Commit
•
9711163
1
Parent(s):
818433f
End of training
Browse files- README.md +164 -0
- all_results.json +13 -0
- config.json +63 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +916 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnextv2-tiny-1k-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: convnextv2-tiny-1k-224-finetuned-eurosat
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.625
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# convnextv2-tiny-1k-224-finetuned-eurosat
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.2021
|
| 36 |
+
- Accuracy: 0.625
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 32
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 128
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 130
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 1 | 2.0300 | 0.0 |
|
| 71 |
+
| No log | 2.0 | 3 | 2.0208 | 0.0 |
|
| 72 |
+
| No log | 3.0 | 5 | 1.9970 | 0.0 |
|
| 73 |
+
| No log | 4.0 | 6 | 1.9853 | 0.125 |
|
| 74 |
+
| No log | 5.0 | 7 | 1.9666 | 0.125 |
|
| 75 |
+
| No log | 6.0 | 9 | 1.9215 | 0.25 |
|
| 76 |
+
| 1.024 | 7.0 | 11 | 1.8757 | 0.125 |
|
| 77 |
+
| 1.024 | 8.0 | 12 | 1.8580 | 0.125 |
|
| 78 |
+
| 1.024 | 9.0 | 13 | 1.8413 | 0.125 |
|
| 79 |
+
| 1.024 | 10.0 | 15 | 1.7954 | 0.375 |
|
| 80 |
+
| 1.024 | 11.0 | 17 | 1.7510 | 0.5 |
|
| 81 |
+
| 1.024 | 12.0 | 18 | 1.7309 | 0.625 |
|
| 82 |
+
| 1.024 | 13.0 | 19 | 1.7132 | 0.625 |
|
| 83 |
+
| 0.8487 | 14.0 | 21 | 1.6768 | 0.625 |
|
| 84 |
+
| 0.8487 | 15.0 | 23 | 1.6402 | 0.625 |
|
| 85 |
+
| 0.8487 | 16.0 | 24 | 1.6197 | 0.625 |
|
| 86 |
+
| 0.8487 | 17.0 | 25 | 1.5952 | 0.625 |
|
| 87 |
+
| 0.8487 | 18.0 | 27 | 1.5259 | 0.625 |
|
| 88 |
+
| 0.8487 | 19.0 | 29 | 1.4599 | 0.625 |
|
| 89 |
+
| 0.6549 | 20.0 | 30 | 1.4526 | 0.625 |
|
| 90 |
+
| 0.6549 | 21.0 | 31 | 1.4459 | 0.625 |
|
| 91 |
+
| 0.6549 | 22.0 | 33 | 1.4222 | 0.625 |
|
| 92 |
+
| 0.6549 | 23.0 | 35 | 1.4136 | 0.625 |
|
| 93 |
+
| 0.6549 | 24.0 | 36 | 1.4238 | 0.625 |
|
| 94 |
+
| 0.6549 | 25.0 | 37 | 1.4286 | 0.625 |
|
| 95 |
+
| 0.6549 | 26.0 | 39 | 1.4231 | 0.625 |
|
| 96 |
+
| 0.479 | 27.0 | 41 | 1.3964 | 0.625 |
|
| 97 |
+
| 0.479 | 28.0 | 42 | 1.3757 | 0.625 |
|
| 98 |
+
| 0.479 | 29.0 | 43 | 1.3501 | 0.625 |
|
| 99 |
+
| 0.479 | 30.0 | 45 | 1.2779 | 0.625 |
|
| 100 |
+
| 0.479 | 31.0 | 47 | 1.2360 | 0.625 |
|
| 101 |
+
| 0.479 | 32.0 | 48 | 1.2185 | 0.625 |
|
| 102 |
+
| 0.479 | 33.0 | 49 | 1.1920 | 0.625 |
|
| 103 |
+
| 0.3504 | 34.0 | 51 | 1.1326 | 0.625 |
|
| 104 |
+
| 0.3504 | 35.0 | 53 | 1.1018 | 0.625 |
|
| 105 |
+
| 0.3504 | 36.0 | 54 | 1.0970 | 0.625 |
|
| 106 |
+
| 0.3504 | 37.0 | 55 | 1.1030 | 0.625 |
|
| 107 |
+
| 0.3504 | 38.0 | 57 | 1.1378 | 0.625 |
|
| 108 |
+
| 0.3504 | 39.0 | 59 | 1.1720 | 0.625 |
|
| 109 |
+
| 0.2864 | 40.0 | 60 | 1.1867 | 0.625 |
|
| 110 |
+
| 0.2864 | 41.0 | 61 | 1.1960 | 0.625 |
|
| 111 |
+
| 0.2864 | 42.0 | 63 | 1.1959 | 0.625 |
|
| 112 |
+
| 0.2864 | 43.0 | 65 | 1.1727 | 0.625 |
|
| 113 |
+
| 0.2864 | 44.0 | 66 | 1.1653 | 0.625 |
|
| 114 |
+
| 0.2864 | 45.0 | 67 | 1.1644 | 0.625 |
|
| 115 |
+
| 0.2864 | 46.0 | 69 | 1.1809 | 0.625 |
|
| 116 |
+
| 0.2357 | 47.0 | 71 | 1.1902 | 0.625 |
|
| 117 |
+
| 0.2357 | 48.0 | 72 | 1.1872 | 0.625 |
|
| 118 |
+
| 0.2357 | 49.0 | 73 | 1.1894 | 0.625 |
|
| 119 |
+
| 0.2357 | 50.0 | 75 | 1.1982 | 0.625 |
|
| 120 |
+
| 0.2357 | 51.0 | 77 | 1.2418 | 0.625 |
|
| 121 |
+
| 0.2357 | 52.0 | 78 | 1.2575 | 0.625 |
|
| 122 |
+
| 0.2357 | 53.0 | 79 | 1.2708 | 0.625 |
|
| 123 |
+
| 0.1561 | 54.0 | 81 | 1.2666 | 0.625 |
|
| 124 |
+
| 0.1561 | 55.0 | 83 | 1.2241 | 0.625 |
|
| 125 |
+
| 0.1561 | 56.0 | 84 | 1.2089 | 0.625 |
|
| 126 |
+
| 0.1561 | 57.0 | 85 | 1.1914 | 0.625 |
|
| 127 |
+
| 0.1561 | 58.0 | 87 | 1.1559 | 0.625 |
|
| 128 |
+
| 0.1561 | 59.0 | 89 | 1.1387 | 0.625 |
|
| 129 |
+
| 0.1453 | 60.0 | 90 | 1.1337 | 0.625 |
|
| 130 |
+
| 0.1453 | 61.0 | 91 | 1.1290 | 0.625 |
|
| 131 |
+
| 0.1453 | 62.0 | 93 | 1.1369 | 0.625 |
|
| 132 |
+
| 0.1453 | 63.0 | 95 | 1.1439 | 0.625 |
|
| 133 |
+
| 0.1453 | 64.0 | 96 | 1.1448 | 0.625 |
|
| 134 |
+
| 0.1453 | 65.0 | 97 | 1.1530 | 0.625 |
|
| 135 |
+
| 0.1453 | 66.0 | 99 | 1.1718 | 0.625 |
|
| 136 |
+
| 0.1271 | 67.0 | 101 | 1.1965 | 0.625 |
|
| 137 |
+
| 0.1271 | 68.0 | 102 | 1.2092 | 0.625 |
|
| 138 |
+
| 0.1271 | 69.0 | 103 | 1.2176 | 0.625 |
|
| 139 |
+
| 0.1271 | 70.0 | 105 | 1.2337 | 0.625 |
|
| 140 |
+
| 0.1271 | 71.0 | 107 | 1.2376 | 0.625 |
|
| 141 |
+
| 0.1271 | 72.0 | 108 | 1.2384 | 0.625 |
|
| 142 |
+
| 0.1271 | 73.0 | 109 | 1.2378 | 0.625 |
|
| 143 |
+
| 0.1153 | 74.0 | 111 | 1.2385 | 0.625 |
|
| 144 |
+
| 0.1153 | 75.0 | 113 | 1.2316 | 0.625 |
|
| 145 |
+
| 0.1153 | 76.0 | 114 | 1.2274 | 0.625 |
|
| 146 |
+
| 0.1153 | 77.0 | 115 | 1.2252 | 0.625 |
|
| 147 |
+
| 0.1153 | 78.0 | 117 | 1.2196 | 0.625 |
|
| 148 |
+
| 0.1153 | 79.0 | 119 | 1.2145 | 0.625 |
|
| 149 |
+
| 0.0882 | 80.0 | 120 | 1.2130 | 0.625 |
|
| 150 |
+
| 0.0882 | 81.0 | 121 | 1.2117 | 0.625 |
|
| 151 |
+
| 0.0882 | 82.0 | 123 | 1.2097 | 0.625 |
|
| 152 |
+
| 0.0882 | 83.0 | 125 | 1.2075 | 0.625 |
|
| 153 |
+
| 0.0882 | 84.0 | 126 | 1.2054 | 0.625 |
|
| 154 |
+
| 0.0882 | 85.0 | 127 | 1.2039 | 0.625 |
|
| 155 |
+
| 0.0882 | 86.0 | 129 | 1.2025 | 0.625 |
|
| 156 |
+
| 0.0987 | 86.6667 | 130 | 1.2021 | 0.625 |
|
| 157 |
+
|
| 158 |
+
|
| 159 |
+
### Framework versions
|
| 160 |
+
|
| 161 |
+
- Transformers 4.44.0
|
| 162 |
+
- Pytorch 2.4.0
|
| 163 |
+
- Datasets 2.21.0
|
| 164 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 86.66666666666667,
|
| 3 |
+
"eval_accuracy": 0.625,
|
| 4 |
+
"eval_loss": 1.2021381855010986,
|
| 5 |
+
"eval_runtime": 0.2304,
|
| 6 |
+
"eval_samples_per_second": 34.717,
|
| 7 |
+
"eval_steps_per_second": 4.34,
|
| 8 |
+
"total_flos": 1.574865655328932e+17,
|
| 9 |
+
"train_loss": 0.3546037518061124,
|
| 10 |
+
"train_runtime": 225.362,
|
| 11 |
+
"train_samples_per_second": 41.533,
|
| 12 |
+
"train_steps_per_second": 0.577
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/convnextv2-tiny-1k-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ConvNextV2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
3,
|
| 9 |
+
9,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"drop_path_rate": 0.0,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_sizes": [
|
| 15 |
+
96,
|
| 16 |
+
192,
|
| 17 |
+
384,
|
| 18 |
+
768
|
| 19 |
+
],
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "Joggers",
|
| 22 |
+
"1": "capri",
|
| 23 |
+
"2": "jeans",
|
| 24 |
+
"3": "legging",
|
| 25 |
+
"4": "plazzo",
|
| 26 |
+
"5": "shorts",
|
| 27 |
+
"6": "skirt",
|
| 28 |
+
"7": "trouser"
|
| 29 |
+
},
|
| 30 |
+
"image_size": 224,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"Joggers": 0,
|
| 34 |
+
"capri": 1,
|
| 35 |
+
"jeans": 2,
|
| 36 |
+
"legging": 3,
|
| 37 |
+
"plazzo": 4,
|
| 38 |
+
"shorts": 5,
|
| 39 |
+
"skirt": 6,
|
| 40 |
+
"trouser": 7
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-12,
|
| 43 |
+
"model_type": "convnextv2",
|
| 44 |
+
"num_channels": 3,
|
| 45 |
+
"num_stages": 4,
|
| 46 |
+
"out_features": [
|
| 47 |
+
"stage4"
|
| 48 |
+
],
|
| 49 |
+
"out_indices": [
|
| 50 |
+
4
|
| 51 |
+
],
|
| 52 |
+
"patch_size": 4,
|
| 53 |
+
"problem_type": "single_label_classification",
|
| 54 |
+
"stage_names": [
|
| 55 |
+
"stem",
|
| 56 |
+
"stage1",
|
| 57 |
+
"stage2",
|
| 58 |
+
"stage3",
|
| 59 |
+
"stage4"
|
| 60 |
+
],
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.44.0"
|
| 63 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 86.66666666666667,
|
| 3 |
+
"eval_accuracy": 0.625,
|
| 4 |
+
"eval_loss": 1.2021381855010986,
|
| 5 |
+
"eval_runtime": 0.2304,
|
| 6 |
+
"eval_samples_per_second": 34.717,
|
| 7 |
+
"eval_steps_per_second": 4.34
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76e72daa47f949e84cf8be0ea3c00e00e92ed8369d17437418d3c618795149c2
|
| 3 |
+
size 111514288
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 86.66666666666667,
|
| 3 |
+
"total_flos": 1.574865655328932e+17,
|
| 4 |
+
"train_loss": 0.3546037518061124,
|
| 5 |
+
"train_runtime": 225.362,
|
| 6 |
+
"train_samples_per_second": 41.533,
|
| 7 |
+
"train_steps_per_second": 0.577
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,916 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 86.66666666666667,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 130,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.0,
|
| 14 |
+
"eval_loss": 2.030040740966797,
|
| 15 |
+
"eval_runtime": 0.2932,
|
| 16 |
+
"eval_samples_per_second": 27.282,
|
| 17 |
+
"eval_steps_per_second": 3.41,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.0,
|
| 23 |
+
"eval_loss": 2.020792007446289,
|
| 24 |
+
"eval_runtime": 0.2487,
|
| 25 |
+
"eval_samples_per_second": 32.169,
|
| 26 |
+
"eval_steps_per_second": 4.021,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.0,
|
| 32 |
+
"eval_loss": 1.996970534324646,
|
| 33 |
+
"eval_runtime": 0.2271,
|
| 34 |
+
"eval_samples_per_second": 35.23,
|
| 35 |
+
"eval_steps_per_second": 4.404,
|
| 36 |
+
"step": 5
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.125,
|
| 41 |
+
"eval_loss": 1.9852917194366455,
|
| 42 |
+
"eval_runtime": 0.2294,
|
| 43 |
+
"eval_samples_per_second": 34.875,
|
| 44 |
+
"eval_steps_per_second": 4.359,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.125,
|
| 50 |
+
"eval_loss": 1.9666370153427124,
|
| 51 |
+
"eval_runtime": 0.23,
|
| 52 |
+
"eval_samples_per_second": 34.788,
|
| 53 |
+
"eval_steps_per_second": 4.348,
|
| 54 |
+
"step": 7
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.25,
|
| 59 |
+
"eval_loss": 1.9215028285980225,
|
| 60 |
+
"eval_runtime": 0.2245,
|
| 61 |
+
"eval_samples_per_second": 35.632,
|
| 62 |
+
"eval_steps_per_second": 4.454,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.666666666666667,
|
| 67 |
+
"grad_norm": 14.784972190856934,
|
| 68 |
+
"learning_rate": 3.846153846153846e-05,
|
| 69 |
+
"loss": 1.024,
|
| 70 |
+
"step": 10
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 7.0,
|
| 74 |
+
"eval_accuracy": 0.125,
|
| 75 |
+
"eval_loss": 1.8757238388061523,
|
| 76 |
+
"eval_runtime": 0.2259,
|
| 77 |
+
"eval_samples_per_second": 35.411,
|
| 78 |
+
"eval_steps_per_second": 4.426,
|
| 79 |
+
"step": 11
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 8.0,
|
| 83 |
+
"eval_accuracy": 0.125,
|
| 84 |
+
"eval_loss": 1.8579578399658203,
|
| 85 |
+
"eval_runtime": 0.2276,
|
| 86 |
+
"eval_samples_per_second": 35.149,
|
| 87 |
+
"eval_steps_per_second": 4.394,
|
| 88 |
+
"step": 12
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 9.0,
|
| 92 |
+
"eval_accuracy": 0.125,
|
| 93 |
+
"eval_loss": 1.8413233757019043,
|
| 94 |
+
"eval_runtime": 0.232,
|
| 95 |
+
"eval_samples_per_second": 34.49,
|
| 96 |
+
"eval_steps_per_second": 4.311,
|
| 97 |
+
"step": 13
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 10.0,
|
| 101 |
+
"eval_accuracy": 0.375,
|
| 102 |
+
"eval_loss": 1.7954258918762207,
|
| 103 |
+
"eval_runtime": 0.2267,
|
| 104 |
+
"eval_samples_per_second": 35.29,
|
| 105 |
+
"eval_steps_per_second": 4.411,
|
| 106 |
+
"step": 15
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 11.0,
|
| 110 |
+
"eval_accuracy": 0.5,
|
| 111 |
+
"eval_loss": 1.7509543895721436,
|
| 112 |
+
"eval_runtime": 0.2337,
|
| 113 |
+
"eval_samples_per_second": 34.23,
|
| 114 |
+
"eval_steps_per_second": 4.279,
|
| 115 |
+
"step": 17
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 12.0,
|
| 119 |
+
"eval_accuracy": 0.625,
|
| 120 |
+
"eval_loss": 1.7309346199035645,
|
| 121 |
+
"eval_runtime": 0.2261,
|
| 122 |
+
"eval_samples_per_second": 35.381,
|
| 123 |
+
"eval_steps_per_second": 4.423,
|
| 124 |
+
"step": 18
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 13.0,
|
| 128 |
+
"eval_accuracy": 0.625,
|
| 129 |
+
"eval_loss": 1.7131527662277222,
|
| 130 |
+
"eval_runtime": 0.2297,
|
| 131 |
+
"eval_samples_per_second": 34.829,
|
| 132 |
+
"eval_steps_per_second": 4.354,
|
| 133 |
+
"step": 19
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 13.333333333333334,
|
| 137 |
+
"grad_norm": 9.231935501098633,
|
| 138 |
+
"learning_rate": 4.700854700854701e-05,
|
| 139 |
+
"loss": 0.8487,
|
| 140 |
+
"step": 20
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 14.0,
|
| 144 |
+
"eval_accuracy": 0.625,
|
| 145 |
+
"eval_loss": 1.6768202781677246,
|
| 146 |
+
"eval_runtime": 0.2263,
|
| 147 |
+
"eval_samples_per_second": 35.354,
|
| 148 |
+
"eval_steps_per_second": 4.419,
|
| 149 |
+
"step": 21
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 15.0,
|
| 153 |
+
"eval_accuracy": 0.625,
|
| 154 |
+
"eval_loss": 1.64021635055542,
|
| 155 |
+
"eval_runtime": 0.2376,
|
| 156 |
+
"eval_samples_per_second": 33.673,
|
| 157 |
+
"eval_steps_per_second": 4.209,
|
| 158 |
+
"step": 23
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 16.0,
|
| 162 |
+
"eval_accuracy": 0.625,
|
| 163 |
+
"eval_loss": 1.6197324991226196,
|
| 164 |
+
"eval_runtime": 0.2274,
|
| 165 |
+
"eval_samples_per_second": 35.183,
|
| 166 |
+
"eval_steps_per_second": 4.398,
|
| 167 |
+
"step": 24
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 17.0,
|
| 171 |
+
"eval_accuracy": 0.625,
|
| 172 |
+
"eval_loss": 1.5951614379882812,
|
| 173 |
+
"eval_runtime": 0.2246,
|
| 174 |
+
"eval_samples_per_second": 35.616,
|
| 175 |
+
"eval_steps_per_second": 4.452,
|
| 176 |
+
"step": 25
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 18.0,
|
| 180 |
+
"eval_accuracy": 0.625,
|
| 181 |
+
"eval_loss": 1.525948166847229,
|
| 182 |
+
"eval_runtime": 0.229,
|
| 183 |
+
"eval_samples_per_second": 34.929,
|
| 184 |
+
"eval_steps_per_second": 4.366,
|
| 185 |
+
"step": 27
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 19.0,
|
| 189 |
+
"eval_accuracy": 0.625,
|
| 190 |
+
"eval_loss": 1.4598863124847412,
|
| 191 |
+
"eval_runtime": 0.228,
|
| 192 |
+
"eval_samples_per_second": 35.095,
|
| 193 |
+
"eval_steps_per_second": 4.387,
|
| 194 |
+
"step": 29
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.0,
|
| 198 |
+
"grad_norm": 15.795075416564941,
|
| 199 |
+
"learning_rate": 4.2735042735042735e-05,
|
| 200 |
+
"loss": 0.6549,
|
| 201 |
+
"step": 30
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 20.0,
|
| 205 |
+
"eval_accuracy": 0.625,
|
| 206 |
+
"eval_loss": 1.4526441097259521,
|
| 207 |
+
"eval_runtime": 0.2272,
|
| 208 |
+
"eval_samples_per_second": 35.213,
|
| 209 |
+
"eval_steps_per_second": 4.402,
|
| 210 |
+
"step": 30
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 21.0,
|
| 214 |
+
"eval_accuracy": 0.625,
|
| 215 |
+
"eval_loss": 1.4458982944488525,
|
| 216 |
+
"eval_runtime": 0.227,
|
| 217 |
+
"eval_samples_per_second": 35.238,
|
| 218 |
+
"eval_steps_per_second": 4.405,
|
| 219 |
+
"step": 31
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 22.0,
|
| 223 |
+
"eval_accuracy": 0.625,
|
| 224 |
+
"eval_loss": 1.4222255945205688,
|
| 225 |
+
"eval_runtime": 0.2296,
|
| 226 |
+
"eval_samples_per_second": 34.847,
|
| 227 |
+
"eval_steps_per_second": 4.356,
|
| 228 |
+
"step": 33
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 23.0,
|
| 232 |
+
"eval_accuracy": 0.625,
|
| 233 |
+
"eval_loss": 1.4135932922363281,
|
| 234 |
+
"eval_runtime": 0.23,
|
| 235 |
+
"eval_samples_per_second": 34.776,
|
| 236 |
+
"eval_steps_per_second": 4.347,
|
| 237 |
+
"step": 35
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 24.0,
|
| 241 |
+
"eval_accuracy": 0.625,
|
| 242 |
+
"eval_loss": 1.4238104820251465,
|
| 243 |
+
"eval_runtime": 0.2362,
|
| 244 |
+
"eval_samples_per_second": 33.867,
|
| 245 |
+
"eval_steps_per_second": 4.233,
|
| 246 |
+
"step": 36
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 25.0,
|
| 250 |
+
"eval_accuracy": 0.625,
|
| 251 |
+
"eval_loss": 1.4286460876464844,
|
| 252 |
+
"eval_runtime": 0.2278,
|
| 253 |
+
"eval_samples_per_second": 35.125,
|
| 254 |
+
"eval_steps_per_second": 4.391,
|
| 255 |
+
"step": 37
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 26.0,
|
| 259 |
+
"eval_accuracy": 0.625,
|
| 260 |
+
"eval_loss": 1.42312753200531,
|
| 261 |
+
"eval_runtime": 0.2304,
|
| 262 |
+
"eval_samples_per_second": 34.725,
|
| 263 |
+
"eval_steps_per_second": 4.341,
|
| 264 |
+
"step": 39
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 26.666666666666668,
|
| 268 |
+
"grad_norm": 7.896138668060303,
|
| 269 |
+
"learning_rate": 3.846153846153846e-05,
|
| 270 |
+
"loss": 0.479,
|
| 271 |
+
"step": 40
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 27.0,
|
| 275 |
+
"eval_accuracy": 0.625,
|
| 276 |
+
"eval_loss": 1.3963532447814941,
|
| 277 |
+
"eval_runtime": 0.225,
|
| 278 |
+
"eval_samples_per_second": 35.554,
|
| 279 |
+
"eval_steps_per_second": 4.444,
|
| 280 |
+
"step": 41
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 28.0,
|
| 284 |
+
"eval_accuracy": 0.625,
|
| 285 |
+
"eval_loss": 1.375662088394165,
|
| 286 |
+
"eval_runtime": 0.2285,
|
| 287 |
+
"eval_samples_per_second": 35.009,
|
| 288 |
+
"eval_steps_per_second": 4.376,
|
| 289 |
+
"step": 42
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 29.0,
|
| 293 |
+
"eval_accuracy": 0.625,
|
| 294 |
+
"eval_loss": 1.350050687789917,
|
| 295 |
+
"eval_runtime": 0.2264,
|
| 296 |
+
"eval_samples_per_second": 35.335,
|
| 297 |
+
"eval_steps_per_second": 4.417,
|
| 298 |
+
"step": 43
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 30.0,
|
| 302 |
+
"eval_accuracy": 0.625,
|
| 303 |
+
"eval_loss": 1.277871012687683,
|
| 304 |
+
"eval_runtime": 0.2258,
|
| 305 |
+
"eval_samples_per_second": 35.433,
|
| 306 |
+
"eval_steps_per_second": 4.429,
|
| 307 |
+
"step": 45
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 31.0,
|
| 311 |
+
"eval_accuracy": 0.625,
|
| 312 |
+
"eval_loss": 1.2359542846679688,
|
| 313 |
+
"eval_runtime": 0.2324,
|
| 314 |
+
"eval_samples_per_second": 34.427,
|
| 315 |
+
"eval_steps_per_second": 4.303,
|
| 316 |
+
"step": 47
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 32.0,
|
| 320 |
+
"eval_accuracy": 0.625,
|
| 321 |
+
"eval_loss": 1.218457579612732,
|
| 322 |
+
"eval_runtime": 0.2295,
|
| 323 |
+
"eval_samples_per_second": 34.863,
|
| 324 |
+
"eval_steps_per_second": 4.358,
|
| 325 |
+
"step": 48
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 33.0,
|
| 329 |
+
"eval_accuracy": 0.625,
|
| 330 |
+
"eval_loss": 1.1920298337936401,
|
| 331 |
+
"eval_runtime": 0.2285,
|
| 332 |
+
"eval_samples_per_second": 35.005,
|
| 333 |
+
"eval_steps_per_second": 4.376,
|
| 334 |
+
"step": 49
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 33.333333333333336,
|
| 338 |
+
"grad_norm": 39.576210021972656,
|
| 339 |
+
"learning_rate": 3.418803418803419e-05,
|
| 340 |
+
"loss": 0.3504,
|
| 341 |
+
"step": 50
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 34.0,
|
| 345 |
+
"eval_accuracy": 0.625,
|
| 346 |
+
"eval_loss": 1.1325857639312744,
|
| 347 |
+
"eval_runtime": 0.2278,
|
| 348 |
+
"eval_samples_per_second": 35.122,
|
| 349 |
+
"eval_steps_per_second": 4.39,
|
| 350 |
+
"step": 51
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 35.0,
|
| 354 |
+
"eval_accuracy": 0.625,
|
| 355 |
+
"eval_loss": 1.1017863750457764,
|
| 356 |
+
"eval_runtime": 0.2263,
|
| 357 |
+
"eval_samples_per_second": 35.352,
|
| 358 |
+
"eval_steps_per_second": 4.419,
|
| 359 |
+
"step": 53
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 36.0,
|
| 363 |
+
"eval_accuracy": 0.625,
|
| 364 |
+
"eval_loss": 1.0970098972320557,
|
| 365 |
+
"eval_runtime": 0.2308,
|
| 366 |
+
"eval_samples_per_second": 34.656,
|
| 367 |
+
"eval_steps_per_second": 4.332,
|
| 368 |
+
"step": 54
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 37.0,
|
| 372 |
+
"eval_accuracy": 0.625,
|
| 373 |
+
"eval_loss": 1.1029536724090576,
|
| 374 |
+
"eval_runtime": 0.2758,
|
| 375 |
+
"eval_samples_per_second": 29.01,
|
| 376 |
+
"eval_steps_per_second": 3.626,
|
| 377 |
+
"step": 55
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 38.0,
|
| 381 |
+
"eval_accuracy": 0.625,
|
| 382 |
+
"eval_loss": 1.1377930641174316,
|
| 383 |
+
"eval_runtime": 0.226,
|
| 384 |
+
"eval_samples_per_second": 35.391,
|
| 385 |
+
"eval_steps_per_second": 4.424,
|
| 386 |
+
"step": 57
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 39.0,
|
| 390 |
+
"eval_accuracy": 0.625,
|
| 391 |
+
"eval_loss": 1.1719943284988403,
|
| 392 |
+
"eval_runtime": 0.2317,
|
| 393 |
+
"eval_samples_per_second": 34.529,
|
| 394 |
+
"eval_steps_per_second": 4.316,
|
| 395 |
+
"step": 59
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 40.0,
|
| 399 |
+
"grad_norm": 31.4616756439209,
|
| 400 |
+
"learning_rate": 2.9914529914529915e-05,
|
| 401 |
+
"loss": 0.2864,
|
| 402 |
+
"step": 60
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 40.0,
|
| 406 |
+
"eval_accuracy": 0.625,
|
| 407 |
+
"eval_loss": 1.1867077350616455,
|
| 408 |
+
"eval_runtime": 0.2264,
|
| 409 |
+
"eval_samples_per_second": 35.336,
|
| 410 |
+
"eval_steps_per_second": 4.417,
|
| 411 |
+
"step": 60
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 41.0,
|
| 415 |
+
"eval_accuracy": 0.625,
|
| 416 |
+
"eval_loss": 1.1960291862487793,
|
| 417 |
+
"eval_runtime": 0.2297,
|
| 418 |
+
"eval_samples_per_second": 34.825,
|
| 419 |
+
"eval_steps_per_second": 4.353,
|
| 420 |
+
"step": 61
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 42.0,
|
| 424 |
+
"eval_accuracy": 0.625,
|
| 425 |
+
"eval_loss": 1.1959271430969238,
|
| 426 |
+
"eval_runtime": 0.2272,
|
| 427 |
+
"eval_samples_per_second": 35.217,
|
| 428 |
+
"eval_steps_per_second": 4.402,
|
| 429 |
+
"step": 63
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 43.0,
|
| 433 |
+
"eval_accuracy": 0.625,
|
| 434 |
+
"eval_loss": 1.1726518869400024,
|
| 435 |
+
"eval_runtime": 0.2279,
|
| 436 |
+
"eval_samples_per_second": 35.11,
|
| 437 |
+
"eval_steps_per_second": 4.389,
|
| 438 |
+
"step": 65
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 44.0,
|
| 442 |
+
"eval_accuracy": 0.625,
|
| 443 |
+
"eval_loss": 1.165253758430481,
|
| 444 |
+
"eval_runtime": 0.227,
|
| 445 |
+
"eval_samples_per_second": 35.239,
|
| 446 |
+
"eval_steps_per_second": 4.405,
|
| 447 |
+
"step": 66
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 45.0,
|
| 451 |
+
"eval_accuracy": 0.625,
|
| 452 |
+
"eval_loss": 1.1643680334091187,
|
| 453 |
+
"eval_runtime": 0.2339,
|
| 454 |
+
"eval_samples_per_second": 34.204,
|
| 455 |
+
"eval_steps_per_second": 4.276,
|
| 456 |
+
"step": 67
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 46.0,
|
| 460 |
+
"eval_accuracy": 0.625,
|
| 461 |
+
"eval_loss": 1.1808971166610718,
|
| 462 |
+
"eval_runtime": 0.2293,
|
| 463 |
+
"eval_samples_per_second": 34.886,
|
| 464 |
+
"eval_steps_per_second": 4.361,
|
| 465 |
+
"step": 69
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 46.666666666666664,
|
| 469 |
+
"grad_norm": 18.457019805908203,
|
| 470 |
+
"learning_rate": 2.564102564102564e-05,
|
| 471 |
+
"loss": 0.2357,
|
| 472 |
+
"step": 70
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 47.0,
|
| 476 |
+
"eval_accuracy": 0.625,
|
| 477 |
+
"eval_loss": 1.1901675462722778,
|
| 478 |
+
"eval_runtime": 0.2261,
|
| 479 |
+
"eval_samples_per_second": 35.381,
|
| 480 |
+
"eval_steps_per_second": 4.423,
|
| 481 |
+
"step": 71
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 48.0,
|
| 485 |
+
"eval_accuracy": 0.625,
|
| 486 |
+
"eval_loss": 1.1872090101242065,
|
| 487 |
+
"eval_runtime": 0.2272,
|
| 488 |
+
"eval_samples_per_second": 35.206,
|
| 489 |
+
"eval_steps_per_second": 4.401,
|
| 490 |
+
"step": 72
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 49.0,
|
| 494 |
+
"eval_accuracy": 0.625,
|
| 495 |
+
"eval_loss": 1.189396858215332,
|
| 496 |
+
"eval_runtime": 0.2263,
|
| 497 |
+
"eval_samples_per_second": 35.345,
|
| 498 |
+
"eval_steps_per_second": 4.418,
|
| 499 |
+
"step": 73
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 50.0,
|
| 503 |
+
"eval_accuracy": 0.625,
|
| 504 |
+
"eval_loss": 1.1982437372207642,
|
| 505 |
+
"eval_runtime": 0.2428,
|
| 506 |
+
"eval_samples_per_second": 32.942,
|
| 507 |
+
"eval_steps_per_second": 4.118,
|
| 508 |
+
"step": 75
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 51.0,
|
| 512 |
+
"eval_accuracy": 0.625,
|
| 513 |
+
"eval_loss": 1.2417709827423096,
|
| 514 |
+
"eval_runtime": 0.2272,
|
| 515 |
+
"eval_samples_per_second": 35.217,
|
| 516 |
+
"eval_steps_per_second": 4.402,
|
| 517 |
+
"step": 77
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 52.0,
|
| 521 |
+
"eval_accuracy": 0.625,
|
| 522 |
+
"eval_loss": 1.2575104236602783,
|
| 523 |
+
"eval_runtime": 0.2279,
|
| 524 |
+
"eval_samples_per_second": 35.099,
|
| 525 |
+
"eval_steps_per_second": 4.387,
|
| 526 |
+
"step": 78
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 53.0,
|
| 530 |
+
"eval_accuracy": 0.625,
|
| 531 |
+
"eval_loss": 1.2707685232162476,
|
| 532 |
+
"eval_runtime": 0.2281,
|
| 533 |
+
"eval_samples_per_second": 35.068,
|
| 534 |
+
"eval_steps_per_second": 4.384,
|
| 535 |
+
"step": 79
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 53.333333333333336,
|
| 539 |
+
"grad_norm": 4.976161479949951,
|
| 540 |
+
"learning_rate": 2.1367521367521368e-05,
|
| 541 |
+
"loss": 0.1561,
|
| 542 |
+
"step": 80
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 54.0,
|
| 546 |
+
"eval_accuracy": 0.625,
|
| 547 |
+
"eval_loss": 1.2665772438049316,
|
| 548 |
+
"eval_runtime": 0.2284,
|
| 549 |
+
"eval_samples_per_second": 35.019,
|
| 550 |
+
"eval_steps_per_second": 4.377,
|
| 551 |
+
"step": 81
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 55.0,
|
| 555 |
+
"eval_accuracy": 0.625,
|
| 556 |
+
"eval_loss": 1.2240548133850098,
|
| 557 |
+
"eval_runtime": 0.2281,
|
| 558 |
+
"eval_samples_per_second": 35.073,
|
| 559 |
+
"eval_steps_per_second": 4.384,
|
| 560 |
+
"step": 83
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 56.0,
|
| 564 |
+
"eval_accuracy": 0.625,
|
| 565 |
+
"eval_loss": 1.2088531255722046,
|
| 566 |
+
"eval_runtime": 0.227,
|
| 567 |
+
"eval_samples_per_second": 35.239,
|
| 568 |
+
"eval_steps_per_second": 4.405,
|
| 569 |
+
"step": 84
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 57.0,
|
| 573 |
+
"eval_accuracy": 0.625,
|
| 574 |
+
"eval_loss": 1.1913509368896484,
|
| 575 |
+
"eval_runtime": 0.2251,
|
| 576 |
+
"eval_samples_per_second": 35.546,
|
| 577 |
+
"eval_steps_per_second": 4.443,
|
| 578 |
+
"step": 85
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 58.0,
|
| 582 |
+
"eval_accuracy": 0.625,
|
| 583 |
+
"eval_loss": 1.1558996438980103,
|
| 584 |
+
"eval_runtime": 0.231,
|
| 585 |
+
"eval_samples_per_second": 34.632,
|
| 586 |
+
"eval_steps_per_second": 4.329,
|
| 587 |
+
"step": 87
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 59.0,
|
| 591 |
+
"eval_accuracy": 0.625,
|
| 592 |
+
"eval_loss": 1.1386878490447998,
|
| 593 |
+
"eval_runtime": 0.2302,
|
| 594 |
+
"eval_samples_per_second": 34.748,
|
| 595 |
+
"eval_steps_per_second": 4.344,
|
| 596 |
+
"step": 89
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 60.0,
|
| 600 |
+
"grad_norm": 19.57244300842285,
|
| 601 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 602 |
+
"loss": 0.1453,
|
| 603 |
+
"step": 90
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 60.0,
|
| 607 |
+
"eval_accuracy": 0.625,
|
| 608 |
+
"eval_loss": 1.1336504220962524,
|
| 609 |
+
"eval_runtime": 0.2275,
|
| 610 |
+
"eval_samples_per_second": 35.169,
|
| 611 |
+
"eval_steps_per_second": 4.396,
|
| 612 |
+
"step": 90
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 61.0,
|
| 616 |
+
"eval_accuracy": 0.625,
|
| 617 |
+
"eval_loss": 1.1289597749710083,
|
| 618 |
+
"eval_runtime": 0.2329,
|
| 619 |
+
"eval_samples_per_second": 34.356,
|
| 620 |
+
"eval_steps_per_second": 4.295,
|
| 621 |
+
"step": 91
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 62.0,
|
| 625 |
+
"eval_accuracy": 0.625,
|
| 626 |
+
"eval_loss": 1.1369203329086304,
|
| 627 |
+
"eval_runtime": 0.2293,
|
| 628 |
+
"eval_samples_per_second": 34.894,
|
| 629 |
+
"eval_steps_per_second": 4.362,
|
| 630 |
+
"step": 93
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 63.0,
|
| 634 |
+
"eval_accuracy": 0.625,
|
| 635 |
+
"eval_loss": 1.1438777446746826,
|
| 636 |
+
"eval_runtime": 0.2263,
|
| 637 |
+
"eval_samples_per_second": 35.359,
|
| 638 |
+
"eval_steps_per_second": 4.42,
|
| 639 |
+
"step": 95
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 64.0,
|
| 643 |
+
"eval_accuracy": 0.625,
|
| 644 |
+
"eval_loss": 1.14479660987854,
|
| 645 |
+
"eval_runtime": 0.2307,
|
| 646 |
+
"eval_samples_per_second": 34.673,
|
| 647 |
+
"eval_steps_per_second": 4.334,
|
| 648 |
+
"step": 96
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 65.0,
|
| 652 |
+
"eval_accuracy": 0.625,
|
| 653 |
+
"eval_loss": 1.153009057044983,
|
| 654 |
+
"eval_runtime": 0.2302,
|
| 655 |
+
"eval_samples_per_second": 34.748,
|
| 656 |
+
"eval_steps_per_second": 4.344,
|
| 657 |
+
"step": 97
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 66.0,
|
| 661 |
+
"eval_accuracy": 0.625,
|
| 662 |
+
"eval_loss": 1.1718435287475586,
|
| 663 |
+
"eval_runtime": 0.2286,
|
| 664 |
+
"eval_samples_per_second": 35.003,
|
| 665 |
+
"eval_steps_per_second": 4.375,
|
| 666 |
+
"step": 99
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 66.66666666666667,
|
| 670 |
+
"grad_norm": 5.6247944831848145,
|
| 671 |
+
"learning_rate": 1.282051282051282e-05,
|
| 672 |
+
"loss": 0.1271,
|
| 673 |
+
"step": 100
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 67.0,
|
| 677 |
+
"eval_accuracy": 0.625,
|
| 678 |
+
"eval_loss": 1.1965450048446655,
|
| 679 |
+
"eval_runtime": 0.2246,
|
| 680 |
+
"eval_samples_per_second": 35.611,
|
| 681 |
+
"eval_steps_per_second": 4.451,
|
| 682 |
+
"step": 101
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 68.0,
|
| 686 |
+
"eval_accuracy": 0.625,
|
| 687 |
+
"eval_loss": 1.2091799974441528,
|
| 688 |
+
"eval_runtime": 0.2266,
|
| 689 |
+
"eval_samples_per_second": 35.297,
|
| 690 |
+
"eval_steps_per_second": 4.412,
|
| 691 |
+
"step": 102
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 69.0,
|
| 695 |
+
"eval_accuracy": 0.625,
|
| 696 |
+
"eval_loss": 1.2176190614700317,
|
| 697 |
+
"eval_runtime": 0.226,
|
| 698 |
+
"eval_samples_per_second": 35.4,
|
| 699 |
+
"eval_steps_per_second": 4.425,
|
| 700 |
+
"step": 103
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 70.0,
|
| 704 |
+
"eval_accuracy": 0.625,
|
| 705 |
+
"eval_loss": 1.2336797714233398,
|
| 706 |
+
"eval_runtime": 0.2275,
|
| 707 |
+
"eval_samples_per_second": 35.172,
|
| 708 |
+
"eval_steps_per_second": 4.397,
|
| 709 |
+
"step": 105
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 71.0,
|
| 713 |
+
"eval_accuracy": 0.625,
|
| 714 |
+
"eval_loss": 1.2376230955123901,
|
| 715 |
+
"eval_runtime": 0.2255,
|
| 716 |
+
"eval_samples_per_second": 35.481,
|
| 717 |
+
"eval_steps_per_second": 4.435,
|
| 718 |
+
"step": 107
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 72.0,
|
| 722 |
+
"eval_accuracy": 0.625,
|
| 723 |
+
"eval_loss": 1.238419532775879,
|
| 724 |
+
"eval_runtime": 0.2258,
|
| 725 |
+
"eval_samples_per_second": 35.428,
|
| 726 |
+
"eval_steps_per_second": 4.429,
|
| 727 |
+
"step": 108
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 73.0,
|
| 731 |
+
"eval_accuracy": 0.625,
|
| 732 |
+
"eval_loss": 1.2378357648849487,
|
| 733 |
+
"eval_runtime": 0.2254,
|
| 734 |
+
"eval_samples_per_second": 35.491,
|
| 735 |
+
"eval_steps_per_second": 4.436,
|
| 736 |
+
"step": 109
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 73.33333333333333,
|
| 740 |
+
"grad_norm": 16.670150756835938,
|
| 741 |
+
"learning_rate": 8.547008547008548e-06,
|
| 742 |
+
"loss": 0.1153,
|
| 743 |
+
"step": 110
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 74.0,
|
| 747 |
+
"eval_accuracy": 0.625,
|
| 748 |
+
"eval_loss": 1.238478183746338,
|
| 749 |
+
"eval_runtime": 0.2784,
|
| 750 |
+
"eval_samples_per_second": 28.737,
|
| 751 |
+
"eval_steps_per_second": 3.592,
|
| 752 |
+
"step": 111
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 75.0,
|
| 756 |
+
"eval_accuracy": 0.625,
|
| 757 |
+
"eval_loss": 1.2316068410873413,
|
| 758 |
+
"eval_runtime": 0.2262,
|
| 759 |
+
"eval_samples_per_second": 35.368,
|
| 760 |
+
"eval_steps_per_second": 4.421,
|
| 761 |
+
"step": 113
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 76.0,
|
| 765 |
+
"eval_accuracy": 0.625,
|
| 766 |
+
"eval_loss": 1.2274171113967896,
|
| 767 |
+
"eval_runtime": 0.226,
|
| 768 |
+
"eval_samples_per_second": 35.392,
|
| 769 |
+
"eval_steps_per_second": 4.424,
|
| 770 |
+
"step": 114
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 77.0,
|
| 774 |
+
"eval_accuracy": 0.625,
|
| 775 |
+
"eval_loss": 1.2251871824264526,
|
| 776 |
+
"eval_runtime": 0.2311,
|
| 777 |
+
"eval_samples_per_second": 34.618,
|
| 778 |
+
"eval_steps_per_second": 4.327,
|
| 779 |
+
"step": 115
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 78.0,
|
| 783 |
+
"eval_accuracy": 0.625,
|
| 784 |
+
"eval_loss": 1.2195590734481812,
|
| 785 |
+
"eval_runtime": 0.2344,
|
| 786 |
+
"eval_samples_per_second": 34.126,
|
| 787 |
+
"eval_steps_per_second": 4.266,
|
| 788 |
+
"step": 117
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 79.0,
|
| 792 |
+
"eval_accuracy": 0.625,
|
| 793 |
+
"eval_loss": 1.2144805192947388,
|
| 794 |
+
"eval_runtime": 0.2276,
|
| 795 |
+
"eval_samples_per_second": 35.145,
|
| 796 |
+
"eval_steps_per_second": 4.393,
|
| 797 |
+
"step": 119
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 80.0,
|
| 801 |
+
"grad_norm": 18.376235961914062,
|
| 802 |
+
"learning_rate": 4.273504273504274e-06,
|
| 803 |
+
"loss": 0.0882,
|
| 804 |
+
"step": 120
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 80.0,
|
| 808 |
+
"eval_accuracy": 0.625,
|
| 809 |
+
"eval_loss": 1.213006615638733,
|
| 810 |
+
"eval_runtime": 0.2356,
|
| 811 |
+
"eval_samples_per_second": 33.955,
|
| 812 |
+
"eval_steps_per_second": 4.244,
|
| 813 |
+
"step": 120
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 81.0,
|
| 817 |
+
"eval_accuracy": 0.625,
|
| 818 |
+
"eval_loss": 1.2117276191711426,
|
| 819 |
+
"eval_runtime": 0.2323,
|
| 820 |
+
"eval_samples_per_second": 34.443,
|
| 821 |
+
"eval_steps_per_second": 4.305,
|
| 822 |
+
"step": 121
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 82.0,
|
| 826 |
+
"eval_accuracy": 0.625,
|
| 827 |
+
"eval_loss": 1.2097160816192627,
|
| 828 |
+
"eval_runtime": 0.2308,
|
| 829 |
+
"eval_samples_per_second": 34.655,
|
| 830 |
+
"eval_steps_per_second": 4.332,
|
| 831 |
+
"step": 123
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 83.0,
|
| 835 |
+
"eval_accuracy": 0.625,
|
| 836 |
+
"eval_loss": 1.2075334787368774,
|
| 837 |
+
"eval_runtime": 0.2252,
|
| 838 |
+
"eval_samples_per_second": 35.532,
|
| 839 |
+
"eval_steps_per_second": 4.441,
|
| 840 |
+
"step": 125
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 84.0,
|
| 844 |
+
"eval_accuracy": 0.625,
|
| 845 |
+
"eval_loss": 1.205414056777954,
|
| 846 |
+
"eval_runtime": 0.2269,
|
| 847 |
+
"eval_samples_per_second": 35.264,
|
| 848 |
+
"eval_steps_per_second": 4.408,
|
| 849 |
+
"step": 126
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 85.0,
|
| 853 |
+
"eval_accuracy": 0.625,
|
| 854 |
+
"eval_loss": 1.2038739919662476,
|
| 855 |
+
"eval_runtime": 0.2445,
|
| 856 |
+
"eval_samples_per_second": 32.718,
|
| 857 |
+
"eval_steps_per_second": 4.09,
|
| 858 |
+
"step": 127
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 86.0,
|
| 862 |
+
"eval_accuracy": 0.625,
|
| 863 |
+
"eval_loss": 1.2025001049041748,
|
| 864 |
+
"eval_runtime": 0.244,
|
| 865 |
+
"eval_samples_per_second": 32.782,
|
| 866 |
+
"eval_steps_per_second": 4.098,
|
| 867 |
+
"step": 129
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 86.66666666666667,
|
| 871 |
+
"grad_norm": 6.174490928649902,
|
| 872 |
+
"learning_rate": 0.0,
|
| 873 |
+
"loss": 0.0987,
|
| 874 |
+
"step": 130
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 86.66666666666667,
|
| 878 |
+
"eval_accuracy": 0.625,
|
| 879 |
+
"eval_loss": 1.2021381855010986,
|
| 880 |
+
"eval_runtime": 0.2265,
|
| 881 |
+
"eval_samples_per_second": 35.317,
|
| 882 |
+
"eval_steps_per_second": 4.415,
|
| 883 |
+
"step": 130
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 86.66666666666667,
|
| 887 |
+
"step": 130,
|
| 888 |
+
"total_flos": 1.574865655328932e+17,
|
| 889 |
+
"train_loss": 0.3546037518061124,
|
| 890 |
+
"train_runtime": 225.362,
|
| 891 |
+
"train_samples_per_second": 41.533,
|
| 892 |
+
"train_steps_per_second": 0.577
|
| 893 |
+
}
|
| 894 |
+
],
|
| 895 |
+
"logging_steps": 10,
|
| 896 |
+
"max_steps": 130,
|
| 897 |
+
"num_input_tokens_seen": 0,
|
| 898 |
+
"num_train_epochs": 130,
|
| 899 |
+
"save_steps": 500,
|
| 900 |
+
"stateful_callbacks": {
|
| 901 |
+
"TrainerControl": {
|
| 902 |
+
"args": {
|
| 903 |
+
"should_epoch_stop": false,
|
| 904 |
+
"should_evaluate": false,
|
| 905 |
+
"should_log": false,
|
| 906 |
+
"should_save": false,
|
| 907 |
+
"should_training_stop": false
|
| 908 |
+
},
|
| 909 |
+
"attributes": {}
|
| 910 |
+
}
|
| 911 |
+
},
|
| 912 |
+
"total_flos": 1.574865655328932e+17,
|
| 913 |
+
"train_batch_size": 32,
|
| 914 |
+
"trial_name": null,
|
| 915 |
+
"trial_params": null
|
| 916 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a96c4a20e581fe9e08fca4557c67ff0e68b5b590c00d24f0cf2780c856e33981
|
| 3 |
+
size 5240
|