Checkpoint 91770
Browse files- README.md +180 -54
- trainer_state.json +1428 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,76 +1,202 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
base_model: google/flan-t5-xl
|
| 7 |
-
model-index:
|
| 8 |
-
- name: flan-t5-xl-spider-dict_qpl-20240304-v3
|
| 9 |
-
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
| 13 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.0957
|
| 20 |
-
- Execution Accuracy: 69.3424
|
| 21 |
|
| 22 |
-
## Model description
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
-
## Training and evaluation data
|
| 31 |
|
| 32 |
-
More information needed
|
| 33 |
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
-
###
|
| 37 |
|
| 38 |
-
|
| 39 |
-
- learning_rate: 0.0002
|
| 40 |
-
- train_batch_size: 1
|
| 41 |
-
- eval_batch_size: 8
|
| 42 |
-
- seed: 1
|
| 43 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
-
- lr_scheduler_type: linear
|
| 45 |
-
- num_epochs: 17
|
| 46 |
|
| 47 |
-
|
|
|
|
|
|
|
| 48 |
|
| 49 |
-
|
| 50 |
-
|:-------------:|:-----:|:------:|:------------------:|:---------------:|
|
| 51 |
-
| 0.068 | 1.0 | 6555 | 39.4584 | 0.0767 |
|
| 52 |
-
| 0.0432 | 2.0 | 13110 | 52.9981 | 0.0608 |
|
| 53 |
-
| 0.033 | 3.0 | 19665 | 60.3482 | 0.0612 |
|
| 54 |
-
| 0.0297 | 4.0 | 26220 | 62.8627 | 0.0589 |
|
| 55 |
-
| 0.0213 | 5.0 | 32775 | 64.1199 | 0.0605 |
|
| 56 |
-
| 0.0188 | 6.0 | 39330 | 64.3133 | 0.0619 |
|
| 57 |
-
| 0.0166 | 7.0 | 45885 | 66.441 | 0.0611 |
|
| 58 |
-
| 0.0162 | 8.0 | 52440 | 65.8607 | 0.0669 |
|
| 59 |
-
| 0.0109 | 9.0 | 58995 | 68.9555 | 0.0666 |
|
| 60 |
-
| 0.0101 | 10.0 | 65550 | 68.1818 | 0.0736 |
|
| 61 |
-
| 0.0085 | 11.0 | 72105 | 68.0851 | 0.0764 |
|
| 62 |
-
| 0.0069 | 12.0 | 78660 | 69.0522 | 0.0801 |
|
| 63 |
-
| 0.0068 | 13.0 | 85215 | 69.2456 | 0.0884 |
|
| 64 |
-
| 0.0052 | 14.0 | 91770 | 70.793 | 0.0883 |
|
| 65 |
-
| 0.0039 | 15.0 | 98325 | 70.5029 | 0.0936 |
|
| 66 |
-
| 0.005 | 16.0 | 104880 | 67.9884 | 0.0904 |
|
| 67 |
-
| 0.0042 | 17.0 | 111435 | 0.0957 | 69.3424 |
|
| 68 |
|
|
|
|
| 69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
### Framework versions
|
| 71 |
|
| 72 |
-
- PEFT 0.9.0
|
| 73 |
-
- Transformers 4.38.2
|
| 74 |
-
- Pytorch 2.1.0+cu118
|
| 75 |
-
- Datasets 2.18.0
|
| 76 |
-
- Tokenizers 0.15.2
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: peft
|
|
|
|
|
|
|
| 3 |
base_model: google/flan-t5-xl
|
|
|
|
|
|
|
|
|
|
| 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 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.9.0
|
|
|
|
|
|
|
|
|
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 70.793,
|
| 3 |
+
"best_model_checkpoint": "flan-t5-xl-spider-dict_qpl-20240304-v3/checkpoint-91770",
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 91770,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 2.1395843029022217,
|
| 14 |
+
"learning_rate": 0.0001989829646580219,
|
| 15 |
+
"loss": 1.1111,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15,
|
| 20 |
+
"grad_norm": 1.5051442384719849,
|
| 21 |
+
"learning_rate": 0.00019796592931604375,
|
| 22 |
+
"loss": 0.2196,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.23,
|
| 27 |
+
"grad_norm": 1.0700268745422363,
|
| 28 |
+
"learning_rate": 0.00019694889397406563,
|
| 29 |
+
"loss": 0.1653,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.31,
|
| 34 |
+
"grad_norm": 0.6627328395843506,
|
| 35 |
+
"learning_rate": 0.00019593185863208746,
|
| 36 |
+
"loss": 0.1313,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.38,
|
| 41 |
+
"grad_norm": 0.8090806603431702,
|
| 42 |
+
"learning_rate": 0.00019491482329010934,
|
| 43 |
+
"loss": 0.1141,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46,
|
| 48 |
+
"grad_norm": 0.5775860548019409,
|
| 49 |
+
"learning_rate": 0.0001938977879481312,
|
| 50 |
+
"loss": 0.1071,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.53,
|
| 55 |
+
"grad_norm": 0.548545777797699,
|
| 56 |
+
"learning_rate": 0.00019288075260615308,
|
| 57 |
+
"loss": 0.0963,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.61,
|
| 62 |
+
"grad_norm": 0.8567075729370117,
|
| 63 |
+
"learning_rate": 0.00019186371726417494,
|
| 64 |
+
"loss": 0.0852,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.69,
|
| 69 |
+
"grad_norm": 0.2921431064605713,
|
| 70 |
+
"learning_rate": 0.00019084668192219682,
|
| 71 |
+
"loss": 0.0787,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.76,
|
| 76 |
+
"grad_norm": 0.1600842922925949,
|
| 77 |
+
"learning_rate": 0.00018982964658021868,
|
| 78 |
+
"loss": 0.0789,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.84,
|
| 83 |
+
"grad_norm": 0.48446208238601685,
|
| 84 |
+
"learning_rate": 0.00018881261123824053,
|
| 85 |
+
"loss": 0.0732,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.92,
|
| 90 |
+
"grad_norm": 0.5679713487625122,
|
| 91 |
+
"learning_rate": 0.0001877955758962624,
|
| 92 |
+
"loss": 0.0699,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.99,
|
| 97 |
+
"grad_norm": 1.3154789209365845,
|
| 98 |
+
"learning_rate": 0.00018677854055428427,
|
| 99 |
+
"loss": 0.068,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0,
|
| 104 |
+
"eval_execution_accuracy": 39.4584,
|
| 105 |
+
"eval_loss": 0.0767175704240799,
|
| 106 |
+
"eval_runtime": 1448.6397,
|
| 107 |
+
"eval_samples_per_second": 0.714,
|
| 108 |
+
"eval_steps_per_second": 0.09,
|
| 109 |
+
"step": 6555
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.07,
|
| 113 |
+
"grad_norm": 0.3169132173061371,
|
| 114 |
+
"learning_rate": 0.00018576150521230613,
|
| 115 |
+
"loss": 0.0608,
|
| 116 |
+
"step": 7000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.14,
|
| 120 |
+
"grad_norm": 0.5822262763977051,
|
| 121 |
+
"learning_rate": 0.000184744469870328,
|
| 122 |
+
"loss": 0.0594,
|
| 123 |
+
"step": 7500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.22,
|
| 127 |
+
"grad_norm": 0.39004069566726685,
|
| 128 |
+
"learning_rate": 0.00018372743452834986,
|
| 129 |
+
"loss": 0.0601,
|
| 130 |
+
"step": 8000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.3,
|
| 134 |
+
"grad_norm": 0.48953133821487427,
|
| 135 |
+
"learning_rate": 0.00018271039918637175,
|
| 136 |
+
"loss": 0.0563,
|
| 137 |
+
"step": 8500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.37,
|
| 141 |
+
"grad_norm": 0.24563811719417572,
|
| 142 |
+
"learning_rate": 0.0001816933638443936,
|
| 143 |
+
"loss": 0.0547,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.45,
|
| 148 |
+
"grad_norm": 0.028272481635212898,
|
| 149 |
+
"learning_rate": 0.00018067632850241546,
|
| 150 |
+
"loss": 0.0513,
|
| 151 |
+
"step": 9500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.53,
|
| 155 |
+
"grad_norm": 0.5085881948471069,
|
| 156 |
+
"learning_rate": 0.00017965929316043731,
|
| 157 |
+
"loss": 0.054,
|
| 158 |
+
"step": 10000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.6,
|
| 162 |
+
"grad_norm": 0.3579294681549072,
|
| 163 |
+
"learning_rate": 0.0001786422578184592,
|
| 164 |
+
"loss": 0.0523,
|
| 165 |
+
"step": 10500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.68,
|
| 169 |
+
"grad_norm": 0.717029869556427,
|
| 170 |
+
"learning_rate": 0.00017762522247648105,
|
| 171 |
+
"loss": 0.048,
|
| 172 |
+
"step": 11000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.75,
|
| 176 |
+
"grad_norm": 0.5166067481040955,
|
| 177 |
+
"learning_rate": 0.00017660818713450294,
|
| 178 |
+
"loss": 0.0494,
|
| 179 |
+
"step": 11500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.83,
|
| 183 |
+
"grad_norm": 0.7487884759902954,
|
| 184 |
+
"learning_rate": 0.0001755911517925248,
|
| 185 |
+
"loss": 0.0444,
|
| 186 |
+
"step": 12000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.91,
|
| 190 |
+
"grad_norm": 0.24778613448143005,
|
| 191 |
+
"learning_rate": 0.00017457411645054667,
|
| 192 |
+
"loss": 0.0427,
|
| 193 |
+
"step": 12500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.98,
|
| 197 |
+
"grad_norm": 0.3205878436565399,
|
| 198 |
+
"learning_rate": 0.00017355708110856853,
|
| 199 |
+
"loss": 0.0432,
|
| 200 |
+
"step": 13000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.0,
|
| 204 |
+
"eval_execution_accuracy": 52.9981,
|
| 205 |
+
"eval_loss": 0.06084170565009117,
|
| 206 |
+
"eval_runtime": 1830.3328,
|
| 207 |
+
"eval_samples_per_second": 0.565,
|
| 208 |
+
"eval_steps_per_second": 0.071,
|
| 209 |
+
"step": 13110
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.06,
|
| 213 |
+
"grad_norm": 0.424517959356308,
|
| 214 |
+
"learning_rate": 0.00017254004576659039,
|
| 215 |
+
"loss": 0.0422,
|
| 216 |
+
"step": 13500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.14,
|
| 220 |
+
"grad_norm": 0.5932648777961731,
|
| 221 |
+
"learning_rate": 0.00017152301042461227,
|
| 222 |
+
"loss": 0.0447,
|
| 223 |
+
"step": 14000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.21,
|
| 227 |
+
"grad_norm": 0.1377120316028595,
|
| 228 |
+
"learning_rate": 0.00017050597508263412,
|
| 229 |
+
"loss": 0.0399,
|
| 230 |
+
"step": 14500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.29,
|
| 234 |
+
"grad_norm": 0.257429301738739,
|
| 235 |
+
"learning_rate": 0.000169488939740656,
|
| 236 |
+
"loss": 0.0361,
|
| 237 |
+
"step": 15000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.36,
|
| 241 |
+
"grad_norm": 0.18395432829856873,
|
| 242 |
+
"learning_rate": 0.00016847190439867786,
|
| 243 |
+
"loss": 0.038,
|
| 244 |
+
"step": 15500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.44,
|
| 248 |
+
"grad_norm": 0.526056706905365,
|
| 249 |
+
"learning_rate": 0.00016745486905669975,
|
| 250 |
+
"loss": 0.0343,
|
| 251 |
+
"step": 16000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.52,
|
| 255 |
+
"grad_norm": 0.17391307651996613,
|
| 256 |
+
"learning_rate": 0.0001664378337147216,
|
| 257 |
+
"loss": 0.0357,
|
| 258 |
+
"step": 16500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.59,
|
| 262 |
+
"grad_norm": 0.2732052505016327,
|
| 263 |
+
"learning_rate": 0.00016542079837274346,
|
| 264 |
+
"loss": 0.0366,
|
| 265 |
+
"step": 17000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.67,
|
| 269 |
+
"grad_norm": 0.3006477355957031,
|
| 270 |
+
"learning_rate": 0.0001644037630307653,
|
| 271 |
+
"loss": 0.033,
|
| 272 |
+
"step": 17500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.75,
|
| 276 |
+
"grad_norm": 0.011468607001006603,
|
| 277 |
+
"learning_rate": 0.0001633867276887872,
|
| 278 |
+
"loss": 0.0335,
|
| 279 |
+
"step": 18000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.82,
|
| 283 |
+
"grad_norm": 0.5990091562271118,
|
| 284 |
+
"learning_rate": 0.00016236969234680905,
|
| 285 |
+
"loss": 0.0355,
|
| 286 |
+
"step": 18500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.9,
|
| 290 |
+
"grad_norm": 0.29567310214042664,
|
| 291 |
+
"learning_rate": 0.00016135265700483093,
|
| 292 |
+
"loss": 0.0337,
|
| 293 |
+
"step": 19000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.97,
|
| 297 |
+
"grad_norm": 0.006056224461644888,
|
| 298 |
+
"learning_rate": 0.0001603356216628528,
|
| 299 |
+
"loss": 0.033,
|
| 300 |
+
"step": 19500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.0,
|
| 304 |
+
"eval_execution_accuracy": 60.3482,
|
| 305 |
+
"eval_loss": 0.06122712045907974,
|
| 306 |
+
"eval_runtime": 1764.8897,
|
| 307 |
+
"eval_samples_per_second": 0.586,
|
| 308 |
+
"eval_steps_per_second": 0.074,
|
| 309 |
+
"step": 19665
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.05,
|
| 313 |
+
"grad_norm": 0.30340930819511414,
|
| 314 |
+
"learning_rate": 0.00015931858632087467,
|
| 315 |
+
"loss": 0.0297,
|
| 316 |
+
"step": 20000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.13,
|
| 320 |
+
"grad_norm": 0.017457757145166397,
|
| 321 |
+
"learning_rate": 0.00015830155097889653,
|
| 322 |
+
"loss": 0.0305,
|
| 323 |
+
"step": 20500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.2,
|
| 327 |
+
"grad_norm": 0.254963755607605,
|
| 328 |
+
"learning_rate": 0.00015728451563691838,
|
| 329 |
+
"loss": 0.028,
|
| 330 |
+
"step": 21000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.28,
|
| 334 |
+
"grad_norm": 0.8444741368293762,
|
| 335 |
+
"learning_rate": 0.00015626748029494024,
|
| 336 |
+
"loss": 0.027,
|
| 337 |
+
"step": 21500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.36,
|
| 341 |
+
"grad_norm": 0.47470298409461975,
|
| 342 |
+
"learning_rate": 0.00015525044495296212,
|
| 343 |
+
"loss": 0.0297,
|
| 344 |
+
"step": 22000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.43,
|
| 348 |
+
"grad_norm": 0.08465476334095001,
|
| 349 |
+
"learning_rate": 0.00015423340961098398,
|
| 350 |
+
"loss": 0.0288,
|
| 351 |
+
"step": 22500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.51,
|
| 355 |
+
"grad_norm": 0.32479336857795715,
|
| 356 |
+
"learning_rate": 0.00015321637426900586,
|
| 357 |
+
"loss": 0.0302,
|
| 358 |
+
"step": 23000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.59,
|
| 362 |
+
"grad_norm": 3.906116008758545,
|
| 363 |
+
"learning_rate": 0.00015219933892702772,
|
| 364 |
+
"loss": 0.0297,
|
| 365 |
+
"step": 23500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.66,
|
| 369 |
+
"grad_norm": 0.821506917476654,
|
| 370 |
+
"learning_rate": 0.0001511823035850496,
|
| 371 |
+
"loss": 0.0266,
|
| 372 |
+
"step": 24000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.74,
|
| 376 |
+
"grad_norm": 0.36568546295166016,
|
| 377 |
+
"learning_rate": 0.00015016526824307146,
|
| 378 |
+
"loss": 0.0296,
|
| 379 |
+
"step": 24500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.81,
|
| 383 |
+
"grad_norm": 0.6190164089202881,
|
| 384 |
+
"learning_rate": 0.0001491482329010933,
|
| 385 |
+
"loss": 0.0287,
|
| 386 |
+
"step": 25000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.89,
|
| 390 |
+
"grad_norm": 0.2852056920528412,
|
| 391 |
+
"learning_rate": 0.00014813119755911517,
|
| 392 |
+
"loss": 0.0271,
|
| 393 |
+
"step": 25500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.97,
|
| 397 |
+
"grad_norm": 0.10050356388092041,
|
| 398 |
+
"learning_rate": 0.00014711416221713705,
|
| 399 |
+
"loss": 0.0297,
|
| 400 |
+
"step": 26000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.0,
|
| 404 |
+
"eval_execution_accuracy": 62.8627,
|
| 405 |
+
"eval_loss": 0.0589316301047802,
|
| 406 |
+
"eval_runtime": 1802.5956,
|
| 407 |
+
"eval_samples_per_second": 0.574,
|
| 408 |
+
"eval_steps_per_second": 0.072,
|
| 409 |
+
"step": 26220
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.04,
|
| 413 |
+
"grad_norm": 0.4248579740524292,
|
| 414 |
+
"learning_rate": 0.00014609712687515893,
|
| 415 |
+
"loss": 0.027,
|
| 416 |
+
"step": 26500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.12,
|
| 420 |
+
"grad_norm": 0.5822145342826843,
|
| 421 |
+
"learning_rate": 0.0001450800915331808,
|
| 422 |
+
"loss": 0.0234,
|
| 423 |
+
"step": 27000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.2,
|
| 427 |
+
"grad_norm": 0.028582902625203133,
|
| 428 |
+
"learning_rate": 0.00014406305619120267,
|
| 429 |
+
"loss": 0.0256,
|
| 430 |
+
"step": 27500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 4.27,
|
| 434 |
+
"grad_norm": 0.026179086416959763,
|
| 435 |
+
"learning_rate": 0.00014304602084922453,
|
| 436 |
+
"loss": 0.0248,
|
| 437 |
+
"step": 28000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.35,
|
| 441 |
+
"grad_norm": 0.24167686700820923,
|
| 442 |
+
"learning_rate": 0.00014202898550724638,
|
| 443 |
+
"loss": 0.024,
|
| 444 |
+
"step": 28500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.42,
|
| 448 |
+
"grad_norm": 0.21196796000003815,
|
| 449 |
+
"learning_rate": 0.00014101195016526824,
|
| 450 |
+
"loss": 0.0232,
|
| 451 |
+
"step": 29000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 4.5,
|
| 455 |
+
"grad_norm": 0.1384715437889099,
|
| 456 |
+
"learning_rate": 0.00013999491482329012,
|
| 457 |
+
"loss": 0.0231,
|
| 458 |
+
"step": 29500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.58,
|
| 462 |
+
"grad_norm": 0.25323405861854553,
|
| 463 |
+
"learning_rate": 0.00013897787948131198,
|
| 464 |
+
"loss": 0.0227,
|
| 465 |
+
"step": 30000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.65,
|
| 469 |
+
"grad_norm": 0.17340293526649475,
|
| 470 |
+
"learning_rate": 0.00013796084413933386,
|
| 471 |
+
"loss": 0.0232,
|
| 472 |
+
"step": 30500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 4.73,
|
| 476 |
+
"grad_norm": 0.01007129717618227,
|
| 477 |
+
"learning_rate": 0.00013694380879735572,
|
| 478 |
+
"loss": 0.0212,
|
| 479 |
+
"step": 31000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.81,
|
| 483 |
+
"grad_norm": 0.5236365795135498,
|
| 484 |
+
"learning_rate": 0.0001359267734553776,
|
| 485 |
+
"loss": 0.0233,
|
| 486 |
+
"step": 31500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 4.88,
|
| 490 |
+
"grad_norm": 0.49340179562568665,
|
| 491 |
+
"learning_rate": 0.00013490973811339945,
|
| 492 |
+
"loss": 0.0258,
|
| 493 |
+
"step": 32000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 4.96,
|
| 497 |
+
"grad_norm": 0.7839340567588806,
|
| 498 |
+
"learning_rate": 0.0001338927027714213,
|
| 499 |
+
"loss": 0.0213,
|
| 500 |
+
"step": 32500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.0,
|
| 504 |
+
"eval_execution_accuracy": 64.1199,
|
| 505 |
+
"eval_loss": 0.06054983288049698,
|
| 506 |
+
"eval_runtime": 1797.3766,
|
| 507 |
+
"eval_samples_per_second": 0.575,
|
| 508 |
+
"eval_steps_per_second": 0.072,
|
| 509 |
+
"step": 32775
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.03,
|
| 513 |
+
"grad_norm": 0.47601643204689026,
|
| 514 |
+
"learning_rate": 0.00013287566742944317,
|
| 515 |
+
"loss": 0.0198,
|
| 516 |
+
"step": 33000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 5.11,
|
| 520 |
+
"grad_norm": 0.3969705402851105,
|
| 521 |
+
"learning_rate": 0.00013185863208746505,
|
| 522 |
+
"loss": 0.0201,
|
| 523 |
+
"step": 33500
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 5.19,
|
| 527 |
+
"grad_norm": 0.06148134917020798,
|
| 528 |
+
"learning_rate": 0.0001308415967454869,
|
| 529 |
+
"loss": 0.021,
|
| 530 |
+
"step": 34000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 5.26,
|
| 534 |
+
"grad_norm": 0.0021157702431082726,
|
| 535 |
+
"learning_rate": 0.0001298245614035088,
|
| 536 |
+
"loss": 0.0189,
|
| 537 |
+
"step": 34500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 5.34,
|
| 541 |
+
"grad_norm": 0.09957286715507507,
|
| 542 |
+
"learning_rate": 0.00012880752606153064,
|
| 543 |
+
"loss": 0.0214,
|
| 544 |
+
"step": 35000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 5.42,
|
| 548 |
+
"grad_norm": 0.0950658768415451,
|
| 549 |
+
"learning_rate": 0.00012779049071955253,
|
| 550 |
+
"loss": 0.0206,
|
| 551 |
+
"step": 35500
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 5.49,
|
| 555 |
+
"grad_norm": 0.5534018874168396,
|
| 556 |
+
"learning_rate": 0.00012677345537757438,
|
| 557 |
+
"loss": 0.0182,
|
| 558 |
+
"step": 36000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 5.57,
|
| 562 |
+
"grad_norm": 0.21119213104248047,
|
| 563 |
+
"learning_rate": 0.00012575642003559624,
|
| 564 |
+
"loss": 0.0195,
|
| 565 |
+
"step": 36500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 5.64,
|
| 569 |
+
"grad_norm": 0.10089027881622314,
|
| 570 |
+
"learning_rate": 0.0001247393846936181,
|
| 571 |
+
"loss": 0.0196,
|
| 572 |
+
"step": 37000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 5.72,
|
| 576 |
+
"grad_norm": 0.36528435349464417,
|
| 577 |
+
"learning_rate": 0.00012372234935163998,
|
| 578 |
+
"loss": 0.0187,
|
| 579 |
+
"step": 37500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 5.8,
|
| 583 |
+
"grad_norm": 0.13980288803577423,
|
| 584 |
+
"learning_rate": 0.00012270531400966183,
|
| 585 |
+
"loss": 0.0177,
|
| 586 |
+
"step": 38000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 5.87,
|
| 590 |
+
"grad_norm": 0.03852877765893936,
|
| 591 |
+
"learning_rate": 0.00012168827866768371,
|
| 592 |
+
"loss": 0.0219,
|
| 593 |
+
"step": 38500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.95,
|
| 597 |
+
"grad_norm": 0.23849190771579742,
|
| 598 |
+
"learning_rate": 0.00012067124332570557,
|
| 599 |
+
"loss": 0.0188,
|
| 600 |
+
"step": 39000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 6.0,
|
| 604 |
+
"eval_execution_accuracy": 64.3133,
|
| 605 |
+
"eval_loss": 0.061897873878479004,
|
| 606 |
+
"eval_runtime": 1866.1394,
|
| 607 |
+
"eval_samples_per_second": 0.554,
|
| 608 |
+
"eval_steps_per_second": 0.07,
|
| 609 |
+
"step": 39330
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 6.03,
|
| 613 |
+
"grad_norm": 0.6830750703811646,
|
| 614 |
+
"learning_rate": 0.00011965420798372744,
|
| 615 |
+
"loss": 0.0175,
|
| 616 |
+
"step": 39500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 6.1,
|
| 620 |
+
"grad_norm": 0.013556591235101223,
|
| 621 |
+
"learning_rate": 0.00011863717264174932,
|
| 622 |
+
"loss": 0.0166,
|
| 623 |
+
"step": 40000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 6.18,
|
| 627 |
+
"grad_norm": 0.06067229434847832,
|
| 628 |
+
"learning_rate": 0.00011762013729977118,
|
| 629 |
+
"loss": 0.0167,
|
| 630 |
+
"step": 40500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 6.25,
|
| 634 |
+
"grad_norm": 0.815282940864563,
|
| 635 |
+
"learning_rate": 0.00011660310195779305,
|
| 636 |
+
"loss": 0.0179,
|
| 637 |
+
"step": 41000
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 6.33,
|
| 641 |
+
"grad_norm": 0.09995106607675552,
|
| 642 |
+
"learning_rate": 0.0001155860666158149,
|
| 643 |
+
"loss": 0.0164,
|
| 644 |
+
"step": 41500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.41,
|
| 648 |
+
"grad_norm": 0.07753593474626541,
|
| 649 |
+
"learning_rate": 0.00011456903127383679,
|
| 650 |
+
"loss": 0.0162,
|
| 651 |
+
"step": 42000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 6.48,
|
| 655 |
+
"grad_norm": 0.16108450293540955,
|
| 656 |
+
"learning_rate": 0.00011355199593185864,
|
| 657 |
+
"loss": 0.0176,
|
| 658 |
+
"step": 42500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 6.56,
|
| 662 |
+
"grad_norm": 0.1027306616306305,
|
| 663 |
+
"learning_rate": 0.00011253496058988051,
|
| 664 |
+
"loss": 0.0176,
|
| 665 |
+
"step": 43000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 6.64,
|
| 669 |
+
"grad_norm": 0.527164876461029,
|
| 670 |
+
"learning_rate": 0.00011151792524790237,
|
| 671 |
+
"loss": 0.0148,
|
| 672 |
+
"step": 43500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 6.71,
|
| 676 |
+
"grad_norm": 0.12876121699810028,
|
| 677 |
+
"learning_rate": 0.00011050088990592425,
|
| 678 |
+
"loss": 0.016,
|
| 679 |
+
"step": 44000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 6.79,
|
| 683 |
+
"grad_norm": 0.07147472351789474,
|
| 684 |
+
"learning_rate": 0.00010948385456394609,
|
| 685 |
+
"loss": 0.0166,
|
| 686 |
+
"step": 44500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 6.86,
|
| 690 |
+
"grad_norm": 0.11269113421440125,
|
| 691 |
+
"learning_rate": 0.00010846681922196797,
|
| 692 |
+
"loss": 0.0159,
|
| 693 |
+
"step": 45000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.94,
|
| 697 |
+
"grad_norm": 0.0018060138681903481,
|
| 698 |
+
"learning_rate": 0.00010744978387998983,
|
| 699 |
+
"loss": 0.0166,
|
| 700 |
+
"step": 45500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 7.0,
|
| 704 |
+
"eval_execution_accuracy": 66.441,
|
| 705 |
+
"eval_loss": 0.06106872484087944,
|
| 706 |
+
"eval_runtime": 1845.4627,
|
| 707 |
+
"eval_samples_per_second": 0.56,
|
| 708 |
+
"eval_steps_per_second": 0.07,
|
| 709 |
+
"step": 45885
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 7.02,
|
| 713 |
+
"grad_norm": 0.010804968886077404,
|
| 714 |
+
"learning_rate": 0.00010643274853801171,
|
| 715 |
+
"loss": 0.0148,
|
| 716 |
+
"step": 46000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 7.09,
|
| 720 |
+
"grad_norm": 0.014622188173234463,
|
| 721 |
+
"learning_rate": 0.00010541571319603355,
|
| 722 |
+
"loss": 0.0147,
|
| 723 |
+
"step": 46500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 7.17,
|
| 727 |
+
"grad_norm": 0.13804876804351807,
|
| 728 |
+
"learning_rate": 0.00010439867785405544,
|
| 729 |
+
"loss": 0.015,
|
| 730 |
+
"step": 47000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 7.25,
|
| 734 |
+
"grad_norm": 0.0409139022231102,
|
| 735 |
+
"learning_rate": 0.00010338164251207729,
|
| 736 |
+
"loss": 0.0126,
|
| 737 |
+
"step": 47500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 7.32,
|
| 741 |
+
"grad_norm": 0.11225342750549316,
|
| 742 |
+
"learning_rate": 0.00010236460717009918,
|
| 743 |
+
"loss": 0.014,
|
| 744 |
+
"step": 48000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 7.4,
|
| 748 |
+
"grad_norm": 0.021166274324059486,
|
| 749 |
+
"learning_rate": 0.00010134757182812102,
|
| 750 |
+
"loss": 0.0146,
|
| 751 |
+
"step": 48500
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 7.48,
|
| 755 |
+
"grad_norm": 0.2523152828216553,
|
| 756 |
+
"learning_rate": 0.0001003305364861429,
|
| 757 |
+
"loss": 0.014,
|
| 758 |
+
"step": 49000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 7.55,
|
| 762 |
+
"grad_norm": 0.014010763727128506,
|
| 763 |
+
"learning_rate": 9.931350114416477e-05,
|
| 764 |
+
"loss": 0.0142,
|
| 765 |
+
"step": 49500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 7.63,
|
| 769 |
+
"grad_norm": 0.3102033734321594,
|
| 770 |
+
"learning_rate": 9.829646580218663e-05,
|
| 771 |
+
"loss": 0.0131,
|
| 772 |
+
"step": 50000
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 7.7,
|
| 776 |
+
"grad_norm": 0.00048806238919496536,
|
| 777 |
+
"learning_rate": 9.72794304602085e-05,
|
| 778 |
+
"loss": 0.014,
|
| 779 |
+
"step": 50500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 7.78,
|
| 783 |
+
"grad_norm": 1.1056194305419922,
|
| 784 |
+
"learning_rate": 9.626239511823036e-05,
|
| 785 |
+
"loss": 0.0122,
|
| 786 |
+
"step": 51000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 7.86,
|
| 790 |
+
"grad_norm": 0.07580041885375977,
|
| 791 |
+
"learning_rate": 9.524535977625223e-05,
|
| 792 |
+
"loss": 0.0118,
|
| 793 |
+
"step": 51500
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 7.93,
|
| 797 |
+
"grad_norm": 0.06150615215301514,
|
| 798 |
+
"learning_rate": 9.422832443427409e-05,
|
| 799 |
+
"loss": 0.0162,
|
| 800 |
+
"step": 52000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 8.0,
|
| 804 |
+
"eval_execution_accuracy": 65.8607,
|
| 805 |
+
"eval_loss": 0.0669085830450058,
|
| 806 |
+
"eval_runtime": 1870.6797,
|
| 807 |
+
"eval_samples_per_second": 0.553,
|
| 808 |
+
"eval_steps_per_second": 0.069,
|
| 809 |
+
"step": 52440
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 8.01,
|
| 813 |
+
"grad_norm": 0.3560275733470917,
|
| 814 |
+
"learning_rate": 9.321128909229596e-05,
|
| 815 |
+
"loss": 0.0137,
|
| 816 |
+
"step": 52500
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 8.09,
|
| 820 |
+
"grad_norm": 0.0782669186592102,
|
| 821 |
+
"learning_rate": 9.219425375031783e-05,
|
| 822 |
+
"loss": 0.0114,
|
| 823 |
+
"step": 53000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 8.16,
|
| 827 |
+
"grad_norm": 0.008491788990795612,
|
| 828 |
+
"learning_rate": 9.11772184083397e-05,
|
| 829 |
+
"loss": 0.0124,
|
| 830 |
+
"step": 53500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 8.24,
|
| 834 |
+
"grad_norm": 0.1824067234992981,
|
| 835 |
+
"learning_rate": 9.016018306636155e-05,
|
| 836 |
+
"loss": 0.0122,
|
| 837 |
+
"step": 54000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 8.31,
|
| 841 |
+
"grad_norm": 0.1216733381152153,
|
| 842 |
+
"learning_rate": 8.914314772438342e-05,
|
| 843 |
+
"loss": 0.0124,
|
| 844 |
+
"step": 54500
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 8.39,
|
| 848 |
+
"grad_norm": 0.4382436275482178,
|
| 849 |
+
"learning_rate": 8.812611238240529e-05,
|
| 850 |
+
"loss": 0.0115,
|
| 851 |
+
"step": 55000
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 8.47,
|
| 855 |
+
"grad_norm": 0.35070136189460754,
|
| 856 |
+
"learning_rate": 8.710907704042716e-05,
|
| 857 |
+
"loss": 0.0111,
|
| 858 |
+
"step": 55500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 8.54,
|
| 862 |
+
"grad_norm": 0.03633696213364601,
|
| 863 |
+
"learning_rate": 8.609204169844902e-05,
|
| 864 |
+
"loss": 0.0111,
|
| 865 |
+
"step": 56000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 8.62,
|
| 869 |
+
"grad_norm": 0.05109800025820732,
|
| 870 |
+
"learning_rate": 8.507500635647089e-05,
|
| 871 |
+
"loss": 0.0129,
|
| 872 |
+
"step": 56500
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.7,
|
| 876 |
+
"grad_norm": 0.02394057996571064,
|
| 877 |
+
"learning_rate": 8.405797101449276e-05,
|
| 878 |
+
"loss": 0.012,
|
| 879 |
+
"step": 57000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 8.77,
|
| 883 |
+
"grad_norm": 0.5572072863578796,
|
| 884 |
+
"learning_rate": 8.304093567251462e-05,
|
| 885 |
+
"loss": 0.0121,
|
| 886 |
+
"step": 57500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 8.85,
|
| 890 |
+
"grad_norm": 0.10420696437358856,
|
| 891 |
+
"learning_rate": 8.202390033053648e-05,
|
| 892 |
+
"loss": 0.0113,
|
| 893 |
+
"step": 58000
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 8.92,
|
| 897 |
+
"grad_norm": 0.14662973582744598,
|
| 898 |
+
"learning_rate": 8.100686498855835e-05,
|
| 899 |
+
"loss": 0.0109,
|
| 900 |
+
"step": 58500
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 9.0,
|
| 904 |
+
"eval_execution_accuracy": 68.9555,
|
| 905 |
+
"eval_loss": 0.06655910611152649,
|
| 906 |
+
"eval_runtime": 1868.1909,
|
| 907 |
+
"eval_samples_per_second": 0.553,
|
| 908 |
+
"eval_steps_per_second": 0.07,
|
| 909 |
+
"step": 58995
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 9.0,
|
| 913 |
+
"grad_norm": 0.44341155886650085,
|
| 914 |
+
"learning_rate": 7.998982964658023e-05,
|
| 915 |
+
"loss": 0.0117,
|
| 916 |
+
"step": 59000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 9.08,
|
| 920 |
+
"grad_norm": 0.07052640616893768,
|
| 921 |
+
"learning_rate": 7.897279430460209e-05,
|
| 922 |
+
"loss": 0.0109,
|
| 923 |
+
"step": 59500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 9.15,
|
| 927 |
+
"grad_norm": 0.22480645775794983,
|
| 928 |
+
"learning_rate": 7.795575896262396e-05,
|
| 929 |
+
"loss": 0.0095,
|
| 930 |
+
"step": 60000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 9.23,
|
| 934 |
+
"grad_norm": 0.3521146774291992,
|
| 935 |
+
"learning_rate": 7.693872362064583e-05,
|
| 936 |
+
"loss": 0.0105,
|
| 937 |
+
"step": 60500
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 9.31,
|
| 941 |
+
"grad_norm": 0.17205676436424255,
|
| 942 |
+
"learning_rate": 7.59216882786677e-05,
|
| 943 |
+
"loss": 0.0099,
|
| 944 |
+
"step": 61000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 9.38,
|
| 948 |
+
"grad_norm": 0.018218664452433586,
|
| 949 |
+
"learning_rate": 7.490465293668955e-05,
|
| 950 |
+
"loss": 0.01,
|
| 951 |
+
"step": 61500
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 9.46,
|
| 955 |
+
"grad_norm": 0.0007620451506227255,
|
| 956 |
+
"learning_rate": 7.388761759471142e-05,
|
| 957 |
+
"loss": 0.0097,
|
| 958 |
+
"step": 62000
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 9.53,
|
| 962 |
+
"grad_norm": 0.12471388280391693,
|
| 963 |
+
"learning_rate": 7.287058225273329e-05,
|
| 964 |
+
"loss": 0.0102,
|
| 965 |
+
"step": 62500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 9.61,
|
| 969 |
+
"grad_norm": 0.0011848780559375882,
|
| 970 |
+
"learning_rate": 7.185354691075516e-05,
|
| 971 |
+
"loss": 0.0093,
|
| 972 |
+
"step": 63000
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 9.69,
|
| 976 |
+
"grad_norm": 0.32076504826545715,
|
| 977 |
+
"learning_rate": 7.083651156877702e-05,
|
| 978 |
+
"loss": 0.0096,
|
| 979 |
+
"step": 63500
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 9.76,
|
| 983 |
+
"grad_norm": 1.0963212251663208,
|
| 984 |
+
"learning_rate": 6.981947622679888e-05,
|
| 985 |
+
"loss": 0.0103,
|
| 986 |
+
"step": 64000
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 9.84,
|
| 990 |
+
"grad_norm": 0.2559475004673004,
|
| 991 |
+
"learning_rate": 6.880244088482075e-05,
|
| 992 |
+
"loss": 0.011,
|
| 993 |
+
"step": 64500
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 9.92,
|
| 997 |
+
"grad_norm": 0.1217416375875473,
|
| 998 |
+
"learning_rate": 6.778540554284262e-05,
|
| 999 |
+
"loss": 0.0092,
|
| 1000 |
+
"step": 65000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 9.99,
|
| 1004 |
+
"grad_norm": 0.004103431012481451,
|
| 1005 |
+
"learning_rate": 6.676837020086448e-05,
|
| 1006 |
+
"loss": 0.0101,
|
| 1007 |
+
"step": 65500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 10.0,
|
| 1011 |
+
"eval_execution_accuracy": 68.1818,
|
| 1012 |
+
"eval_loss": 0.07360666990280151,
|
| 1013 |
+
"eval_runtime": 1900.7634,
|
| 1014 |
+
"eval_samples_per_second": 0.544,
|
| 1015 |
+
"eval_steps_per_second": 0.068,
|
| 1016 |
+
"step": 65550
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 10.07,
|
| 1020 |
+
"grad_norm": 0.13344629108905792,
|
| 1021 |
+
"learning_rate": 6.575133485888635e-05,
|
| 1022 |
+
"loss": 0.0092,
|
| 1023 |
+
"step": 66000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 10.14,
|
| 1027 |
+
"grad_norm": 0.0032061520032584667,
|
| 1028 |
+
"learning_rate": 6.473429951690822e-05,
|
| 1029 |
+
"loss": 0.0081,
|
| 1030 |
+
"step": 66500
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 10.22,
|
| 1034 |
+
"grad_norm": 0.21120476722717285,
|
| 1035 |
+
"learning_rate": 6.371726417493009e-05,
|
| 1036 |
+
"loss": 0.0086,
|
| 1037 |
+
"step": 67000
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 10.3,
|
| 1041 |
+
"grad_norm": 0.00848371535539627,
|
| 1042 |
+
"learning_rate": 6.270022883295194e-05,
|
| 1043 |
+
"loss": 0.0081,
|
| 1044 |
+
"step": 67500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 10.37,
|
| 1048 |
+
"grad_norm": 0.0012110616080462933,
|
| 1049 |
+
"learning_rate": 6.168319349097381e-05,
|
| 1050 |
+
"loss": 0.0085,
|
| 1051 |
+
"step": 68000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 10.45,
|
| 1055 |
+
"grad_norm": 0.05799203738570213,
|
| 1056 |
+
"learning_rate": 6.066615814899568e-05,
|
| 1057 |
+
"loss": 0.0078,
|
| 1058 |
+
"step": 68500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 10.53,
|
| 1062 |
+
"grad_norm": 0.03763442113995552,
|
| 1063 |
+
"learning_rate": 5.9649122807017544e-05,
|
| 1064 |
+
"loss": 0.008,
|
| 1065 |
+
"step": 69000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 10.6,
|
| 1069 |
+
"grad_norm": 0.01833200454711914,
|
| 1070 |
+
"learning_rate": 5.8632087465039406e-05,
|
| 1071 |
+
"loss": 0.0089,
|
| 1072 |
+
"step": 69500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 10.68,
|
| 1076 |
+
"grad_norm": 0.27255308628082275,
|
| 1077 |
+
"learning_rate": 5.7615052123061275e-05,
|
| 1078 |
+
"loss": 0.0085,
|
| 1079 |
+
"step": 70000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 10.76,
|
| 1083 |
+
"grad_norm": 0.049906667321920395,
|
| 1084 |
+
"learning_rate": 5.659801678108314e-05,
|
| 1085 |
+
"loss": 0.0093,
|
| 1086 |
+
"step": 70500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 10.83,
|
| 1090 |
+
"grad_norm": 0.49261561036109924,
|
| 1091 |
+
"learning_rate": 5.558098143910501e-05,
|
| 1092 |
+
"loss": 0.0099,
|
| 1093 |
+
"step": 71000
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 10.91,
|
| 1097 |
+
"grad_norm": 0.010688086971640587,
|
| 1098 |
+
"learning_rate": 5.456394609712687e-05,
|
| 1099 |
+
"loss": 0.0092,
|
| 1100 |
+
"step": 71500
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 10.98,
|
| 1104 |
+
"grad_norm": 0.015557405538856983,
|
| 1105 |
+
"learning_rate": 5.354691075514875e-05,
|
| 1106 |
+
"loss": 0.0085,
|
| 1107 |
+
"step": 72000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 11.0,
|
| 1111 |
+
"eval_execution_accuracy": 68.0851,
|
| 1112 |
+
"eval_loss": 0.07639693468809128,
|
| 1113 |
+
"eval_runtime": 1996.6932,
|
| 1114 |
+
"eval_samples_per_second": 0.518,
|
| 1115 |
+
"eval_steps_per_second": 0.065,
|
| 1116 |
+
"step": 72105
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 11.06,
|
| 1120 |
+
"grad_norm": 0.1298118531703949,
|
| 1121 |
+
"learning_rate": 5.2529875413170615e-05,
|
| 1122 |
+
"loss": 0.0078,
|
| 1123 |
+
"step": 72500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 11.14,
|
| 1127 |
+
"grad_norm": 0.08524327725172043,
|
| 1128 |
+
"learning_rate": 5.151284007119248e-05,
|
| 1129 |
+
"loss": 0.0085,
|
| 1130 |
+
"step": 73000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 11.21,
|
| 1134 |
+
"grad_norm": 0.1634071171283722,
|
| 1135 |
+
"learning_rate": 5.049580472921435e-05,
|
| 1136 |
+
"loss": 0.0071,
|
| 1137 |
+
"step": 73500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 11.29,
|
| 1141 |
+
"grad_norm": 0.0011399647919461131,
|
| 1142 |
+
"learning_rate": 4.947876938723621e-05,
|
| 1143 |
+
"loss": 0.0069,
|
| 1144 |
+
"step": 74000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 11.37,
|
| 1148 |
+
"grad_norm": 0.010579722002148628,
|
| 1149 |
+
"learning_rate": 4.846173404525807e-05,
|
| 1150 |
+
"loss": 0.0072,
|
| 1151 |
+
"step": 74500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 11.44,
|
| 1155 |
+
"grad_norm": 0.014801290817558765,
|
| 1156 |
+
"learning_rate": 4.744469870327994e-05,
|
| 1157 |
+
"loss": 0.0067,
|
| 1158 |
+
"step": 75000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 11.52,
|
| 1162 |
+
"grad_norm": 0.0037248600274324417,
|
| 1163 |
+
"learning_rate": 4.642766336130181e-05,
|
| 1164 |
+
"loss": 0.0075,
|
| 1165 |
+
"step": 75500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 11.59,
|
| 1169 |
+
"grad_norm": 0.00024146214127540588,
|
| 1170 |
+
"learning_rate": 4.541062801932367e-05,
|
| 1171 |
+
"loss": 0.0065,
|
| 1172 |
+
"step": 76000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 11.67,
|
| 1176 |
+
"grad_norm": 0.013673787005245686,
|
| 1177 |
+
"learning_rate": 4.439359267734554e-05,
|
| 1178 |
+
"loss": 0.0071,
|
| 1179 |
+
"step": 76500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 11.75,
|
| 1183 |
+
"grad_norm": 0.4386146366596222,
|
| 1184 |
+
"learning_rate": 4.3376557335367405e-05,
|
| 1185 |
+
"loss": 0.0073,
|
| 1186 |
+
"step": 77000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 11.82,
|
| 1190 |
+
"grad_norm": 0.011454693973064423,
|
| 1191 |
+
"learning_rate": 4.2359521993389274e-05,
|
| 1192 |
+
"loss": 0.0071,
|
| 1193 |
+
"step": 77500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 11.9,
|
| 1197 |
+
"grad_norm": 0.2784646451473236,
|
| 1198 |
+
"learning_rate": 4.1342486651411136e-05,
|
| 1199 |
+
"loss": 0.0084,
|
| 1200 |
+
"step": 78000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 11.98,
|
| 1204 |
+
"grad_norm": 0.1163712665438652,
|
| 1205 |
+
"learning_rate": 4.0325451309433006e-05,
|
| 1206 |
+
"loss": 0.0069,
|
| 1207 |
+
"step": 78500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 12.0,
|
| 1211 |
+
"eval_execution_accuracy": 69.0522,
|
| 1212 |
+
"eval_loss": 0.08005601912736893,
|
| 1213 |
+
"eval_runtime": 1886.3805,
|
| 1214 |
+
"eval_samples_per_second": 0.548,
|
| 1215 |
+
"eval_steps_per_second": 0.069,
|
| 1216 |
+
"step": 78660
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 12.05,
|
| 1220 |
+
"grad_norm": 0.41248416900634766,
|
| 1221 |
+
"learning_rate": 3.930841596745487e-05,
|
| 1222 |
+
"loss": 0.007,
|
| 1223 |
+
"step": 79000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 12.13,
|
| 1227 |
+
"grad_norm": 0.38738590478897095,
|
| 1228 |
+
"learning_rate": 3.829138062547674e-05,
|
| 1229 |
+
"loss": 0.0069,
|
| 1230 |
+
"step": 79500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 12.2,
|
| 1234 |
+
"grad_norm": 0.24087974429130554,
|
| 1235 |
+
"learning_rate": 3.72743452834986e-05,
|
| 1236 |
+
"loss": 0.0057,
|
| 1237 |
+
"step": 80000
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 12.28,
|
| 1241 |
+
"grad_norm": 0.18917705118656158,
|
| 1242 |
+
"learning_rate": 3.625730994152047e-05,
|
| 1243 |
+
"loss": 0.0065,
|
| 1244 |
+
"step": 80500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 12.36,
|
| 1248 |
+
"grad_norm": 0.05060713738203049,
|
| 1249 |
+
"learning_rate": 3.524027459954233e-05,
|
| 1250 |
+
"loss": 0.0054,
|
| 1251 |
+
"step": 81000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 12.43,
|
| 1255 |
+
"grad_norm": 0.07384895533323288,
|
| 1256 |
+
"learning_rate": 3.422323925756421e-05,
|
| 1257 |
+
"loss": 0.0063,
|
| 1258 |
+
"step": 81500
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 12.51,
|
| 1262 |
+
"grad_norm": 0.22887946665287018,
|
| 1263 |
+
"learning_rate": 3.320620391558607e-05,
|
| 1264 |
+
"loss": 0.0057,
|
| 1265 |
+
"step": 82000
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 12.59,
|
| 1269 |
+
"grad_norm": 0.2123759686946869,
|
| 1270 |
+
"learning_rate": 3.218916857360794e-05,
|
| 1271 |
+
"loss": 0.0074,
|
| 1272 |
+
"step": 82500
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 12.66,
|
| 1276 |
+
"grad_norm": 0.09510879218578339,
|
| 1277 |
+
"learning_rate": 3.11721332316298e-05,
|
| 1278 |
+
"loss": 0.0056,
|
| 1279 |
+
"step": 83000
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 12.74,
|
| 1283 |
+
"grad_norm": 0.00010326172196073458,
|
| 1284 |
+
"learning_rate": 3.0155097889651668e-05,
|
| 1285 |
+
"loss": 0.0058,
|
| 1286 |
+
"step": 83500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 12.81,
|
| 1290 |
+
"grad_norm": 0.37206101417541504,
|
| 1291 |
+
"learning_rate": 2.9138062547673534e-05,
|
| 1292 |
+
"loss": 0.0059,
|
| 1293 |
+
"step": 84000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 12.89,
|
| 1297 |
+
"grad_norm": 0.10882502794265747,
|
| 1298 |
+
"learning_rate": 2.81210272056954e-05,
|
| 1299 |
+
"loss": 0.0053,
|
| 1300 |
+
"step": 84500
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 12.97,
|
| 1304 |
+
"grad_norm": 0.010751358233392239,
|
| 1305 |
+
"learning_rate": 2.7103991863717266e-05,
|
| 1306 |
+
"loss": 0.0068,
|
| 1307 |
+
"step": 85000
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 13.0,
|
| 1311 |
+
"eval_execution_accuracy": 69.2456,
|
| 1312 |
+
"eval_loss": 0.0884392261505127,
|
| 1313 |
+
"eval_runtime": 1938.7518,
|
| 1314 |
+
"eval_samples_per_second": 0.533,
|
| 1315 |
+
"eval_steps_per_second": 0.067,
|
| 1316 |
+
"step": 85215
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 13.04,
|
| 1320 |
+
"grad_norm": 0.10975372046232224,
|
| 1321 |
+
"learning_rate": 2.608695652173913e-05,
|
| 1322 |
+
"loss": 0.0057,
|
| 1323 |
+
"step": 85500
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 13.12,
|
| 1327 |
+
"grad_norm": 0.0004275761893950403,
|
| 1328 |
+
"learning_rate": 2.5069921179760997e-05,
|
| 1329 |
+
"loss": 0.0048,
|
| 1330 |
+
"step": 86000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 13.2,
|
| 1334 |
+
"grad_norm": 0.3996267020702362,
|
| 1335 |
+
"learning_rate": 2.4052885837782867e-05,
|
| 1336 |
+
"loss": 0.0051,
|
| 1337 |
+
"step": 86500
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 13.27,
|
| 1341 |
+
"grad_norm": 0.00662227114662528,
|
| 1342 |
+
"learning_rate": 2.3035850495804733e-05,
|
| 1343 |
+
"loss": 0.0062,
|
| 1344 |
+
"step": 87000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 13.35,
|
| 1348 |
+
"grad_norm": 0.09702113270759583,
|
| 1349 |
+
"learning_rate": 2.20188151538266e-05,
|
| 1350 |
+
"loss": 0.0051,
|
| 1351 |
+
"step": 87500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 13.42,
|
| 1355 |
+
"grad_norm": 0.0026878053322434425,
|
| 1356 |
+
"learning_rate": 2.100177981184846e-05,
|
| 1357 |
+
"loss": 0.0063,
|
| 1358 |
+
"step": 88000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 13.5,
|
| 1362 |
+
"grad_norm": 0.05382531136274338,
|
| 1363 |
+
"learning_rate": 1.9984744469870327e-05,
|
| 1364 |
+
"loss": 0.0042,
|
| 1365 |
+
"step": 88500
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 13.58,
|
| 1369 |
+
"grad_norm": 0.770341157913208,
|
| 1370 |
+
"learning_rate": 1.8967709127892193e-05,
|
| 1371 |
+
"loss": 0.0052,
|
| 1372 |
+
"step": 89000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 13.65,
|
| 1376 |
+
"grad_norm": 0.00518847955390811,
|
| 1377 |
+
"learning_rate": 1.795067378591406e-05,
|
| 1378 |
+
"loss": 0.0052,
|
| 1379 |
+
"step": 89500
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 13.73,
|
| 1383 |
+
"grad_norm": 0.0707794651389122,
|
| 1384 |
+
"learning_rate": 1.6933638443935928e-05,
|
| 1385 |
+
"loss": 0.0053,
|
| 1386 |
+
"step": 90000
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 13.81,
|
| 1390 |
+
"grad_norm": 0.5020930767059326,
|
| 1391 |
+
"learning_rate": 1.5916603101957794e-05,
|
| 1392 |
+
"loss": 0.0057,
|
| 1393 |
+
"step": 90500
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 13.88,
|
| 1397 |
+
"grad_norm": 0.11777380853891373,
|
| 1398 |
+
"learning_rate": 1.489956775997966e-05,
|
| 1399 |
+
"loss": 0.0056,
|
| 1400 |
+
"step": 91000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 13.96,
|
| 1404 |
+
"grad_norm": 0.0008695057476870716,
|
| 1405 |
+
"learning_rate": 1.3882532418001526e-05,
|
| 1406 |
+
"loss": 0.0052,
|
| 1407 |
+
"step": 91500
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 14.0,
|
| 1411 |
+
"eval_execution_accuracy": 70.793,
|
| 1412 |
+
"eval_loss": 0.08826606720685959,
|
| 1413 |
+
"eval_runtime": 1858.3154,
|
| 1414 |
+
"eval_samples_per_second": 0.556,
|
| 1415 |
+
"eval_steps_per_second": 0.07,
|
| 1416 |
+
"step": 91770
|
| 1417 |
+
}
|
| 1418 |
+
],
|
| 1419 |
+
"logging_steps": 500,
|
| 1420 |
+
"max_steps": 98325,
|
| 1421 |
+
"num_input_tokens_seen": 0,
|
| 1422 |
+
"num_train_epochs": 15,
|
| 1423 |
+
"save_steps": 500,
|
| 1424 |
+
"total_flos": 8.553259153863475e+17,
|
| 1425 |
+
"train_batch_size": 1,
|
| 1426 |
+
"trial_name": null,
|
| 1427 |
+
"trial_params": null
|
| 1428 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dede708255d17950cd0ceacfc76f91fd3379b42a34bfdc561353a82976b8fcf6
|
| 3 |
size 5112
|