
"step": 88
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.83,
|
| 573 |
+
"learning_rate": 0.0004006586590948141,
|
| 574 |
+
"loss": 2.0276,
|
| 575 |
+
"step": 89
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.86,
|
| 579 |
+
"learning_rate": 0.0004006586590948141,
|
| 580 |
+
"loss": 1.5355,
|
| 581 |
+
"step": 90
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.9,
|
| 585 |
+
"learning_rate": 0.0004006586590948141,
|
| 586 |
+
"loss": 1.1985,
|
| 587 |
+
"step": 91
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.93,
|
| 591 |
+
"learning_rate": 0.0004006586590948141,
|
| 592 |
+
"loss": 2.2275,
|
| 593 |
+
"step": 92
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.96,
|
| 597 |
+
"learning_rate": 0.0004006586590948141,
|
| 598 |
+
"loss": 2.7711,
|
| 599 |
+
"step": 93
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.99,
|
| 603 |
+
"learning_rate": 0.0004006586590948141,
|
| 604 |
+
"loss": 1.9637,
|
| 605 |
+
"step": 94
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 3.01,
|
| 609 |
+
"learning_rate": 0.0003980121597469096,
|
| 610 |
+
"loss": 1.175,
|
| 611 |
+
"step": 95
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.04,
|
| 615 |
+
"learning_rate": 0.000395339871255365,
|
| 616 |
+
"loss": 1.093,
|
| 617 |
+
"step": 96
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.07,
|
| 621 |
+
"learning_rate": 0.00039264225923078876,
|
| 622 |
+
"loss": 1.0794,
|
| 623 |
+
"step": 97
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 3.1,
|
| 627 |
+
"learning_rate": 0.00038991979369607703,
|
| 628 |
+
"loss": 1.1933,
|
| 629 |
+
"step": 98
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.14,
|
| 633 |
+
"learning_rate": 0.0003871729490045185,
|
| 634 |
+
"loss": 1.0789,
|
| 635 |
+
"step": 99
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 3.17,
|
| 639 |
+
"learning_rate": 0.00038440220375714435,
|
| 640 |
+
"loss": 1.0748,
|
| 641 |
+
"step": 100
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.17,
|
| 645 |
+
"eval_loss": 1.3322774171829224,
|
| 646 |
+
"eval_runtime": 61.5642,
|
| 647 |
+
"eval_samples_per_second": 4.061,
|
| 648 |
+
"eval_steps_per_second": 4.061,
|
| 649 |
+
"step": 100
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 3.2,
|
| 653 |
+
"learning_rate": 0.00038160804071933895,
|
| 654 |
+
"loss": 1.0428,
|
| 655 |
+
"step": 101
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.23,
|
| 659 |
+
"learning_rate": 0.000378790946736724,
|
| 660 |
+
"loss": 0.9776,
|
| 661 |
+
"step": 102
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.26,
|
| 665 |
+
"learning_rate": 0.0003759514126503324,
|
| 666 |
+
"loss": 1.0653,
|
| 667 |
+
"step": 103
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.3,
|
| 671 |
+
"learning_rate": 0.0003730899332110855,
|
| 672 |
+
"loss": 1.0331,
|
| 673 |
+
"step": 104
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 3.33,
|
| 677 |
+
"learning_rate": 0.00037020700699358984,
|
| 678 |
+
"loss": 1.0289,
|
| 679 |
+
"step": 105
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 3.36,
|
| 683 |
+
"learning_rate": 0.0003673031363092666,
|
| 684 |
+
"loss": 1.0181,
|
| 685 |
+
"step": 106
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 3.39,
|
| 689 |
+
"learning_rate": 0.0003643788271188308,
|
| 690 |
+
"loss": 1.0117,
|
| 691 |
+
"step": 107
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 3.43,
|
| 695 |
+
"learning_rate": 0.0003614345889441346,
|
| 696 |
+
"loss": 1.0623,
|
| 697 |
+
"step": 108
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.46,
|
| 701 |
+
"learning_rate": 0.00035847093477938953,
|
| 702 |
+
"loss": 0.9958,
|
| 703 |
+
"step": 109
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.49,
|
| 707 |
+
"learning_rate": 0.0003554883810017844,
|
| 708 |
+
"loss": 1.0066,
|
| 709 |
+
"step": 110
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.52,
|
| 713 |
+
"learning_rate": 0.00035248744728151344,
|
| 714 |
+
"loss": 1.0598,
|
| 715 |
+
"step": 111
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 3.55,
|
| 719 |
+
"learning_rate": 0.0003494686564912302,
|
| 720 |
+
"loss": 1.0502,
|
| 721 |
+
"step": 112
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.59,
|
| 725 |
+
"learning_rate": 0.0003464325346149449,
|
| 726 |
+
"loss": 1.0306,
|
| 727 |
+
"step": 113
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 3.62,
|
| 731 |
+
"learning_rate": 0.0003433796106563779,
|
| 732 |
+
"loss": 0.9659,
|
| 733 |
+
"step": 114
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 3.65,
|
| 737 |
+
"learning_rate": 0.0003403104165467883,
|
| 738 |
+
"loss": 1.1223,
|
| 739 |
+
"step": 115
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 3.68,
|
| 743 |
+
"learning_rate": 0.0003372254870522917,
|
| 744 |
+
"loss": 1.097,
|
| 745 |
+
"step": 116
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.72,
|
| 749 |
+
"learning_rate": 0.0003341253596806848,
|
| 750 |
+
"loss": 0.9847,
|
| 751 |
+
"step": 117
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.75,
|
| 755 |
+
"learning_rate": 0.0003310105745877915,
|
| 756 |
+
"loss": 1.0495,
|
| 757 |
+
"step": 118
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.78,
|
| 761 |
+
"learning_rate": 0.0003278816744833479,
|
| 762 |
+
"loss": 1.0697,
|
| 763 |
+
"step": 119
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 3.81,
|
| 767 |
+
"learning_rate": 0.0003247392045364426,
|
| 768 |
+
"loss": 1.1284,
|
| 769 |
+
"step": 120
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 3.84,
|
| 773 |
+
"learning_rate": 0.0003215837122805282,
|
| 774 |
+
"loss": 0.9914,
|
| 775 |
+
"step": 121
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 3.88,
|
| 779 |
+
"learning_rate": 0.0003184157475180208,
|
| 780 |
+
"loss": 1.035,
|
| 781 |
+
"step": 122
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.91,
|
| 785 |
+
"learning_rate": 0.00031523586222450417,
|
| 786 |
+
"loss": 1.0098,
|
| 787 |
+
"step": 123
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 3.94,
|
| 791 |
+
"learning_rate": 0.000312044610452556,
|
| 792 |
+
"loss": 1.0373,
|
| 793 |
+
"step": 124
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.97,
|
| 797 |
+
"learning_rate": 0.00030884254823521063,
|
| 798 |
+
"loss": 1.0539,
|
| 799 |
+
"step": 125
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 3.97,
|
| 803 |
+
"eval_loss": 1.29022216796875,
|
| 804 |
+
"eval_runtime": 61.524,
|
| 805 |
+
"eval_samples_per_second": 4.063,
|
| 806 |
+
"eval_steps_per_second": 4.063,
|
| 807 |
+
"step": 125
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.01,
|
| 811 |
+
"learning_rate": 0.0003056302334890786,
|
| 812 |
+
"loss": 0.9474,
|
| 813 |
+
"step": 126
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.02,
|
| 817 |
+
"learning_rate": 0.00030240822591713666,
|
| 818 |
+
"loss": 0.9781,
|
| 819 |
+
"step": 127
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.05,
|
| 823 |
+
"learning_rate": 0.00029917708691120704,
|
| 824 |
+
"loss": 0.915,
|
| 825 |
+
"step": 128
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.08,
|
| 829 |
+
"learning_rate": 0.0002959373794541426,
|
| 830 |
+
"loss": 0.8535,
|
| 831 |
+
"step": 129
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 4.11,
|
| 835 |
+
"learning_rate": 0.00029268966802173434,
|
| 836 |
+
"loss": 0.9403,
|
| 837 |
+
"step": 130
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.15,
|
| 841 |
+
"learning_rate": 0.0002894345184843594,
|
| 842 |
+
"loss": 0.8462,
|
| 843 |
+
"step": 131
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.18,
|
| 847 |
+
"learning_rate": 0.00028617249800838514,
|
| 848 |
+
"loss": 0.8375,
|
| 849 |
+
"step": 132
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.21,
|
| 853 |
+
"learning_rate": 0.00028290417495734836,
|
| 854 |
+
"loss": 0.9175,
|
| 855 |
+
"step": 133
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.24,
|
| 859 |
+
"learning_rate": 0.0002796301187929257,
|
| 860 |
+
"loss": 0.8843,
|
| 861 |
+
"step": 134
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.27,
|
| 865 |
+
"learning_rate": 0.0002763508999757119,
|
| 866 |
+
"loss": 0.9091,
|
| 867 |
+
"step": 135
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 4.31,
|
| 871 |
+
"learning_rate": 0.0002730670898658255,
|
| 872 |
+
"loss": 0.864,
|
| 873 |
+
"step": 136
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 4.34,
|
| 877 |
+
"learning_rate": 0.00026977926062335617,
|
| 878 |
+
"loss": 0.834,
|
| 879 |
+
"step": 137
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 4.37,
|
| 883 |
+
"learning_rate": 0.0002664879851086738,
|
| 884 |
+
"loss": 0.9073,
|
| 885 |
+
"step": 138
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.4,
|
| 889 |
+
"learning_rate": 0.0002631938367826156,
|
| 890 |
+
"loss": 0.8836,
|
| 891 |
+
"step": 139
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 4.44,
|
| 895 |
+
"learning_rate": 0.00025989738960656737,
|
| 896 |
+
"loss": 0.8742,
|
| 897 |
+
"step": 140
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 4.47,
|
| 901 |
+
"learning_rate": 0.0002565992179424591,
|
| 902 |
+
"loss": 0.8922,
|
| 903 |
+
"step": 141
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 4.5,
|
| 907 |
+
"learning_rate": 0.00025329989645268977,
|
| 908 |
+
"loss": 0.9441,
|
| 909 |
+
"step": 142
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 4.53,
|
| 913 |
+
"learning_rate": 0.00025,
|
| 914 |
+
"loss": 0.831,
|
| 915 |
+
"step": 143
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 4.56,
|
| 919 |
+
"learning_rate": 0.0002467001035473103,
|
| 920 |
+
"loss": 0.8394,
|
| 921 |
+
"step": 144
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 4.6,
|
| 925 |
+
"learning_rate": 0.000243400782057541,
|
| 926 |
+
"loss": 0.9186,
|
| 927 |
+
"step": 145
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 4.63,
|
| 931 |
+
"learning_rate": 0.0002401026103934327,
|
| 932 |
+
"loss": 0.8257,
|
| 933 |
+
"step": 146
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 4.66,
|
| 937 |
+
"learning_rate": 0.0002368061632173844,
|
| 938 |
+
"loss": 0.9173,
|
| 939 |
+
"step": 147
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 4.69,
|
| 943 |
+
"learning_rate": 0.00023351201489132614,
|
| 944 |
+
"loss": 0.8363,
|
| 945 |
+
"step": 148
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 4.73,
|
| 949 |
+
"learning_rate": 0.00023022073937664384,
|
| 950 |
+
"loss": 0.8743,
|
| 951 |
+
"step": 149
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 4.76,
|
| 955 |
+
"learning_rate": 0.00022693291013417452,
|
| 956 |
+
"loss": 0.845,
|
| 957 |
+
"step": 150
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 4.76,
|
| 961 |
+
"eval_loss": 1.3330121040344238,
|
| 962 |
+
"eval_runtime": 61.21,
|
| 963 |
+
"eval_samples_per_second": 4.084,
|
| 964 |
+
"eval_steps_per_second": 4.084,
|
| 965 |
+
"step": 150
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 4.79,
|
| 969 |
+
"learning_rate": 0.0002236491000242881,
|
| 970 |
+
"loss": 0.948,
|
| 971 |
+
"step": 151
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 4.82,
|
| 975 |
+
"learning_rate": 0.00022036988120707434,
|
| 976 |
+
"loss": 0.8581,
|
| 977 |
+
"step": 152
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 4.85,
|
| 981 |
+
"learning_rate": 0.00021709582504265168,
|
| 982 |
+
"loss": 0.8916,
|
| 983 |
+
"step": 153
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.89,
|
| 987 |
+
"learning_rate": 0.00021382750199161495,
|
| 988 |
+
"loss": 0.9227,
|
| 989 |
+
"step": 154
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 4.92,
|
| 993 |
+
"learning_rate": 0.0002105654815156406,
|
| 994 |
+
"loss": 0.8323,
|
| 995 |
+
"step": 155
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 4.95,
|
| 999 |
+
"learning_rate": 0.0002073103319782656,
|
| 1000 |
+
"loss": 0.8527,
|
| 1001 |
+
"step": 156
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 4.98,
|
| 1005 |
+
"learning_rate": 0.0002040626205458574,
|
| 1006 |
+
"loss": 0.809,
|
| 1007 |
+
"step": 157
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 5.02,
|
| 1011 |
+
"learning_rate": 0.000200822913088793,
|
| 1012 |
+
"loss": 0.8528,
|
| 1013 |
+
"step": 158
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 5.03,
|
| 1017 |
+
"learning_rate": 0.00019759177408286337,
|
| 1018 |
+
"loss": 0.7714,
|
| 1019 |
+
"step": 159
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 5.06,
|
| 1023 |
+
"learning_rate": 0.00019436976651092142,
|
| 1024 |
+
"loss": 0.6798,
|
| 1025 |
+
"step": 160
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 5.09,
|
| 1029 |
+
"learning_rate": 0.00019115745176478944,
|
| 1030 |
+
"loss": 0.7205,
|
| 1031 |
+
"step": 161
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 5.12,
|
| 1035 |
+
"learning_rate": 0.00018795538954744406,
|
| 1036 |
+
"loss": 0.7903,
|
| 1037 |
+
"step": 162
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 5.16,
|
| 1041 |
+
"learning_rate": 0.00018476413777549584,
|
| 1042 |
+
"loss": 0.7309,
|
| 1043 |
+
"step": 163
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 5.19,
|
| 1047 |
+
"learning_rate": 0.0001815842524819793,
|
| 1048 |
+
"loss": 0.7607,
|
| 1049 |
+
"step": 164
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.22,
|
| 1053 |
+
"learning_rate": 0.00017841628771947187,
|
| 1054 |
+
"loss": 0.7078,
|
| 1055 |
+
"step": 165
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 5.25,
|
| 1059 |
+
"learning_rate": 0.00017526079546355744,
|
| 1060 |
+
"loss": 0.6838,
|
| 1061 |
+
"step": 166
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 5.29,
|
| 1065 |
+
"learning_rate": 0.00017211832551665212,
|
| 1066 |
+
"loss": 0.7719,
|
| 1067 |
+
"step": 167
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 5.32,
|
| 1071 |
+
"learning_rate": 0.00016898942541220858,
|
| 1072 |
+
"loss": 0.6696,
|
| 1073 |
+
"step": 168
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 5.35,
|
| 1077 |
+
"learning_rate": 0.00016587464031931528,
|
| 1078 |
+
"loss": 0.7306,
|
| 1079 |
+
"step": 169
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 5.38,
|
| 1083 |
+
"learning_rate": 0.00016277451294770834,
|
| 1084 |
+
"loss": 0.6611,
|
| 1085 |
+
"step": 170
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 5.42,
|
| 1089 |
+
"learning_rate": 0.00015968958345321176,
|
| 1090 |
+
"loss": 0.7144,
|
| 1091 |
+
"step": 171
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 5.45,
|
| 1095 |
+
"learning_rate": 0.0001566203893436221,
|
| 1096 |
+
"loss": 0.7285,
|
| 1097 |
+
"step": 172
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 5.48,
|
| 1101 |
+
"learning_rate": 0.0001535674653850551,
|
| 1102 |
+
"loss": 0.7178,
|
| 1103 |
+
"step": 173
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 5.51,
|
| 1107 |
+
"learning_rate": 0.00015053134350876982,
|
| 1108 |
+
"loss": 0.6815,
|
| 1109 |
+
"step": 174
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 5.54,
|
| 1113 |
+
"learning_rate": 0.00014751255271848663,
|
| 1114 |
+
"loss": 0.6957,
|
| 1115 |
+
"step": 175
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 5.54,
|
| 1119 |
+
"eval_loss": 1.3759878873825073,
|
| 1120 |
+
"eval_runtime": 61.4139,
|
| 1121 |
+
"eval_samples_per_second": 4.071,
|
| 1122 |
+
"eval_steps_per_second": 4.071,
|
| 1123 |
+
"step": 175
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 5.58,
|
| 1127 |
+
"learning_rate": 0.00014451161899821559,
|
| 1128 |
+
"loss": 0.6367,
|
| 1129 |
+
"step": 176
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 5.61,
|
| 1133 |
+
"learning_rate": 0.00014152906522061048,
|
| 1134 |
+
"loss": 0.7081,
|
| 1135 |
+
"step": 177
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 5.64,
|
| 1139 |
+
"learning_rate": 0.00013856541105586545,
|
| 1140 |
+
"loss": 0.6698,
|
| 1141 |
+
"step": 178
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 5.67,
|
| 1145 |
+
"learning_rate": 0.00013562117288116923,
|
| 1146 |
+
"loss": 0.7209,
|
| 1147 |
+
"step": 179
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 5.71,
|
| 1151 |
+
"learning_rate": 0.00013269686369073348,
|
| 1152 |
+
"loss": 0.7789,
|
| 1153 |
+
"step": 180
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 5.74,
|
| 1157 |
+
"learning_rate": 0.00012979299300641017,
|
| 1158 |
+
"loss": 0.7125,
|
| 1159 |
+
"step": 181
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 5.77,
|
| 1163 |
+
"learning_rate": 0.00012691006678891445,
|
| 1164 |
+
"loss": 0.7243,
|
| 1165 |
+
"step": 182
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 5.8,
|
| 1169 |
+
"learning_rate": 0.0001240485873496677,
|
| 1170 |
+
"loss": 0.721,
|
| 1171 |
+
"step": 183
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 5.83,
|
| 1175 |
+
"learning_rate": 0.00012120905326327598,
|
| 1176 |
+
"loss": 0.7852,
|
| 1177 |
+
"step": 184
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 5.87,
|
| 1181 |
+
"learning_rate": 0.00011839195928066102,
|
| 1182 |
+
"loss": 0.6858,
|
| 1183 |
+
"step": 185
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 5.9,
|
| 1187 |
+
"learning_rate": 0.00011559779624285562,
|
| 1188 |
+
"loss": 0.756,
|
| 1189 |
+
"step": 186
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 5.93,
|
| 1193 |
+
"learning_rate": 0.0001128270509954816,
|
| 1194 |
+
"loss": 0.7065,
|
| 1195 |
+
"step": 187
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 5.96,
|
| 1199 |
+
"learning_rate": 0.00011008020630392302,
|
| 1200 |
+
"loss": 0.7263,
|
| 1201 |
+
"step": 188
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 6.0,
|
| 1205 |
+
"learning_rate": 0.0001073577407692113,
|
| 1206 |
+
"loss": 0.7368,
|
| 1207 |
+
"step": 189
|
| 1208 |
+
}
|
| 1209 |
+
],
|
| 1210 |
+
"logging_steps": 1,
|
| 1211 |
+
"max_steps": 248,
|
| 1212 |
+
"num_train_epochs": 8,
|
| 1213 |
+
"save_steps": 500,
|
| 1214 |
+
"total_flos": 2.4806906989746586e+17,
|
| 1215 |
+
"trial_name": null,
|
| 1216 |
+
"trial_params": null
|
| 1217 |
+
}
|
checkpoint-189/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebc1ba8de529c7c32cc6ab052beaeb5c04d634fe0a2b1904e12ba3ec54228a80
|
| 3 |
+
size 4603
|