Commit
•
360860b
1
Parent(s):
b4ab127
Upload folder using huggingface_hub
Browse files- README.md +204 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- all_results.json +11 -0
- eval_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +1350 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: google/flan-t5-base
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.7.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/flan-t5-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.2,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v",
|
| 23 |
+
"q"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "SEQ_2_SEQ_LM"
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b3296fcff514fee3ff0d0fd95872e9945028e0a5171922fe4e120f7bc1da6fb
|
| 3 |
+
size 7098016
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.05540305748581886,
|
| 4 |
+
"eval_runtime": 27.2595,
|
| 5 |
+
"eval_samples_per_second": 288.266,
|
| 6 |
+
"eval_steps_per_second": 18.049,
|
| 7 |
+
"train_loss": 0.09247852528257068,
|
| 8 |
+
"train_runtime": 8790.0948,
|
| 9 |
+
"train_samples_per_second": 80.453,
|
| 10 |
+
"train_steps_per_second": 5.028
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.05540305748581886,
|
| 4 |
+
"eval_runtime": 27.2595,
|
| 5 |
+
"eval_samples_per_second": 288.266,
|
| 6 |
+
"eval_steps_per_second": 18.049
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.09247852528257068,
|
| 4 |
+
"train_runtime": 8790.0948,
|
| 5 |
+
"train_samples_per_second": 80.453,
|
| 6 |
+
"train_steps_per_second": 5.028
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 44200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11,
|
| 13 |
+
"grad_norm": 0.4132317900657654,
|
| 14 |
+
"learning_rate": 0.0009886877828054299,
|
| 15 |
+
"loss": 0.285,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"eval_loss": 0.12178385257720947,
|
| 21 |
+
"eval_runtime": 27.3061,
|
| 22 |
+
"eval_samples_per_second": 287.774,
|
| 23 |
+
"eval_steps_per_second": 18.018,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.23,
|
| 28 |
+
"grad_norm": 0.4537642300128937,
|
| 29 |
+
"learning_rate": 0.0009773755656108597,
|
| 30 |
+
"loss": 0.1782,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.23,
|
| 35 |
+
"eval_loss": 0.10424336045980453,
|
| 36 |
+
"eval_runtime": 27.2202,
|
| 37 |
+
"eval_samples_per_second": 288.683,
|
| 38 |
+
"eval_steps_per_second": 18.075,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.34,
|
| 43 |
+
"grad_norm": 0.4927336871623993,
|
| 44 |
+
"learning_rate": 0.0009660633484162896,
|
| 45 |
+
"loss": 0.1623,
|
| 46 |
+
"step": 1500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.34,
|
| 50 |
+
"eval_loss": 0.1000167727470398,
|
| 51 |
+
"eval_runtime": 27.2235,
|
| 52 |
+
"eval_samples_per_second": 288.648,
|
| 53 |
+
"eval_steps_per_second": 18.073,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.45,
|
| 58 |
+
"grad_norm": 0.3784632682800293,
|
| 59 |
+
"learning_rate": 0.0009547511312217196,
|
| 60 |
+
"loss": 0.1487,
|
| 61 |
+
"step": 2000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.45,
|
| 65 |
+
"eval_loss": 0.10203839093446732,
|
| 66 |
+
"eval_runtime": 27.2422,
|
| 67 |
+
"eval_samples_per_second": 288.45,
|
| 68 |
+
"eval_steps_per_second": 18.06,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.57,
|
| 73 |
+
"grad_norm": 0.4409666955471039,
|
| 74 |
+
"learning_rate": 0.0009434389140271493,
|
| 75 |
+
"loss": 0.1419,
|
| 76 |
+
"step": 2500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.57,
|
| 80 |
+
"eval_loss": 0.0881214290857315,
|
| 81 |
+
"eval_runtime": 27.2438,
|
| 82 |
+
"eval_samples_per_second": 288.432,
|
| 83 |
+
"eval_steps_per_second": 18.059,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.68,
|
| 88 |
+
"grad_norm": 0.33156296610832214,
|
| 89 |
+
"learning_rate": 0.0009321266968325792,
|
| 90 |
+
"loss": 0.1371,
|
| 91 |
+
"step": 3000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.68,
|
| 95 |
+
"eval_loss": 0.08762603253126144,
|
| 96 |
+
"eval_runtime": 27.2331,
|
| 97 |
+
"eval_samples_per_second": 288.546,
|
| 98 |
+
"eval_steps_per_second": 18.066,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.79,
|
| 103 |
+
"grad_norm": 0.26063305139541626,
|
| 104 |
+
"learning_rate": 0.000920814479638009,
|
| 105 |
+
"loss": 0.1366,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.79,
|
| 110 |
+
"eval_loss": 0.08680489659309387,
|
| 111 |
+
"eval_runtime": 27.2296,
|
| 112 |
+
"eval_samples_per_second": 288.583,
|
| 113 |
+
"eval_steps_per_second": 18.069,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9,
|
| 118 |
+
"grad_norm": 0.6152302622795105,
|
| 119 |
+
"learning_rate": 0.0009095022624434389,
|
| 120 |
+
"loss": 0.1288,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9,
|
| 125 |
+
"eval_loss": 0.08397215604782104,
|
| 126 |
+
"eval_runtime": 27.259,
|
| 127 |
+
"eval_samples_per_second": 288.272,
|
| 128 |
+
"eval_steps_per_second": 18.049,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.02,
|
| 133 |
+
"grad_norm": 0.20703616738319397,
|
| 134 |
+
"learning_rate": 0.0008981900452488689,
|
| 135 |
+
"loss": 0.1329,
|
| 136 |
+
"step": 4500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.02,
|
| 140 |
+
"eval_loss": 0.0818256288766861,
|
| 141 |
+
"eval_runtime": 27.2728,
|
| 142 |
+
"eval_samples_per_second": 288.126,
|
| 143 |
+
"eval_steps_per_second": 18.04,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.13,
|
| 148 |
+
"grad_norm": 0.47000011801719666,
|
| 149 |
+
"learning_rate": 0.0008868778280542986,
|
| 150 |
+
"loss": 0.1221,
|
| 151 |
+
"step": 5000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.13,
|
| 155 |
+
"eval_loss": 0.08076580613851547,
|
| 156 |
+
"eval_runtime": 27.2281,
|
| 157 |
+
"eval_samples_per_second": 288.599,
|
| 158 |
+
"eval_steps_per_second": 18.07,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.24,
|
| 163 |
+
"grad_norm": 0.3874566853046417,
|
| 164 |
+
"learning_rate": 0.0008755656108597285,
|
| 165 |
+
"loss": 0.1202,
|
| 166 |
+
"step": 5500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.24,
|
| 170 |
+
"eval_loss": 0.08285848051309586,
|
| 171 |
+
"eval_runtime": 27.2548,
|
| 172 |
+
"eval_samples_per_second": 288.316,
|
| 173 |
+
"eval_steps_per_second": 18.052,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.36,
|
| 178 |
+
"grad_norm": 0.35874509811401367,
|
| 179 |
+
"learning_rate": 0.0008642533936651585,
|
| 180 |
+
"loss": 0.1186,
|
| 181 |
+
"step": 6000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.36,
|
| 185 |
+
"eval_loss": 0.081941157579422,
|
| 186 |
+
"eval_runtime": 27.2605,
|
| 187 |
+
"eval_samples_per_second": 288.256,
|
| 188 |
+
"eval_steps_per_second": 18.048,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.47,
|
| 193 |
+
"grad_norm": 0.34497329592704773,
|
| 194 |
+
"learning_rate": 0.0008529411764705882,
|
| 195 |
+
"loss": 0.1163,
|
| 196 |
+
"step": 6500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.47,
|
| 200 |
+
"eval_loss": 0.07750312983989716,
|
| 201 |
+
"eval_runtime": 27.2737,
|
| 202 |
+
"eval_samples_per_second": 288.116,
|
| 203 |
+
"eval_steps_per_second": 18.039,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.58,
|
| 208 |
+
"grad_norm": 0.34537777304649353,
|
| 209 |
+
"learning_rate": 0.0008416289592760181,
|
| 210 |
+
"loss": 0.1213,
|
| 211 |
+
"step": 7000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.58,
|
| 215 |
+
"eval_loss": 0.0756232738494873,
|
| 216 |
+
"eval_runtime": 27.2421,
|
| 217 |
+
"eval_samples_per_second": 288.451,
|
| 218 |
+
"eval_steps_per_second": 18.06,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.7,
|
| 223 |
+
"grad_norm": 0.31827136874198914,
|
| 224 |
+
"learning_rate": 0.000830316742081448,
|
| 225 |
+
"loss": 0.1169,
|
| 226 |
+
"step": 7500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.7,
|
| 230 |
+
"eval_loss": 0.07395777106285095,
|
| 231 |
+
"eval_runtime": 27.2385,
|
| 232 |
+
"eval_samples_per_second": 288.489,
|
| 233 |
+
"eval_steps_per_second": 18.063,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.81,
|
| 238 |
+
"grad_norm": 0.43441176414489746,
|
| 239 |
+
"learning_rate": 0.0008190045248868778,
|
| 240 |
+
"loss": 0.1151,
|
| 241 |
+
"step": 8000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.81,
|
| 245 |
+
"eval_loss": 0.08032752573490143,
|
| 246 |
+
"eval_runtime": 27.2392,
|
| 247 |
+
"eval_samples_per_second": 288.481,
|
| 248 |
+
"eval_steps_per_second": 18.062,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.92,
|
| 253 |
+
"grad_norm": 0.403935968875885,
|
| 254 |
+
"learning_rate": 0.0008076923076923078,
|
| 255 |
+
"loss": 0.1162,
|
| 256 |
+
"step": 8500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.92,
|
| 260 |
+
"eval_loss": 0.07349220663309097,
|
| 261 |
+
"eval_runtime": 27.2543,
|
| 262 |
+
"eval_samples_per_second": 288.322,
|
| 263 |
+
"eval_steps_per_second": 18.052,
|
| 264 |
+
"step": 8500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.04,
|
| 268 |
+
"grad_norm": 0.2286953330039978,
|
| 269 |
+
"learning_rate": 0.0007963800904977375,
|
| 270 |
+
"loss": 0.1157,
|
| 271 |
+
"step": 9000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.04,
|
| 275 |
+
"eval_loss": 0.07655400782823563,
|
| 276 |
+
"eval_runtime": 27.2562,
|
| 277 |
+
"eval_samples_per_second": 288.301,
|
| 278 |
+
"eval_steps_per_second": 18.051,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.15,
|
| 283 |
+
"grad_norm": 0.2294893115758896,
|
| 284 |
+
"learning_rate": 0.0007850678733031674,
|
| 285 |
+
"loss": 0.1121,
|
| 286 |
+
"step": 9500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.15,
|
| 290 |
+
"eval_loss": 0.07088885456323624,
|
| 291 |
+
"eval_runtime": 27.2467,
|
| 292 |
+
"eval_samples_per_second": 288.402,
|
| 293 |
+
"eval_steps_per_second": 18.057,
|
| 294 |
+
"step": 9500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.26,
|
| 298 |
+
"grad_norm": 0.44981372356414795,
|
| 299 |
+
"learning_rate": 0.0007737556561085974,
|
| 300 |
+
"loss": 0.1073,
|
| 301 |
+
"step": 10000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.26,
|
| 305 |
+
"eval_loss": 0.07331141084432602,
|
| 306 |
+
"eval_runtime": 27.2427,
|
| 307 |
+
"eval_samples_per_second": 288.445,
|
| 308 |
+
"eval_steps_per_second": 18.06,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.38,
|
| 313 |
+
"grad_norm": 0.4742676019668579,
|
| 314 |
+
"learning_rate": 0.0007624434389140271,
|
| 315 |
+
"loss": 0.1063,
|
| 316 |
+
"step": 10500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.38,
|
| 320 |
+
"eval_loss": 0.07561534643173218,
|
| 321 |
+
"eval_runtime": 27.2233,
|
| 322 |
+
"eval_samples_per_second": 288.65,
|
| 323 |
+
"eval_steps_per_second": 18.073,
|
| 324 |
+
"step": 10500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.49,
|
| 328 |
+
"grad_norm": 0.4676545262336731,
|
| 329 |
+
"learning_rate": 0.0007511312217194571,
|
| 330 |
+
"loss": 0.1109,
|
| 331 |
+
"step": 11000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.49,
|
| 335 |
+
"eval_loss": 0.07197986543178558,
|
| 336 |
+
"eval_runtime": 27.2211,
|
| 337 |
+
"eval_samples_per_second": 288.673,
|
| 338 |
+
"eval_steps_per_second": 18.074,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.6,
|
| 343 |
+
"grad_norm": 0.5688673257827759,
|
| 344 |
+
"learning_rate": 0.0007398190045248869,
|
| 345 |
+
"loss": 0.1072,
|
| 346 |
+
"step": 11500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.6,
|
| 350 |
+
"eval_loss": 0.07261210680007935,
|
| 351 |
+
"eval_runtime": 27.2328,
|
| 352 |
+
"eval_samples_per_second": 288.549,
|
| 353 |
+
"eval_steps_per_second": 18.066,
|
| 354 |
+
"step": 11500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.71,
|
| 358 |
+
"grad_norm": 0.24911655485630035,
|
| 359 |
+
"learning_rate": 0.0007285067873303167,
|
| 360 |
+
"loss": 0.1055,
|
| 361 |
+
"step": 12000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.71,
|
| 365 |
+
"eval_loss": 0.06898481398820877,
|
| 366 |
+
"eval_runtime": 27.2378,
|
| 367 |
+
"eval_samples_per_second": 288.496,
|
| 368 |
+
"eval_steps_per_second": 18.063,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.83,
|
| 373 |
+
"grad_norm": 0.4301845133304596,
|
| 374 |
+
"learning_rate": 0.0007171945701357467,
|
| 375 |
+
"loss": 0.1004,
|
| 376 |
+
"step": 12500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.83,
|
| 380 |
+
"eval_loss": 0.06929654628038406,
|
| 381 |
+
"eval_runtime": 27.2358,
|
| 382 |
+
"eval_samples_per_second": 288.517,
|
| 383 |
+
"eval_steps_per_second": 18.064,
|
| 384 |
+
"step": 12500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.94,
|
| 388 |
+
"grad_norm": 0.4303476810455322,
|
| 389 |
+
"learning_rate": 0.0007058823529411765,
|
| 390 |
+
"loss": 0.0995,
|
| 391 |
+
"step": 13000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.94,
|
| 395 |
+
"eval_loss": 0.06872580200433731,
|
| 396 |
+
"eval_runtime": 27.2296,
|
| 397 |
+
"eval_samples_per_second": 288.583,
|
| 398 |
+
"eval_steps_per_second": 18.069,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.05,
|
| 403 |
+
"grad_norm": 0.3978405296802521,
|
| 404 |
+
"learning_rate": 0.0006945701357466064,
|
| 405 |
+
"loss": 0.0999,
|
| 406 |
+
"step": 13500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 3.05,
|
| 410 |
+
"eval_loss": 0.06932587921619415,
|
| 411 |
+
"eval_runtime": 27.2271,
|
| 412 |
+
"eval_samples_per_second": 288.609,
|
| 413 |
+
"eval_steps_per_second": 18.07,
|
| 414 |
+
"step": 13500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.17,
|
| 418 |
+
"grad_norm": 0.26857316493988037,
|
| 419 |
+
"learning_rate": 0.0006832579185520362,
|
| 420 |
+
"loss": 0.0959,
|
| 421 |
+
"step": 14000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.17,
|
| 425 |
+
"eval_loss": 0.07186341285705566,
|
| 426 |
+
"eval_runtime": 27.231,
|
| 427 |
+
"eval_samples_per_second": 288.569,
|
| 428 |
+
"eval_steps_per_second": 18.068,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.28,
|
| 433 |
+
"grad_norm": 0.4276795983314514,
|
| 434 |
+
"learning_rate": 0.0006719457013574661,
|
| 435 |
+
"loss": 0.0982,
|
| 436 |
+
"step": 14500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 3.28,
|
| 440 |
+
"eval_loss": 0.07152236998081207,
|
| 441 |
+
"eval_runtime": 27.2215,
|
| 442 |
+
"eval_samples_per_second": 288.669,
|
| 443 |
+
"eval_steps_per_second": 18.074,
|
| 444 |
+
"step": 14500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.39,
|
| 448 |
+
"grad_norm": 0.41015538573265076,
|
| 449 |
+
"learning_rate": 0.000660633484162896,
|
| 450 |
+
"loss": 0.0969,
|
| 451 |
+
"step": 15000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.39,
|
| 455 |
+
"eval_loss": 0.07108399271965027,
|
| 456 |
+
"eval_runtime": 27.2286,
|
| 457 |
+
"eval_samples_per_second": 288.594,
|
| 458 |
+
"eval_steps_per_second": 18.069,
|
| 459 |
+
"step": 15000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.51,
|
| 463 |
+
"grad_norm": 0.180690735578537,
|
| 464 |
+
"learning_rate": 0.0006493212669683258,
|
| 465 |
+
"loss": 0.0995,
|
| 466 |
+
"step": 15500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 3.51,
|
| 470 |
+
"eval_loss": 0.06466764211654663,
|
| 471 |
+
"eval_runtime": 27.2483,
|
| 472 |
+
"eval_samples_per_second": 288.385,
|
| 473 |
+
"eval_steps_per_second": 18.056,
|
| 474 |
+
"step": 15500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.62,
|
| 478 |
+
"grad_norm": 0.2916184067726135,
|
| 479 |
+
"learning_rate": 0.0006380090497737556,
|
| 480 |
+
"loss": 0.0962,
|
| 481 |
+
"step": 16000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 3.62,
|
| 485 |
+
"eval_loss": 0.06967472285032272,
|
| 486 |
+
"eval_runtime": 27.2534,
|
| 487 |
+
"eval_samples_per_second": 288.331,
|
| 488 |
+
"eval_steps_per_second": 18.053,
|
| 489 |
+
"step": 16000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.73,
|
| 493 |
+
"grad_norm": 0.444690465927124,
|
| 494 |
+
"learning_rate": 0.0006266968325791855,
|
| 495 |
+
"loss": 0.0959,
|
| 496 |
+
"step": 16500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.73,
|
| 500 |
+
"eval_loss": 0.06753501296043396,
|
| 501 |
+
"eval_runtime": 27.2523,
|
| 502 |
+
"eval_samples_per_second": 288.343,
|
| 503 |
+
"eval_steps_per_second": 18.054,
|
| 504 |
+
"step": 16500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.85,
|
| 508 |
+
"grad_norm": 0.3559369146823883,
|
| 509 |
+
"learning_rate": 0.0006153846153846154,
|
| 510 |
+
"loss": 0.0949,
|
| 511 |
+
"step": 17000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.85,
|
| 515 |
+
"eval_loss": 0.06987947970628738,
|
| 516 |
+
"eval_runtime": 27.2447,
|
| 517 |
+
"eval_samples_per_second": 288.423,
|
| 518 |
+
"eval_steps_per_second": 18.059,
|
| 519 |
+
"step": 17000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.96,
|
| 523 |
+
"grad_norm": 0.3376706838607788,
|
| 524 |
+
"learning_rate": 0.0006040723981900453,
|
| 525 |
+
"loss": 0.096,
|
| 526 |
+
"step": 17500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.96,
|
| 530 |
+
"eval_loss": 0.06431511789560318,
|
| 531 |
+
"eval_runtime": 27.2316,
|
| 532 |
+
"eval_samples_per_second": 288.562,
|
| 533 |
+
"eval_steps_per_second": 18.067,
|
| 534 |
+
"step": 17500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 4.07,
|
| 538 |
+
"grad_norm": 0.4778081476688385,
|
| 539 |
+
"learning_rate": 0.0005927601809954751,
|
| 540 |
+
"loss": 0.0916,
|
| 541 |
+
"step": 18000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 4.07,
|
| 545 |
+
"eval_loss": 0.06719387322664261,
|
| 546 |
+
"eval_runtime": 27.1935,
|
| 547 |
+
"eval_samples_per_second": 288.967,
|
| 548 |
+
"eval_steps_per_second": 18.093,
|
| 549 |
+
"step": 18000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.19,
|
| 553 |
+
"grad_norm": 0.6138429641723633,
|
| 554 |
+
"learning_rate": 0.000581447963800905,
|
| 555 |
+
"loss": 0.0887,
|
| 556 |
+
"step": 18500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 4.19,
|
| 560 |
+
"eval_loss": 0.06378566473722458,
|
| 561 |
+
"eval_runtime": 27.2223,
|
| 562 |
+
"eval_samples_per_second": 288.661,
|
| 563 |
+
"eval_steps_per_second": 18.073,
|
| 564 |
+
"step": 18500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 4.3,
|
| 568 |
+
"grad_norm": 0.48502928018569946,
|
| 569 |
+
"learning_rate": 0.0005701357466063349,
|
| 570 |
+
"loss": 0.0902,
|
| 571 |
+
"step": 19000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 4.3,
|
| 575 |
+
"eval_loss": 0.06466159969568253,
|
| 576 |
+
"eval_runtime": 27.224,
|
| 577 |
+
"eval_samples_per_second": 288.642,
|
| 578 |
+
"eval_steps_per_second": 18.072,
|
| 579 |
+
"step": 19000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.41,
|
| 583 |
+
"grad_norm": 0.28751033544540405,
|
| 584 |
+
"learning_rate": 0.0005588235294117647,
|
| 585 |
+
"loss": 0.089,
|
| 586 |
+
"step": 19500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 4.41,
|
| 590 |
+
"eval_loss": 0.06292453408241272,
|
| 591 |
+
"eval_runtime": 27.2238,
|
| 592 |
+
"eval_samples_per_second": 288.644,
|
| 593 |
+
"eval_steps_per_second": 18.072,
|
| 594 |
+
"step": 19500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 4.52,
|
| 598 |
+
"grad_norm": 0.2429145723581314,
|
| 599 |
+
"learning_rate": 0.0005475113122171947,
|
| 600 |
+
"loss": 0.0881,
|
| 601 |
+
"step": 20000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 4.52,
|
| 605 |
+
"eval_loss": 0.0646950751543045,
|
| 606 |
+
"eval_runtime": 27.2322,
|
| 607 |
+
"eval_samples_per_second": 288.555,
|
| 608 |
+
"eval_steps_per_second": 18.067,
|
| 609 |
+
"step": 20000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.64,
|
| 613 |
+
"grad_norm": 0.13486433029174805,
|
| 614 |
+
"learning_rate": 0.0005361990950226244,
|
| 615 |
+
"loss": 0.0875,
|
| 616 |
+
"step": 20500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.64,
|
| 620 |
+
"eval_loss": 0.06334567815065384,
|
| 621 |
+
"eval_runtime": 27.2229,
|
| 622 |
+
"eval_samples_per_second": 288.654,
|
| 623 |
+
"eval_steps_per_second": 18.073,
|
| 624 |
+
"step": 20500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.75,
|
| 628 |
+
"grad_norm": 0.2922358512878418,
|
| 629 |
+
"learning_rate": 0.0005248868778280543,
|
| 630 |
+
"loss": 0.0894,
|
| 631 |
+
"step": 21000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 4.75,
|
| 635 |
+
"eval_loss": 0.06537148356437683,
|
| 636 |
+
"eval_runtime": 27.2312,
|
| 637 |
+
"eval_samples_per_second": 288.566,
|
| 638 |
+
"eval_steps_per_second": 18.068,
|
| 639 |
+
"step": 21000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.86,
|
| 643 |
+
"grad_norm": 0.22684411704540253,
|
| 644 |
+
"learning_rate": 0.0005135746606334842,
|
| 645 |
+
"loss": 0.0901,
|
| 646 |
+
"step": 21500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.86,
|
| 650 |
+
"eval_loss": 0.06314302235841751,
|
| 651 |
+
"eval_runtime": 27.237,
|
| 652 |
+
"eval_samples_per_second": 288.504,
|
| 653 |
+
"eval_steps_per_second": 18.064,
|
| 654 |
+
"step": 21500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.98,
|
| 658 |
+
"grad_norm": 0.641290545463562,
|
| 659 |
+
"learning_rate": 0.000502262443438914,
|
| 660 |
+
"loss": 0.0898,
|
| 661 |
+
"step": 22000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.98,
|
| 665 |
+
"eval_loss": 0.06266883760690689,
|
| 666 |
+
"eval_runtime": 27.2238,
|
| 667 |
+
"eval_samples_per_second": 288.645,
|
| 668 |
+
"eval_steps_per_second": 18.072,
|
| 669 |
+
"step": 22000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 5.09,
|
| 673 |
+
"grad_norm": 0.31225764751434326,
|
| 674 |
+
"learning_rate": 0.0004909502262443439,
|
| 675 |
+
"loss": 0.0813,
|
| 676 |
+
"step": 22500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 5.09,
|
| 680 |
+
"eval_loss": 0.06273192167282104,
|
| 681 |
+
"eval_runtime": 27.2277,
|
| 682 |
+
"eval_samples_per_second": 288.603,
|
| 683 |
+
"eval_steps_per_second": 18.07,
|
| 684 |
+
"step": 22500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 5.2,
|
| 688 |
+
"grad_norm": 0.44664525985717773,
|
| 689 |
+
"learning_rate": 0.0004796380090497738,
|
| 690 |
+
"loss": 0.083,
|
| 691 |
+
"step": 23000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 5.2,
|
| 695 |
+
"eval_loss": 0.06290117651224136,
|
| 696 |
+
"eval_runtime": 27.2049,
|
| 697 |
+
"eval_samples_per_second": 288.845,
|
| 698 |
+
"eval_steps_per_second": 18.085,
|
| 699 |
+
"step": 23000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 5.32,
|
| 703 |
+
"grad_norm": 0.1560264378786087,
|
| 704 |
+
"learning_rate": 0.00046832579185520365,
|
| 705 |
+
"loss": 0.0833,
|
| 706 |
+
"step": 23500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 5.32,
|
| 710 |
+
"eval_loss": 0.06229640915989876,
|
| 711 |
+
"eval_runtime": 27.2246,
|
| 712 |
+
"eval_samples_per_second": 288.636,
|
| 713 |
+
"eval_steps_per_second": 18.072,
|
| 714 |
+
"step": 23500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 5.43,
|
| 718 |
+
"grad_norm": 0.11389543116092682,
|
| 719 |
+
"learning_rate": 0.00045701357466063346,
|
| 720 |
+
"loss": 0.083,
|
| 721 |
+
"step": 24000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 5.43,
|
| 725 |
+
"eval_loss": 0.06498704105615616,
|
| 726 |
+
"eval_runtime": 27.2302,
|
| 727 |
+
"eval_samples_per_second": 288.576,
|
| 728 |
+
"eval_steps_per_second": 18.068,
|
| 729 |
+
"step": 24000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.54,
|
| 733 |
+
"grad_norm": 0.6757131814956665,
|
| 734 |
+
"learning_rate": 0.0004457013574660634,
|
| 735 |
+
"loss": 0.0825,
|
| 736 |
+
"step": 24500
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 5.54,
|
| 740 |
+
"eval_loss": 0.06173526123166084,
|
| 741 |
+
"eval_runtime": 27.2094,
|
| 742 |
+
"eval_samples_per_second": 288.798,
|
| 743 |
+
"eval_steps_per_second": 18.082,
|
| 744 |
+
"step": 24500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.66,
|
| 748 |
+
"grad_norm": 0.2726614475250244,
|
| 749 |
+
"learning_rate": 0.00043438914027149324,
|
| 750 |
+
"loss": 0.0829,
|
| 751 |
+
"step": 25000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 5.66,
|
| 755 |
+
"eval_loss": 0.060302384197711945,
|
| 756 |
+
"eval_runtime": 27.2049,
|
| 757 |
+
"eval_samples_per_second": 288.845,
|
| 758 |
+
"eval_steps_per_second": 18.085,
|
| 759 |
+
"step": 25000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 5.77,
|
| 763 |
+
"grad_norm": 0.8743285536766052,
|
| 764 |
+
"learning_rate": 0.0004230769230769231,
|
| 765 |
+
"loss": 0.0818,
|
| 766 |
+
"step": 25500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 5.77,
|
| 770 |
+
"eval_loss": 0.062085919082164764,
|
| 771 |
+
"eval_runtime": 27.2011,
|
| 772 |
+
"eval_samples_per_second": 288.885,
|
| 773 |
+
"eval_steps_per_second": 18.087,
|
| 774 |
+
"step": 25500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 5.88,
|
| 778 |
+
"grad_norm": 0.2872491478919983,
|
| 779 |
+
"learning_rate": 0.0004117647058823529,
|
| 780 |
+
"loss": 0.0807,
|
| 781 |
+
"step": 26000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 5.88,
|
| 785 |
+
"eval_loss": 0.059214599430561066,
|
| 786 |
+
"eval_runtime": 27.2158,
|
| 787 |
+
"eval_samples_per_second": 288.73,
|
| 788 |
+
"eval_steps_per_second": 18.078,
|
| 789 |
+
"step": 26000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.0,
|
| 793 |
+
"grad_norm": 0.5603688955307007,
|
| 794 |
+
"learning_rate": 0.0004004524886877828,
|
| 795 |
+
"loss": 0.082,
|
| 796 |
+
"step": 26500
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 6.0,
|
| 800 |
+
"eval_loss": 0.05830477178096771,
|
| 801 |
+
"eval_runtime": 27.2102,
|
| 802 |
+
"eval_samples_per_second": 288.788,
|
| 803 |
+
"eval_steps_per_second": 18.081,
|
| 804 |
+
"step": 26500
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 6.11,
|
| 808 |
+
"grad_norm": 0.4404628574848175,
|
| 809 |
+
"learning_rate": 0.0003891402714932127,
|
| 810 |
+
"loss": 0.0763,
|
| 811 |
+
"step": 27000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 6.11,
|
| 815 |
+
"eval_loss": 0.05895010381937027,
|
| 816 |
+
"eval_runtime": 27.2169,
|
| 817 |
+
"eval_samples_per_second": 288.718,
|
| 818 |
+
"eval_steps_per_second": 18.077,
|
| 819 |
+
"step": 27000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 6.22,
|
| 823 |
+
"grad_norm": 0.27021318674087524,
|
| 824 |
+
"learning_rate": 0.00037782805429864254,
|
| 825 |
+
"loss": 0.0781,
|
| 826 |
+
"step": 27500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 6.22,
|
| 830 |
+
"eval_loss": 0.06117743253707886,
|
| 831 |
+
"eval_runtime": 27.2077,
|
| 832 |
+
"eval_samples_per_second": 288.815,
|
| 833 |
+
"eval_steps_per_second": 18.083,
|
| 834 |
+
"step": 27500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 6.33,
|
| 838 |
+
"grad_norm": 0.5952714681625366,
|
| 839 |
+
"learning_rate": 0.0003665158371040724,
|
| 840 |
+
"loss": 0.077,
|
| 841 |
+
"step": 28000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 6.33,
|
| 845 |
+
"eval_loss": 0.06172608584165573,
|
| 846 |
+
"eval_runtime": 27.2143,
|
| 847 |
+
"eval_samples_per_second": 288.745,
|
| 848 |
+
"eval_steps_per_second": 18.079,
|
| 849 |
+
"step": 28000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 6.45,
|
| 853 |
+
"grad_norm": 0.11397124826908112,
|
| 854 |
+
"learning_rate": 0.00035520361990950226,
|
| 855 |
+
"loss": 0.0763,
|
| 856 |
+
"step": 28500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 6.45,
|
| 860 |
+
"eval_loss": 0.06007913500070572,
|
| 861 |
+
"eval_runtime": 27.1971,
|
| 862 |
+
"eval_samples_per_second": 288.928,
|
| 863 |
+
"eval_steps_per_second": 18.09,
|
| 864 |
+
"step": 28500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 6.56,
|
| 868 |
+
"grad_norm": 0.18584699928760529,
|
| 869 |
+
"learning_rate": 0.0003438914027149321,
|
| 870 |
+
"loss": 0.0741,
|
| 871 |
+
"step": 29000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 6.56,
|
| 875 |
+
"eval_loss": 0.05769050493836403,
|
| 876 |
+
"eval_runtime": 27.1856,
|
| 877 |
+
"eval_samples_per_second": 289.05,
|
| 878 |
+
"eval_steps_per_second": 18.098,
|
| 879 |
+
"step": 29000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 6.67,
|
| 883 |
+
"grad_norm": 0.26046234369277954,
|
| 884 |
+
"learning_rate": 0.000332579185520362,
|
| 885 |
+
"loss": 0.0746,
|
| 886 |
+
"step": 29500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 6.67,
|
| 890 |
+
"eval_loss": 0.05827530845999718,
|
| 891 |
+
"eval_runtime": 27.1863,
|
| 892 |
+
"eval_samples_per_second": 289.043,
|
| 893 |
+
"eval_steps_per_second": 18.097,
|
| 894 |
+
"step": 29500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 6.79,
|
| 898 |
+
"grad_norm": 0.12222661823034286,
|
| 899 |
+
"learning_rate": 0.0003212669683257919,
|
| 900 |
+
"loss": 0.0735,
|
| 901 |
+
"step": 30000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 6.79,
|
| 905 |
+
"eval_loss": 0.05913107842206955,
|
| 906 |
+
"eval_runtime": 27.1918,
|
| 907 |
+
"eval_samples_per_second": 288.984,
|
| 908 |
+
"eval_steps_per_second": 18.094,
|
| 909 |
+
"step": 30000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 6.9,
|
| 913 |
+
"grad_norm": 0.28610703349113464,
|
| 914 |
+
"learning_rate": 0.0003099547511312217,
|
| 915 |
+
"loss": 0.0726,
|
| 916 |
+
"step": 30500
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 6.9,
|
| 920 |
+
"eval_loss": 0.05818793550133705,
|
| 921 |
+
"eval_runtime": 27.2089,
|
| 922 |
+
"eval_samples_per_second": 288.803,
|
| 923 |
+
"eval_steps_per_second": 18.082,
|
| 924 |
+
"step": 30500
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 7.01,
|
| 928 |
+
"grad_norm": 0.3682945966720581,
|
| 929 |
+
"learning_rate": 0.00029864253393665157,
|
| 930 |
+
"loss": 0.0741,
|
| 931 |
+
"step": 31000
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 7.01,
|
| 935 |
+
"eval_loss": 0.05868174880743027,
|
| 936 |
+
"eval_runtime": 27.1916,
|
| 937 |
+
"eval_samples_per_second": 288.986,
|
| 938 |
+
"eval_steps_per_second": 18.094,
|
| 939 |
+
"step": 31000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 7.13,
|
| 943 |
+
"grad_norm": 0.16477471590042114,
|
| 944 |
+
"learning_rate": 0.00028733031674208143,
|
| 945 |
+
"loss": 0.0715,
|
| 946 |
+
"step": 31500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 7.13,
|
| 950 |
+
"eval_loss": 0.05955735221505165,
|
| 951 |
+
"eval_runtime": 27.1945,
|
| 952 |
+
"eval_samples_per_second": 288.955,
|
| 953 |
+
"eval_steps_per_second": 18.092,
|
| 954 |
+
"step": 31500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 7.24,
|
| 958 |
+
"grad_norm": 0.24769556522369385,
|
| 959 |
+
"learning_rate": 0.00027601809954751135,
|
| 960 |
+
"loss": 0.07,
|
| 961 |
+
"step": 32000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 7.24,
|
| 965 |
+
"eval_loss": 0.057150740176439285,
|
| 966 |
+
"eval_runtime": 27.1825,
|
| 967 |
+
"eval_samples_per_second": 289.083,
|
| 968 |
+
"eval_steps_per_second": 18.1,
|
| 969 |
+
"step": 32000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 7.35,
|
| 973 |
+
"grad_norm": 0.3199273347854614,
|
| 974 |
+
"learning_rate": 0.0002647058823529412,
|
| 975 |
+
"loss": 0.0686,
|
| 976 |
+
"step": 32500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 7.35,
|
| 980 |
+
"eval_loss": 0.05786846950650215,
|
| 981 |
+
"eval_runtime": 27.2001,
|
| 982 |
+
"eval_samples_per_second": 288.896,
|
| 983 |
+
"eval_steps_per_second": 18.088,
|
| 984 |
+
"step": 32500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 7.47,
|
| 988 |
+
"grad_norm": 0.3163066804409027,
|
| 989 |
+
"learning_rate": 0.000253393665158371,
|
| 990 |
+
"loss": 0.0703,
|
| 991 |
+
"step": 33000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 7.47,
|
| 995 |
+
"eval_loss": 0.05759541690349579,
|
| 996 |
+
"eval_runtime": 27.1994,
|
| 997 |
+
"eval_samples_per_second": 288.904,
|
| 998 |
+
"eval_steps_per_second": 18.089,
|
| 999 |
+
"step": 33000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 7.58,
|
| 1003 |
+
"grad_norm": 0.4390794336795807,
|
| 1004 |
+
"learning_rate": 0.0002420814479638009,
|
| 1005 |
+
"loss": 0.0694,
|
| 1006 |
+
"step": 33500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 7.58,
|
| 1010 |
+
"eval_loss": 0.06044788658618927,
|
| 1011 |
+
"eval_runtime": 27.2196,
|
| 1012 |
+
"eval_samples_per_second": 288.689,
|
| 1013 |
+
"eval_steps_per_second": 18.075,
|
| 1014 |
+
"step": 33500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 7.69,
|
| 1018 |
+
"grad_norm": 0.19777078926563263,
|
| 1019 |
+
"learning_rate": 0.0002307692307692308,
|
| 1020 |
+
"loss": 0.0683,
|
| 1021 |
+
"step": 34000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 7.69,
|
| 1025 |
+
"eval_loss": 0.05697755515575409,
|
| 1026 |
+
"eval_runtime": 27.2282,
|
| 1027 |
+
"eval_samples_per_second": 288.598,
|
| 1028 |
+
"eval_steps_per_second": 18.069,
|
| 1029 |
+
"step": 34000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 7.81,
|
| 1033 |
+
"grad_norm": 0.418797105550766,
|
| 1034 |
+
"learning_rate": 0.00021945701357466062,
|
| 1035 |
+
"loss": 0.0712,
|
| 1036 |
+
"step": 34500
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 7.81,
|
| 1040 |
+
"eval_loss": 0.05598929896950722,
|
| 1041 |
+
"eval_runtime": 27.2203,
|
| 1042 |
+
"eval_samples_per_second": 288.682,
|
| 1043 |
+
"eval_steps_per_second": 18.075,
|
| 1044 |
+
"step": 34500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 7.92,
|
| 1048 |
+
"grad_norm": 0.4459814727306366,
|
| 1049 |
+
"learning_rate": 0.0002081447963800905,
|
| 1050 |
+
"loss": 0.0672,
|
| 1051 |
+
"step": 35000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 7.92,
|
| 1055 |
+
"eval_loss": 0.05849257484078407,
|
| 1056 |
+
"eval_runtime": 27.2068,
|
| 1057 |
+
"eval_samples_per_second": 288.825,
|
| 1058 |
+
"eval_steps_per_second": 18.084,
|
| 1059 |
+
"step": 35000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 8.03,
|
| 1063 |
+
"grad_norm": 0.2313721477985382,
|
| 1064 |
+
"learning_rate": 0.00019683257918552037,
|
| 1065 |
+
"loss": 0.0675,
|
| 1066 |
+
"step": 35500
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 8.03,
|
| 1070 |
+
"eval_loss": 0.05674152076244354,
|
| 1071 |
+
"eval_runtime": 27.2055,
|
| 1072 |
+
"eval_samples_per_second": 288.839,
|
| 1073 |
+
"eval_steps_per_second": 18.085,
|
| 1074 |
+
"step": 35500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 8.14,
|
| 1078 |
+
"grad_norm": 0.2439548671245575,
|
| 1079 |
+
"learning_rate": 0.00018552036199095024,
|
| 1080 |
+
"loss": 0.0651,
|
| 1081 |
+
"step": 36000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 8.14,
|
| 1085 |
+
"eval_loss": 0.05658886954188347,
|
| 1086 |
+
"eval_runtime": 27.2233,
|
| 1087 |
+
"eval_samples_per_second": 288.65,
|
| 1088 |
+
"eval_steps_per_second": 18.073,
|
| 1089 |
+
"step": 36000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 8.26,
|
| 1093 |
+
"grad_norm": 0.3285837471485138,
|
| 1094 |
+
"learning_rate": 0.0001742081447963801,
|
| 1095 |
+
"loss": 0.0648,
|
| 1096 |
+
"step": 36500
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 8.26,
|
| 1100 |
+
"eval_loss": 0.05789176747202873,
|
| 1101 |
+
"eval_runtime": 27.2295,
|
| 1102 |
+
"eval_samples_per_second": 288.584,
|
| 1103 |
+
"eval_steps_per_second": 18.069,
|
| 1104 |
+
"step": 36500
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 8.37,
|
| 1108 |
+
"grad_norm": 0.3167458772659302,
|
| 1109 |
+
"learning_rate": 0.00016289592760180996,
|
| 1110 |
+
"loss": 0.067,
|
| 1111 |
+
"step": 37000
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 8.37,
|
| 1115 |
+
"eval_loss": 0.05568605288863182,
|
| 1116 |
+
"eval_runtime": 27.2118,
|
| 1117 |
+
"eval_samples_per_second": 288.772,
|
| 1118 |
+
"eval_steps_per_second": 18.08,
|
| 1119 |
+
"step": 37000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 8.48,
|
| 1123 |
+
"grad_norm": 0.1530727595090866,
|
| 1124 |
+
"learning_rate": 0.00015158371040723982,
|
| 1125 |
+
"loss": 0.0651,
|
| 1126 |
+
"step": 37500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 8.48,
|
| 1130 |
+
"eval_loss": 0.057902004569768906,
|
| 1131 |
+
"eval_runtime": 27.219,
|
| 1132 |
+
"eval_samples_per_second": 288.695,
|
| 1133 |
+
"eval_steps_per_second": 18.076,
|
| 1134 |
+
"step": 37500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 8.6,
|
| 1138 |
+
"grad_norm": 0.21044595539569855,
|
| 1139 |
+
"learning_rate": 0.00014027149321266968,
|
| 1140 |
+
"loss": 0.0666,
|
| 1141 |
+
"step": 38000
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 8.6,
|
| 1145 |
+
"eval_loss": 0.05458011105656624,
|
| 1146 |
+
"eval_runtime": 27.2446,
|
| 1147 |
+
"eval_samples_per_second": 288.424,
|
| 1148 |
+
"eval_steps_per_second": 18.059,
|
| 1149 |
+
"step": 38000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 8.71,
|
| 1153 |
+
"grad_norm": 0.23161017894744873,
|
| 1154 |
+
"learning_rate": 0.00012895927601809957,
|
| 1155 |
+
"loss": 0.0635,
|
| 1156 |
+
"step": 38500
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 8.71,
|
| 1160 |
+
"eval_loss": 0.056671272963285446,
|
| 1161 |
+
"eval_runtime": 27.2141,
|
| 1162 |
+
"eval_samples_per_second": 288.748,
|
| 1163 |
+
"eval_steps_per_second": 18.079,
|
| 1164 |
+
"step": 38500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 8.82,
|
| 1168 |
+
"grad_norm": 0.14228539168834686,
|
| 1169 |
+
"learning_rate": 0.00011764705882352942,
|
| 1170 |
+
"loss": 0.0622,
|
| 1171 |
+
"step": 39000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 8.82,
|
| 1175 |
+
"eval_loss": 0.05409713461995125,
|
| 1176 |
+
"eval_runtime": 27.229,
|
| 1177 |
+
"eval_samples_per_second": 288.59,
|
| 1178 |
+
"eval_steps_per_second": 18.069,
|
| 1179 |
+
"step": 39000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 8.94,
|
| 1183 |
+
"grad_norm": 0.19111554324626923,
|
| 1184 |
+
"learning_rate": 0.00010633484162895928,
|
| 1185 |
+
"loss": 0.0645,
|
| 1186 |
+
"step": 39500
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 8.94,
|
| 1190 |
+
"eval_loss": 0.05430610105395317,
|
| 1191 |
+
"eval_runtime": 27.2287,
|
| 1192 |
+
"eval_samples_per_second": 288.592,
|
| 1193 |
+
"eval_steps_per_second": 18.069,
|
| 1194 |
+
"step": 39500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 9.05,
|
| 1198 |
+
"grad_norm": 0.1508806049823761,
|
| 1199 |
+
"learning_rate": 9.502262443438914e-05,
|
| 1200 |
+
"loss": 0.0631,
|
| 1201 |
+
"step": 40000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 9.05,
|
| 1205 |
+
"eval_loss": 0.05481436848640442,
|
| 1206 |
+
"eval_runtime": 27.2111,
|
| 1207 |
+
"eval_samples_per_second": 288.78,
|
| 1208 |
+
"eval_steps_per_second": 18.081,
|
| 1209 |
+
"step": 40000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 9.16,
|
| 1213 |
+
"grad_norm": 0.26917019486427307,
|
| 1214 |
+
"learning_rate": 8.3710407239819e-05,
|
| 1215 |
+
"loss": 0.063,
|
| 1216 |
+
"step": 40500
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 9.16,
|
| 1220 |
+
"eval_loss": 0.056788042187690735,
|
| 1221 |
+
"eval_runtime": 27.2329,
|
| 1222 |
+
"eval_samples_per_second": 288.548,
|
| 1223 |
+
"eval_steps_per_second": 18.066,
|
| 1224 |
+
"step": 40500
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 9.28,
|
| 1228 |
+
"grad_norm": 0.26919251680374146,
|
| 1229 |
+
"learning_rate": 7.239819004524887e-05,
|
| 1230 |
+
"loss": 0.0614,
|
| 1231 |
+
"step": 41000
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 9.28,
|
| 1235 |
+
"eval_loss": 0.056851934641599655,
|
| 1236 |
+
"eval_runtime": 27.2442,
|
| 1237 |
+
"eval_samples_per_second": 288.428,
|
| 1238 |
+
"eval_steps_per_second": 18.059,
|
| 1239 |
+
"step": 41000
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 9.39,
|
| 1243 |
+
"grad_norm": 0.222616046667099,
|
| 1244 |
+
"learning_rate": 6.108597285067873e-05,
|
| 1245 |
+
"loss": 0.0588,
|
| 1246 |
+
"step": 41500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 9.39,
|
| 1250 |
+
"eval_loss": 0.05487231910228729,
|
| 1251 |
+
"eval_runtime": 27.23,
|
| 1252 |
+
"eval_samples_per_second": 288.579,
|
| 1253 |
+
"eval_steps_per_second": 18.068,
|
| 1254 |
+
"step": 41500
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 9.5,
|
| 1258 |
+
"grad_norm": 0.2073131799697876,
|
| 1259 |
+
"learning_rate": 4.9773755656108595e-05,
|
| 1260 |
+
"loss": 0.0616,
|
| 1261 |
+
"step": 42000
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 9.5,
|
| 1265 |
+
"eval_loss": 0.05528046563267708,
|
| 1266 |
+
"eval_runtime": 27.2327,
|
| 1267 |
+
"eval_samples_per_second": 288.55,
|
| 1268 |
+
"eval_steps_per_second": 18.067,
|
| 1269 |
+
"step": 42000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 9.62,
|
| 1273 |
+
"grad_norm": 0.19287574291229248,
|
| 1274 |
+
"learning_rate": 3.846153846153846e-05,
|
| 1275 |
+
"loss": 0.0609,
|
| 1276 |
+
"step": 42500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 9.62,
|
| 1280 |
+
"eval_loss": 0.055462516844272614,
|
| 1281 |
+
"eval_runtime": 27.2342,
|
| 1282 |
+
"eval_samples_per_second": 288.535,
|
| 1283 |
+
"eval_steps_per_second": 18.066,
|
| 1284 |
+
"step": 42500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 9.73,
|
| 1288 |
+
"grad_norm": 0.11690975725650787,
|
| 1289 |
+
"learning_rate": 2.7149321266968327e-05,
|
| 1290 |
+
"loss": 0.0612,
|
| 1291 |
+
"step": 43000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 9.73,
|
| 1295 |
+
"eval_loss": 0.055802907794713974,
|
| 1296 |
+
"eval_runtime": 27.263,
|
| 1297 |
+
"eval_samples_per_second": 288.23,
|
| 1298 |
+
"eval_steps_per_second": 18.046,
|
| 1299 |
+
"step": 43000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 9.84,
|
| 1303 |
+
"grad_norm": 0.19802606105804443,
|
| 1304 |
+
"learning_rate": 1.583710407239819e-05,
|
| 1305 |
+
"loss": 0.0588,
|
| 1306 |
+
"step": 43500
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 9.84,
|
| 1310 |
+
"eval_loss": 0.05586336553096771,
|
| 1311 |
+
"eval_runtime": 27.2516,
|
| 1312 |
+
"eval_samples_per_second": 288.35,
|
| 1313 |
+
"eval_steps_per_second": 18.054,
|
| 1314 |
+
"step": 43500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 9.95,
|
| 1318 |
+
"grad_norm": 0.29080289602279663,
|
| 1319 |
+
"learning_rate": 4.5248868778280546e-06,
|
| 1320 |
+
"loss": 0.0622,
|
| 1321 |
+
"step": 44000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 9.95,
|
| 1325 |
+
"eval_loss": 0.05555348098278046,
|
| 1326 |
+
"eval_runtime": 27.2559,
|
| 1327 |
+
"eval_samples_per_second": 288.305,
|
| 1328 |
+
"eval_steps_per_second": 18.051,
|
| 1329 |
+
"step": 44000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 10.0,
|
| 1333 |
+
"step": 44200,
|
| 1334 |
+
"total_flos": 8.389179359649792e+16,
|
| 1335 |
+
"train_loss": 0.09247852528257068,
|
| 1336 |
+
"train_runtime": 8790.0948,
|
| 1337 |
+
"train_samples_per_second": 80.453,
|
| 1338 |
+
"train_steps_per_second": 5.028
|
| 1339 |
+
}
|
| 1340 |
+
],
|
| 1341 |
+
"logging_steps": 500,
|
| 1342 |
+
"max_steps": 44200,
|
| 1343 |
+
"num_input_tokens_seen": 0,
|
| 1344 |
+
"num_train_epochs": 10,
|
| 1345 |
+
"save_steps": 500,
|
| 1346 |
+
"total_flos": 8.389179359649792e+16,
|
| 1347 |
+
"train_batch_size": 16,
|
| 1348 |
+
"trial_name": null,
|
| 1349 |
+
"trial_params": null
|
| 1350 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:234fbc7bf0d159d3d95c13453a8fd74105a86470e2dc26447e416696e864f884
|
| 3 |
+
size 5048
|