Upload 24 files
Browse files- checkpoint-2200/README.md +207 -0
- checkpoint-2200/adapter_config.json +23 -0
- checkpoint-2200/adapter_model.bin +3 -0
- checkpoint-2200/optimizer.pt +3 -0
- checkpoint-2200/rng_state.pth +3 -0
- checkpoint-2200/scheduler.pt +3 -0
- checkpoint-2200/trainer_state.json +1427 -0
- checkpoint-2200/training_args.bin +3 -0
- checkpoint-2400/README.md +207 -0
- checkpoint-2400/adapter_config.json +23 -0
- checkpoint-2400/adapter_model.bin +3 -0
- checkpoint-2400/optimizer.pt +3 -0
- checkpoint-2400/rng_state.pth +3 -0
- checkpoint-2400/scheduler.pt +3 -0
- checkpoint-2400/trainer_state.json +1555 -0
- checkpoint-2400/training_args.bin +3 -0
- checkpoint-2600/README.md +207 -0
- checkpoint-2600/adapter_config.json +23 -0
- checkpoint-2600/adapter_model.bin +3 -0
- checkpoint-2600/optimizer.pt +3 -0
- checkpoint-2600/rng_state.pth +3 -0
- checkpoint-2600/scheduler.pt +3 -0
- checkpoint-2600/trainer_state.json +1683 -0
- checkpoint-2600/training_args.bin +3 -0
checkpoint-2200/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: medalpaca/medalpaca-7b
|
| 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 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
- PEFT 0.6.0.dev0
|
checkpoint-2200/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "medalpaca/medalpaca-7b",
|
| 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 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 8,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-2200/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7eaa51169fb5f5f33b328f26090dcd19a47bde0a9efe64e78856dbbe04a07e7a
|
| 3 |
+
size 888
|
checkpoint-2200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b58443c2d861480704921bda74eeb5713121914f5d4530030375138e5e7a68c
|
| 3 |
+
size 33662074
|
checkpoint-2200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4042591ec169dbc8de9e2b06fbb1c08654e6176305e57a77e17dfd3480c6d26b
|
| 3 |
+
size 14244
|
checkpoint-2200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2f4a1dc3c36d111f3330fd30f64ac80df89b8d29c0f656bd3be0b3b1c80172
|
| 3 |
+
size 1064
|
checkpoint-2200/trainer_state.json
ADDED
|
@@ -0,0 +1,1427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5713418126106262,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-2200",
|
| 4 |
+
"epoch": 2.5143755134111934,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 14 |
+
"loss": 3.282,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 4.000000000000001e-06,
|
| 20 |
+
"loss": 3.2806,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 6e-06,
|
| 26 |
+
"loss": 3.2842,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 8.000000000000001e-06,
|
| 32 |
+
"loss": 3.2378,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 1e-05,
|
| 38 |
+
"loss": 3.202,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 1.2e-05,
|
| 44 |
+
"loss": 3.1307,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"learning_rate": 1.4e-05,
|
| 50 |
+
"loss": 3.0392,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 56 |
+
"loss": 2.9102,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.1,
|
| 61 |
+
"learning_rate": 1.8e-05,
|
| 62 |
+
"loss": 2.7595,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.11,
|
| 67 |
+
"learning_rate": 2e-05,
|
| 68 |
+
"loss": 2.5737,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 1.9999224156779658e-05,
|
| 74 |
+
"loss": 2.347,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.14,
|
| 79 |
+
"learning_rate": 1.999689674750517e-05,
|
| 80 |
+
"loss": 2.0934,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15,
|
| 85 |
+
"learning_rate": 1.9993018133317476e-05,
|
| 86 |
+
"loss": 1.8305,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16,
|
| 91 |
+
"learning_rate": 1.998758891605588e-05,
|
| 92 |
+
"loss": 1.5447,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17,
|
| 97 |
+
"learning_rate": 1.9980609938164664e-05,
|
| 98 |
+
"loss": 1.3394,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.18,
|
| 103 |
+
"learning_rate": 1.9972082282562367e-05,
|
| 104 |
+
"loss": 1.2032,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.19,
|
| 109 |
+
"learning_rate": 1.9962007272473744e-05,
|
| 110 |
+
"loss": 1.1096,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.21,
|
| 115 |
+
"learning_rate": 1.9950386471224445e-05,
|
| 116 |
+
"loss": 1.0456,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.22,
|
| 121 |
+
"learning_rate": 1.9937221681998447e-05,
|
| 122 |
+
"loss": 0.9977,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23,
|
| 127 |
+
"learning_rate": 1.9922514947558248e-05,
|
| 128 |
+
"loss": 0.9786,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.23,
|
| 133 |
+
"eval_loss": 0.982032299041748,
|
| 134 |
+
"eval_runtime": 759.4598,
|
| 135 |
+
"eval_samples_per_second": 16.387,
|
| 136 |
+
"eval_steps_per_second": 2.049,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.24,
|
| 141 |
+
"learning_rate": 1.9906268549927886e-05,
|
| 142 |
+
"loss": 0.948,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.25,
|
| 147 |
+
"learning_rate": 1.9888485010038848e-05,
|
| 148 |
+
"loss": 0.9164,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.26,
|
| 153 |
+
"learning_rate": 1.9869167087338908e-05,
|
| 154 |
+
"loss": 0.8977,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.27,
|
| 159 |
+
"learning_rate": 1.984831777936394e-05,
|
| 160 |
+
"loss": 0.876,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.29,
|
| 165 |
+
"learning_rate": 1.9825940321272792e-05,
|
| 166 |
+
"loss": 0.8604,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.3,
|
| 171 |
+
"learning_rate": 1.980203818534529e-05,
|
| 172 |
+
"loss": 0.8424,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.31,
|
| 177 |
+
"learning_rate": 1.9776615080443462e-05,
|
| 178 |
+
"loss": 0.8434,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.32,
|
| 183 |
+
"learning_rate": 1.9749674951436016e-05,
|
| 184 |
+
"loss": 0.8357,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.33,
|
| 189 |
+
"learning_rate": 1.972122197858625e-05,
|
| 190 |
+
"loss": 0.8239,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.34,
|
| 195 |
+
"learning_rate": 1.9691260576903372e-05,
|
| 196 |
+
"loss": 0.8177,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.35,
|
| 201 |
+
"learning_rate": 1.965979539545746e-05,
|
| 202 |
+
"loss": 0.8151,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.37,
|
| 207 |
+
"learning_rate": 1.9626831316658058e-05,
|
| 208 |
+
"loss": 0.8074,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.38,
|
| 213 |
+
"learning_rate": 1.959237345549657e-05,
|
| 214 |
+
"loss": 0.7768,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.39,
|
| 219 |
+
"learning_rate": 1.955642715875259e-05,
|
| 220 |
+
"loss": 0.7673,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.4,
|
| 225 |
+
"learning_rate": 1.951899800416425e-05,
|
| 226 |
+
"loss": 0.7448,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.41,
|
| 231 |
+
"learning_rate": 1.9480091799562706e-05,
|
| 232 |
+
"loss": 0.7334,
|
| 233 |
+
"step": 360
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.42,
|
| 237 |
+
"learning_rate": 1.9439714581970983e-05,
|
| 238 |
+
"loss": 0.734,
|
| 239 |
+
"step": 370
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.43,
|
| 243 |
+
"learning_rate": 1.9397872616667175e-05,
|
| 244 |
+
"loss": 0.7301,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.45,
|
| 249 |
+
"learning_rate": 1.935457239621231e-05,
|
| 250 |
+
"loss": 0.734,
|
| 251 |
+
"step": 390
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.46,
|
| 255 |
+
"learning_rate": 1.9309820639442886e-05,
|
| 256 |
+
"loss": 0.7062,
|
| 257 |
+
"step": 400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.46,
|
| 261 |
+
"eval_loss": 0.7326281070709229,
|
| 262 |
+
"eval_runtime": 757.8879,
|
| 263 |
+
"eval_samples_per_second": 16.421,
|
| 264 |
+
"eval_steps_per_second": 2.053,
|
| 265 |
+
"step": 400
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.47,
|
| 269 |
+
"learning_rate": 1.9263624290428314e-05,
|
| 270 |
+
"loss": 0.7074,
|
| 271 |
+
"step": 410
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.48,
|
| 275 |
+
"learning_rate": 1.9215990517393436e-05,
|
| 276 |
+
"loss": 0.7001,
|
| 277 |
+
"step": 420
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.49,
|
| 281 |
+
"learning_rate": 1.9166926711606222e-05,
|
| 282 |
+
"loss": 0.6991,
|
| 283 |
+
"step": 430
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"learning_rate": 1.9116440486230893e-05,
|
| 288 |
+
"loss": 0.6935,
|
| 289 |
+
"step": 440
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.51,
|
| 293 |
+
"learning_rate": 1.9064539675146584e-05,
|
| 294 |
+
"loss": 0.6922,
|
| 295 |
+
"step": 450
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.53,
|
| 299 |
+
"learning_rate": 1.9011232331731773e-05,
|
| 300 |
+
"loss": 0.6861,
|
| 301 |
+
"step": 460
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.54,
|
| 305 |
+
"learning_rate": 1.8956526727614663e-05,
|
| 306 |
+
"loss": 0.6978,
|
| 307 |
+
"step": 470
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.55,
|
| 311 |
+
"learning_rate": 1.8900431351389657e-05,
|
| 312 |
+
"loss": 0.6699,
|
| 313 |
+
"step": 480
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.56,
|
| 317 |
+
"learning_rate": 1.8842954907300236e-05,
|
| 318 |
+
"loss": 0.6846,
|
| 319 |
+
"step": 490
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.57,
|
| 323 |
+
"learning_rate": 1.878410631388829e-05,
|
| 324 |
+
"loss": 0.6772,
|
| 325 |
+
"step": 500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.58,
|
| 329 |
+
"learning_rate": 1.8723894702610258e-05,
|
| 330 |
+
"loss": 0.6808,
|
| 331 |
+
"step": 510
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.59,
|
| 335 |
+
"learning_rate": 1.866232941642023e-05,
|
| 336 |
+
"loss": 0.6869,
|
| 337 |
+
"step": 520
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.61,
|
| 341 |
+
"learning_rate": 1.8599420008320176e-05,
|
| 342 |
+
"loss": 0.6595,
|
| 343 |
+
"step": 530
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.62,
|
| 347 |
+
"learning_rate": 1.8535176239877653e-05,
|
| 348 |
+
"loss": 0.6669,
|
| 349 |
+
"step": 540
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.63,
|
| 353 |
+
"learning_rate": 1.8469608079711105e-05,
|
| 354 |
+
"loss": 0.6648,
|
| 355 |
+
"step": 550
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.64,
|
| 359 |
+
"learning_rate": 1.8402725701943028e-05,
|
| 360 |
+
"loss": 0.6486,
|
| 361 |
+
"step": 560
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.65,
|
| 365 |
+
"learning_rate": 1.8334539484621304e-05,
|
| 366 |
+
"loss": 0.6735,
|
| 367 |
+
"step": 570
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.66,
|
| 371 |
+
"learning_rate": 1.8265060008108815e-05,
|
| 372 |
+
"loss": 0.6498,
|
| 373 |
+
"step": 580
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.67,
|
| 377 |
+
"learning_rate": 1.8194298053441725e-05,
|
| 378 |
+
"loss": 0.6578,
|
| 379 |
+
"step": 590
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.69,
|
| 383 |
+
"learning_rate": 1.812226460065658e-05,
|
| 384 |
+
"loss": 0.6392,
|
| 385 |
+
"step": 600
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.69,
|
| 389 |
+
"eval_loss": 0.6629914045333862,
|
| 390 |
+
"eval_runtime": 765.6279,
|
| 391 |
+
"eval_samples_per_second": 16.255,
|
| 392 |
+
"eval_steps_per_second": 2.032,
|
| 393 |
+
"step": 600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.7,
|
| 397 |
+
"learning_rate": 1.804897082708659e-05,
|
| 398 |
+
"loss": 0.6524,
|
| 399 |
+
"step": 610
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.71,
|
| 403 |
+
"learning_rate": 1.797442810562721e-05,
|
| 404 |
+
"loss": 0.6513,
|
| 405 |
+
"step": 620
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.72,
|
| 409 |
+
"learning_rate": 1.7898648002971456e-05,
|
| 410 |
+
"loss": 0.6466,
|
| 411 |
+
"step": 630
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.73,
|
| 415 |
+
"learning_rate": 1.7821642277815108e-05,
|
| 416 |
+
"loss": 0.6305,
|
| 417 |
+
"step": 640
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.74,
|
| 421 |
+
"learning_rate": 1.774342287903212e-05,
|
| 422 |
+
"loss": 0.6418,
|
| 423 |
+
"step": 650
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.75,
|
| 427 |
+
"learning_rate": 1.766400194382054e-05,
|
| 428 |
+
"loss": 0.636,
|
| 429 |
+
"step": 660
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.77,
|
| 433 |
+
"learning_rate": 1.75833917958192e-05,
|
| 434 |
+
"loss": 0.6279,
|
| 435 |
+
"step": 670
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.78,
|
| 439 |
+
"learning_rate": 1.7501604943195466e-05,
|
| 440 |
+
"loss": 0.6369,
|
| 441 |
+
"step": 680
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.79,
|
| 445 |
+
"learning_rate": 1.741865407670435e-05,
|
| 446 |
+
"loss": 0.6308,
|
| 447 |
+
"step": 690
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.8,
|
| 451 |
+
"learning_rate": 1.733455206771934e-05,
|
| 452 |
+
"loss": 0.616,
|
| 453 |
+
"step": 700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.81,
|
| 457 |
+
"learning_rate": 1.724931196623513e-05,
|
| 458 |
+
"loss": 0.6334,
|
| 459 |
+
"step": 710
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.82,
|
| 463 |
+
"learning_rate": 1.716294699884269e-05,
|
| 464 |
+
"loss": 0.6289,
|
| 465 |
+
"step": 720
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.83,
|
| 469 |
+
"learning_rate": 1.70754705666769e-05,
|
| 470 |
+
"loss": 0.6251,
|
| 471 |
+
"step": 730
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.85,
|
| 475 |
+
"learning_rate": 1.6986896243337137e-05,
|
| 476 |
+
"loss": 0.619,
|
| 477 |
+
"step": 740
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.86,
|
| 481 |
+
"learning_rate": 1.6897237772781046e-05,
|
| 482 |
+
"loss": 0.6226,
|
| 483 |
+
"step": 750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.87,
|
| 487 |
+
"learning_rate": 1.6806509067191926e-05,
|
| 488 |
+
"loss": 0.6229,
|
| 489 |
+
"step": 760
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.88,
|
| 493 |
+
"learning_rate": 1.6714724204820017e-05,
|
| 494 |
+
"loss": 0.6016,
|
| 495 |
+
"step": 770
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.89,
|
| 499 |
+
"learning_rate": 1.6621897427797947e-05,
|
| 500 |
+
"loss": 0.6061,
|
| 501 |
+
"step": 780
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.9,
|
| 505 |
+
"learning_rate": 1.6528043139930845e-05,
|
| 506 |
+
"loss": 0.6027,
|
| 507 |
+
"step": 790
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.91,
|
| 511 |
+
"learning_rate": 1.64331759044613e-05,
|
| 512 |
+
"loss": 0.6018,
|
| 513 |
+
"step": 800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.91,
|
| 517 |
+
"eval_loss": 0.6285067796707153,
|
| 518 |
+
"eval_runtime": 765.1757,
|
| 519 |
+
"eval_samples_per_second": 16.264,
|
| 520 |
+
"eval_steps_per_second": 2.034,
|
| 521 |
+
"step": 800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.93,
|
| 525 |
+
"learning_rate": 1.63373104418096e-05,
|
| 526 |
+
"loss": 0.6094,
|
| 527 |
+
"step": 810
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.94,
|
| 531 |
+
"learning_rate": 1.6240461627289607e-05,
|
| 532 |
+
"loss": 0.6224,
|
| 533 |
+
"step": 820
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.95,
|
| 537 |
+
"learning_rate": 1.614264448880054e-05,
|
| 538 |
+
"loss": 0.6032,
|
| 539 |
+
"step": 830
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.96,
|
| 543 |
+
"learning_rate": 1.6043874204495152e-05,
|
| 544 |
+
"loss": 0.6048,
|
| 545 |
+
"step": 840
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.97,
|
| 549 |
+
"learning_rate": 1.5944166100424534e-05,
|
| 550 |
+
"loss": 0.6036,
|
| 551 |
+
"step": 850
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.98,
|
| 555 |
+
"learning_rate": 1.584353564815999e-05,
|
| 556 |
+
"loss": 0.5932,
|
| 557 |
+
"step": 860
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.99,
|
| 561 |
+
"learning_rate": 1.5741998462392352e-05,
|
| 562 |
+
"loss": 0.6003,
|
| 563 |
+
"step": 870
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.01,
|
| 567 |
+
"learning_rate": 1.5639570298509067e-05,
|
| 568 |
+
"loss": 0.6128,
|
| 569 |
+
"step": 880
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.02,
|
| 573 |
+
"learning_rate": 1.5536267050149428e-05,
|
| 574 |
+
"loss": 0.5968,
|
| 575 |
+
"step": 890
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.03,
|
| 579 |
+
"learning_rate": 1.5432104746738417e-05,
|
| 580 |
+
"loss": 0.6027,
|
| 581 |
+
"step": 900
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.04,
|
| 585 |
+
"learning_rate": 1.5327099550999416e-05,
|
| 586 |
+
"loss": 0.6122,
|
| 587 |
+
"step": 910
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.05,
|
| 591 |
+
"learning_rate": 1.5221267756446266e-05,
|
| 592 |
+
"loss": 0.5984,
|
| 593 |
+
"step": 920
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.06,
|
| 597 |
+
"learning_rate": 1.5114625784855028e-05,
|
| 598 |
+
"loss": 0.5965,
|
| 599 |
+
"step": 930
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.07,
|
| 603 |
+
"learning_rate": 1.5007190183715836e-05,
|
| 604 |
+
"loss": 0.5942,
|
| 605 |
+
"step": 940
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.09,
|
| 609 |
+
"learning_rate": 1.4898977623665243e-05,
|
| 610 |
+
"loss": 0.6,
|
| 611 |
+
"step": 950
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.1,
|
| 615 |
+
"learning_rate": 1.4790004895899465e-05,
|
| 616 |
+
"loss": 0.6051,
|
| 617 |
+
"step": 960
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.11,
|
| 621 |
+
"learning_rate": 1.4680288909568905e-05,
|
| 622 |
+
"loss": 0.5903,
|
| 623 |
+
"step": 970
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.12,
|
| 627 |
+
"learning_rate": 1.4569846689154401e-05,
|
| 628 |
+
"loss": 0.6049,
|
| 629 |
+
"step": 980
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.13,
|
| 633 |
+
"learning_rate": 1.4458695371825535e-05,
|
| 634 |
+
"loss": 0.5852,
|
| 635 |
+
"step": 990
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.14,
|
| 639 |
+
"learning_rate": 1.4346852204781511e-05,
|
| 640 |
+
"loss": 0.5869,
|
| 641 |
+
"step": 1000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.14,
|
| 645 |
+
"eval_loss": 0.6076732277870178,
|
| 646 |
+
"eval_runtime": 765.3772,
|
| 647 |
+
"eval_samples_per_second": 16.26,
|
| 648 |
+
"eval_steps_per_second": 2.033,
|
| 649 |
+
"step": 1000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.15,
|
| 653 |
+
"learning_rate": 1.4234334542574906e-05,
|
| 654 |
+
"loss": 0.5893,
|
| 655 |
+
"step": 1010
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.17,
|
| 659 |
+
"learning_rate": 1.4121159844418793e-05,
|
| 660 |
+
"loss": 0.5874,
|
| 661 |
+
"step": 1020
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.18,
|
| 665 |
+
"learning_rate": 1.400734567147763e-05,
|
| 666 |
+
"loss": 0.595,
|
| 667 |
+
"step": 1030
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.19,
|
| 671 |
+
"learning_rate": 1.3892909684142311e-05,
|
| 672 |
+
"loss": 0.5961,
|
| 673 |
+
"step": 1040
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.2,
|
| 677 |
+
"learning_rate": 1.3777869639289822e-05,
|
| 678 |
+
"loss": 0.5826,
|
| 679 |
+
"step": 1050
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.21,
|
| 683 |
+
"learning_rate": 1.3662243387527936e-05,
|
| 684 |
+
"loss": 0.5835,
|
| 685 |
+
"step": 1060
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.22,
|
| 689 |
+
"learning_rate": 1.3546048870425356e-05,
|
| 690 |
+
"loss": 0.5858,
|
| 691 |
+
"step": 1070
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.23,
|
| 695 |
+
"learning_rate": 1.3429304117727755e-05,
|
| 696 |
+
"loss": 0.5931,
|
| 697 |
+
"step": 1080
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.25,
|
| 701 |
+
"learning_rate": 1.3312027244560104e-05,
|
| 702 |
+
"loss": 0.5858,
|
| 703 |
+
"step": 1090
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.26,
|
| 707 |
+
"learning_rate": 1.3194236448615798e-05,
|
| 708 |
+
"loss": 0.5834,
|
| 709 |
+
"step": 1100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.27,
|
| 713 |
+
"learning_rate": 1.3075950007332923e-05,
|
| 714 |
+
"loss": 0.5854,
|
| 715 |
+
"step": 1110
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.28,
|
| 719 |
+
"learning_rate": 1.2957186275058188e-05,
|
| 720 |
+
"loss": 0.5879,
|
| 721 |
+
"step": 1120
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.29,
|
| 725 |
+
"learning_rate": 1.2837963680198895e-05,
|
| 726 |
+
"loss": 0.5958,
|
| 727 |
+
"step": 1130
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.3,
|
| 731 |
+
"learning_rate": 1.2718300722363431e-05,
|
| 732 |
+
"loss": 0.5787,
|
| 733 |
+
"step": 1140
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.31,
|
| 737 |
+
"learning_rate": 1.2598215969490703e-05,
|
| 738 |
+
"loss": 0.5827,
|
| 739 |
+
"step": 1150
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.33,
|
| 743 |
+
"learning_rate": 1.2477728054968993e-05,
|
| 744 |
+
"loss": 0.589,
|
| 745 |
+
"step": 1160
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.34,
|
| 749 |
+
"learning_rate": 1.2356855674744625e-05,
|
| 750 |
+
"loss": 0.5806,
|
| 751 |
+
"step": 1170
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.35,
|
| 755 |
+
"learning_rate": 1.2235617584420938e-05,
|
| 756 |
+
"loss": 0.563,
|
| 757 |
+
"step": 1180
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.36,
|
| 761 |
+
"learning_rate": 1.2114032596348023e-05,
|
| 762 |
+
"loss": 0.5812,
|
| 763 |
+
"step": 1190
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.37,
|
| 767 |
+
"learning_rate": 1.1992119576703614e-05,
|
| 768 |
+
"loss": 0.5995,
|
| 769 |
+
"step": 1200
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.37,
|
| 773 |
+
"eval_loss": 0.5944839119911194,
|
| 774 |
+
"eval_runtime": 764.7162,
|
| 775 |
+
"eval_samples_per_second": 16.274,
|
| 776 |
+
"eval_steps_per_second": 2.035,
|
| 777 |
+
"step": 1200
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.38,
|
| 781 |
+
"learning_rate": 1.1869897442565665e-05,
|
| 782 |
+
"loss": 0.5852,
|
| 783 |
+
"step": 1210
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.39,
|
| 787 |
+
"learning_rate": 1.1747385158977008e-05,
|
| 788 |
+
"loss": 0.5798,
|
| 789 |
+
"step": 1220
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.41,
|
| 793 |
+
"learning_rate": 1.162460173600256e-05,
|
| 794 |
+
"loss": 0.5846,
|
| 795 |
+
"step": 1230
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.42,
|
| 799 |
+
"learning_rate": 1.1501566225779592e-05,
|
| 800 |
+
"loss": 0.5674,
|
| 801 |
+
"step": 1240
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.43,
|
| 805 |
+
"learning_rate": 1.1378297719561388e-05,
|
| 806 |
+
"loss": 0.5616,
|
| 807 |
+
"step": 1250
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.44,
|
| 811 |
+
"learning_rate": 1.1254815344754919e-05,
|
| 812 |
+
"loss": 0.5738,
|
| 813 |
+
"step": 1260
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.45,
|
| 817 |
+
"learning_rate": 1.1131138261952845e-05,
|
| 818 |
+
"loss": 0.5831,
|
| 819 |
+
"step": 1270
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.46,
|
| 823 |
+
"learning_rate": 1.100728566196041e-05,
|
| 824 |
+
"loss": 0.5732,
|
| 825 |
+
"step": 1280
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.47,
|
| 829 |
+
"learning_rate": 1.088327676281762e-05,
|
| 830 |
+
"loss": 0.5702,
|
| 831 |
+
"step": 1290
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.49,
|
| 835 |
+
"learning_rate": 1.0759130806817204e-05,
|
| 836 |
+
"loss": 0.5748,
|
| 837 |
+
"step": 1300
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.5,
|
| 841 |
+
"learning_rate": 1.0634867057518824e-05,
|
| 842 |
+
"loss": 0.5764,
|
| 843 |
+
"step": 1310
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.51,
|
| 847 |
+
"learning_rate": 1.0510504796759966e-05,
|
| 848 |
+
"loss": 0.5716,
|
| 849 |
+
"step": 1320
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.52,
|
| 853 |
+
"learning_rate": 1.0386063321664007e-05,
|
| 854 |
+
"loss": 0.5685,
|
| 855 |
+
"step": 1330
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.53,
|
| 859 |
+
"learning_rate": 1.0261561941645894e-05,
|
| 860 |
+
"loss": 0.5713,
|
| 861 |
+
"step": 1340
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.54,
|
| 865 |
+
"learning_rate": 1.013701997541596e-05,
|
| 866 |
+
"loss": 0.5668,
|
| 867 |
+
"step": 1350
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.55,
|
| 871 |
+
"learning_rate": 1.0012456747982231e-05,
|
| 872 |
+
"loss": 0.5714,
|
| 873 |
+
"step": 1360
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.57,
|
| 877 |
+
"learning_rate": 9.887891587651807e-06,
|
| 878 |
+
"loss": 0.5714,
|
| 879 |
+
"step": 1370
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.58,
|
| 883 |
+
"learning_rate": 9.763343823031718e-06,
|
| 884 |
+
"loss": 0.5702,
|
| 885 |
+
"step": 1380
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.59,
|
| 889 |
+
"learning_rate": 9.638832780029716e-06,
|
| 890 |
+
"loss": 0.5706,
|
| 891 |
+
"step": 1390
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.6,
|
| 895 |
+
"learning_rate": 9.514377778855521e-06,
|
| 896 |
+
"loss": 0.57,
|
| 897 |
+
"step": 1400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6,
|
| 901 |
+
"eval_loss": 0.5853541493415833,
|
| 902 |
+
"eval_runtime": 765.003,
|
| 903 |
+
"eval_samples_per_second": 16.268,
|
| 904 |
+
"eval_steps_per_second": 2.034,
|
| 905 |
+
"step": 1400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.61,
|
| 909 |
+
"learning_rate": 9.389998131022906e-06,
|
| 910 |
+
"loss": 0.563,
|
| 911 |
+
"step": 1410
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.62,
|
| 915 |
+
"learning_rate": 9.265713136353184e-06,
|
| 916 |
+
"loss": 0.5559,
|
| 917 |
+
"step": 1420
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.63,
|
| 921 |
+
"learning_rate": 9.141542079980453e-06,
|
| 922 |
+
"loss": 0.5765,
|
| 923 |
+
"step": 1430
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.65,
|
| 927 |
+
"learning_rate": 9.017504229359157e-06,
|
| 928 |
+
"loss": 0.5737,
|
| 929 |
+
"step": 1440
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.66,
|
| 933 |
+
"learning_rate": 8.893618831274399e-06,
|
| 934 |
+
"loss": 0.5588,
|
| 935 |
+
"step": 1450
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.67,
|
| 939 |
+
"learning_rate": 8.769905108855412e-06,
|
| 940 |
+
"loss": 0.5619,
|
| 941 |
+
"step": 1460
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.68,
|
| 945 |
+
"learning_rate": 8.646382258592762e-06,
|
| 946 |
+
"loss": 0.5612,
|
| 947 |
+
"step": 1470
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.69,
|
| 951 |
+
"learning_rate": 8.523069447359631e-06,
|
| 952 |
+
"loss": 0.5647,
|
| 953 |
+
"step": 1480
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.7,
|
| 957 |
+
"learning_rate": 8.399985809437737e-06,
|
| 958 |
+
"loss": 0.5803,
|
| 959 |
+
"step": 1490
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.71,
|
| 963 |
+
"learning_rate": 8.277150443548285e-06,
|
| 964 |
+
"loss": 0.554,
|
| 965 |
+
"step": 1500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.73,
|
| 969 |
+
"learning_rate": 8.154582409888441e-06,
|
| 970 |
+
"loss": 0.5734,
|
| 971 |
+
"step": 1510
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.74,
|
| 975 |
+
"learning_rate": 8.032300727173797e-06,
|
| 976 |
+
"loss": 0.5646,
|
| 977 |
+
"step": 1520
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.75,
|
| 981 |
+
"learning_rate": 7.91032436968725e-06,
|
| 982 |
+
"loss": 0.5665,
|
| 983 |
+
"step": 1530
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.76,
|
| 987 |
+
"learning_rate": 7.788672264334804e-06,
|
| 988 |
+
"loss": 0.5519,
|
| 989 |
+
"step": 1540
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.77,
|
| 993 |
+
"learning_rate": 7.667363287708692e-06,
|
| 994 |
+
"loss": 0.5676,
|
| 995 |
+
"step": 1550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.78,
|
| 999 |
+
"learning_rate": 7.546416263158326e-06,
|
| 1000 |
+
"loss": 0.5516,
|
| 1001 |
+
"step": 1560
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.79,
|
| 1005 |
+
"learning_rate": 7.42584995786952e-06,
|
| 1006 |
+
"loss": 0.5553,
|
| 1007 |
+
"step": 1570
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.81,
|
| 1011 |
+
"learning_rate": 7.305683079952381e-06,
|
| 1012 |
+
"loss": 0.56,
|
| 1013 |
+
"step": 1580
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.82,
|
| 1017 |
+
"learning_rate": 7.185934275538416e-06,
|
| 1018 |
+
"loss": 0.5715,
|
| 1019 |
+
"step": 1590
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.83,
|
| 1023 |
+
"learning_rate": 7.066622125887237e-06,
|
| 1024 |
+
"loss": 0.5459,
|
| 1025 |
+
"step": 1600
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.83,
|
| 1029 |
+
"eval_loss": 0.5793296098709106,
|
| 1030 |
+
"eval_runtime": 764.5785,
|
| 1031 |
+
"eval_samples_per_second": 16.277,
|
| 1032 |
+
"eval_steps_per_second": 2.035,
|
| 1033 |
+
"step": 1600
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.84,
|
| 1037 |
+
"learning_rate": 6.947765144503323e-06,
|
| 1038 |
+
"loss": 0.5499,
|
| 1039 |
+
"step": 1610
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.85,
|
| 1043 |
+
"learning_rate": 6.8293817742633175e-06,
|
| 1044 |
+
"loss": 0.5483,
|
| 1045 |
+
"step": 1620
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.86,
|
| 1049 |
+
"learning_rate": 6.711490384554257e-06,
|
| 1050 |
+
"loss": 0.5565,
|
| 1051 |
+
"step": 1630
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.87,
|
| 1055 |
+
"learning_rate": 6.59410926842323e-06,
|
| 1056 |
+
"loss": 0.5596,
|
| 1057 |
+
"step": 1640
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.89,
|
| 1061 |
+
"learning_rate": 6.477256639738872e-06,
|
| 1062 |
+
"loss": 0.5623,
|
| 1063 |
+
"step": 1650
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.9,
|
| 1067 |
+
"learning_rate": 6.360950630365126e-06,
|
| 1068 |
+
"loss": 0.5509,
|
| 1069 |
+
"step": 1660
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.91,
|
| 1073 |
+
"learning_rate": 6.245209287347767e-06,
|
| 1074 |
+
"loss": 0.561,
|
| 1075 |
+
"step": 1670
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.92,
|
| 1079 |
+
"learning_rate": 6.130050570114049e-06,
|
| 1080 |
+
"loss": 0.57,
|
| 1081 |
+
"step": 1680
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.93,
|
| 1085 |
+
"learning_rate": 6.015492347685983e-06,
|
| 1086 |
+
"loss": 0.5624,
|
| 1087 |
+
"step": 1690
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.94,
|
| 1091 |
+
"learning_rate": 5.901552395907606e-06,
|
| 1092 |
+
"loss": 0.5574,
|
| 1093 |
+
"step": 1700
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.95,
|
| 1097 |
+
"learning_rate": 5.788248394686743e-06,
|
| 1098 |
+
"loss": 0.5588,
|
| 1099 |
+
"step": 1710
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.97,
|
| 1103 |
+
"learning_rate": 5.67559792525163e-06,
|
| 1104 |
+
"loss": 0.5487,
|
| 1105 |
+
"step": 1720
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.98,
|
| 1109 |
+
"learning_rate": 5.563618467422864e-06,
|
| 1110 |
+
"loss": 0.5579,
|
| 1111 |
+
"step": 1730
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 1.99,
|
| 1115 |
+
"learning_rate": 5.452327396901078e-06,
|
| 1116 |
+
"loss": 0.5577,
|
| 1117 |
+
"step": 1740
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.0,
|
| 1121 |
+
"learning_rate": 5.341741982570789e-06,
|
| 1122 |
+
"loss": 0.5519,
|
| 1123 |
+
"step": 1750
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.01,
|
| 1127 |
+
"learning_rate": 5.231879383820782e-06,
|
| 1128 |
+
"loss": 0.5664,
|
| 1129 |
+
"step": 1760
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.02,
|
| 1133 |
+
"learning_rate": 5.122756647881543e-06,
|
| 1134 |
+
"loss": 0.5572,
|
| 1135 |
+
"step": 1770
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.03,
|
| 1139 |
+
"learning_rate": 5.0143907071800445e-06,
|
| 1140 |
+
"loss": 0.5516,
|
| 1141 |
+
"step": 1780
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.05,
|
| 1145 |
+
"learning_rate": 4.9067983767123736e-06,
|
| 1146 |
+
"loss": 0.5498,
|
| 1147 |
+
"step": 1790
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.06,
|
| 1151 |
+
"learning_rate": 4.79999635143455e-06,
|
| 1152 |
+
"loss": 0.571,
|
| 1153 |
+
"step": 1800
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.06,
|
| 1157 |
+
"eval_loss": 0.5752249956130981,
|
| 1158 |
+
"eval_runtime": 764.7047,
|
| 1159 |
+
"eval_samples_per_second": 16.274,
|
| 1160 |
+
"eval_steps_per_second": 2.035,
|
| 1161 |
+
"step": 1800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.07,
|
| 1165 |
+
"learning_rate": 4.694001203672028e-06,
|
| 1166 |
+
"loss": 0.5661,
|
| 1167 |
+
"step": 1810
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.08,
|
| 1171 |
+
"learning_rate": 4.588829380548168e-06,
|
| 1172 |
+
"loss": 0.5733,
|
| 1173 |
+
"step": 1820
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.09,
|
| 1177 |
+
"learning_rate": 4.484497201432147e-06,
|
| 1178 |
+
"loss": 0.5725,
|
| 1179 |
+
"step": 1830
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.1,
|
| 1183 |
+
"learning_rate": 4.381020855406738e-06,
|
| 1184 |
+
"loss": 0.556,
|
| 1185 |
+
"step": 1840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.11,
|
| 1189 |
+
"learning_rate": 4.278416398756245e-06,
|
| 1190 |
+
"loss": 0.5671,
|
| 1191 |
+
"step": 1850
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.13,
|
| 1195 |
+
"learning_rate": 4.176699752475087e-06,
|
| 1196 |
+
"loss": 0.566,
|
| 1197 |
+
"step": 1860
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.14,
|
| 1201 |
+
"learning_rate": 4.075886699797338e-06,
|
| 1202 |
+
"loss": 0.5692,
|
| 1203 |
+
"step": 1870
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.15,
|
| 1207 |
+
"learning_rate": 3.975992883747688e-06,
|
| 1208 |
+
"loss": 0.5582,
|
| 1209 |
+
"step": 1880
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.16,
|
| 1213 |
+
"learning_rate": 3.877033804714133e-06,
|
| 1214 |
+
"loss": 0.5477,
|
| 1215 |
+
"step": 1890
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.17,
|
| 1219 |
+
"learning_rate": 3.7790248180427758e-06,
|
| 1220 |
+
"loss": 0.5488,
|
| 1221 |
+
"step": 1900
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.18,
|
| 1225 |
+
"learning_rate": 3.6819811316551867e-06,
|
| 1226 |
+
"loss": 0.5591,
|
| 1227 |
+
"step": 1910
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.19,
|
| 1231 |
+
"learning_rate": 3.585917803688603e-06,
|
| 1232 |
+
"loss": 0.5548,
|
| 1233 |
+
"step": 1920
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.21,
|
| 1237 |
+
"learning_rate": 3.4908497401593634e-06,
|
| 1238 |
+
"loss": 0.5517,
|
| 1239 |
+
"step": 1930
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.22,
|
| 1243 |
+
"learning_rate": 3.3967916926499823e-06,
|
| 1244 |
+
"loss": 0.556,
|
| 1245 |
+
"step": 1940
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.23,
|
| 1249 |
+
"learning_rate": 3.303758256020154e-06,
|
| 1250 |
+
"loss": 0.5398,
|
| 1251 |
+
"step": 1950
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.24,
|
| 1255 |
+
"learning_rate": 3.211763866142097e-06,
|
| 1256 |
+
"loss": 0.5487,
|
| 1257 |
+
"step": 1960
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.25,
|
| 1261 |
+
"learning_rate": 3.1208227976605475e-06,
|
| 1262 |
+
"loss": 0.5503,
|
| 1263 |
+
"step": 1970
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.26,
|
| 1267 |
+
"learning_rate": 3.0309491617777943e-06,
|
| 1268 |
+
"loss": 0.5609,
|
| 1269 |
+
"step": 1980
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.27,
|
| 1273 |
+
"learning_rate": 2.9421569040640564e-06,
|
| 1274 |
+
"loss": 0.5569,
|
| 1275 |
+
"step": 1990
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.29,
|
| 1279 |
+
"learning_rate": 2.854459802293561e-06,
|
| 1280 |
+
"loss": 0.5558,
|
| 1281 |
+
"step": 2000
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.29,
|
| 1285 |
+
"eval_loss": 0.5727296471595764,
|
| 1286 |
+
"eval_runtime": 764.8947,
|
| 1287 |
+
"eval_samples_per_second": 16.27,
|
| 1288 |
+
"eval_steps_per_second": 2.034,
|
| 1289 |
+
"step": 2000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.3,
|
| 1293 |
+
"learning_rate": 2.767871464306682e-06,
|
| 1294 |
+
"loss": 0.5596,
|
| 1295 |
+
"step": 2010
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 2.31,
|
| 1299 |
+
"learning_rate": 2.682405325898416e-06,
|
| 1300 |
+
"loss": 0.5565,
|
| 1301 |
+
"step": 2020
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.32,
|
| 1305 |
+
"learning_rate": 2.5980746487335785e-06,
|
| 1306 |
+
"loss": 0.5482,
|
| 1307 |
+
"step": 2030
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.33,
|
| 1311 |
+
"learning_rate": 2.514892518288988e-06,
|
| 1312 |
+
"loss": 0.559,
|
| 1313 |
+
"step": 2040
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.34,
|
| 1317 |
+
"learning_rate": 2.432871841823047e-06,
|
| 1318 |
+
"loss": 0.5621,
|
| 1319 |
+
"step": 2050
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.35,
|
| 1323 |
+
"learning_rate": 2.3520253463729058e-06,
|
| 1324 |
+
"loss": 0.5485,
|
| 1325 |
+
"step": 2060
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.37,
|
| 1329 |
+
"learning_rate": 2.272365576779637e-06,
|
| 1330 |
+
"loss": 0.5598,
|
| 1331 |
+
"step": 2070
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 2.38,
|
| 1335 |
+
"learning_rate": 2.1939048937416783e-06,
|
| 1336 |
+
"loss": 0.5655,
|
| 1337 |
+
"step": 2080
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.39,
|
| 1341 |
+
"learning_rate": 2.116655471896828e-06,
|
| 1342 |
+
"loss": 0.5522,
|
| 1343 |
+
"step": 2090
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.4,
|
| 1347 |
+
"learning_rate": 2.0406292979331333e-06,
|
| 1348 |
+
"loss": 0.552,
|
| 1349 |
+
"step": 2100
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.41,
|
| 1353 |
+
"learning_rate": 1.965838168728912e-06,
|
| 1354 |
+
"loss": 0.5565,
|
| 1355 |
+
"step": 2110
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.42,
|
| 1359 |
+
"learning_rate": 1.8922936895222798e-06,
|
| 1360 |
+
"loss": 0.5576,
|
| 1361 |
+
"step": 2120
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.43,
|
| 1365 |
+
"learning_rate": 1.8200072721103545e-06,
|
| 1366 |
+
"loss": 0.5629,
|
| 1367 |
+
"step": 2130
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.45,
|
| 1371 |
+
"learning_rate": 1.7489901330785053e-06,
|
| 1372 |
+
"loss": 0.5461,
|
| 1373 |
+
"step": 2140
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 2.46,
|
| 1377 |
+
"learning_rate": 1.6792532920599025e-06,
|
| 1378 |
+
"loss": 0.5503,
|
| 1379 |
+
"step": 2150
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 2.47,
|
| 1383 |
+
"learning_rate": 1.610807570025611e-06,
|
| 1384 |
+
"loss": 0.5422,
|
| 1385 |
+
"step": 2160
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.48,
|
| 1389 |
+
"learning_rate": 1.5436635876055107e-06,
|
| 1390 |
+
"loss": 0.5537,
|
| 1391 |
+
"step": 2170
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.49,
|
| 1395 |
+
"learning_rate": 1.4778317634403082e-06,
|
| 1396 |
+
"loss": 0.5676,
|
| 1397 |
+
"step": 2180
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.5,
|
| 1401 |
+
"learning_rate": 1.4133223125648966e-06,
|
| 1402 |
+
"loss": 0.5664,
|
| 1403 |
+
"step": 2190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.51,
|
| 1407 |
+
"learning_rate": 1.350145244823302e-06,
|
| 1408 |
+
"loss": 0.5467,
|
| 1409 |
+
"step": 2200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.51,
|
| 1413 |
+
"eval_loss": 0.5713418126106262,
|
| 1414 |
+
"eval_runtime": 764.6146,
|
| 1415 |
+
"eval_samples_per_second": 16.276,
|
| 1416 |
+
"eval_steps_per_second": 2.035,
|
| 1417 |
+
"step": 2200
|
| 1418 |
+
}
|
| 1419 |
+
],
|
| 1420 |
+
"logging_steps": 10,
|
| 1421 |
+
"max_steps": 2622,
|
| 1422 |
+
"num_train_epochs": 3,
|
| 1423 |
+
"save_steps": 200,
|
| 1424 |
+
"total_flos": 2.647958121057878e+18,
|
| 1425 |
+
"trial_name": null,
|
| 1426 |
+
"trial_params": null
|
| 1427 |
+
}
|
checkpoint-2200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:351af72ecf82c54d3b93447930b5e2d6fab44f4b186eb4be6787a376d125d1f7
|
| 3 |
+
size 4472
|
checkpoint-2400/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: medalpaca/medalpaca-7b
|
| 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 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
- PEFT 0.6.0.dev0
|
checkpoint-2400/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "medalpaca/medalpaca-7b",
|
| 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 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 8,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-2400/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7eaa51169fb5f5f33b328f26090dcd19a47bde0a9efe64e78856dbbe04a07e7a
|
| 3 |
+
size 888
|
checkpoint-2400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96d7dc44adb0f0c8d32d26358ab1277100852045c5423c39c137902c2aa57f1
|
| 3 |
+
size 33662074
|
checkpoint-2400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:281cb51e0363cc6aea0d39fefd292074a4c176f7921d09e56b746f6cc5a89420
|
| 3 |
+
size 14244
|
checkpoint-2400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c0b2e8d6b725b1c92875b2a30cbfd2e758bb4b3a007ceb3d7370e5b1326cdd1
|
| 3 |
+
size 1064
|
checkpoint-2400/trainer_state.json
ADDED
|
@@ -0,0 +1,1555 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5707904696464539,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-2400",
|
| 4 |
+
"epoch": 2.7429551055394836,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 14 |
+
"loss": 3.282,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 4.000000000000001e-06,
|
| 20 |
+
"loss": 3.2806,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 6e-06,
|
| 26 |
+
"loss": 3.2842,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 8.000000000000001e-06,
|
| 32 |
+
"loss": 3.2378,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 1e-05,
|
| 38 |
+
"loss": 3.202,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 1.2e-05,
|
| 44 |
+
"loss": 3.1307,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"learning_rate": 1.4e-05,
|
| 50 |
+
"loss": 3.0392,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 56 |
+
"loss": 2.9102,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.1,
|
| 61 |
+
"learning_rate": 1.8e-05,
|
| 62 |
+
"loss": 2.7595,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.11,
|
| 67 |
+
"learning_rate": 2e-05,
|
| 68 |
+
"loss": 2.5737,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 1.9999224156779658e-05,
|
| 74 |
+
"loss": 2.347,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.14,
|
| 79 |
+
"learning_rate": 1.999689674750517e-05,
|
| 80 |
+
"loss": 2.0934,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15,
|
| 85 |
+
"learning_rate": 1.9993018133317476e-05,
|
| 86 |
+
"loss": 1.8305,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16,
|
| 91 |
+
"learning_rate": 1.998758891605588e-05,
|
| 92 |
+
"loss": 1.5447,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17,
|
| 97 |
+
"learning_rate": 1.9980609938164664e-05,
|
| 98 |
+
"loss": 1.3394,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.18,
|
| 103 |
+
"learning_rate": 1.9972082282562367e-05,
|
| 104 |
+
"loss": 1.2032,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.19,
|
| 109 |
+
"learning_rate": 1.9962007272473744e-05,
|
| 110 |
+
"loss": 1.1096,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.21,
|
| 115 |
+
"learning_rate": 1.9950386471224445e-05,
|
| 116 |
+
"loss": 1.0456,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.22,
|
| 121 |
+
"learning_rate": 1.9937221681998447e-05,
|
| 122 |
+
"loss": 0.9977,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23,
|
| 127 |
+
"learning_rate": 1.9922514947558248e-05,
|
| 128 |
+
"loss": 0.9786,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.23,
|
| 133 |
+
"eval_loss": 0.982032299041748,
|
| 134 |
+
"eval_runtime": 759.4598,
|
| 135 |
+
"eval_samples_per_second": 16.387,
|
| 136 |
+
"eval_steps_per_second": 2.049,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.24,
|
| 141 |
+
"learning_rate": 1.9906268549927886e-05,
|
| 142 |
+
"loss": 0.948,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.25,
|
| 147 |
+
"learning_rate": 1.9888485010038848e-05,
|
| 148 |
+
"loss": 0.9164,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.26,
|
| 153 |
+
"learning_rate": 1.9869167087338908e-05,
|
| 154 |
+
"loss": 0.8977,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.27,
|
| 159 |
+
"learning_rate": 1.984831777936394e-05,
|
| 160 |
+
"loss": 0.876,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.29,
|
| 165 |
+
"learning_rate": 1.9825940321272792e-05,
|
| 166 |
+
"loss": 0.8604,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.3,
|
| 171 |
+
"learning_rate": 1.980203818534529e-05,
|
| 172 |
+
"loss": 0.8424,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.31,
|
| 177 |
+
"learning_rate": 1.9776615080443462e-05,
|
| 178 |
+
"loss": 0.8434,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.32,
|
| 183 |
+
"learning_rate": 1.9749674951436016e-05,
|
| 184 |
+
"loss": 0.8357,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.33,
|
| 189 |
+
"learning_rate": 1.972122197858625e-05,
|
| 190 |
+
"loss": 0.8239,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.34,
|
| 195 |
+
"learning_rate": 1.9691260576903372e-05,
|
| 196 |
+
"loss": 0.8177,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.35,
|
| 201 |
+
"learning_rate": 1.965979539545746e-05,
|
| 202 |
+
"loss": 0.8151,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.37,
|
| 207 |
+
"learning_rate": 1.9626831316658058e-05,
|
| 208 |
+
"loss": 0.8074,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.38,
|
| 213 |
+
"learning_rate": 1.959237345549657e-05,
|
| 214 |
+
"loss": 0.7768,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.39,
|
| 219 |
+
"learning_rate": 1.955642715875259e-05,
|
| 220 |
+
"loss": 0.7673,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.4,
|
| 225 |
+
"learning_rate": 1.951899800416425e-05,
|
| 226 |
+
"loss": 0.7448,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.41,
|
| 231 |
+
"learning_rate": 1.9480091799562706e-05,
|
| 232 |
+
"loss": 0.7334,
|
| 233 |
+
"step": 360
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.42,
|
| 237 |
+
"learning_rate": 1.9439714581970983e-05,
|
| 238 |
+
"loss": 0.734,
|
| 239 |
+
"step": 370
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.43,
|
| 243 |
+
"learning_rate": 1.9397872616667175e-05,
|
| 244 |
+
"loss": 0.7301,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.45,
|
| 249 |
+
"learning_rate": 1.935457239621231e-05,
|
| 250 |
+
"loss": 0.734,
|
| 251 |
+
"step": 390
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.46,
|
| 255 |
+
"learning_rate": 1.9309820639442886e-05,
|
| 256 |
+
"loss": 0.7062,
|
| 257 |
+
"step": 400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.46,
|
| 261 |
+
"eval_loss": 0.7326281070709229,
|
| 262 |
+
"eval_runtime": 757.8879,
|
| 263 |
+
"eval_samples_per_second": 16.421,
|
| 264 |
+
"eval_steps_per_second": 2.053,
|
| 265 |
+
"step": 400
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.47,
|
| 269 |
+
"learning_rate": 1.9263624290428314e-05,
|
| 270 |
+
"loss": 0.7074,
|
| 271 |
+
"step": 410
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.48,
|
| 275 |
+
"learning_rate": 1.9215990517393436e-05,
|
| 276 |
+
"loss": 0.7001,
|
| 277 |
+
"step": 420
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.49,
|
| 281 |
+
"learning_rate": 1.9166926711606222e-05,
|
| 282 |
+
"loss": 0.6991,
|
| 283 |
+
"step": 430
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"learning_rate": 1.9116440486230893e-05,
|
| 288 |
+
"loss": 0.6935,
|
| 289 |
+
"step": 440
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.51,
|
| 293 |
+
"learning_rate": 1.9064539675146584e-05,
|
| 294 |
+
"loss": 0.6922,
|
| 295 |
+
"step": 450
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.53,
|
| 299 |
+
"learning_rate": 1.9011232331731773e-05,
|
| 300 |
+
"loss": 0.6861,
|
| 301 |
+
"step": 460
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.54,
|
| 305 |
+
"learning_rate": 1.8956526727614663e-05,
|
| 306 |
+
"loss": 0.6978,
|
| 307 |
+
"step": 470
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.55,
|
| 311 |
+
"learning_rate": 1.8900431351389657e-05,
|
| 312 |
+
"loss": 0.6699,
|
| 313 |
+
"step": 480
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.56,
|
| 317 |
+
"learning_rate": 1.8842954907300236e-05,
|
| 318 |
+
"loss": 0.6846,
|
| 319 |
+
"step": 490
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.57,
|
| 323 |
+
"learning_rate": 1.878410631388829e-05,
|
| 324 |
+
"loss": 0.6772,
|
| 325 |
+
"step": 500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.58,
|
| 329 |
+
"learning_rate": 1.8723894702610258e-05,
|
| 330 |
+
"loss": 0.6808,
|
| 331 |
+
"step": 510
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.59,
|
| 335 |
+
"learning_rate": 1.866232941642023e-05,
|
| 336 |
+
"loss": 0.6869,
|
| 337 |
+
"step": 520
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.61,
|
| 341 |
+
"learning_rate": 1.8599420008320176e-05,
|
| 342 |
+
"loss": 0.6595,
|
| 343 |
+
"step": 530
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.62,
|
| 347 |
+
"learning_rate": 1.8535176239877653e-05,
|
| 348 |
+
"loss": 0.6669,
|
| 349 |
+
"step": 540
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.63,
|
| 353 |
+
"learning_rate": 1.8469608079711105e-05,
|
| 354 |
+
"loss": 0.6648,
|
| 355 |
+
"step": 550
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.64,
|
| 359 |
+
"learning_rate": 1.8402725701943028e-05,
|
| 360 |
+
"loss": 0.6486,
|
| 361 |
+
"step": 560
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.65,
|
| 365 |
+
"learning_rate": 1.8334539484621304e-05,
|
| 366 |
+
"loss": 0.6735,
|
| 367 |
+
"step": 570
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.66,
|
| 371 |
+
"learning_rate": 1.8265060008108815e-05,
|
| 372 |
+
"loss": 0.6498,
|
| 373 |
+
"step": 580
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.67,
|
| 377 |
+
"learning_rate": 1.8194298053441725e-05,
|
| 378 |
+
"loss": 0.6578,
|
| 379 |
+
"step": 590
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.69,
|
| 383 |
+
"learning_rate": 1.812226460065658e-05,
|
| 384 |
+
"loss": 0.6392,
|
| 385 |
+
"step": 600
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.69,
|
| 389 |
+
"eval_loss": 0.6629914045333862,
|
| 390 |
+
"eval_runtime": 765.6279,
|
| 391 |
+
"eval_samples_per_second": 16.255,
|
| 392 |
+
"eval_steps_per_second": 2.032,
|
| 393 |
+
"step": 600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.7,
|
| 397 |
+
"learning_rate": 1.804897082708659e-05,
|
| 398 |
+
"loss": 0.6524,
|
| 399 |
+
"step": 610
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.71,
|
| 403 |
+
"learning_rate": 1.797442810562721e-05,
|
| 404 |
+
"loss": 0.6513,
|
| 405 |
+
"step": 620
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.72,
|
| 409 |
+
"learning_rate": 1.7898648002971456e-05,
|
| 410 |
+
"loss": 0.6466,
|
| 411 |
+
"step": 630
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.73,
|
| 415 |
+
"learning_rate": 1.7821642277815108e-05,
|
| 416 |
+
"loss": 0.6305,
|
| 417 |
+
"step": 640
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.74,
|
| 421 |
+
"learning_rate": 1.774342287903212e-05,
|
| 422 |
+
"loss": 0.6418,
|
| 423 |
+
"step": 650
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.75,
|
| 427 |
+
"learning_rate": 1.766400194382054e-05,
|
| 428 |
+
"loss": 0.636,
|
| 429 |
+
"step": 660
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.77,
|
| 433 |
+
"learning_rate": 1.75833917958192e-05,
|
| 434 |
+
"loss": 0.6279,
|
| 435 |
+
"step": 670
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.78,
|
| 439 |
+
"learning_rate": 1.7501604943195466e-05,
|
| 440 |
+
"loss": 0.6369,
|
| 441 |
+
"step": 680
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.79,
|
| 445 |
+
"learning_rate": 1.741865407670435e-05,
|
| 446 |
+
"loss": 0.6308,
|
| 447 |
+
"step": 690
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.8,
|
| 451 |
+
"learning_rate": 1.733455206771934e-05,
|
| 452 |
+
"loss": 0.616,
|
| 453 |
+
"step": 700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.81,
|
| 457 |
+
"learning_rate": 1.724931196623513e-05,
|
| 458 |
+
"loss": 0.6334,
|
| 459 |
+
"step": 710
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.82,
|
| 463 |
+
"learning_rate": 1.716294699884269e-05,
|
| 464 |
+
"loss": 0.6289,
|
| 465 |
+
"step": 720
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.83,
|
| 469 |
+
"learning_rate": 1.70754705666769e-05,
|
| 470 |
+
"loss": 0.6251,
|
| 471 |
+
"step": 730
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.85,
|
| 475 |
+
"learning_rate": 1.6986896243337137e-05,
|
| 476 |
+
"loss": 0.619,
|
| 477 |
+
"step": 740
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.86,
|
| 481 |
+
"learning_rate": 1.6897237772781046e-05,
|
| 482 |
+
"loss": 0.6226,
|
| 483 |
+
"step": 750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.87,
|
| 487 |
+
"learning_rate": 1.6806509067191926e-05,
|
| 488 |
+
"loss": 0.6229,
|
| 489 |
+
"step": 760
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.88,
|
| 493 |
+
"learning_rate": 1.6714724204820017e-05,
|
| 494 |
+
"loss": 0.6016,
|
| 495 |
+
"step": 770
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.89,
|
| 499 |
+
"learning_rate": 1.6621897427797947e-05,
|
| 500 |
+
"loss": 0.6061,
|
| 501 |
+
"step": 780
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.9,
|
| 505 |
+
"learning_rate": 1.6528043139930845e-05,
|
| 506 |
+
"loss": 0.6027,
|
| 507 |
+
"step": 790
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.91,
|
| 511 |
+
"learning_rate": 1.64331759044613e-05,
|
| 512 |
+
"loss": 0.6018,
|
| 513 |
+
"step": 800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.91,
|
| 517 |
+
"eval_loss": 0.6285067796707153,
|
| 518 |
+
"eval_runtime": 765.1757,
|
| 519 |
+
"eval_samples_per_second": 16.264,
|
| 520 |
+
"eval_steps_per_second": 2.034,
|
| 521 |
+
"step": 800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.93,
|
| 525 |
+
"learning_rate": 1.63373104418096e-05,
|
| 526 |
+
"loss": 0.6094,
|
| 527 |
+
"step": 810
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.94,
|
| 531 |
+
"learning_rate": 1.6240461627289607e-05,
|
| 532 |
+
"loss": 0.6224,
|
| 533 |
+
"step": 820
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.95,
|
| 537 |
+
"learning_rate": 1.614264448880054e-05,
|
| 538 |
+
"loss": 0.6032,
|
| 539 |
+
"step": 830
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.96,
|
| 543 |
+
"learning_rate": 1.6043874204495152e-05,
|
| 544 |
+
"loss": 0.6048,
|
| 545 |
+
"step": 840
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.97,
|
| 549 |
+
"learning_rate": 1.5944166100424534e-05,
|
| 550 |
+
"loss": 0.6036,
|
| 551 |
+
"step": 850
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.98,
|
| 555 |
+
"learning_rate": 1.584353564815999e-05,
|
| 556 |
+
"loss": 0.5932,
|
| 557 |
+
"step": 860
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.99,
|
| 561 |
+
"learning_rate": 1.5741998462392352e-05,
|
| 562 |
+
"loss": 0.6003,
|
| 563 |
+
"step": 870
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.01,
|
| 567 |
+
"learning_rate": 1.5639570298509067e-05,
|
| 568 |
+
"loss": 0.6128,
|
| 569 |
+
"step": 880
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.02,
|
| 573 |
+
"learning_rate": 1.5536267050149428e-05,
|
| 574 |
+
"loss": 0.5968,
|
| 575 |
+
"step": 890
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.03,
|
| 579 |
+
"learning_rate": 1.5432104746738417e-05,
|
| 580 |
+
"loss": 0.6027,
|
| 581 |
+
"step": 900
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.04,
|
| 585 |
+
"learning_rate": 1.5327099550999416e-05,
|
| 586 |
+
"loss": 0.6122,
|
| 587 |
+
"step": 910
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.05,
|
| 591 |
+
"learning_rate": 1.5221267756446266e-05,
|
| 592 |
+
"loss": 0.5984,
|
| 593 |
+
"step": 920
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.06,
|
| 597 |
+
"learning_rate": 1.5114625784855028e-05,
|
| 598 |
+
"loss": 0.5965,
|
| 599 |
+
"step": 930
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.07,
|
| 603 |
+
"learning_rate": 1.5007190183715836e-05,
|
| 604 |
+
"loss": 0.5942,
|
| 605 |
+
"step": 940
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.09,
|
| 609 |
+
"learning_rate": 1.4898977623665243e-05,
|
| 610 |
+
"loss": 0.6,
|
| 611 |
+
"step": 950
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.1,
|
| 615 |
+
"learning_rate": 1.4790004895899465e-05,
|
| 616 |
+
"loss": 0.6051,
|
| 617 |
+
"step": 960
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.11,
|
| 621 |
+
"learning_rate": 1.4680288909568905e-05,
|
| 622 |
+
"loss": 0.5903,
|
| 623 |
+
"step": 970
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.12,
|
| 627 |
+
"learning_rate": 1.4569846689154401e-05,
|
| 628 |
+
"loss": 0.6049,
|
| 629 |
+
"step": 980
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.13,
|
| 633 |
+
"learning_rate": 1.4458695371825535e-05,
|
| 634 |
+
"loss": 0.5852,
|
| 635 |
+
"step": 990
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.14,
|
| 639 |
+
"learning_rate": 1.4346852204781511e-05,
|
| 640 |
+
"loss": 0.5869,
|
| 641 |
+
"step": 1000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.14,
|
| 645 |
+
"eval_loss": 0.6076732277870178,
|
| 646 |
+
"eval_runtime": 765.3772,
|
| 647 |
+
"eval_samples_per_second": 16.26,
|
| 648 |
+
"eval_steps_per_second": 2.033,
|
| 649 |
+
"step": 1000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.15,
|
| 653 |
+
"learning_rate": 1.4234334542574906e-05,
|
| 654 |
+
"loss": 0.5893,
|
| 655 |
+
"step": 1010
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.17,
|
| 659 |
+
"learning_rate": 1.4121159844418793e-05,
|
| 660 |
+
"loss": 0.5874,
|
| 661 |
+
"step": 1020
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.18,
|
| 665 |
+
"learning_rate": 1.400734567147763e-05,
|
| 666 |
+
"loss": 0.595,
|
| 667 |
+
"step": 1030
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.19,
|
| 671 |
+
"learning_rate": 1.3892909684142311e-05,
|
| 672 |
+
"loss": 0.5961,
|
| 673 |
+
"step": 1040
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.2,
|
| 677 |
+
"learning_rate": 1.3777869639289822e-05,
|
| 678 |
+
"loss": 0.5826,
|
| 679 |
+
"step": 1050
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.21,
|
| 683 |
+
"learning_rate": 1.3662243387527936e-05,
|
| 684 |
+
"loss": 0.5835,
|
| 685 |
+
"step": 1060
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.22,
|
| 689 |
+
"learning_rate": 1.3546048870425356e-05,
|
| 690 |
+
"loss": 0.5858,
|
| 691 |
+
"step": 1070
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.23,
|
| 695 |
+
"learning_rate": 1.3429304117727755e-05,
|
| 696 |
+
"loss": 0.5931,
|
| 697 |
+
"step": 1080
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.25,
|
| 701 |
+
"learning_rate": 1.3312027244560104e-05,
|
| 702 |
+
"loss": 0.5858,
|
| 703 |
+
"step": 1090
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.26,
|
| 707 |
+
"learning_rate": 1.3194236448615798e-05,
|
| 708 |
+
"loss": 0.5834,
|
| 709 |
+
"step": 1100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.27,
|
| 713 |
+
"learning_rate": 1.3075950007332923e-05,
|
| 714 |
+
"loss": 0.5854,
|
| 715 |
+
"step": 1110
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.28,
|
| 719 |
+
"learning_rate": 1.2957186275058188e-05,
|
| 720 |
+
"loss": 0.5879,
|
| 721 |
+
"step": 1120
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.29,
|
| 725 |
+
"learning_rate": 1.2837963680198895e-05,
|
| 726 |
+
"loss": 0.5958,
|
| 727 |
+
"step": 1130
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.3,
|
| 731 |
+
"learning_rate": 1.2718300722363431e-05,
|
| 732 |
+
"loss": 0.5787,
|
| 733 |
+
"step": 1140
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.31,
|
| 737 |
+
"learning_rate": 1.2598215969490703e-05,
|
| 738 |
+
"loss": 0.5827,
|
| 739 |
+
"step": 1150
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.33,
|
| 743 |
+
"learning_rate": 1.2477728054968993e-05,
|
| 744 |
+
"loss": 0.589,
|
| 745 |
+
"step": 1160
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.34,
|
| 749 |
+
"learning_rate": 1.2356855674744625e-05,
|
| 750 |
+
"loss": 0.5806,
|
| 751 |
+
"step": 1170
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.35,
|
| 755 |
+
"learning_rate": 1.2235617584420938e-05,
|
| 756 |
+
"loss": 0.563,
|
| 757 |
+
"step": 1180
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.36,
|
| 761 |
+
"learning_rate": 1.2114032596348023e-05,
|
| 762 |
+
"loss": 0.5812,
|
| 763 |
+
"step": 1190
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.37,
|
| 767 |
+
"learning_rate": 1.1992119576703614e-05,
|
| 768 |
+
"loss": 0.5995,
|
| 769 |
+
"step": 1200
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.37,
|
| 773 |
+
"eval_loss": 0.5944839119911194,
|
| 774 |
+
"eval_runtime": 764.7162,
|
| 775 |
+
"eval_samples_per_second": 16.274,
|
| 776 |
+
"eval_steps_per_second": 2.035,
|
| 777 |
+
"step": 1200
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.38,
|
| 781 |
+
"learning_rate": 1.1869897442565665e-05,
|
| 782 |
+
"loss": 0.5852,
|
| 783 |
+
"step": 1210
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.39,
|
| 787 |
+
"learning_rate": 1.1747385158977008e-05,
|
| 788 |
+
"loss": 0.5798,
|
| 789 |
+
"step": 1220
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.41,
|
| 793 |
+
"learning_rate": 1.162460173600256e-05,
|
| 794 |
+
"loss": 0.5846,
|
| 795 |
+
"step": 1230
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.42,
|
| 799 |
+
"learning_rate": 1.1501566225779592e-05,
|
| 800 |
+
"loss": 0.5674,
|
| 801 |
+
"step": 1240
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.43,
|
| 805 |
+
"learning_rate": 1.1378297719561388e-05,
|
| 806 |
+
"loss": 0.5616,
|
| 807 |
+
"step": 1250
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.44,
|
| 811 |
+
"learning_rate": 1.1254815344754919e-05,
|
| 812 |
+
"loss": 0.5738,
|
| 813 |
+
"step": 1260
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.45,
|
| 817 |
+
"learning_rate": 1.1131138261952845e-05,
|
| 818 |
+
"loss": 0.5831,
|
| 819 |
+
"step": 1270
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.46,
|
| 823 |
+
"learning_rate": 1.100728566196041e-05,
|
| 824 |
+
"loss": 0.5732,
|
| 825 |
+
"step": 1280
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.47,
|
| 829 |
+
"learning_rate": 1.088327676281762e-05,
|
| 830 |
+
"loss": 0.5702,
|
| 831 |
+
"step": 1290
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.49,
|
| 835 |
+
"learning_rate": 1.0759130806817204e-05,
|
| 836 |
+
"loss": 0.5748,
|
| 837 |
+
"step": 1300
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.5,
|
| 841 |
+
"learning_rate": 1.0634867057518824e-05,
|
| 842 |
+
"loss": 0.5764,
|
| 843 |
+
"step": 1310
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.51,
|
| 847 |
+
"learning_rate": 1.0510504796759966e-05,
|
| 848 |
+
"loss": 0.5716,
|
| 849 |
+
"step": 1320
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.52,
|
| 853 |
+
"learning_rate": 1.0386063321664007e-05,
|
| 854 |
+
"loss": 0.5685,
|
| 855 |
+
"step": 1330
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.53,
|
| 859 |
+
"learning_rate": 1.0261561941645894e-05,
|
| 860 |
+
"loss": 0.5713,
|
| 861 |
+
"step": 1340
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.54,
|
| 865 |
+
"learning_rate": 1.013701997541596e-05,
|
| 866 |
+
"loss": 0.5668,
|
| 867 |
+
"step": 1350
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.55,
|
| 871 |
+
"learning_rate": 1.0012456747982231e-05,
|
| 872 |
+
"loss": 0.5714,
|
| 873 |
+
"step": 1360
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.57,
|
| 877 |
+
"learning_rate": 9.887891587651807e-06,
|
| 878 |
+
"loss": 0.5714,
|
| 879 |
+
"step": 1370
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.58,
|
| 883 |
+
"learning_rate": 9.763343823031718e-06,
|
| 884 |
+
"loss": 0.5702,
|
| 885 |
+
"step": 1380
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.59,
|
| 889 |
+
"learning_rate": 9.638832780029716e-06,
|
| 890 |
+
"loss": 0.5706,
|
| 891 |
+
"step": 1390
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.6,
|
| 895 |
+
"learning_rate": 9.514377778855521e-06,
|
| 896 |
+
"loss": 0.57,
|
| 897 |
+
"step": 1400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6,
|
| 901 |
+
"eval_loss": 0.5853541493415833,
|
| 902 |
+
"eval_runtime": 765.003,
|
| 903 |
+
"eval_samples_per_second": 16.268,
|
| 904 |
+
"eval_steps_per_second": 2.034,
|
| 905 |
+
"step": 1400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.61,
|
| 909 |
+
"learning_rate": 9.389998131022906e-06,
|
| 910 |
+
"loss": 0.563,
|
| 911 |
+
"step": 1410
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.62,
|
| 915 |
+
"learning_rate": 9.265713136353184e-06,
|
| 916 |
+
"loss": 0.5559,
|
| 917 |
+
"step": 1420
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.63,
|
| 921 |
+
"learning_rate": 9.141542079980453e-06,
|
| 922 |
+
"loss": 0.5765,
|
| 923 |
+
"step": 1430
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.65,
|
| 927 |
+
"learning_rate": 9.017504229359157e-06,
|
| 928 |
+
"loss": 0.5737,
|
| 929 |
+
"step": 1440
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.66,
|
| 933 |
+
"learning_rate": 8.893618831274399e-06,
|
| 934 |
+
"loss": 0.5588,
|
| 935 |
+
"step": 1450
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.67,
|
| 939 |
+
"learning_rate": 8.769905108855412e-06,
|
| 940 |
+
"loss": 0.5619,
|
| 941 |
+
"step": 1460
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.68,
|
| 945 |
+
"learning_rate": 8.646382258592762e-06,
|
| 946 |
+
"loss": 0.5612,
|
| 947 |
+
"step": 1470
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.69,
|
| 951 |
+
"learning_rate": 8.523069447359631e-06,
|
| 952 |
+
"loss": 0.5647,
|
| 953 |
+
"step": 1480
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.7,
|
| 957 |
+
"learning_rate": 8.399985809437737e-06,
|
| 958 |
+
"loss": 0.5803,
|
| 959 |
+
"step": 1490
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.71,
|
| 963 |
+
"learning_rate": 8.277150443548285e-06,
|
| 964 |
+
"loss": 0.554,
|
| 965 |
+
"step": 1500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.73,
|
| 969 |
+
"learning_rate": 8.154582409888441e-06,
|
| 970 |
+
"loss": 0.5734,
|
| 971 |
+
"step": 1510
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.74,
|
| 975 |
+
"learning_rate": 8.032300727173797e-06,
|
| 976 |
+
"loss": 0.5646,
|
| 977 |
+
"step": 1520
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.75,
|
| 981 |
+
"learning_rate": 7.91032436968725e-06,
|
| 982 |
+
"loss": 0.5665,
|
| 983 |
+
"step": 1530
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.76,
|
| 987 |
+
"learning_rate": 7.788672264334804e-06,
|
| 988 |
+
"loss": 0.5519,
|
| 989 |
+
"step": 1540
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.77,
|
| 993 |
+
"learning_rate": 7.667363287708692e-06,
|
| 994 |
+
"loss": 0.5676,
|
| 995 |
+
"step": 1550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.78,
|
| 999 |
+
"learning_rate": 7.546416263158326e-06,
|
| 1000 |
+
"loss": 0.5516,
|
| 1001 |
+
"step": 1560
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.79,
|
| 1005 |
+
"learning_rate": 7.42584995786952e-06,
|
| 1006 |
+
"loss": 0.5553,
|
| 1007 |
+
"step": 1570
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.81,
|
| 1011 |
+
"learning_rate": 7.305683079952381e-06,
|
| 1012 |
+
"loss": 0.56,
|
| 1013 |
+
"step": 1580
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.82,
|
| 1017 |
+
"learning_rate": 7.185934275538416e-06,
|
| 1018 |
+
"loss": 0.5715,
|
| 1019 |
+
"step": 1590
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.83,
|
| 1023 |
+
"learning_rate": 7.066622125887237e-06,
|
| 1024 |
+
"loss": 0.5459,
|
| 1025 |
+
"step": 1600
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.83,
|
| 1029 |
+
"eval_loss": 0.5793296098709106,
|
| 1030 |
+
"eval_runtime": 764.5785,
|
| 1031 |
+
"eval_samples_per_second": 16.277,
|
| 1032 |
+
"eval_steps_per_second": 2.035,
|
| 1033 |
+
"step": 1600
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.84,
|
| 1037 |
+
"learning_rate": 6.947765144503323e-06,
|
| 1038 |
+
"loss": 0.5499,
|
| 1039 |
+
"step": 1610
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.85,
|
| 1043 |
+
"learning_rate": 6.8293817742633175e-06,
|
| 1044 |
+
"loss": 0.5483,
|
| 1045 |
+
"step": 1620
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.86,
|
| 1049 |
+
"learning_rate": 6.711490384554257e-06,
|
| 1050 |
+
"loss": 0.5565,
|
| 1051 |
+
"step": 1630
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.87,
|
| 1055 |
+
"learning_rate": 6.59410926842323e-06,
|
| 1056 |
+
"loss": 0.5596,
|
| 1057 |
+
"step": 1640
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.89,
|
| 1061 |
+
"learning_rate": 6.477256639738872e-06,
|
| 1062 |
+
"loss": 0.5623,
|
| 1063 |
+
"step": 1650
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.9,
|
| 1067 |
+
"learning_rate": 6.360950630365126e-06,
|
| 1068 |
+
"loss": 0.5509,
|
| 1069 |
+
"step": 1660
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.91,
|
| 1073 |
+
"learning_rate": 6.245209287347767e-06,
|
| 1074 |
+
"loss": 0.561,
|
| 1075 |
+
"step": 1670
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.92,
|
| 1079 |
+
"learning_rate": 6.130050570114049e-06,
|
| 1080 |
+
"loss": 0.57,
|
| 1081 |
+
"step": 1680
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.93,
|
| 1085 |
+
"learning_rate": 6.015492347685983e-06,
|
| 1086 |
+
"loss": 0.5624,
|
| 1087 |
+
"step": 1690
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.94,
|
| 1091 |
+
"learning_rate": 5.901552395907606e-06,
|
| 1092 |
+
"loss": 0.5574,
|
| 1093 |
+
"step": 1700
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.95,
|
| 1097 |
+
"learning_rate": 5.788248394686743e-06,
|
| 1098 |
+
"loss": 0.5588,
|
| 1099 |
+
"step": 1710
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.97,
|
| 1103 |
+
"learning_rate": 5.67559792525163e-06,
|
| 1104 |
+
"loss": 0.5487,
|
| 1105 |
+
"step": 1720
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.98,
|
| 1109 |
+
"learning_rate": 5.563618467422864e-06,
|
| 1110 |
+
"loss": 0.5579,
|
| 1111 |
+
"step": 1730
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 1.99,
|
| 1115 |
+
"learning_rate": 5.452327396901078e-06,
|
| 1116 |
+
"loss": 0.5577,
|
| 1117 |
+
"step": 1740
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.0,
|
| 1121 |
+
"learning_rate": 5.341741982570789e-06,
|
| 1122 |
+
"loss": 0.5519,
|
| 1123 |
+
"step": 1750
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.01,
|
| 1127 |
+
"learning_rate": 5.231879383820782e-06,
|
| 1128 |
+
"loss": 0.5664,
|
| 1129 |
+
"step": 1760
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.02,
|
| 1133 |
+
"learning_rate": 5.122756647881543e-06,
|
| 1134 |
+
"loss": 0.5572,
|
| 1135 |
+
"step": 1770
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.03,
|
| 1139 |
+
"learning_rate": 5.0143907071800445e-06,
|
| 1140 |
+
"loss": 0.5516,
|
| 1141 |
+
"step": 1780
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.05,
|
| 1145 |
+
"learning_rate": 4.9067983767123736e-06,
|
| 1146 |
+
"loss": 0.5498,
|
| 1147 |
+
"step": 1790
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.06,
|
| 1151 |
+
"learning_rate": 4.79999635143455e-06,
|
| 1152 |
+
"loss": 0.571,
|
| 1153 |
+
"step": 1800
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.06,
|
| 1157 |
+
"eval_loss": 0.5752249956130981,
|
| 1158 |
+
"eval_runtime": 764.7047,
|
| 1159 |
+
"eval_samples_per_second": 16.274,
|
| 1160 |
+
"eval_steps_per_second": 2.035,
|
| 1161 |
+
"step": 1800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.07,
|
| 1165 |
+
"learning_rate": 4.694001203672028e-06,
|
| 1166 |
+
"loss": 0.5661,
|
| 1167 |
+
"step": 1810
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.08,
|
| 1171 |
+
"learning_rate": 4.588829380548168e-06,
|
| 1172 |
+
"loss": 0.5733,
|
| 1173 |
+
"step": 1820
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.09,
|
| 1177 |
+
"learning_rate": 4.484497201432147e-06,
|
| 1178 |
+
"loss": 0.5725,
|
| 1179 |
+
"step": 1830
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.1,
|
| 1183 |
+
"learning_rate": 4.381020855406738e-06,
|
| 1184 |
+
"loss": 0.556,
|
| 1185 |
+
"step": 1840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.11,
|
| 1189 |
+
"learning_rate": 4.278416398756245e-06,
|
| 1190 |
+
"loss": 0.5671,
|
| 1191 |
+
"step": 1850
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.13,
|
| 1195 |
+
"learning_rate": 4.176699752475087e-06,
|
| 1196 |
+
"loss": 0.566,
|
| 1197 |
+
"step": 1860
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.14,
|
| 1201 |
+
"learning_rate": 4.075886699797338e-06,
|
| 1202 |
+
"loss": 0.5692,
|
| 1203 |
+
"step": 1870
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.15,
|
| 1207 |
+
"learning_rate": 3.975992883747688e-06,
|
| 1208 |
+
"loss": 0.5582,
|
| 1209 |
+
"step": 1880
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.16,
|
| 1213 |
+
"learning_rate": 3.877033804714133e-06,
|
| 1214 |
+
"loss": 0.5477,
|
| 1215 |
+
"step": 1890
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.17,
|
| 1219 |
+
"learning_rate": 3.7790248180427758e-06,
|
| 1220 |
+
"loss": 0.5488,
|
| 1221 |
+
"step": 1900
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.18,
|
| 1225 |
+
"learning_rate": 3.6819811316551867e-06,
|
| 1226 |
+
"loss": 0.5591,
|
| 1227 |
+
"step": 1910
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.19,
|
| 1231 |
+
"learning_rate": 3.585917803688603e-06,
|
| 1232 |
+
"loss": 0.5548,
|
| 1233 |
+
"step": 1920
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.21,
|
| 1237 |
+
"learning_rate": 3.4908497401593634e-06,
|
| 1238 |
+
"loss": 0.5517,
|
| 1239 |
+
"step": 1930
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.22,
|
| 1243 |
+
"learning_rate": 3.3967916926499823e-06,
|
| 1244 |
+
"loss": 0.556,
|
| 1245 |
+
"step": 1940
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.23,
|
| 1249 |
+
"learning_rate": 3.303758256020154e-06,
|
| 1250 |
+
"loss": 0.5398,
|
| 1251 |
+
"step": 1950
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.24,
|
| 1255 |
+
"learning_rate": 3.211763866142097e-06,
|
| 1256 |
+
"loss": 0.5487,
|
| 1257 |
+
"step": 1960
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.25,
|
| 1261 |
+
"learning_rate": 3.1208227976605475e-06,
|
| 1262 |
+
"loss": 0.5503,
|
| 1263 |
+
"step": 1970
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.26,
|
| 1267 |
+
"learning_rate": 3.0309491617777943e-06,
|
| 1268 |
+
"loss": 0.5609,
|
| 1269 |
+
"step": 1980
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.27,
|
| 1273 |
+
"learning_rate": 2.9421569040640564e-06,
|
| 1274 |
+
"loss": 0.5569,
|
| 1275 |
+
"step": 1990
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.29,
|
| 1279 |
+
"learning_rate": 2.854459802293561e-06,
|
| 1280 |
+
"loss": 0.5558,
|
| 1281 |
+
"step": 2000
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.29,
|
| 1285 |
+
"eval_loss": 0.5727296471595764,
|
| 1286 |
+
"eval_runtime": 764.8947,
|
| 1287 |
+
"eval_samples_per_second": 16.27,
|
| 1288 |
+
"eval_steps_per_second": 2.034,
|
| 1289 |
+
"step": 2000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.3,
|
| 1293 |
+
"learning_rate": 2.767871464306682e-06,
|
| 1294 |
+
"loss": 0.5596,
|
| 1295 |
+
"step": 2010
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 2.31,
|
| 1299 |
+
"learning_rate": 2.682405325898416e-06,
|
| 1300 |
+
"loss": 0.5565,
|
| 1301 |
+
"step": 2020
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.32,
|
| 1305 |
+
"learning_rate": 2.5980746487335785e-06,
|
| 1306 |
+
"loss": 0.5482,
|
| 1307 |
+
"step": 2030
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.33,
|
| 1311 |
+
"learning_rate": 2.514892518288988e-06,
|
| 1312 |
+
"loss": 0.559,
|
| 1313 |
+
"step": 2040
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.34,
|
| 1317 |
+
"learning_rate": 2.432871841823047e-06,
|
| 1318 |
+
"loss": 0.5621,
|
| 1319 |
+
"step": 2050
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.35,
|
| 1323 |
+
"learning_rate": 2.3520253463729058e-06,
|
| 1324 |
+
"loss": 0.5485,
|
| 1325 |
+
"step": 2060
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.37,
|
| 1329 |
+
"learning_rate": 2.272365576779637e-06,
|
| 1330 |
+
"loss": 0.5598,
|
| 1331 |
+
"step": 2070
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 2.38,
|
| 1335 |
+
"learning_rate": 2.1939048937416783e-06,
|
| 1336 |
+
"loss": 0.5655,
|
| 1337 |
+
"step": 2080
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.39,
|
| 1341 |
+
"learning_rate": 2.116655471896828e-06,
|
| 1342 |
+
"loss": 0.5522,
|
| 1343 |
+
"step": 2090
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.4,
|
| 1347 |
+
"learning_rate": 2.0406292979331333e-06,
|
| 1348 |
+
"loss": 0.552,
|
| 1349 |
+
"step": 2100
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.41,
|
| 1353 |
+
"learning_rate": 1.965838168728912e-06,
|
| 1354 |
+
"loss": 0.5565,
|
| 1355 |
+
"step": 2110
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.42,
|
| 1359 |
+
"learning_rate": 1.8922936895222798e-06,
|
| 1360 |
+
"loss": 0.5576,
|
| 1361 |
+
"step": 2120
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.43,
|
| 1365 |
+
"learning_rate": 1.8200072721103545e-06,
|
| 1366 |
+
"loss": 0.5629,
|
| 1367 |
+
"step": 2130
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.45,
|
| 1371 |
+
"learning_rate": 1.7489901330785053e-06,
|
| 1372 |
+
"loss": 0.5461,
|
| 1373 |
+
"step": 2140
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 2.46,
|
| 1377 |
+
"learning_rate": 1.6792532920599025e-06,
|
| 1378 |
+
"loss": 0.5503,
|
| 1379 |
+
"step": 2150
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 2.47,
|
| 1383 |
+
"learning_rate": 1.610807570025611e-06,
|
| 1384 |
+
"loss": 0.5422,
|
| 1385 |
+
"step": 2160
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.48,
|
| 1389 |
+
"learning_rate": 1.5436635876055107e-06,
|
| 1390 |
+
"loss": 0.5537,
|
| 1391 |
+
"step": 2170
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.49,
|
| 1395 |
+
"learning_rate": 1.4778317634403082e-06,
|
| 1396 |
+
"loss": 0.5676,
|
| 1397 |
+
"step": 2180
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.5,
|
| 1401 |
+
"learning_rate": 1.4133223125648966e-06,
|
| 1402 |
+
"loss": 0.5664,
|
| 1403 |
+
"step": 2190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.51,
|
| 1407 |
+
"learning_rate": 1.350145244823302e-06,
|
| 1408 |
+
"loss": 0.5467,
|
| 1409 |
+
"step": 2200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.51,
|
| 1413 |
+
"eval_loss": 0.5713418126106262,
|
| 1414 |
+
"eval_runtime": 764.6146,
|
| 1415 |
+
"eval_samples_per_second": 16.276,
|
| 1416 |
+
"eval_steps_per_second": 2.035,
|
| 1417 |
+
"step": 2200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.53,
|
| 1421 |
+
"learning_rate": 1.2883103633154582e-06,
|
| 1422 |
+
"loss": 0.5413,
|
| 1423 |
+
"step": 2210
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.54,
|
| 1427 |
+
"learning_rate": 1.2278272628760857e-06,
|
| 1428 |
+
"loss": 0.5494,
|
| 1429 |
+
"step": 2220
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 2.55,
|
| 1433 |
+
"learning_rate": 1.1687053285858685e-06,
|
| 1434 |
+
"loss": 0.5596,
|
| 1435 |
+
"step": 2230
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.56,
|
| 1439 |
+
"learning_rate": 1.1109537343151877e-06,
|
| 1440 |
+
"loss": 0.5609,
|
| 1441 |
+
"step": 2240
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.57,
|
| 1445 |
+
"learning_rate": 1.0545814413006138e-06,
|
| 1446 |
+
"loss": 0.5574,
|
| 1447 |
+
"step": 2250
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 2.58,
|
| 1451 |
+
"learning_rate": 9.995971967544217e-07,
|
| 1452 |
+
"loss": 0.5472,
|
| 1453 |
+
"step": 2260
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.59,
|
| 1457 |
+
"learning_rate": 9.460095325072805e-07,
|
| 1458 |
+
"loss": 0.564,
|
| 1459 |
+
"step": 2270
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.61,
|
| 1463 |
+
"learning_rate": 8.9382676368439e-07,
|
| 1464 |
+
"loss": 0.5483,
|
| 1465 |
+
"step": 2280
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.62,
|
| 1469 |
+
"learning_rate": 8.430569874152339e-07,
|
| 1470 |
+
"loss": 0.534,
|
| 1471 |
+
"step": 2290
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.63,
|
| 1475 |
+
"learning_rate": 7.937080815771569e-07,
|
| 1476 |
+
"loss": 0.5628,
|
| 1477 |
+
"step": 2300
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 2.64,
|
| 1481 |
+
"learning_rate": 7.457877035729588e-07,
|
| 1482 |
+
"loss": 0.571,
|
| 1483 |
+
"step": 2310
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 2.65,
|
| 1487 |
+
"learning_rate": 6.993032891427221e-07,
|
| 1488 |
+
"loss": 0.5507,
|
| 1489 |
+
"step": 2320
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 2.66,
|
| 1493 |
+
"learning_rate": 6.542620512100029e-07,
|
| 1494 |
+
"loss": 0.5575,
|
| 1495 |
+
"step": 2330
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.67,
|
| 1499 |
+
"learning_rate": 6.106709787626198e-07,
|
| 1500 |
+
"loss": 0.5529,
|
| 1501 |
+
"step": 2340
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.69,
|
| 1505 |
+
"learning_rate": 5.685368357681731e-07,
|
| 1506 |
+
"loss": 0.5483,
|
| 1507 |
+
"step": 2350
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.7,
|
| 1511 |
+
"learning_rate": 5.278661601245061e-07,
|
| 1512 |
+
"loss": 0.5598,
|
| 1513 |
+
"step": 2360
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 2.71,
|
| 1517 |
+
"learning_rate": 4.886652626452115e-07,
|
| 1518 |
+
"loss": 0.5454,
|
| 1519 |
+
"step": 2370
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 2.72,
|
| 1523 |
+
"learning_rate": 4.50940226080393e-07,
|
| 1524 |
+
"loss": 0.547,
|
| 1525 |
+
"step": 2380
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 2.73,
|
| 1529 |
+
"learning_rate": 4.146969041728255e-07,
|
| 1530 |
+
"loss": 0.5459,
|
| 1531 |
+
"step": 2390
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 2.74,
|
| 1535 |
+
"learning_rate": 3.7994092074962405e-07,
|
| 1536 |
+
"loss": 0.5424,
|
| 1537 |
+
"step": 2400
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.74,
|
| 1541 |
+
"eval_loss": 0.5707904696464539,
|
| 1542 |
+
"eval_runtime": 763.6658,
|
| 1543 |
+
"eval_samples_per_second": 16.296,
|
| 1544 |
+
"eval_steps_per_second": 2.038,
|
| 1545 |
+
"step": 2400
|
| 1546 |
+
}
|
| 1547 |
+
],
|
| 1548 |
+
"logging_steps": 10,
|
| 1549 |
+
"max_steps": 2622,
|
| 1550 |
+
"num_train_epochs": 3,
|
| 1551 |
+
"save_steps": 200,
|
| 1552 |
+
"total_flos": 2.888356327591772e+18,
|
| 1553 |
+
"trial_name": null,
|
| 1554 |
+
"trial_params": null
|
| 1555 |
+
}
|
checkpoint-2400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:351af72ecf82c54d3b93447930b5e2d6fab44f4b186eb4be6787a376d125d1f7
|
| 3 |
+
size 4472
|
checkpoint-2600/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: medalpaca/medalpaca-7b
|
| 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 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
- PEFT 0.6.0.dev0
|
checkpoint-2600/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "medalpaca/medalpaca-7b",
|
| 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 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 8,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-2600/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7eaa51169fb5f5f33b328f26090dcd19a47bde0a9efe64e78856dbbe04a07e7a
|
| 3 |
+
size 888
|
checkpoint-2600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f81df4b8918e6bb8e6afc3cf0ca091f465cc47a2e1be4fd12077b61bb964da53
|
| 3 |
+
size 33662074
|
checkpoint-2600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6670f81e08d8dd66c7b47fc3117cdba85e0a8bbb9c2e9371ef379271e0b418cf
|
| 3 |
+
size 14244
|
checkpoint-2600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b1d4ef506d87d932ba22ab1d9ac50419b53a116e1c678ffe7fd19cf2d58e207
|
| 3 |
+
size 1064
|
checkpoint-2600/trainer_state.json
ADDED
|
@@ -0,0 +1,1683 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5706716179847717,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-2600",
|
| 4 |
+
"epoch": 2.971534697667774,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 14 |
+
"loss": 3.282,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 4.000000000000001e-06,
|
| 20 |
+
"loss": 3.2806,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 6e-06,
|
| 26 |
+
"loss": 3.2842,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 8.000000000000001e-06,
|
| 32 |
+
"loss": 3.2378,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 1e-05,
|
| 38 |
+
"loss": 3.202,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 1.2e-05,
|
| 44 |
+
"loss": 3.1307,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"learning_rate": 1.4e-05,
|
| 50 |
+
"loss": 3.0392,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 56 |
+
"loss": 2.9102,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.1,
|
| 61 |
+
"learning_rate": 1.8e-05,
|
| 62 |
+
"loss": 2.7595,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.11,
|
| 67 |
+
"learning_rate": 2e-05,
|
| 68 |
+
"loss": 2.5737,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 1.9999224156779658e-05,
|
| 74 |
+
"loss": 2.347,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.14,
|
| 79 |
+
"learning_rate": 1.999689674750517e-05,
|
| 80 |
+
"loss": 2.0934,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15,
|
| 85 |
+
"learning_rate": 1.9993018133317476e-05,
|
| 86 |
+
"loss": 1.8305,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16,
|
| 91 |
+
"learning_rate": 1.998758891605588e-05,
|
| 92 |
+
"loss": 1.5447,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17,
|
| 97 |
+
"learning_rate": 1.9980609938164664e-05,
|
| 98 |
+
"loss": 1.3394,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.18,
|
| 103 |
+
"learning_rate": 1.9972082282562367e-05,
|
| 104 |
+
"loss": 1.2032,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.19,
|
| 109 |
+
"learning_rate": 1.9962007272473744e-05,
|
| 110 |
+
"loss": 1.1096,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.21,
|
| 115 |
+
"learning_rate": 1.9950386471224445e-05,
|
| 116 |
+
"loss": 1.0456,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.22,
|
| 121 |
+
"learning_rate": 1.9937221681998447e-05,
|
| 122 |
+
"loss": 0.9977,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23,
|
| 127 |
+
"learning_rate": 1.9922514947558248e-05,
|
| 128 |
+
"loss": 0.9786,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.23,
|
| 133 |
+
"eval_loss": 0.982032299041748,
|
| 134 |
+
"eval_runtime": 759.4598,
|
| 135 |
+
"eval_samples_per_second": 16.387,
|
| 136 |
+
"eval_steps_per_second": 2.049,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.24,
|
| 141 |
+
"learning_rate": 1.9906268549927886e-05,
|
| 142 |
+
"loss": 0.948,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.25,
|
| 147 |
+
"learning_rate": 1.9888485010038848e-05,
|
| 148 |
+
"loss": 0.9164,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.26,
|
| 153 |
+
"learning_rate": 1.9869167087338908e-05,
|
| 154 |
+
"loss": 0.8977,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.27,
|
| 159 |
+
"learning_rate": 1.984831777936394e-05,
|
| 160 |
+
"loss": 0.876,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.29,
|
| 165 |
+
"learning_rate": 1.9825940321272792e-05,
|
| 166 |
+
"loss": 0.8604,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.3,
|
| 171 |
+
"learning_rate": 1.980203818534529e-05,
|
| 172 |
+
"loss": 0.8424,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.31,
|
| 177 |
+
"learning_rate": 1.9776615080443462e-05,
|
| 178 |
+
"loss": 0.8434,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.32,
|
| 183 |
+
"learning_rate": 1.9749674951436016e-05,
|
| 184 |
+
"loss": 0.8357,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.33,
|
| 189 |
+
"learning_rate": 1.972122197858625e-05,
|
| 190 |
+
"loss": 0.8239,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.34,
|
| 195 |
+
"learning_rate": 1.9691260576903372e-05,
|
| 196 |
+
"loss": 0.8177,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.35,
|
| 201 |
+
"learning_rate": 1.965979539545746e-05,
|
| 202 |
+
"loss": 0.8151,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.37,
|
| 207 |
+
"learning_rate": 1.9626831316658058e-05,
|
| 208 |
+
"loss": 0.8074,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.38,
|
| 213 |
+
"learning_rate": 1.959237345549657e-05,
|
| 214 |
+
"loss": 0.7768,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.39,
|
| 219 |
+
"learning_rate": 1.955642715875259e-05,
|
| 220 |
+
"loss": 0.7673,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.4,
|
| 225 |
+
"learning_rate": 1.951899800416425e-05,
|
| 226 |
+
"loss": 0.7448,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.41,
|
| 231 |
+
"learning_rate": 1.9480091799562706e-05,
|
| 232 |
+
"loss": 0.7334,
|
| 233 |
+
"step": 360
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.42,
|
| 237 |
+
"learning_rate": 1.9439714581970983e-05,
|
| 238 |
+
"loss": 0.734,
|
| 239 |
+
"step": 370
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.43,
|
| 243 |
+
"learning_rate": 1.9397872616667175e-05,
|
| 244 |
+
"loss": 0.7301,
|
| 245 |
+
"step": 380
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.45,
|
| 249 |
+
"learning_rate": 1.935457239621231e-05,
|
| 250 |
+
"loss": 0.734,
|
| 251 |
+
"step": 390
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.46,
|
| 255 |
+
"learning_rate": 1.9309820639442886e-05,
|
| 256 |
+
"loss": 0.7062,
|
| 257 |
+
"step": 400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.46,
|
| 261 |
+
"eval_loss": 0.7326281070709229,
|
| 262 |
+
"eval_runtime": 757.8879,
|
| 263 |
+
"eval_samples_per_second": 16.421,
|
| 264 |
+
"eval_steps_per_second": 2.053,
|
| 265 |
+
"step": 400
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.47,
|
| 269 |
+
"learning_rate": 1.9263624290428314e-05,
|
| 270 |
+
"loss": 0.7074,
|
| 271 |
+
"step": 410
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.48,
|
| 275 |
+
"learning_rate": 1.9215990517393436e-05,
|
| 276 |
+
"loss": 0.7001,
|
| 277 |
+
"step": 420
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.49,
|
| 281 |
+
"learning_rate": 1.9166926711606222e-05,
|
| 282 |
+
"loss": 0.6991,
|
| 283 |
+
"step": 430
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5,
|
| 287 |
+
"learning_rate": 1.9116440486230893e-05,
|
| 288 |
+
"loss": 0.6935,
|
| 289 |
+
"step": 440
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.51,
|
| 293 |
+
"learning_rate": 1.9064539675146584e-05,
|
| 294 |
+
"loss": 0.6922,
|
| 295 |
+
"step": 450
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.53,
|
| 299 |
+
"learning_rate": 1.9011232331731773e-05,
|
| 300 |
+
"loss": 0.6861,
|
| 301 |
+
"step": 460
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.54,
|
| 305 |
+
"learning_rate": 1.8956526727614663e-05,
|
| 306 |
+
"loss": 0.6978,
|
| 307 |
+
"step": 470
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.55,
|
| 311 |
+
"learning_rate": 1.8900431351389657e-05,
|
| 312 |
+
"loss": 0.6699,
|
| 313 |
+
"step": 480
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.56,
|
| 317 |
+
"learning_rate": 1.8842954907300236e-05,
|
| 318 |
+
"loss": 0.6846,
|
| 319 |
+
"step": 490
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.57,
|
| 323 |
+
"learning_rate": 1.878410631388829e-05,
|
| 324 |
+
"loss": 0.6772,
|
| 325 |
+
"step": 500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.58,
|
| 329 |
+
"learning_rate": 1.8723894702610258e-05,
|
| 330 |
+
"loss": 0.6808,
|
| 331 |
+
"step": 510
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.59,
|
| 335 |
+
"learning_rate": 1.866232941642023e-05,
|
| 336 |
+
"loss": 0.6869,
|
| 337 |
+
"step": 520
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.61,
|
| 341 |
+
"learning_rate": 1.8599420008320176e-05,
|
| 342 |
+
"loss": 0.6595,
|
| 343 |
+
"step": 530
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.62,
|
| 347 |
+
"learning_rate": 1.8535176239877653e-05,
|
| 348 |
+
"loss": 0.6669,
|
| 349 |
+
"step": 540
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.63,
|
| 353 |
+
"learning_rate": 1.8469608079711105e-05,
|
| 354 |
+
"loss": 0.6648,
|
| 355 |
+
"step": 550
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.64,
|
| 359 |
+
"learning_rate": 1.8402725701943028e-05,
|
| 360 |
+
"loss": 0.6486,
|
| 361 |
+
"step": 560
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.65,
|
| 365 |
+
"learning_rate": 1.8334539484621304e-05,
|
| 366 |
+
"loss": 0.6735,
|
| 367 |
+
"step": 570
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.66,
|
| 371 |
+
"learning_rate": 1.8265060008108815e-05,
|
| 372 |
+
"loss": 0.6498,
|
| 373 |
+
"step": 580
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.67,
|
| 377 |
+
"learning_rate": 1.8194298053441725e-05,
|
| 378 |
+
"loss": 0.6578,
|
| 379 |
+
"step": 590
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.69,
|
| 383 |
+
"learning_rate": 1.812226460065658e-05,
|
| 384 |
+
"loss": 0.6392,
|
| 385 |
+
"step": 600
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.69,
|
| 389 |
+
"eval_loss": 0.6629914045333862,
|
| 390 |
+
"eval_runtime": 765.6279,
|
| 391 |
+
"eval_samples_per_second": 16.255,
|
| 392 |
+
"eval_steps_per_second": 2.032,
|
| 393 |
+
"step": 600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.7,
|
| 397 |
+
"learning_rate": 1.804897082708659e-05,
|
| 398 |
+
"loss": 0.6524,
|
| 399 |
+
"step": 610
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.71,
|
| 403 |
+
"learning_rate": 1.797442810562721e-05,
|
| 404 |
+
"loss": 0.6513,
|
| 405 |
+
"step": 620
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.72,
|
| 409 |
+
"learning_rate": 1.7898648002971456e-05,
|
| 410 |
+
"loss": 0.6466,
|
| 411 |
+
"step": 630
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.73,
|
| 415 |
+
"learning_rate": 1.7821642277815108e-05,
|
| 416 |
+
"loss": 0.6305,
|
| 417 |
+
"step": 640
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.74,
|
| 421 |
+
"learning_rate": 1.774342287903212e-05,
|
| 422 |
+
"loss": 0.6418,
|
| 423 |
+
"step": 650
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.75,
|
| 427 |
+
"learning_rate": 1.766400194382054e-05,
|
| 428 |
+
"loss": 0.636,
|
| 429 |
+
"step": 660
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.77,
|
| 433 |
+
"learning_rate": 1.75833917958192e-05,
|
| 434 |
+
"loss": 0.6279,
|
| 435 |
+
"step": 670
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.78,
|
| 439 |
+
"learning_rate": 1.7501604943195466e-05,
|
| 440 |
+
"loss": 0.6369,
|
| 441 |
+
"step": 680
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.79,
|
| 445 |
+
"learning_rate": 1.741865407670435e-05,
|
| 446 |
+
"loss": 0.6308,
|
| 447 |
+
"step": 690
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.8,
|
| 451 |
+
"learning_rate": 1.733455206771934e-05,
|
| 452 |
+
"loss": 0.616,
|
| 453 |
+
"step": 700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.81,
|
| 457 |
+
"learning_rate": 1.724931196623513e-05,
|
| 458 |
+
"loss": 0.6334,
|
| 459 |
+
"step": 710
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.82,
|
| 463 |
+
"learning_rate": 1.716294699884269e-05,
|
| 464 |
+
"loss": 0.6289,
|
| 465 |
+
"step": 720
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.83,
|
| 469 |
+
"learning_rate": 1.70754705666769e-05,
|
| 470 |
+
"loss": 0.6251,
|
| 471 |
+
"step": 730
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.85,
|
| 475 |
+
"learning_rate": 1.6986896243337137e-05,
|
| 476 |
+
"loss": 0.619,
|
| 477 |
+
"step": 740
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.86,
|
| 481 |
+
"learning_rate": 1.6897237772781046e-05,
|
| 482 |
+
"loss": 0.6226,
|
| 483 |
+
"step": 750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.87,
|
| 487 |
+
"learning_rate": 1.6806509067191926e-05,
|
| 488 |
+
"loss": 0.6229,
|
| 489 |
+
"step": 760
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.88,
|
| 493 |
+
"learning_rate": 1.6714724204820017e-05,
|
| 494 |
+
"loss": 0.6016,
|
| 495 |
+
"step": 770
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.89,
|
| 499 |
+
"learning_rate": 1.6621897427797947e-05,
|
| 500 |
+
"loss": 0.6061,
|
| 501 |
+
"step": 780
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.9,
|
| 505 |
+
"learning_rate": 1.6528043139930845e-05,
|
| 506 |
+
"loss": 0.6027,
|
| 507 |
+
"step": 790
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.91,
|
| 511 |
+
"learning_rate": 1.64331759044613e-05,
|
| 512 |
+
"loss": 0.6018,
|
| 513 |
+
"step": 800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.91,
|
| 517 |
+
"eval_loss": 0.6285067796707153,
|
| 518 |
+
"eval_runtime": 765.1757,
|
| 519 |
+
"eval_samples_per_second": 16.264,
|
| 520 |
+
"eval_steps_per_second": 2.034,
|
| 521 |
+
"step": 800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.93,
|
| 525 |
+
"learning_rate": 1.63373104418096e-05,
|
| 526 |
+
"loss": 0.6094,
|
| 527 |
+
"step": 810
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.94,
|
| 531 |
+
"learning_rate": 1.6240461627289607e-05,
|
| 532 |
+
"loss": 0.6224,
|
| 533 |
+
"step": 820
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.95,
|
| 537 |
+
"learning_rate": 1.614264448880054e-05,
|
| 538 |
+
"loss": 0.6032,
|
| 539 |
+
"step": 830
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.96,
|
| 543 |
+
"learning_rate": 1.6043874204495152e-05,
|
| 544 |
+
"loss": 0.6048,
|
| 545 |
+
"step": 840
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.97,
|
| 549 |
+
"learning_rate": 1.5944166100424534e-05,
|
| 550 |
+
"loss": 0.6036,
|
| 551 |
+
"step": 850
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.98,
|
| 555 |
+
"learning_rate": 1.584353564815999e-05,
|
| 556 |
+
"loss": 0.5932,
|
| 557 |
+
"step": 860
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.99,
|
| 561 |
+
"learning_rate": 1.5741998462392352e-05,
|
| 562 |
+
"loss": 0.6003,
|
| 563 |
+
"step": 870
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.01,
|
| 567 |
+
"learning_rate": 1.5639570298509067e-05,
|
| 568 |
+
"loss": 0.6128,
|
| 569 |
+
"step": 880
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.02,
|
| 573 |
+
"learning_rate": 1.5536267050149428e-05,
|
| 574 |
+
"loss": 0.5968,
|
| 575 |
+
"step": 890
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.03,
|
| 579 |
+
"learning_rate": 1.5432104746738417e-05,
|
| 580 |
+
"loss": 0.6027,
|
| 581 |
+
"step": 900
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.04,
|
| 585 |
+
"learning_rate": 1.5327099550999416e-05,
|
| 586 |
+
"loss": 0.6122,
|
| 587 |
+
"step": 910
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.05,
|
| 591 |
+
"learning_rate": 1.5221267756446266e-05,
|
| 592 |
+
"loss": 0.5984,
|
| 593 |
+
"step": 920
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.06,
|
| 597 |
+
"learning_rate": 1.5114625784855028e-05,
|
| 598 |
+
"loss": 0.5965,
|
| 599 |
+
"step": 930
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.07,
|
| 603 |
+
"learning_rate": 1.5007190183715836e-05,
|
| 604 |
+
"loss": 0.5942,
|
| 605 |
+
"step": 940
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.09,
|
| 609 |
+
"learning_rate": 1.4898977623665243e-05,
|
| 610 |
+
"loss": 0.6,
|
| 611 |
+
"step": 950
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.1,
|
| 615 |
+
"learning_rate": 1.4790004895899465e-05,
|
| 616 |
+
"loss": 0.6051,
|
| 617 |
+
"step": 960
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.11,
|
| 621 |
+
"learning_rate": 1.4680288909568905e-05,
|
| 622 |
+
"loss": 0.5903,
|
| 623 |
+
"step": 970
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.12,
|
| 627 |
+
"learning_rate": 1.4569846689154401e-05,
|
| 628 |
+
"loss": 0.6049,
|
| 629 |
+
"step": 980
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.13,
|
| 633 |
+
"learning_rate": 1.4458695371825535e-05,
|
| 634 |
+
"loss": 0.5852,
|
| 635 |
+
"step": 990
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.14,
|
| 639 |
+
"learning_rate": 1.4346852204781511e-05,
|
| 640 |
+
"loss": 0.5869,
|
| 641 |
+
"step": 1000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.14,
|
| 645 |
+
"eval_loss": 0.6076732277870178,
|
| 646 |
+
"eval_runtime": 765.3772,
|
| 647 |
+
"eval_samples_per_second": 16.26,
|
| 648 |
+
"eval_steps_per_second": 2.033,
|
| 649 |
+
"step": 1000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.15,
|
| 653 |
+
"learning_rate": 1.4234334542574906e-05,
|
| 654 |
+
"loss": 0.5893,
|
| 655 |
+
"step": 1010
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.17,
|
| 659 |
+
"learning_rate": 1.4121159844418793e-05,
|
| 660 |
+
"loss": 0.5874,
|
| 661 |
+
"step": 1020
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.18,
|
| 665 |
+
"learning_rate": 1.400734567147763e-05,
|
| 666 |
+
"loss": 0.595,
|
| 667 |
+
"step": 1030
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.19,
|
| 671 |
+
"learning_rate": 1.3892909684142311e-05,
|
| 672 |
+
"loss": 0.5961,
|
| 673 |
+
"step": 1040
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.2,
|
| 677 |
+
"learning_rate": 1.3777869639289822e-05,
|
| 678 |
+
"loss": 0.5826,
|
| 679 |
+
"step": 1050
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.21,
|
| 683 |
+
"learning_rate": 1.3662243387527936e-05,
|
| 684 |
+
"loss": 0.5835,
|
| 685 |
+
"step": 1060
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.22,
|
| 689 |
+
"learning_rate": 1.3546048870425356e-05,
|
| 690 |
+
"loss": 0.5858,
|
| 691 |
+
"step": 1070
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.23,
|
| 695 |
+
"learning_rate": 1.3429304117727755e-05,
|
| 696 |
+
"loss": 0.5931,
|
| 697 |
+
"step": 1080
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.25,
|
| 701 |
+
"learning_rate": 1.3312027244560104e-05,
|
| 702 |
+
"loss": 0.5858,
|
| 703 |
+
"step": 1090
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.26,
|
| 707 |
+
"learning_rate": 1.3194236448615798e-05,
|
| 708 |
+
"loss": 0.5834,
|
| 709 |
+
"step": 1100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.27,
|
| 713 |
+
"learning_rate": 1.3075950007332923e-05,
|
| 714 |
+
"loss": 0.5854,
|
| 715 |
+
"step": 1110
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.28,
|
| 719 |
+
"learning_rate": 1.2957186275058188e-05,
|
| 720 |
+
"loss": 0.5879,
|
| 721 |
+
"step": 1120
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.29,
|
| 725 |
+
"learning_rate": 1.2837963680198895e-05,
|
| 726 |
+
"loss": 0.5958,
|
| 727 |
+
"step": 1130
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.3,
|
| 731 |
+
"learning_rate": 1.2718300722363431e-05,
|
| 732 |
+
"loss": 0.5787,
|
| 733 |
+
"step": 1140
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.31,
|
| 737 |
+
"learning_rate": 1.2598215969490703e-05,
|
| 738 |
+
"loss": 0.5827,
|
| 739 |
+
"step": 1150
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.33,
|
| 743 |
+
"learning_rate": 1.2477728054968993e-05,
|
| 744 |
+
"loss": 0.589,
|
| 745 |
+
"step": 1160
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.34,
|
| 749 |
+
"learning_rate": 1.2356855674744625e-05,
|
| 750 |
+
"loss": 0.5806,
|
| 751 |
+
"step": 1170
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.35,
|
| 755 |
+
"learning_rate": 1.2235617584420938e-05,
|
| 756 |
+
"loss": 0.563,
|
| 757 |
+
"step": 1180
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.36,
|
| 761 |
+
"learning_rate": 1.2114032596348023e-05,
|
| 762 |
+
"loss": 0.5812,
|
| 763 |
+
"step": 1190
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.37,
|
| 767 |
+
"learning_rate": 1.1992119576703614e-05,
|
| 768 |
+
"loss": 0.5995,
|
| 769 |
+
"step": 1200
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.37,
|
| 773 |
+
"eval_loss": 0.5944839119911194,
|
| 774 |
+
"eval_runtime": 764.7162,
|
| 775 |
+
"eval_samples_per_second": 16.274,
|
| 776 |
+
"eval_steps_per_second": 2.035,
|
| 777 |
+
"step": 1200
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.38,
|
| 781 |
+
"learning_rate": 1.1869897442565665e-05,
|
| 782 |
+
"loss": 0.5852,
|
| 783 |
+
"step": 1210
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.39,
|
| 787 |
+
"learning_rate": 1.1747385158977008e-05,
|
| 788 |
+
"loss": 0.5798,
|
| 789 |
+
"step": 1220
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.41,
|
| 793 |
+
"learning_rate": 1.162460173600256e-05,
|
| 794 |
+
"loss": 0.5846,
|
| 795 |
+
"step": 1230
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.42,
|
| 799 |
+
"learning_rate": 1.1501566225779592e-05,
|
| 800 |
+
"loss": 0.5674,
|
| 801 |
+
"step": 1240
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.43,
|
| 805 |
+
"learning_rate": 1.1378297719561388e-05,
|
| 806 |
+
"loss": 0.5616,
|
| 807 |
+
"step": 1250
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.44,
|
| 811 |
+
"learning_rate": 1.1254815344754919e-05,
|
| 812 |
+
"loss": 0.5738,
|
| 813 |
+
"step": 1260
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.45,
|
| 817 |
+
"learning_rate": 1.1131138261952845e-05,
|
| 818 |
+
"loss": 0.5831,
|
| 819 |
+
"step": 1270
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.46,
|
| 823 |
+
"learning_rate": 1.100728566196041e-05,
|
| 824 |
+
"loss": 0.5732,
|
| 825 |
+
"step": 1280
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.47,
|
| 829 |
+
"learning_rate": 1.088327676281762e-05,
|
| 830 |
+
"loss": 0.5702,
|
| 831 |
+
"step": 1290
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.49,
|
| 835 |
+
"learning_rate": 1.0759130806817204e-05,
|
| 836 |
+
"loss": 0.5748,
|
| 837 |
+
"step": 1300
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.5,
|
| 841 |
+
"learning_rate": 1.0634867057518824e-05,
|
| 842 |
+
"loss": 0.5764,
|
| 843 |
+
"step": 1310
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.51,
|
| 847 |
+
"learning_rate": 1.0510504796759966e-05,
|
| 848 |
+
"loss": 0.5716,
|
| 849 |
+
"step": 1320
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.52,
|
| 853 |
+
"learning_rate": 1.0386063321664007e-05,
|
| 854 |
+
"loss": 0.5685,
|
| 855 |
+
"step": 1330
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.53,
|
| 859 |
+
"learning_rate": 1.0261561941645894e-05,
|
| 860 |
+
"loss": 0.5713,
|
| 861 |
+
"step": 1340
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.54,
|
| 865 |
+
"learning_rate": 1.013701997541596e-05,
|
| 866 |
+
"loss": 0.5668,
|
| 867 |
+
"step": 1350
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.55,
|
| 871 |
+
"learning_rate": 1.0012456747982231e-05,
|
| 872 |
+
"loss": 0.5714,
|
| 873 |
+
"step": 1360
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.57,
|
| 877 |
+
"learning_rate": 9.887891587651807e-06,
|
| 878 |
+
"loss": 0.5714,
|
| 879 |
+
"step": 1370
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.58,
|
| 883 |
+
"learning_rate": 9.763343823031718e-06,
|
| 884 |
+
"loss": 0.5702,
|
| 885 |
+
"step": 1380
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.59,
|
| 889 |
+
"learning_rate": 9.638832780029716e-06,
|
| 890 |
+
"loss": 0.5706,
|
| 891 |
+
"step": 1390
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.6,
|
| 895 |
+
"learning_rate": 9.514377778855521e-06,
|
| 896 |
+
"loss": 0.57,
|
| 897 |
+
"step": 1400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.6,
|
| 901 |
+
"eval_loss": 0.5853541493415833,
|
| 902 |
+
"eval_runtime": 765.003,
|
| 903 |
+
"eval_samples_per_second": 16.268,
|
| 904 |
+
"eval_steps_per_second": 2.034,
|
| 905 |
+
"step": 1400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.61,
|
| 909 |
+
"learning_rate": 9.389998131022906e-06,
|
| 910 |
+
"loss": 0.563,
|
| 911 |
+
"step": 1410
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.62,
|
| 915 |
+
"learning_rate": 9.265713136353184e-06,
|
| 916 |
+
"loss": 0.5559,
|
| 917 |
+
"step": 1420
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.63,
|
| 921 |
+
"learning_rate": 9.141542079980453e-06,
|
| 922 |
+
"loss": 0.5765,
|
| 923 |
+
"step": 1430
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.65,
|
| 927 |
+
"learning_rate": 9.017504229359157e-06,
|
| 928 |
+
"loss": 0.5737,
|
| 929 |
+
"step": 1440
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.66,
|
| 933 |
+
"learning_rate": 8.893618831274399e-06,
|
| 934 |
+
"loss": 0.5588,
|
| 935 |
+
"step": 1450
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.67,
|
| 939 |
+
"learning_rate": 8.769905108855412e-06,
|
| 940 |
+
"loss": 0.5619,
|
| 941 |
+
"step": 1460
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.68,
|
| 945 |
+
"learning_rate": 8.646382258592762e-06,
|
| 946 |
+
"loss": 0.5612,
|
| 947 |
+
"step": 1470
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.69,
|
| 951 |
+
"learning_rate": 8.523069447359631e-06,
|
| 952 |
+
"loss": 0.5647,
|
| 953 |
+
"step": 1480
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.7,
|
| 957 |
+
"learning_rate": 8.399985809437737e-06,
|
| 958 |
+
"loss": 0.5803,
|
| 959 |
+
"step": 1490
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.71,
|
| 963 |
+
"learning_rate": 8.277150443548285e-06,
|
| 964 |
+
"loss": 0.554,
|
| 965 |
+
"step": 1500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.73,
|
| 969 |
+
"learning_rate": 8.154582409888441e-06,
|
| 970 |
+
"loss": 0.5734,
|
| 971 |
+
"step": 1510
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.74,
|
| 975 |
+
"learning_rate": 8.032300727173797e-06,
|
| 976 |
+
"loss": 0.5646,
|
| 977 |
+
"step": 1520
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.75,
|
| 981 |
+
"learning_rate": 7.91032436968725e-06,
|
| 982 |
+
"loss": 0.5665,
|
| 983 |
+
"step": 1530
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.76,
|
| 987 |
+
"learning_rate": 7.788672264334804e-06,
|
| 988 |
+
"loss": 0.5519,
|
| 989 |
+
"step": 1540
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.77,
|
| 993 |
+
"learning_rate": 7.667363287708692e-06,
|
| 994 |
+
"loss": 0.5676,
|
| 995 |
+
"step": 1550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.78,
|
| 999 |
+
"learning_rate": 7.546416263158326e-06,
|
| 1000 |
+
"loss": 0.5516,
|
| 1001 |
+
"step": 1560
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.79,
|
| 1005 |
+
"learning_rate": 7.42584995786952e-06,
|
| 1006 |
+
"loss": 0.5553,
|
| 1007 |
+
"step": 1570
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.81,
|
| 1011 |
+
"learning_rate": 7.305683079952381e-06,
|
| 1012 |
+
"loss": 0.56,
|
| 1013 |
+
"step": 1580
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.82,
|
| 1017 |
+
"learning_rate": 7.185934275538416e-06,
|
| 1018 |
+
"loss": 0.5715,
|
| 1019 |
+
"step": 1590
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.83,
|
| 1023 |
+
"learning_rate": 7.066622125887237e-06,
|
| 1024 |
+
"loss": 0.5459,
|
| 1025 |
+
"step": 1600
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.83,
|
| 1029 |
+
"eval_loss": 0.5793296098709106,
|
| 1030 |
+
"eval_runtime": 764.5785,
|
| 1031 |
+
"eval_samples_per_second": 16.277,
|
| 1032 |
+
"eval_steps_per_second": 2.035,
|
| 1033 |
+
"step": 1600
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.84,
|
| 1037 |
+
"learning_rate": 6.947765144503323e-06,
|
| 1038 |
+
"loss": 0.5499,
|
| 1039 |
+
"step": 1610
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.85,
|
| 1043 |
+
"learning_rate": 6.8293817742633175e-06,
|
| 1044 |
+
"loss": 0.5483,
|
| 1045 |
+
"step": 1620
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.86,
|
| 1049 |
+
"learning_rate": 6.711490384554257e-06,
|
| 1050 |
+
"loss": 0.5565,
|
| 1051 |
+
"step": 1630
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.87,
|
| 1055 |
+
"learning_rate": 6.59410926842323e-06,
|
| 1056 |
+
"loss": 0.5596,
|
| 1057 |
+
"step": 1640
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.89,
|
| 1061 |
+
"learning_rate": 6.477256639738872e-06,
|
| 1062 |
+
"loss": 0.5623,
|
| 1063 |
+
"step": 1650
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.9,
|
| 1067 |
+
"learning_rate": 6.360950630365126e-06,
|
| 1068 |
+
"loss": 0.5509,
|
| 1069 |
+
"step": 1660
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.91,
|
| 1073 |
+
"learning_rate": 6.245209287347767e-06,
|
| 1074 |
+
"loss": 0.561,
|
| 1075 |
+
"step": 1670
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.92,
|
| 1079 |
+
"learning_rate": 6.130050570114049e-06,
|
| 1080 |
+
"loss": 0.57,
|
| 1081 |
+
"step": 1680
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.93,
|
| 1085 |
+
"learning_rate": 6.015492347685983e-06,
|
| 1086 |
+
"loss": 0.5624,
|
| 1087 |
+
"step": 1690
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.94,
|
| 1091 |
+
"learning_rate": 5.901552395907606e-06,
|
| 1092 |
+
"loss": 0.5574,
|
| 1093 |
+
"step": 1700
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.95,
|
| 1097 |
+
"learning_rate": 5.788248394686743e-06,
|
| 1098 |
+
"loss": 0.5588,
|
| 1099 |
+
"step": 1710
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.97,
|
| 1103 |
+
"learning_rate": 5.67559792525163e-06,
|
| 1104 |
+
"loss": 0.5487,
|
| 1105 |
+
"step": 1720
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.98,
|
| 1109 |
+
"learning_rate": 5.563618467422864e-06,
|
| 1110 |
+
"loss": 0.5579,
|
| 1111 |
+
"step": 1730
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 1.99,
|
| 1115 |
+
"learning_rate": 5.452327396901078e-06,
|
| 1116 |
+
"loss": 0.5577,
|
| 1117 |
+
"step": 1740
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.0,
|
| 1121 |
+
"learning_rate": 5.341741982570789e-06,
|
| 1122 |
+
"loss": 0.5519,
|
| 1123 |
+
"step": 1750
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.01,
|
| 1127 |
+
"learning_rate": 5.231879383820782e-06,
|
| 1128 |
+
"loss": 0.5664,
|
| 1129 |
+
"step": 1760
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.02,
|
| 1133 |
+
"learning_rate": 5.122756647881543e-06,
|
| 1134 |
+
"loss": 0.5572,
|
| 1135 |
+
"step": 1770
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.03,
|
| 1139 |
+
"learning_rate": 5.0143907071800445e-06,
|
| 1140 |
+
"loss": 0.5516,
|
| 1141 |
+
"step": 1780
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.05,
|
| 1145 |
+
"learning_rate": 4.9067983767123736e-06,
|
| 1146 |
+
"loss": 0.5498,
|
| 1147 |
+
"step": 1790
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.06,
|
| 1151 |
+
"learning_rate": 4.79999635143455e-06,
|
| 1152 |
+
"loss": 0.571,
|
| 1153 |
+
"step": 1800
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.06,
|
| 1157 |
+
"eval_loss": 0.5752249956130981,
|
| 1158 |
+
"eval_runtime": 764.7047,
|
| 1159 |
+
"eval_samples_per_second": 16.274,
|
| 1160 |
+
"eval_steps_per_second": 2.035,
|
| 1161 |
+
"step": 1800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.07,
|
| 1165 |
+
"learning_rate": 4.694001203672028e-06,
|
| 1166 |
+
"loss": 0.5661,
|
| 1167 |
+
"step": 1810
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.08,
|
| 1171 |
+
"learning_rate": 4.588829380548168e-06,
|
| 1172 |
+
"loss": 0.5733,
|
| 1173 |
+
"step": 1820
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.09,
|
| 1177 |
+
"learning_rate": 4.484497201432147e-06,
|
| 1178 |
+
"loss": 0.5725,
|
| 1179 |
+
"step": 1830
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.1,
|
| 1183 |
+
"learning_rate": 4.381020855406738e-06,
|
| 1184 |
+
"loss": 0.556,
|
| 1185 |
+
"step": 1840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.11,
|
| 1189 |
+
"learning_rate": 4.278416398756245e-06,
|
| 1190 |
+
"loss": 0.5671,
|
| 1191 |
+
"step": 1850
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.13,
|
| 1195 |
+
"learning_rate": 4.176699752475087e-06,
|
| 1196 |
+
"loss": 0.566,
|
| 1197 |
+
"step": 1860
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.14,
|
| 1201 |
+
"learning_rate": 4.075886699797338e-06,
|
| 1202 |
+
"loss": 0.5692,
|
| 1203 |
+
"step": 1870
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.15,
|
| 1207 |
+
"learning_rate": 3.975992883747688e-06,
|
| 1208 |
+
"loss": 0.5582,
|
| 1209 |
+
"step": 1880
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.16,
|
| 1213 |
+
"learning_rate": 3.877033804714133e-06,
|
| 1214 |
+
"loss": 0.5477,
|
| 1215 |
+
"step": 1890
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.17,
|
| 1219 |
+
"learning_rate": 3.7790248180427758e-06,
|
| 1220 |
+
"loss": 0.5488,
|
| 1221 |
+
"step": 1900
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.18,
|
| 1225 |
+
"learning_rate": 3.6819811316551867e-06,
|
| 1226 |
+
"loss": 0.5591,
|
| 1227 |
+
"step": 1910
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.19,
|
| 1231 |
+
"learning_rate": 3.585917803688603e-06,
|
| 1232 |
+
"loss": 0.5548,
|
| 1233 |
+
"step": 1920
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.21,
|
| 1237 |
+
"learning_rate": 3.4908497401593634e-06,
|
| 1238 |
+
"loss": 0.5517,
|
| 1239 |
+
"step": 1930
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.22,
|
| 1243 |
+
"learning_rate": 3.3967916926499823e-06,
|
| 1244 |
+
"loss": 0.556,
|
| 1245 |
+
"step": 1940
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.23,
|
| 1249 |
+
"learning_rate": 3.303758256020154e-06,
|
| 1250 |
+
"loss": 0.5398,
|
| 1251 |
+
"step": 1950
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.24,
|
| 1255 |
+
"learning_rate": 3.211763866142097e-06,
|
| 1256 |
+
"loss": 0.5487,
|
| 1257 |
+
"step": 1960
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.25,
|
| 1261 |
+
"learning_rate": 3.1208227976605475e-06,
|
| 1262 |
+
"loss": 0.5503,
|
| 1263 |
+
"step": 1970
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.26,
|
| 1267 |
+
"learning_rate": 3.0309491617777943e-06,
|
| 1268 |
+
"loss": 0.5609,
|
| 1269 |
+
"step": 1980
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.27,
|
| 1273 |
+
"learning_rate": 2.9421569040640564e-06,
|
| 1274 |
+
"loss": 0.5569,
|
| 1275 |
+
"step": 1990
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.29,
|
| 1279 |
+
"learning_rate": 2.854459802293561e-06,
|
| 1280 |
+
"loss": 0.5558,
|
| 1281 |
+
"step": 2000
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.29,
|
| 1285 |
+
"eval_loss": 0.5727296471595764,
|
| 1286 |
+
"eval_runtime": 764.8947,
|
| 1287 |
+
"eval_samples_per_second": 16.27,
|
| 1288 |
+
"eval_steps_per_second": 2.034,
|
| 1289 |
+
"step": 2000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.3,
|
| 1293 |
+
"learning_rate": 2.767871464306682e-06,
|
| 1294 |
+
"loss": 0.5596,
|
| 1295 |
+
"step": 2010
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 2.31,
|
| 1299 |
+
"learning_rate": 2.682405325898416e-06,
|
| 1300 |
+
"loss": 0.5565,
|
| 1301 |
+
"step": 2020
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.32,
|
| 1305 |
+
"learning_rate": 2.5980746487335785e-06,
|
| 1306 |
+
"loss": 0.5482,
|
| 1307 |
+
"step": 2030
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.33,
|
| 1311 |
+
"learning_rate": 2.514892518288988e-06,
|
| 1312 |
+
"loss": 0.559,
|
| 1313 |
+
"step": 2040
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.34,
|
| 1317 |
+
"learning_rate": 2.432871841823047e-06,
|
| 1318 |
+
"loss": 0.5621,
|
| 1319 |
+
"step": 2050
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.35,
|
| 1323 |
+
"learning_rate": 2.3520253463729058e-06,
|
| 1324 |
+
"loss": 0.5485,
|
| 1325 |
+
"step": 2060
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.37,
|
| 1329 |
+
"learning_rate": 2.272365576779637e-06,
|
| 1330 |
+
"loss": 0.5598,
|
| 1331 |
+
"step": 2070
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 2.38,
|
| 1335 |
+
"learning_rate": 2.1939048937416783e-06,
|
| 1336 |
+
"loss": 0.5655,
|
| 1337 |
+
"step": 2080
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.39,
|
| 1341 |
+
"learning_rate": 2.116655471896828e-06,
|
| 1342 |
+
"loss": 0.5522,
|
| 1343 |
+
"step": 2090
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.4,
|
| 1347 |
+
"learning_rate": 2.0406292979331333e-06,
|
| 1348 |
+
"loss": 0.552,
|
| 1349 |
+
"step": 2100
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.41,
|
| 1353 |
+
"learning_rate": 1.965838168728912e-06,
|
| 1354 |
+
"loss": 0.5565,
|
| 1355 |
+
"step": 2110
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.42,
|
| 1359 |
+
"learning_rate": 1.8922936895222798e-06,
|
| 1360 |
+
"loss": 0.5576,
|
| 1361 |
+
"step": 2120
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.43,
|
| 1365 |
+
"learning_rate": 1.8200072721103545e-06,
|
| 1366 |
+
"loss": 0.5629,
|
| 1367 |
+
"step": 2130
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.45,
|
| 1371 |
+
"learning_rate": 1.7489901330785053e-06,
|
| 1372 |
+
"loss": 0.5461,
|
| 1373 |
+
"step": 2140
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 2.46,
|
| 1377 |
+
"learning_rate": 1.6792532920599025e-06,
|
| 1378 |
+
"loss": 0.5503,
|
| 1379 |
+
"step": 2150
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 2.47,
|
| 1383 |
+
"learning_rate": 1.610807570025611e-06,
|
| 1384 |
+
"loss": 0.5422,
|
| 1385 |
+
"step": 2160
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.48,
|
| 1389 |
+
"learning_rate": 1.5436635876055107e-06,
|
| 1390 |
+
"loss": 0.5537,
|
| 1391 |
+
"step": 2170
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.49,
|
| 1395 |
+
"learning_rate": 1.4778317634403082e-06,
|
| 1396 |
+
"loss": 0.5676,
|
| 1397 |
+
"step": 2180
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.5,
|
| 1401 |
+
"learning_rate": 1.4133223125648966e-06,
|
| 1402 |
+
"loss": 0.5664,
|
| 1403 |
+
"step": 2190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.51,
|
| 1407 |
+
"learning_rate": 1.350145244823302e-06,
|
| 1408 |
+
"loss": 0.5467,
|
| 1409 |
+
"step": 2200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.51,
|
| 1413 |
+
"eval_loss": 0.5713418126106262,
|
| 1414 |
+
"eval_runtime": 764.6146,
|
| 1415 |
+
"eval_samples_per_second": 16.276,
|
| 1416 |
+
"eval_steps_per_second": 2.035,
|
| 1417 |
+
"step": 2200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.53,
|
| 1421 |
+
"learning_rate": 1.2883103633154582e-06,
|
| 1422 |
+
"loss": 0.5413,
|
| 1423 |
+
"step": 2210
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.54,
|
| 1427 |
+
"learning_rate": 1.2278272628760857e-06,
|
| 1428 |
+
"loss": 0.5494,
|
| 1429 |
+
"step": 2220
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 2.55,
|
| 1433 |
+
"learning_rate": 1.1687053285858685e-06,
|
| 1434 |
+
"loss": 0.5596,
|
| 1435 |
+
"step": 2230
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.56,
|
| 1439 |
+
"learning_rate": 1.1109537343151877e-06,
|
| 1440 |
+
"loss": 0.5609,
|
| 1441 |
+
"step": 2240
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.57,
|
| 1445 |
+
"learning_rate": 1.0545814413006138e-06,
|
| 1446 |
+
"loss": 0.5574,
|
| 1447 |
+
"step": 2250
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 2.58,
|
| 1451 |
+
"learning_rate": 9.995971967544217e-07,
|
| 1452 |
+
"loss": 0.5472,
|
| 1453 |
+
"step": 2260
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.59,
|
| 1457 |
+
"learning_rate": 9.460095325072805e-07,
|
| 1458 |
+
"loss": 0.564,
|
| 1459 |
+
"step": 2270
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.61,
|
| 1463 |
+
"learning_rate": 8.9382676368439e-07,
|
| 1464 |
+
"loss": 0.5483,
|
| 1465 |
+
"step": 2280
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.62,
|
| 1469 |
+
"learning_rate": 8.430569874152339e-07,
|
| 1470 |
+
"loss": 0.534,
|
| 1471 |
+
"step": 2290
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.63,
|
| 1475 |
+
"learning_rate": 7.937080815771569e-07,
|
| 1476 |
+
"loss": 0.5628,
|
| 1477 |
+
"step": 2300
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 2.64,
|
| 1481 |
+
"learning_rate": 7.457877035729588e-07,
|
| 1482 |
+
"loss": 0.571,
|
| 1483 |
+
"step": 2310
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 2.65,
|
| 1487 |
+
"learning_rate": 6.993032891427221e-07,
|
| 1488 |
+
"loss": 0.5507,
|
| 1489 |
+
"step": 2320
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 2.66,
|
| 1493 |
+
"learning_rate": 6.542620512100029e-07,
|
| 1494 |
+
"loss": 0.5575,
|
| 1495 |
+
"step": 2330
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.67,
|
| 1499 |
+
"learning_rate": 6.106709787626198e-07,
|
| 1500 |
+
"loss": 0.5529,
|
| 1501 |
+
"step": 2340
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.69,
|
| 1505 |
+
"learning_rate": 5.685368357681731e-07,
|
| 1506 |
+
"loss": 0.5483,
|
| 1507 |
+
"step": 2350
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.7,
|
| 1511 |
+
"learning_rate": 5.278661601245061e-07,
|
| 1512 |
+
"loss": 0.5598,
|
| 1513 |
+
"step": 2360
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 2.71,
|
| 1517 |
+
"learning_rate": 4.886652626452115e-07,
|
| 1518 |
+
"loss": 0.5454,
|
| 1519 |
+
"step": 2370
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 2.72,
|
| 1523 |
+
"learning_rate": 4.50940226080393e-07,
|
| 1524 |
+
"loss": 0.547,
|
| 1525 |
+
"step": 2380
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 2.73,
|
| 1529 |
+
"learning_rate": 4.146969041728255e-07,
|
| 1530 |
+
"loss": 0.5459,
|
| 1531 |
+
"step": 2390
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 2.74,
|
| 1535 |
+
"learning_rate": 3.7994092074962405e-07,
|
| 1536 |
+
"loss": 0.5424,
|
| 1537 |
+
"step": 2400
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.74,
|
| 1541 |
+
"eval_loss": 0.5707904696464539,
|
| 1542 |
+
"eval_runtime": 763.6658,
|
| 1543 |
+
"eval_samples_per_second": 16.296,
|
| 1544 |
+
"eval_steps_per_second": 2.038,
|
| 1545 |
+
"step": 2400
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.75,
|
| 1549 |
+
"learning_rate": 3.4667766884961205e-07,
|
| 1550 |
+
"loss": 0.5377,
|
| 1551 |
+
"step": 2410
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.77,
|
| 1555 |
+
"learning_rate": 3.1491230988648035e-07,
|
| 1556 |
+
"loss": 0.5528,
|
| 1557 |
+
"step": 2420
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.78,
|
| 1561 |
+
"learning_rate": 2.8464977284790917e-07,
|
| 1562 |
+
"loss": 0.5363,
|
| 1563 |
+
"step": 2430
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.79,
|
| 1567 |
+
"learning_rate": 2.5589475353073987e-07,
|
| 1568 |
+
"loss": 0.5423,
|
| 1569 |
+
"step": 2440
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.8,
|
| 1573 |
+
"learning_rate": 2.2865171381232677e-07,
|
| 1574 |
+
"loss": 0.5577,
|
| 1575 |
+
"step": 2450
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 2.81,
|
| 1579 |
+
"learning_rate": 2.0292488095820405e-07,
|
| 1580 |
+
"loss": 0.5518,
|
| 1581 |
+
"step": 2460
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 2.82,
|
| 1585 |
+
"learning_rate": 1.787182469661408e-07,
|
| 1586 |
+
"loss": 0.5559,
|
| 1587 |
+
"step": 2470
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 2.83,
|
| 1591 |
+
"learning_rate": 1.5603556794671403e-07,
|
| 1592 |
+
"loss": 0.5618,
|
| 1593 |
+
"step": 2480
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.85,
|
| 1597 |
+
"learning_rate": 1.348803635404683e-07,
|
| 1598 |
+
"loss": 0.561,
|
| 1599 |
+
"step": 2490
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.86,
|
| 1603 |
+
"learning_rate": 1.1525591637178813e-07,
|
| 1604 |
+
"loss": 0.5646,
|
| 1605 |
+
"step": 2500
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.87,
|
| 1609 |
+
"learning_rate": 9.716527153952882e-08,
|
| 1610 |
+
"loss": 0.545,
|
| 1611 |
+
"step": 2510
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 2.88,
|
| 1615 |
+
"learning_rate": 8.061123614452215e-08,
|
| 1616 |
+
"loss": 0.5587,
|
| 1617 |
+
"step": 2520
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 2.89,
|
| 1621 |
+
"learning_rate": 6.559637885399262e-08,
|
| 1622 |
+
"loss": 0.5551,
|
| 1623 |
+
"step": 2530
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 2.9,
|
| 1627 |
+
"learning_rate": 5.21230295029862e-08,
|
| 1628 |
+
"loss": 0.5519,
|
| 1629 |
+
"step": 2540
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 2.91,
|
| 1633 |
+
"learning_rate": 4.0193278732855166e-08,
|
| 1634 |
+
"loss": 0.5526,
|
| 1635 |
+
"step": 2550
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.93,
|
| 1639 |
+
"learning_rate": 2.9808977666848646e-08,
|
| 1640 |
+
"loss": 0.5598,
|
| 1641 |
+
"step": 2560
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.94,
|
| 1645 |
+
"learning_rate": 2.0971737622883515e-08,
|
| 1646 |
+
"loss": 0.54,
|
| 1647 |
+
"step": 2570
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.95,
|
| 1651 |
+
"learning_rate": 1.3682929863514383e-08,
|
| 1652 |
+
"loss": 0.5446,
|
| 1653 |
+
"step": 2580
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 2.96,
|
| 1657 |
+
"learning_rate": 7.94368538315715e-09,
|
| 1658 |
+
"loss": 0.5562,
|
| 1659 |
+
"step": 2590
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 2.97,
|
| 1663 |
+
"learning_rate": 3.754894732598269e-09,
|
| 1664 |
+
"loss": 0.5393,
|
| 1665 |
+
"step": 2600
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 2.97,
|
| 1669 |
+
"eval_loss": 0.5706716179847717,
|
| 1670 |
+
"eval_runtime": 765.1116,
|
| 1671 |
+
"eval_samples_per_second": 16.266,
|
| 1672 |
+
"eval_steps_per_second": 2.034,
|
| 1673 |
+
"step": 2600
|
| 1674 |
+
}
|
| 1675 |
+
],
|
| 1676 |
+
"logging_steps": 10,
|
| 1677 |
+
"max_steps": 2622,
|
| 1678 |
+
"num_train_epochs": 3,
|
| 1679 |
+
"save_steps": 200,
|
| 1680 |
+
"total_flos": 3.1289468506598277e+18,
|
| 1681 |
+
"trial_name": null,
|
| 1682 |
+
"trial_params": null
|
| 1683 |
+
}
|
checkpoint-2600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:351af72ecf82c54d3b93447930b5e2d6fab44f4b186eb4be6787a376d125d1f7
|
| 3 |
+
size 4472
|