End of training
Browse files- README.md +155 -0
- all_results.json +12 -0
- config.json +60 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Dec10_11-37-53_DESKTOP-SKBE9FB/events.out.tfevents.1733852275.DESKTOP-SKBE9FB.15996.0 +3 -0
- runs/Dec10_11-37-53_DESKTOP-SKBE9FB/events.out.tfevents.1733854234.DESKTOP-SKBE9FB.15996.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1788 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: Swin-DMAE-H-DA-REVAL-80
|
| 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: validation
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.75
|
| 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 |
+
# Swin-DMAE-H-DA-REVAL-80
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.0766
|
| 36 |
+
- Accuracy: 0.75
|
| 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: 16
|
| 57 |
+
- eval_batch_size: 16
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 64
|
| 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: 80
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 1.608 | 0.97 | 22 | 1.6091 | 0.25 |
|
| 71 |
+
| 1.5899 | 1.98 | 45 | 1.5960 | 0.1923 |
|
| 72 |
+
| 1.4759 | 2.99 | 68 | 1.4430 | 0.3462 |
|
| 73 |
+
| 1.1012 | 4.0 | 91 | 1.3213 | 0.5192 |
|
| 74 |
+
| 0.8965 | 4.97 | 113 | 1.1938 | 0.4231 |
|
| 75 |
+
| 0.7214 | 5.98 | 136 | 1.1870 | 0.4615 |
|
| 76 |
+
| 0.6757 | 6.99 | 159 | 1.2117 | 0.5 |
|
| 77 |
+
| 0.5529 | 8.0 | 182 | 1.1976 | 0.4615 |
|
| 78 |
+
| 0.5279 | 8.97 | 204 | 1.1250 | 0.5192 |
|
| 79 |
+
| 0.4701 | 9.98 | 227 | 1.0999 | 0.5577 |
|
| 80 |
+
| 0.3721 | 10.99 | 250 | 0.7842 | 0.6538 |
|
| 81 |
+
| 0.3631 | 12.0 | 273 | 1.1728 | 0.6154 |
|
| 82 |
+
| 0.3384 | 12.97 | 295 | 1.2413 | 0.5769 |
|
| 83 |
+
| 0.2531 | 13.98 | 318 | 0.9144 | 0.6346 |
|
| 84 |
+
| 0.2753 | 14.99 | 341 | 0.8959 | 0.6923 |
|
| 85 |
+
| 0.2611 | 16.0 | 364 | 1.1399 | 0.6538 |
|
| 86 |
+
| 0.2072 | 16.97 | 386 | 1.0732 | 0.7115 |
|
| 87 |
+
| 0.2532 | 17.98 | 409 | 1.1922 | 0.7115 |
|
| 88 |
+
| 0.1633 | 18.99 | 432 | 1.0600 | 0.6731 |
|
| 89 |
+
| 0.1946 | 20.0 | 455 | 1.2289 | 0.6538 |
|
| 90 |
+
| 0.2214 | 20.97 | 477 | 1.3591 | 0.6731 |
|
| 91 |
+
| 0.1666 | 21.98 | 500 | 1.0736 | 0.7115 |
|
| 92 |
+
| 0.141 | 22.99 | 523 | 1.0315 | 0.6923 |
|
| 93 |
+
| 0.1275 | 24.0 | 546 | 1.0766 | 0.75 |
|
| 94 |
+
| 0.136 | 24.97 | 568 | 1.1796 | 0.7115 |
|
| 95 |
+
| 0.1402 | 25.98 | 591 | 1.0339 | 0.7115 |
|
| 96 |
+
| 0.1336 | 26.99 | 614 | 1.3446 | 0.6154 |
|
| 97 |
+
| 0.1218 | 28.0 | 637 | 1.2967 | 0.7115 |
|
| 98 |
+
| 0.1034 | 28.97 | 659 | 1.5955 | 0.6538 |
|
| 99 |
+
| 0.1196 | 29.98 | 682 | 1.5721 | 0.5769 |
|
| 100 |
+
| 0.1368 | 30.99 | 705 | 1.8208 | 0.6346 |
|
| 101 |
+
| 0.1477 | 32.0 | 728 | 1.4237 | 0.6923 |
|
| 102 |
+
| 0.1299 | 32.97 | 750 | 1.4061 | 0.7115 |
|
| 103 |
+
| 0.1111 | 33.98 | 773 | 1.6664 | 0.6346 |
|
| 104 |
+
| 0.068 | 34.99 | 796 | 1.7432 | 0.6538 |
|
| 105 |
+
| 0.1142 | 36.0 | 819 | 1.4518 | 0.6923 |
|
| 106 |
+
| 0.1258 | 36.97 | 841 | 1.7217 | 0.6346 |
|
| 107 |
+
| 0.1055 | 37.98 | 864 | 1.6348 | 0.6154 |
|
| 108 |
+
| 0.1049 | 38.99 | 887 | 1.8378 | 0.6346 |
|
| 109 |
+
| 0.0822 | 40.0 | 910 | 1.6760 | 0.6731 |
|
| 110 |
+
| 0.1114 | 40.97 | 932 | 1.7310 | 0.6346 |
|
| 111 |
+
| 0.0704 | 41.98 | 955 | 1.7105 | 0.6538 |
|
| 112 |
+
| 0.0983 | 42.99 | 978 | 1.8320 | 0.5962 |
|
| 113 |
+
| 0.0909 | 44.0 | 1001 | 1.5632 | 0.6346 |
|
| 114 |
+
| 0.0991 | 44.97 | 1023 | 1.7606 | 0.6731 |
|
| 115 |
+
| 0.0658 | 45.98 | 1046 | 1.5927 | 0.6538 |
|
| 116 |
+
| 0.0412 | 46.99 | 1069 | 1.4660 | 0.6538 |
|
| 117 |
+
| 0.0919 | 48.0 | 1092 | 1.3294 | 0.6731 |
|
| 118 |
+
| 0.0726 | 48.97 | 1114 | 1.5551 | 0.6346 |
|
| 119 |
+
| 0.0554 | 49.98 | 1137 | 1.7157 | 0.6154 |
|
| 120 |
+
| 0.0585 | 50.99 | 1160 | 1.8280 | 0.5962 |
|
| 121 |
+
| 0.0607 | 52.0 | 1183 | 1.6142 | 0.6538 |
|
| 122 |
+
| 0.0719 | 52.97 | 1205 | 1.9924 | 0.5962 |
|
| 123 |
+
| 0.0877 | 53.98 | 1228 | 1.7806 | 0.6346 |
|
| 124 |
+
| 0.0743 | 54.99 | 1251 | 1.9820 | 0.6538 |
|
| 125 |
+
| 0.0464 | 56.0 | 1274 | 1.9449 | 0.6346 |
|
| 126 |
+
| 0.077 | 56.97 | 1296 | 1.6826 | 0.6923 |
|
| 127 |
+
| 0.073 | 57.98 | 1319 | 1.7594 | 0.6538 |
|
| 128 |
+
| 0.0623 | 58.99 | 1342 | 1.8303 | 0.6346 |
|
| 129 |
+
| 0.0383 | 60.0 | 1365 | 1.8124 | 0.6154 |
|
| 130 |
+
| 0.0526 | 60.97 | 1387 | 1.8164 | 0.6923 |
|
| 131 |
+
| 0.0679 | 61.98 | 1410 | 1.8586 | 0.6731 |
|
| 132 |
+
| 0.0625 | 62.99 | 1433 | 1.9150 | 0.6346 |
|
| 133 |
+
| 0.0482 | 64.0 | 1456 | 1.9622 | 0.6346 |
|
| 134 |
+
| 0.0646 | 64.97 | 1478 | 1.9476 | 0.6154 |
|
| 135 |
+
| 0.0594 | 65.98 | 1501 | 1.5958 | 0.6923 |
|
| 136 |
+
| 0.0568 | 66.99 | 1524 | 1.8275 | 0.6731 |
|
| 137 |
+
| 0.0662 | 68.0 | 1547 | 1.7576 | 0.6731 |
|
| 138 |
+
| 0.0428 | 68.97 | 1569 | 1.9325 | 0.6538 |
|
| 139 |
+
| 0.0433 | 69.98 | 1592 | 1.8206 | 0.6731 |
|
| 140 |
+
| 0.0511 | 70.99 | 1615 | 1.9029 | 0.6538 |
|
| 141 |
+
| 0.0502 | 72.0 | 1638 | 1.8821 | 0.6538 |
|
| 142 |
+
| 0.0544 | 72.97 | 1660 | 1.9535 | 0.6538 |
|
| 143 |
+
| 0.0399 | 73.98 | 1683 | 1.8455 | 0.6538 |
|
| 144 |
+
| 0.0561 | 74.99 | 1706 | 1.8290 | 0.6538 |
|
| 145 |
+
| 0.041 | 76.0 | 1729 | 1.8427 | 0.6538 |
|
| 146 |
+
| 0.0582 | 76.97 | 1751 | 1.8591 | 0.6538 |
|
| 147 |
+
| 0.0315 | 77.36 | 1760 | 1.8612 | 0.6538 |
|
| 148 |
+
|
| 149 |
+
|
| 150 |
+
### Framework versions
|
| 151 |
+
|
| 152 |
+
- Transformers 4.36.2
|
| 153 |
+
- Pytorch 2.1.2+cu118
|
| 154 |
+
- Datasets 2.16.1
|
| 155 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 77.36,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 1.0766026973724365,
|
| 5 |
+
"eval_runtime": 0.8457,
|
| 6 |
+
"eval_samples_per_second": 61.488,
|
| 7 |
+
"eval_steps_per_second": 4.73,
|
| 8 |
+
"train_loss": 0.22083052936941386,
|
| 9 |
+
"train_runtime": 1958.4327,
|
| 10 |
+
"train_samples_per_second": 59.027,
|
| 11 |
+
"train_steps_per_second": 0.899
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Swinv2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"depths": [
|
| 8 |
+
2,
|
| 9 |
+
2,
|
| 10 |
+
6,
|
| 11 |
+
2
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.1,
|
| 14 |
+
"embed_dim": 96,
|
| 15 |
+
"encoder_stride": 32,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "avanzada",
|
| 21 |
+
"1": "avanzada humeda",
|
| 22 |
+
"2": "leve",
|
| 23 |
+
"3": "moderada",
|
| 24 |
+
"4": "no dmae"
|
| 25 |
+
},
|
| 26 |
+
"image_size": 256,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"avanzada": 0,
|
| 30 |
+
"avanzada humeda": 1,
|
| 31 |
+
"leve": 2,
|
| 32 |
+
"moderada": 3,
|
| 33 |
+
"no dmae": 4
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-05,
|
| 36 |
+
"mlp_ratio": 4.0,
|
| 37 |
+
"model_type": "swinv2",
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"num_heads": [
|
| 40 |
+
3,
|
| 41 |
+
6,
|
| 42 |
+
12,
|
| 43 |
+
24
|
| 44 |
+
],
|
| 45 |
+
"num_layers": 4,
|
| 46 |
+
"patch_size": 4,
|
| 47 |
+
"path_norm": true,
|
| 48 |
+
"pretrained_window_sizes": [
|
| 49 |
+
0,
|
| 50 |
+
0,
|
| 51 |
+
0,
|
| 52 |
+
0
|
| 53 |
+
],
|
| 54 |
+
"problem_type": "single_label_classification",
|
| 55 |
+
"qkv_bias": true,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.36.2",
|
| 58 |
+
"use_absolute_embeddings": false,
|
| 59 |
+
"window_size": 8
|
| 60 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 77.36,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 1.0766026973724365,
|
| 5 |
+
"eval_runtime": 0.8457,
|
| 6 |
+
"eval_samples_per_second": 61.488,
|
| 7 |
+
"eval_steps_per_second": 4.73
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b09130ef89f16643154258f57d22d0af2209e9dcb0e1cac0e94aeb3d45bf8f36
|
| 3 |
+
size 110359372
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 256,
|
| 20 |
+
"width": 256
|
| 21 |
+
}
|
| 22 |
+
}
|
runs/Dec10_11-37-53_DESKTOP-SKBE9FB/events.out.tfevents.1733852275.DESKTOP-SKBE9FB.15996.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5adb2296b33e8398895ed29f8d3b2cf78457d7ff88c4c3fc560962a19daf8cbd
|
| 3 |
+
size 57924
|
runs/Dec10_11-37-53_DESKTOP-SKBE9FB/events.out.tfevents.1733854234.DESKTOP-SKBE9FB.15996.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8208f228f1dc537af195ac5554cead50d644f3f05b0ab0443d38096fdf129c
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 77.36,
|
| 3 |
+
"train_loss": 0.22083052936941386,
|
| 4 |
+
"train_runtime": 1958.4327,
|
| 5 |
+
"train_samples_per_second": 59.027,
|
| 6 |
+
"train_steps_per_second": 0.899
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1788 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.75,
|
| 3 |
+
"best_model_checkpoint": "Swin-DMAE-H-DA-REVAL-80\\checkpoint-546",
|
| 4 |
+
"epoch": 77.36263736263736,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1760,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.44,
|
| 13 |
+
"learning_rate": 2.840909090909091e-06,
|
| 14 |
+
"loss": 1.6093,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.88,
|
| 19 |
+
"learning_rate": 5.681818181818182e-06,
|
| 20 |
+
"loss": 1.608,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.97,
|
| 25 |
+
"eval_accuracy": 0.25,
|
| 26 |
+
"eval_loss": 1.6090906858444214,
|
| 27 |
+
"eval_runtime": 0.9532,
|
| 28 |
+
"eval_samples_per_second": 54.552,
|
| 29 |
+
"eval_steps_per_second": 4.196,
|
| 30 |
+
"step": 22
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.32,
|
| 34 |
+
"learning_rate": 8.522727272727273e-06,
|
| 35 |
+
"loss": 1.6038,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.76,
|
| 40 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 41 |
+
"loss": 1.5899,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.98,
|
| 46 |
+
"eval_accuracy": 0.19230769230769232,
|
| 47 |
+
"eval_loss": 1.5960006713867188,
|
| 48 |
+
"eval_runtime": 0.6772,
|
| 49 |
+
"eval_samples_per_second": 76.791,
|
| 50 |
+
"eval_steps_per_second": 5.907,
|
| 51 |
+
"step": 45
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.2,
|
| 55 |
+
"learning_rate": 1.4204545454545456e-05,
|
| 56 |
+
"loss": 1.5458,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.64,
|
| 61 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 62 |
+
"loss": 1.4759,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.99,
|
| 67 |
+
"eval_accuracy": 0.34615384615384615,
|
| 68 |
+
"eval_loss": 1.4429875612258911,
|
| 69 |
+
"eval_runtime": 0.6507,
|
| 70 |
+
"eval_samples_per_second": 79.919,
|
| 71 |
+
"eval_steps_per_second": 6.148,
|
| 72 |
+
"step": 68
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.08,
|
| 76 |
+
"learning_rate": 1.9886363636363638e-05,
|
| 77 |
+
"loss": 1.3432,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.52,
|
| 82 |
+
"learning_rate": 2.272727272727273e-05,
|
| 83 |
+
"loss": 1.2227,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.96,
|
| 88 |
+
"learning_rate": 2.5568181818181817e-05,
|
| 89 |
+
"loss": 1.1012,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.0,
|
| 94 |
+
"eval_accuracy": 0.5192307692307693,
|
| 95 |
+
"eval_loss": 1.3212602138519287,
|
| 96 |
+
"eval_runtime": 0.6366,
|
| 97 |
+
"eval_samples_per_second": 81.678,
|
| 98 |
+
"eval_steps_per_second": 6.283,
|
| 99 |
+
"step": 91
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.4,
|
| 103 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 104 |
+
"loss": 0.9932,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.84,
|
| 109 |
+
"learning_rate": 3.125e-05,
|
| 110 |
+
"loss": 0.8965,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.97,
|
| 115 |
+
"eval_accuracy": 0.4230769230769231,
|
| 116 |
+
"eval_loss": 1.1938039064407349,
|
| 117 |
+
"eval_runtime": 0.7082,
|
| 118 |
+
"eval_samples_per_second": 73.43,
|
| 119 |
+
"eval_steps_per_second": 5.648,
|
| 120 |
+
"step": 113
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.27,
|
| 124 |
+
"learning_rate": 3.409090909090909e-05,
|
| 125 |
+
"loss": 0.8385,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.71,
|
| 130 |
+
"learning_rate": 3.6931818181818184e-05,
|
| 131 |
+
"loss": 0.7214,
|
| 132 |
+
"step": 130
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 5.98,
|
| 136 |
+
"eval_accuracy": 0.46153846153846156,
|
| 137 |
+
"eval_loss": 1.1870416402816772,
|
| 138 |
+
"eval_runtime": 0.6792,
|
| 139 |
+
"eval_samples_per_second": 76.566,
|
| 140 |
+
"eval_steps_per_second": 5.89,
|
| 141 |
+
"step": 136
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.15,
|
| 145 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 146 |
+
"loss": 0.6341,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.59,
|
| 151 |
+
"learning_rate": 4.261363636363637e-05,
|
| 152 |
+
"loss": 0.6757,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 6.99,
|
| 157 |
+
"eval_accuracy": 0.5,
|
| 158 |
+
"eval_loss": 1.2117116451263428,
|
| 159 |
+
"eval_runtime": 0.6842,
|
| 160 |
+
"eval_samples_per_second": 76.005,
|
| 161 |
+
"eval_steps_per_second": 5.847,
|
| 162 |
+
"step": 159
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.03,
|
| 166 |
+
"learning_rate": 4.545454545454546e-05,
|
| 167 |
+
"loss": 0.5533,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.47,
|
| 172 |
+
"learning_rate": 4.829545454545455e-05,
|
| 173 |
+
"loss": 0.5691,
|
| 174 |
+
"step": 170
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 7.91,
|
| 178 |
+
"learning_rate": 4.9873737373737375e-05,
|
| 179 |
+
"loss": 0.5529,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 8.0,
|
| 184 |
+
"eval_accuracy": 0.46153846153846156,
|
| 185 |
+
"eval_loss": 1.1975771188735962,
|
| 186 |
+
"eval_runtime": 0.6381,
|
| 187 |
+
"eval_samples_per_second": 81.486,
|
| 188 |
+
"eval_steps_per_second": 6.268,
|
| 189 |
+
"step": 182
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.35,
|
| 193 |
+
"learning_rate": 4.955808080808081e-05,
|
| 194 |
+
"loss": 0.4971,
|
| 195 |
+
"step": 190
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.79,
|
| 199 |
+
"learning_rate": 4.9242424242424245e-05,
|
| 200 |
+
"loss": 0.5279,
|
| 201 |
+
"step": 200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 8.97,
|
| 205 |
+
"eval_accuracy": 0.5192307692307693,
|
| 206 |
+
"eval_loss": 1.1249598264694214,
|
| 207 |
+
"eval_runtime": 0.6211,
|
| 208 |
+
"eval_samples_per_second": 83.717,
|
| 209 |
+
"eval_steps_per_second": 6.44,
|
| 210 |
+
"step": 204
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 9.23,
|
| 214 |
+
"learning_rate": 4.892676767676767e-05,
|
| 215 |
+
"loss": 0.5037,
|
| 216 |
+
"step": 210
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.67,
|
| 220 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 221 |
+
"loss": 0.4701,
|
| 222 |
+
"step": 220
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 9.98,
|
| 226 |
+
"eval_accuracy": 0.5576923076923077,
|
| 227 |
+
"eval_loss": 1.099881887435913,
|
| 228 |
+
"eval_runtime": 0.6342,
|
| 229 |
+
"eval_samples_per_second": 81.999,
|
| 230 |
+
"eval_steps_per_second": 6.308,
|
| 231 |
+
"step": 227
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.11,
|
| 235 |
+
"learning_rate": 4.829545454545455e-05,
|
| 236 |
+
"loss": 0.3906,
|
| 237 |
+
"step": 230
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 10.55,
|
| 241 |
+
"learning_rate": 4.797979797979798e-05,
|
| 242 |
+
"loss": 0.3812,
|
| 243 |
+
"step": 240
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 10.99,
|
| 247 |
+
"learning_rate": 4.7664141414141413e-05,
|
| 248 |
+
"loss": 0.3721,
|
| 249 |
+
"step": 250
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 10.99,
|
| 253 |
+
"eval_accuracy": 0.6538461538461539,
|
| 254 |
+
"eval_loss": 0.7842198014259338,
|
| 255 |
+
"eval_runtime": 0.6467,
|
| 256 |
+
"eval_samples_per_second": 80.414,
|
| 257 |
+
"eval_steps_per_second": 6.186,
|
| 258 |
+
"step": 250
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 11.43,
|
| 262 |
+
"learning_rate": 4.7348484848484855e-05,
|
| 263 |
+
"loss": 0.327,
|
| 264 |
+
"step": 260
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 11.87,
|
| 268 |
+
"learning_rate": 4.7032828282828283e-05,
|
| 269 |
+
"loss": 0.3631,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 12.0,
|
| 274 |
+
"eval_accuracy": 0.6153846153846154,
|
| 275 |
+
"eval_loss": 1.1728084087371826,
|
| 276 |
+
"eval_runtime": 0.7257,
|
| 277 |
+
"eval_samples_per_second": 71.658,
|
| 278 |
+
"eval_steps_per_second": 5.512,
|
| 279 |
+
"step": 273
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 12.31,
|
| 283 |
+
"learning_rate": 4.671717171717172e-05,
|
| 284 |
+
"loss": 0.335,
|
| 285 |
+
"step": 280
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 12.75,
|
| 289 |
+
"learning_rate": 4.6401515151515154e-05,
|
| 290 |
+
"loss": 0.3384,
|
| 291 |
+
"step": 290
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 12.97,
|
| 295 |
+
"eval_accuracy": 0.5769230769230769,
|
| 296 |
+
"eval_loss": 1.241263508796692,
|
| 297 |
+
"eval_runtime": 0.7252,
|
| 298 |
+
"eval_samples_per_second": 71.706,
|
| 299 |
+
"eval_steps_per_second": 5.516,
|
| 300 |
+
"step": 295
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 13.19,
|
| 304 |
+
"learning_rate": 4.608585858585859e-05,
|
| 305 |
+
"loss": 0.2861,
|
| 306 |
+
"step": 300
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 13.63,
|
| 310 |
+
"learning_rate": 4.5770202020202024e-05,
|
| 311 |
+
"loss": 0.2531,
|
| 312 |
+
"step": 310
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 13.98,
|
| 316 |
+
"eval_accuracy": 0.6346153846153846,
|
| 317 |
+
"eval_loss": 0.9144014716148376,
|
| 318 |
+
"eval_runtime": 0.6357,
|
| 319 |
+
"eval_samples_per_second": 81.806,
|
| 320 |
+
"eval_steps_per_second": 6.293,
|
| 321 |
+
"step": 318
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 14.07,
|
| 325 |
+
"learning_rate": 4.545454545454546e-05,
|
| 326 |
+
"loss": 0.2761,
|
| 327 |
+
"step": 320
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 14.51,
|
| 331 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 332 |
+
"loss": 0.2721,
|
| 333 |
+
"step": 330
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 14.95,
|
| 337 |
+
"learning_rate": 4.482323232323233e-05,
|
| 338 |
+
"loss": 0.2753,
|
| 339 |
+
"step": 340
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 14.99,
|
| 343 |
+
"eval_accuracy": 0.6923076923076923,
|
| 344 |
+
"eval_loss": 0.8958693146705627,
|
| 345 |
+
"eval_runtime": 0.6421,
|
| 346 |
+
"eval_samples_per_second": 80.979,
|
| 347 |
+
"eval_steps_per_second": 6.229,
|
| 348 |
+
"step": 341
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 15.38,
|
| 352 |
+
"learning_rate": 4.450757575757576e-05,
|
| 353 |
+
"loss": 0.2275,
|
| 354 |
+
"step": 350
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 15.82,
|
| 358 |
+
"learning_rate": 4.41919191919192e-05,
|
| 359 |
+
"loss": 0.2611,
|
| 360 |
+
"step": 360
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 16.0,
|
| 364 |
+
"eval_accuracy": 0.6538461538461539,
|
| 365 |
+
"eval_loss": 1.139877438545227,
|
| 366 |
+
"eval_runtime": 0.7657,
|
| 367 |
+
"eval_samples_per_second": 67.913,
|
| 368 |
+
"eval_steps_per_second": 5.224,
|
| 369 |
+
"step": 364
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 16.26,
|
| 373 |
+
"learning_rate": 4.387626262626263e-05,
|
| 374 |
+
"loss": 0.2614,
|
| 375 |
+
"step": 370
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 16.7,
|
| 379 |
+
"learning_rate": 4.356060606060606e-05,
|
| 380 |
+
"loss": 0.2072,
|
| 381 |
+
"step": 380
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 16.97,
|
| 385 |
+
"eval_accuracy": 0.7115384615384616,
|
| 386 |
+
"eval_loss": 1.0731658935546875,
|
| 387 |
+
"eval_runtime": 0.6391,
|
| 388 |
+
"eval_samples_per_second": 81.359,
|
| 389 |
+
"eval_steps_per_second": 6.258,
|
| 390 |
+
"step": 386
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 17.14,
|
| 394 |
+
"learning_rate": 4.32449494949495e-05,
|
| 395 |
+
"loss": 0.1875,
|
| 396 |
+
"step": 390
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 17.58,
|
| 400 |
+
"learning_rate": 4.292929292929293e-05,
|
| 401 |
+
"loss": 0.2532,
|
| 402 |
+
"step": 400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 17.98,
|
| 406 |
+
"eval_accuracy": 0.7115384615384616,
|
| 407 |
+
"eval_loss": 1.1921563148498535,
|
| 408 |
+
"eval_runtime": 0.7727,
|
| 409 |
+
"eval_samples_per_second": 67.298,
|
| 410 |
+
"eval_steps_per_second": 5.177,
|
| 411 |
+
"step": 409
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 18.02,
|
| 415 |
+
"learning_rate": 4.261363636363637e-05,
|
| 416 |
+
"loss": 0.1789,
|
| 417 |
+
"step": 410
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 18.46,
|
| 421 |
+
"learning_rate": 4.2297979797979795e-05,
|
| 422 |
+
"loss": 0.1653,
|
| 423 |
+
"step": 420
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 18.9,
|
| 427 |
+
"learning_rate": 4.198232323232324e-05,
|
| 428 |
+
"loss": 0.1633,
|
| 429 |
+
"step": 430
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 18.99,
|
| 433 |
+
"eval_accuracy": 0.6730769230769231,
|
| 434 |
+
"eval_loss": 1.059952974319458,
|
| 435 |
+
"eval_runtime": 0.6427,
|
| 436 |
+
"eval_samples_per_second": 80.914,
|
| 437 |
+
"eval_steps_per_second": 6.224,
|
| 438 |
+
"step": 432
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 19.34,
|
| 442 |
+
"learning_rate": 4.166666666666667e-05,
|
| 443 |
+
"loss": 0.1899,
|
| 444 |
+
"step": 440
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 19.78,
|
| 448 |
+
"learning_rate": 4.13510101010101e-05,
|
| 449 |
+
"loss": 0.1946,
|
| 450 |
+
"step": 450
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 20.0,
|
| 454 |
+
"eval_accuracy": 0.6538461538461539,
|
| 455 |
+
"eval_loss": 1.228935718536377,
|
| 456 |
+
"eval_runtime": 0.7167,
|
| 457 |
+
"eval_samples_per_second": 72.558,
|
| 458 |
+
"eval_steps_per_second": 5.581,
|
| 459 |
+
"step": 455
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 20.22,
|
| 463 |
+
"learning_rate": 4.1035353535353535e-05,
|
| 464 |
+
"loss": 0.1413,
|
| 465 |
+
"step": 460
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 20.66,
|
| 469 |
+
"learning_rate": 4.071969696969698e-05,
|
| 470 |
+
"loss": 0.2214,
|
| 471 |
+
"step": 470
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 20.97,
|
| 475 |
+
"eval_accuracy": 0.6730769230769231,
|
| 476 |
+
"eval_loss": 1.3590692281723022,
|
| 477 |
+
"eval_runtime": 0.6267,
|
| 478 |
+
"eval_samples_per_second": 82.98,
|
| 479 |
+
"eval_steps_per_second": 6.383,
|
| 480 |
+
"step": 477
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 21.1,
|
| 484 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 485 |
+
"loss": 0.1925,
|
| 486 |
+
"step": 480
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 21.54,
|
| 490 |
+
"learning_rate": 4.008838383838384e-05,
|
| 491 |
+
"loss": 0.1842,
|
| 492 |
+
"step": 490
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 21.98,
|
| 496 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 497 |
+
"loss": 0.1666,
|
| 498 |
+
"step": 500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 21.98,
|
| 502 |
+
"eval_accuracy": 0.7115384615384616,
|
| 503 |
+
"eval_loss": 1.0735695362091064,
|
| 504 |
+
"eval_runtime": 0.6487,
|
| 505 |
+
"eval_samples_per_second": 80.166,
|
| 506 |
+
"eval_steps_per_second": 6.167,
|
| 507 |
+
"step": 500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 22.42,
|
| 511 |
+
"learning_rate": 3.945707070707071e-05,
|
| 512 |
+
"loss": 0.1609,
|
| 513 |
+
"step": 510
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 22.86,
|
| 517 |
+
"learning_rate": 3.9141414141414145e-05,
|
| 518 |
+
"loss": 0.141,
|
| 519 |
+
"step": 520
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 22.99,
|
| 523 |
+
"eval_accuracy": 0.6923076923076923,
|
| 524 |
+
"eval_loss": 1.031468391418457,
|
| 525 |
+
"eval_runtime": 0.7467,
|
| 526 |
+
"eval_samples_per_second": 69.643,
|
| 527 |
+
"eval_steps_per_second": 5.357,
|
| 528 |
+
"step": 523
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 23.3,
|
| 532 |
+
"learning_rate": 3.8825757575757574e-05,
|
| 533 |
+
"loss": 0.1474,
|
| 534 |
+
"step": 530
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 23.74,
|
| 538 |
+
"learning_rate": 3.8510101010101015e-05,
|
| 539 |
+
"loss": 0.1275,
|
| 540 |
+
"step": 540
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 24.0,
|
| 544 |
+
"eval_accuracy": 0.75,
|
| 545 |
+
"eval_loss": 1.0766026973724365,
|
| 546 |
+
"eval_runtime": 0.6561,
|
| 547 |
+
"eval_samples_per_second": 79.25,
|
| 548 |
+
"eval_steps_per_second": 6.096,
|
| 549 |
+
"step": 546
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 24.18,
|
| 553 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 554 |
+
"loss": 0.1708,
|
| 555 |
+
"step": 550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 24.62,
|
| 559 |
+
"learning_rate": 3.787878787878788e-05,
|
| 560 |
+
"loss": 0.136,
|
| 561 |
+
"step": 560
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 24.97,
|
| 565 |
+
"eval_accuracy": 0.7115384615384616,
|
| 566 |
+
"eval_loss": 1.1796035766601562,
|
| 567 |
+
"eval_runtime": 0.6882,
|
| 568 |
+
"eval_samples_per_second": 75.564,
|
| 569 |
+
"eval_steps_per_second": 5.813,
|
| 570 |
+
"step": 568
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 25.05,
|
| 574 |
+
"learning_rate": 3.7563131313131314e-05,
|
| 575 |
+
"loss": 0.1539,
|
| 576 |
+
"step": 570
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 25.49,
|
| 580 |
+
"learning_rate": 3.724747474747475e-05,
|
| 581 |
+
"loss": 0.129,
|
| 582 |
+
"step": 580
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 25.93,
|
| 586 |
+
"learning_rate": 3.6931818181818184e-05,
|
| 587 |
+
"loss": 0.1402,
|
| 588 |
+
"step": 590
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 25.98,
|
| 592 |
+
"eval_accuracy": 0.7115384615384616,
|
| 593 |
+
"eval_loss": 1.0338743925094604,
|
| 594 |
+
"eval_runtime": 0.6301,
|
| 595 |
+
"eval_samples_per_second": 82.521,
|
| 596 |
+
"eval_steps_per_second": 6.348,
|
| 597 |
+
"step": 591
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 26.37,
|
| 601 |
+
"learning_rate": 3.661616161616162e-05,
|
| 602 |
+
"loss": 0.1492,
|
| 603 |
+
"step": 600
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 26.81,
|
| 607 |
+
"learning_rate": 3.6300505050505054e-05,
|
| 608 |
+
"loss": 0.1336,
|
| 609 |
+
"step": 610
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 26.99,
|
| 613 |
+
"eval_accuracy": 0.6153846153846154,
|
| 614 |
+
"eval_loss": 1.3445886373519897,
|
| 615 |
+
"eval_runtime": 0.6437,
|
| 616 |
+
"eval_samples_per_second": 80.789,
|
| 617 |
+
"eval_steps_per_second": 6.215,
|
| 618 |
+
"step": 614
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 27.25,
|
| 622 |
+
"learning_rate": 3.598484848484849e-05,
|
| 623 |
+
"loss": 0.0881,
|
| 624 |
+
"step": 620
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 27.69,
|
| 628 |
+
"learning_rate": 3.566919191919192e-05,
|
| 629 |
+
"loss": 0.1218,
|
| 630 |
+
"step": 630
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 28.0,
|
| 634 |
+
"eval_accuracy": 0.7115384615384616,
|
| 635 |
+
"eval_loss": 1.2967442274093628,
|
| 636 |
+
"eval_runtime": 0.6371,
|
| 637 |
+
"eval_samples_per_second": 81.614,
|
| 638 |
+
"eval_steps_per_second": 6.278,
|
| 639 |
+
"step": 637
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 28.13,
|
| 643 |
+
"learning_rate": 3.535353535353535e-05,
|
| 644 |
+
"loss": 0.1095,
|
| 645 |
+
"step": 640
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 28.57,
|
| 649 |
+
"learning_rate": 3.5037878787878794e-05,
|
| 650 |
+
"loss": 0.1034,
|
| 651 |
+
"step": 650
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 28.97,
|
| 655 |
+
"eval_accuracy": 0.6538461538461539,
|
| 656 |
+
"eval_loss": 1.5955091714859009,
|
| 657 |
+
"eval_runtime": 0.6367,
|
| 658 |
+
"eval_samples_per_second": 81.675,
|
| 659 |
+
"eval_steps_per_second": 6.283,
|
| 660 |
+
"step": 659
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 29.01,
|
| 664 |
+
"learning_rate": 3.472222222222222e-05,
|
| 665 |
+
"loss": 0.1467,
|
| 666 |
+
"step": 660
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 29.45,
|
| 670 |
+
"learning_rate": 3.440656565656566e-05,
|
| 671 |
+
"loss": 0.1292,
|
| 672 |
+
"step": 670
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 29.89,
|
| 676 |
+
"learning_rate": 3.409090909090909e-05,
|
| 677 |
+
"loss": 0.1196,
|
| 678 |
+
"step": 680
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 29.98,
|
| 682 |
+
"eval_accuracy": 0.5769230769230769,
|
| 683 |
+
"eval_loss": 1.5720566511154175,
|
| 684 |
+
"eval_runtime": 0.6382,
|
| 685 |
+
"eval_samples_per_second": 81.484,
|
| 686 |
+
"eval_steps_per_second": 6.268,
|
| 687 |
+
"step": 682
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 30.33,
|
| 691 |
+
"learning_rate": 3.377525252525253e-05,
|
| 692 |
+
"loss": 0.0938,
|
| 693 |
+
"step": 690
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 30.77,
|
| 697 |
+
"learning_rate": 3.345959595959596e-05,
|
| 698 |
+
"loss": 0.1368,
|
| 699 |
+
"step": 700
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 30.99,
|
| 703 |
+
"eval_accuracy": 0.6346153846153846,
|
| 704 |
+
"eval_loss": 1.8208184242248535,
|
| 705 |
+
"eval_runtime": 0.6327,
|
| 706 |
+
"eval_samples_per_second": 82.194,
|
| 707 |
+
"eval_steps_per_second": 6.323,
|
| 708 |
+
"step": 705
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 31.21,
|
| 712 |
+
"learning_rate": 3.314393939393939e-05,
|
| 713 |
+
"loss": 0.1194,
|
| 714 |
+
"step": 710
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 31.65,
|
| 718 |
+
"learning_rate": 3.282828282828283e-05,
|
| 719 |
+
"loss": 0.1477,
|
| 720 |
+
"step": 720
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 32.0,
|
| 724 |
+
"eval_accuracy": 0.6923076923076923,
|
| 725 |
+
"eval_loss": 1.4237351417541504,
|
| 726 |
+
"eval_runtime": 0.6551,
|
| 727 |
+
"eval_samples_per_second": 79.371,
|
| 728 |
+
"eval_steps_per_second": 6.105,
|
| 729 |
+
"step": 728
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 32.09,
|
| 733 |
+
"learning_rate": 3.251262626262627e-05,
|
| 734 |
+
"loss": 0.1274,
|
| 735 |
+
"step": 730
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 32.53,
|
| 739 |
+
"learning_rate": 3.2196969696969696e-05,
|
| 740 |
+
"loss": 0.1198,
|
| 741 |
+
"step": 740
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 32.97,
|
| 745 |
+
"learning_rate": 3.188131313131314e-05,
|
| 746 |
+
"loss": 0.1299,
|
| 747 |
+
"step": 750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 32.97,
|
| 751 |
+
"eval_accuracy": 0.7115384615384616,
|
| 752 |
+
"eval_loss": 1.4061400890350342,
|
| 753 |
+
"eval_runtime": 0.6447,
|
| 754 |
+
"eval_samples_per_second": 80.663,
|
| 755 |
+
"eval_steps_per_second": 6.205,
|
| 756 |
+
"step": 750
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 33.41,
|
| 760 |
+
"learning_rate": 3.1565656565656566e-05,
|
| 761 |
+
"loss": 0.0806,
|
| 762 |
+
"step": 760
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 33.85,
|
| 766 |
+
"learning_rate": 3.125e-05,
|
| 767 |
+
"loss": 0.1111,
|
| 768 |
+
"step": 770
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 33.98,
|
| 772 |
+
"eval_accuracy": 0.6346153846153846,
|
| 773 |
+
"eval_loss": 1.666426420211792,
|
| 774 |
+
"eval_runtime": 0.6892,
|
| 775 |
+
"eval_samples_per_second": 75.455,
|
| 776 |
+
"eval_steps_per_second": 5.804,
|
| 777 |
+
"step": 773
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 34.29,
|
| 781 |
+
"learning_rate": 3.0934343434343436e-05,
|
| 782 |
+
"loss": 0.0773,
|
| 783 |
+
"step": 780
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 34.73,
|
| 787 |
+
"learning_rate": 3.061868686868687e-05,
|
| 788 |
+
"loss": 0.068,
|
| 789 |
+
"step": 790
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 34.99,
|
| 793 |
+
"eval_accuracy": 0.6538461538461539,
|
| 794 |
+
"eval_loss": 1.7432496547698975,
|
| 795 |
+
"eval_runtime": 0.7027,
|
| 796 |
+
"eval_samples_per_second": 74.004,
|
| 797 |
+
"eval_steps_per_second": 5.693,
|
| 798 |
+
"step": 796
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 35.16,
|
| 802 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 803 |
+
"loss": 0.1432,
|
| 804 |
+
"step": 800
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 35.6,
|
| 808 |
+
"learning_rate": 2.9987373737373737e-05,
|
| 809 |
+
"loss": 0.1142,
|
| 810 |
+
"step": 810
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 36.0,
|
| 814 |
+
"eval_accuracy": 0.6923076923076923,
|
| 815 |
+
"eval_loss": 1.4517791271209717,
|
| 816 |
+
"eval_runtime": 0.6291,
|
| 817 |
+
"eval_samples_per_second": 82.652,
|
| 818 |
+
"eval_steps_per_second": 6.358,
|
| 819 |
+
"step": 819
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 36.04,
|
| 823 |
+
"learning_rate": 2.9671717171717172e-05,
|
| 824 |
+
"loss": 0.1228,
|
| 825 |
+
"step": 820
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 36.48,
|
| 829 |
+
"learning_rate": 2.935606060606061e-05,
|
| 830 |
+
"loss": 0.0968,
|
| 831 |
+
"step": 830
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 36.92,
|
| 835 |
+
"learning_rate": 2.904040404040404e-05,
|
| 836 |
+
"loss": 0.1258,
|
| 837 |
+
"step": 840
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 36.97,
|
| 841 |
+
"eval_accuracy": 0.6346153846153846,
|
| 842 |
+
"eval_loss": 1.7216651439666748,
|
| 843 |
+
"eval_runtime": 0.7027,
|
| 844 |
+
"eval_samples_per_second": 74.003,
|
| 845 |
+
"eval_steps_per_second": 5.693,
|
| 846 |
+
"step": 841
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 37.36,
|
| 850 |
+
"learning_rate": 2.8724747474747477e-05,
|
| 851 |
+
"loss": 0.0971,
|
| 852 |
+
"step": 850
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 37.8,
|
| 856 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 857 |
+
"loss": 0.1055,
|
| 858 |
+
"step": 860
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 37.98,
|
| 862 |
+
"eval_accuracy": 0.6153846153846154,
|
| 863 |
+
"eval_loss": 1.6348490715026855,
|
| 864 |
+
"eval_runtime": 0.6862,
|
| 865 |
+
"eval_samples_per_second": 75.785,
|
| 866 |
+
"eval_steps_per_second": 5.83,
|
| 867 |
+
"step": 864
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 38.24,
|
| 871 |
+
"learning_rate": 2.8093434343434344e-05,
|
| 872 |
+
"loss": 0.1109,
|
| 873 |
+
"step": 870
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 38.68,
|
| 877 |
+
"learning_rate": 2.777777777777778e-05,
|
| 878 |
+
"loss": 0.1049,
|
| 879 |
+
"step": 880
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 38.99,
|
| 883 |
+
"eval_accuracy": 0.6346153846153846,
|
| 884 |
+
"eval_loss": 1.837777853012085,
|
| 885 |
+
"eval_runtime": 0.7382,
|
| 886 |
+
"eval_samples_per_second": 70.445,
|
| 887 |
+
"eval_steps_per_second": 5.419,
|
| 888 |
+
"step": 887
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 39.12,
|
| 892 |
+
"learning_rate": 2.746212121212121e-05,
|
| 893 |
+
"loss": 0.0726,
|
| 894 |
+
"step": 890
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 39.56,
|
| 898 |
+
"learning_rate": 2.714646464646465e-05,
|
| 899 |
+
"loss": 0.0672,
|
| 900 |
+
"step": 900
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 40.0,
|
| 904 |
+
"learning_rate": 2.6830808080808084e-05,
|
| 905 |
+
"loss": 0.0822,
|
| 906 |
+
"step": 910
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 40.0,
|
| 910 |
+
"eval_accuracy": 0.6730769230769231,
|
| 911 |
+
"eval_loss": 1.6760356426239014,
|
| 912 |
+
"eval_runtime": 0.6697,
|
| 913 |
+
"eval_samples_per_second": 77.651,
|
| 914 |
+
"eval_steps_per_second": 5.973,
|
| 915 |
+
"step": 910
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 40.44,
|
| 919 |
+
"learning_rate": 2.6515151515151516e-05,
|
| 920 |
+
"loss": 0.0798,
|
| 921 |
+
"step": 920
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 40.88,
|
| 925 |
+
"learning_rate": 2.619949494949495e-05,
|
| 926 |
+
"loss": 0.1114,
|
| 927 |
+
"step": 930
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 40.97,
|
| 931 |
+
"eval_accuracy": 0.6346153846153846,
|
| 932 |
+
"eval_loss": 1.7310110330581665,
|
| 933 |
+
"eval_runtime": 0.7447,
|
| 934 |
+
"eval_samples_per_second": 69.829,
|
| 935 |
+
"eval_steps_per_second": 5.371,
|
| 936 |
+
"step": 932
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 41.32,
|
| 940 |
+
"learning_rate": 2.5883838383838382e-05,
|
| 941 |
+
"loss": 0.0942,
|
| 942 |
+
"step": 940
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 41.76,
|
| 946 |
+
"learning_rate": 2.5568181818181817e-05,
|
| 947 |
+
"loss": 0.0704,
|
| 948 |
+
"step": 950
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 41.98,
|
| 952 |
+
"eval_accuracy": 0.6538461538461539,
|
| 953 |
+
"eval_loss": 1.7105393409729004,
|
| 954 |
+
"eval_runtime": 0.6411,
|
| 955 |
+
"eval_samples_per_second": 81.105,
|
| 956 |
+
"eval_steps_per_second": 6.239,
|
| 957 |
+
"step": 955
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 42.2,
|
| 961 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 962 |
+
"loss": 0.115,
|
| 963 |
+
"step": 960
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 42.64,
|
| 967 |
+
"learning_rate": 2.4936868686868688e-05,
|
| 968 |
+
"loss": 0.0983,
|
| 969 |
+
"step": 970
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 42.99,
|
| 973 |
+
"eval_accuracy": 0.5961538461538461,
|
| 974 |
+
"eval_loss": 1.8320040702819824,
|
| 975 |
+
"eval_runtime": 0.6571,
|
| 976 |
+
"eval_samples_per_second": 79.13,
|
| 977 |
+
"eval_steps_per_second": 6.087,
|
| 978 |
+
"step": 978
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 43.08,
|
| 982 |
+
"learning_rate": 2.4621212121212123e-05,
|
| 983 |
+
"loss": 0.0707,
|
| 984 |
+
"step": 980
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 43.52,
|
| 988 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 989 |
+
"loss": 0.0665,
|
| 990 |
+
"step": 990
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 43.96,
|
| 994 |
+
"learning_rate": 2.398989898989899e-05,
|
| 995 |
+
"loss": 0.0909,
|
| 996 |
+
"step": 1000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 44.0,
|
| 1000 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1001 |
+
"eval_loss": 1.563212275505066,
|
| 1002 |
+
"eval_runtime": 0.7357,
|
| 1003 |
+
"eval_samples_per_second": 70.683,
|
| 1004 |
+
"eval_steps_per_second": 5.437,
|
| 1005 |
+
"step": 1001
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 44.4,
|
| 1009 |
+
"learning_rate": 2.3674242424242428e-05,
|
| 1010 |
+
"loss": 0.1091,
|
| 1011 |
+
"step": 1010
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 44.84,
|
| 1015 |
+
"learning_rate": 2.335858585858586e-05,
|
| 1016 |
+
"loss": 0.0991,
|
| 1017 |
+
"step": 1020
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 44.97,
|
| 1021 |
+
"eval_accuracy": 0.6730769230769231,
|
| 1022 |
+
"eval_loss": 1.7606291770935059,
|
| 1023 |
+
"eval_runtime": 0.6397,
|
| 1024 |
+
"eval_samples_per_second": 81.294,
|
| 1025 |
+
"eval_steps_per_second": 6.253,
|
| 1026 |
+
"step": 1023
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 45.27,
|
| 1030 |
+
"learning_rate": 2.3042929292929294e-05,
|
| 1031 |
+
"loss": 0.0821,
|
| 1032 |
+
"step": 1030
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 45.71,
|
| 1036 |
+
"learning_rate": 2.272727272727273e-05,
|
| 1037 |
+
"loss": 0.0658,
|
| 1038 |
+
"step": 1040
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 45.98,
|
| 1042 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1043 |
+
"eval_loss": 1.592665433883667,
|
| 1044 |
+
"eval_runtime": 0.6456,
|
| 1045 |
+
"eval_samples_per_second": 80.539,
|
| 1046 |
+
"eval_steps_per_second": 6.195,
|
| 1047 |
+
"step": 1046
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 46.15,
|
| 1051 |
+
"learning_rate": 2.2411616161616164e-05,
|
| 1052 |
+
"loss": 0.0869,
|
| 1053 |
+
"step": 1050
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 46.59,
|
| 1057 |
+
"learning_rate": 2.20959595959596e-05,
|
| 1058 |
+
"loss": 0.0412,
|
| 1059 |
+
"step": 1060
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 46.99,
|
| 1063 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1064 |
+
"eval_loss": 1.4660203456878662,
|
| 1065 |
+
"eval_runtime": 0.6371,
|
| 1066 |
+
"eval_samples_per_second": 81.614,
|
| 1067 |
+
"eval_steps_per_second": 6.278,
|
| 1068 |
+
"step": 1069
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 47.03,
|
| 1072 |
+
"learning_rate": 2.178030303030303e-05,
|
| 1073 |
+
"loss": 0.084,
|
| 1074 |
+
"step": 1070
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 47.47,
|
| 1078 |
+
"learning_rate": 2.1464646464646466e-05,
|
| 1079 |
+
"loss": 0.0618,
|
| 1080 |
+
"step": 1080
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 47.91,
|
| 1084 |
+
"learning_rate": 2.1148989898989898e-05,
|
| 1085 |
+
"loss": 0.0919,
|
| 1086 |
+
"step": 1090
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 48.0,
|
| 1090 |
+
"eval_accuracy": 0.6730769230769231,
|
| 1091 |
+
"eval_loss": 1.3294285535812378,
|
| 1092 |
+
"eval_runtime": 0.6842,
|
| 1093 |
+
"eval_samples_per_second": 76.006,
|
| 1094 |
+
"eval_steps_per_second": 5.847,
|
| 1095 |
+
"step": 1092
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 48.35,
|
| 1099 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 1100 |
+
"loss": 0.0733,
|
| 1101 |
+
"step": 1100
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 48.79,
|
| 1105 |
+
"learning_rate": 2.0517676767676768e-05,
|
| 1106 |
+
"loss": 0.0726,
|
| 1107 |
+
"step": 1110
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 48.97,
|
| 1111 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1112 |
+
"eval_loss": 1.5551464557647705,
|
| 1113 |
+
"eval_runtime": 0.6647,
|
| 1114 |
+
"eval_samples_per_second": 78.236,
|
| 1115 |
+
"eval_steps_per_second": 6.018,
|
| 1116 |
+
"step": 1114
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 49.23,
|
| 1120 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 1121 |
+
"loss": 0.0662,
|
| 1122 |
+
"step": 1120
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 49.67,
|
| 1126 |
+
"learning_rate": 1.9886363636363638e-05,
|
| 1127 |
+
"loss": 0.0554,
|
| 1128 |
+
"step": 1130
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 49.98,
|
| 1132 |
+
"eval_accuracy": 0.6153846153846154,
|
| 1133 |
+
"eval_loss": 1.7157161235809326,
|
| 1134 |
+
"eval_runtime": 0.6597,
|
| 1135 |
+
"eval_samples_per_second": 78.829,
|
| 1136 |
+
"eval_steps_per_second": 6.064,
|
| 1137 |
+
"step": 1137
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 50.11,
|
| 1141 |
+
"learning_rate": 1.9570707070707073e-05,
|
| 1142 |
+
"loss": 0.0697,
|
| 1143 |
+
"step": 1140
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 50.55,
|
| 1147 |
+
"learning_rate": 1.9255050505050508e-05,
|
| 1148 |
+
"loss": 0.1054,
|
| 1149 |
+
"step": 1150
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 50.99,
|
| 1153 |
+
"learning_rate": 1.893939393939394e-05,
|
| 1154 |
+
"loss": 0.0585,
|
| 1155 |
+
"step": 1160
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 50.99,
|
| 1159 |
+
"eval_accuracy": 0.5961538461538461,
|
| 1160 |
+
"eval_loss": 1.8279716968536377,
|
| 1161 |
+
"eval_runtime": 0.6462,
|
| 1162 |
+
"eval_samples_per_second": 80.475,
|
| 1163 |
+
"eval_steps_per_second": 6.19,
|
| 1164 |
+
"step": 1160
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 51.43,
|
| 1168 |
+
"learning_rate": 1.8623737373737374e-05,
|
| 1169 |
+
"loss": 0.0821,
|
| 1170 |
+
"step": 1170
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 51.87,
|
| 1174 |
+
"learning_rate": 1.830808080808081e-05,
|
| 1175 |
+
"loss": 0.0607,
|
| 1176 |
+
"step": 1180
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 52.0,
|
| 1180 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1181 |
+
"eval_loss": 1.6141858100891113,
|
| 1182 |
+
"eval_runtime": 0.6587,
|
| 1183 |
+
"eval_samples_per_second": 78.949,
|
| 1184 |
+
"eval_steps_per_second": 6.073,
|
| 1185 |
+
"step": 1183
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 52.31,
|
| 1189 |
+
"learning_rate": 1.7992424242424244e-05,
|
| 1190 |
+
"loss": 0.0444,
|
| 1191 |
+
"step": 1190
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 52.75,
|
| 1195 |
+
"learning_rate": 1.7676767676767676e-05,
|
| 1196 |
+
"loss": 0.0719,
|
| 1197 |
+
"step": 1200
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 52.97,
|
| 1201 |
+
"eval_accuracy": 0.5961538461538461,
|
| 1202 |
+
"eval_loss": 1.992350459098816,
|
| 1203 |
+
"eval_runtime": 0.6432,
|
| 1204 |
+
"eval_samples_per_second": 80.851,
|
| 1205 |
+
"eval_steps_per_second": 6.219,
|
| 1206 |
+
"step": 1205
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 53.19,
|
| 1210 |
+
"learning_rate": 1.736111111111111e-05,
|
| 1211 |
+
"loss": 0.1031,
|
| 1212 |
+
"step": 1210
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 53.63,
|
| 1216 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 1217 |
+
"loss": 0.0877,
|
| 1218 |
+
"step": 1220
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 53.98,
|
| 1222 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1223 |
+
"eval_loss": 1.7806010246276855,
|
| 1224 |
+
"eval_runtime": 0.6742,
|
| 1225 |
+
"eval_samples_per_second": 77.134,
|
| 1226 |
+
"eval_steps_per_second": 5.933,
|
| 1227 |
+
"step": 1228
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 54.07,
|
| 1231 |
+
"learning_rate": 1.672979797979798e-05,
|
| 1232 |
+
"loss": 0.0783,
|
| 1233 |
+
"step": 1230
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 54.51,
|
| 1237 |
+
"learning_rate": 1.6414141414141416e-05,
|
| 1238 |
+
"loss": 0.0664,
|
| 1239 |
+
"step": 1240
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 54.95,
|
| 1243 |
+
"learning_rate": 1.6098484848484848e-05,
|
| 1244 |
+
"loss": 0.0743,
|
| 1245 |
+
"step": 1250
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 54.99,
|
| 1249 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1250 |
+
"eval_loss": 1.9819928407669067,
|
| 1251 |
+
"eval_runtime": 0.7032,
|
| 1252 |
+
"eval_samples_per_second": 73.95,
|
| 1253 |
+
"eval_steps_per_second": 5.688,
|
| 1254 |
+
"step": 1251
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 55.38,
|
| 1258 |
+
"learning_rate": 1.5782828282828283e-05,
|
| 1259 |
+
"loss": 0.0652,
|
| 1260 |
+
"step": 1260
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 55.82,
|
| 1264 |
+
"learning_rate": 1.5467171717171718e-05,
|
| 1265 |
+
"loss": 0.0464,
|
| 1266 |
+
"step": 1270
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 56.0,
|
| 1270 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1271 |
+
"eval_loss": 1.944918155670166,
|
| 1272 |
+
"eval_runtime": 0.6432,
|
| 1273 |
+
"eval_samples_per_second": 80.851,
|
| 1274 |
+
"eval_steps_per_second": 6.219,
|
| 1275 |
+
"step": 1274
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 56.26,
|
| 1279 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 1280 |
+
"loss": 0.0522,
|
| 1281 |
+
"step": 1280
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 56.7,
|
| 1285 |
+
"learning_rate": 1.4835858585858586e-05,
|
| 1286 |
+
"loss": 0.077,
|
| 1287 |
+
"step": 1290
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 56.97,
|
| 1291 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1292 |
+
"eval_loss": 1.6825530529022217,
|
| 1293 |
+
"eval_runtime": 0.6687,
|
| 1294 |
+
"eval_samples_per_second": 77.768,
|
| 1295 |
+
"eval_steps_per_second": 5.982,
|
| 1296 |
+
"step": 1296
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 57.14,
|
| 1300 |
+
"learning_rate": 1.452020202020202e-05,
|
| 1301 |
+
"loss": 0.0688,
|
| 1302 |
+
"step": 1300
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 57.58,
|
| 1306 |
+
"learning_rate": 1.4204545454545456e-05,
|
| 1307 |
+
"loss": 0.073,
|
| 1308 |
+
"step": 1310
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 57.98,
|
| 1312 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1313 |
+
"eval_loss": 1.7594443559646606,
|
| 1314 |
+
"eval_runtime": 0.6671,
|
| 1315 |
+
"eval_samples_per_second": 77.944,
|
| 1316 |
+
"eval_steps_per_second": 5.996,
|
| 1317 |
+
"step": 1319
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 58.02,
|
| 1321 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1322 |
+
"loss": 0.0488,
|
| 1323 |
+
"step": 1320
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 58.46,
|
| 1327 |
+
"learning_rate": 1.3573232323232325e-05,
|
| 1328 |
+
"loss": 0.0568,
|
| 1329 |
+
"step": 1330
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 58.9,
|
| 1333 |
+
"learning_rate": 1.3257575757575758e-05,
|
| 1334 |
+
"loss": 0.0623,
|
| 1335 |
+
"step": 1340
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 58.99,
|
| 1339 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1340 |
+
"eval_loss": 1.8303287029266357,
|
| 1341 |
+
"eval_runtime": 0.6563,
|
| 1342 |
+
"eval_samples_per_second": 79.235,
|
| 1343 |
+
"eval_steps_per_second": 6.095,
|
| 1344 |
+
"step": 1342
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 59.34,
|
| 1348 |
+
"learning_rate": 1.2941919191919191e-05,
|
| 1349 |
+
"loss": 0.0818,
|
| 1350 |
+
"step": 1350
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 59.78,
|
| 1354 |
+
"learning_rate": 1.2626262626262628e-05,
|
| 1355 |
+
"loss": 0.0383,
|
| 1356 |
+
"step": 1360
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 60.0,
|
| 1360 |
+
"eval_accuracy": 0.6153846153846154,
|
| 1361 |
+
"eval_loss": 1.8124154806137085,
|
| 1362 |
+
"eval_runtime": 0.6437,
|
| 1363 |
+
"eval_samples_per_second": 80.789,
|
| 1364 |
+
"eval_steps_per_second": 6.215,
|
| 1365 |
+
"step": 1365
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 60.22,
|
| 1369 |
+
"learning_rate": 1.2310606060606061e-05,
|
| 1370 |
+
"loss": 0.0486,
|
| 1371 |
+
"step": 1370
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 60.66,
|
| 1375 |
+
"learning_rate": 1.1994949494949495e-05,
|
| 1376 |
+
"loss": 0.0526,
|
| 1377 |
+
"step": 1380
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 60.97,
|
| 1381 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1382 |
+
"eval_loss": 1.8164315223693848,
|
| 1383 |
+
"eval_runtime": 0.6712,
|
| 1384 |
+
"eval_samples_per_second": 77.479,
|
| 1385 |
+
"eval_steps_per_second": 5.96,
|
| 1386 |
+
"step": 1387
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 61.1,
|
| 1390 |
+
"learning_rate": 1.167929292929293e-05,
|
| 1391 |
+
"loss": 0.0676,
|
| 1392 |
+
"step": 1390
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 61.54,
|
| 1396 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 1397 |
+
"loss": 0.0482,
|
| 1398 |
+
"step": 1400
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 61.98,
|
| 1402 |
+
"learning_rate": 1.10479797979798e-05,
|
| 1403 |
+
"loss": 0.0679,
|
| 1404 |
+
"step": 1410
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 61.98,
|
| 1408 |
+
"eval_accuracy": 0.6730769230769231,
|
| 1409 |
+
"eval_loss": 1.8585782051086426,
|
| 1410 |
+
"eval_runtime": 0.6812,
|
| 1411 |
+
"eval_samples_per_second": 76.341,
|
| 1412 |
+
"eval_steps_per_second": 5.872,
|
| 1413 |
+
"step": 1410
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 62.42,
|
| 1417 |
+
"learning_rate": 1.0732323232323233e-05,
|
| 1418 |
+
"loss": 0.0791,
|
| 1419 |
+
"step": 1420
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 62.86,
|
| 1423 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 1424 |
+
"loss": 0.0625,
|
| 1425 |
+
"step": 1430
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 62.99,
|
| 1429 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1430 |
+
"eval_loss": 1.9150481224060059,
|
| 1431 |
+
"eval_runtime": 0.7422,
|
| 1432 |
+
"eval_samples_per_second": 70.065,
|
| 1433 |
+
"eval_steps_per_second": 5.39,
|
| 1434 |
+
"step": 1433
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 63.3,
|
| 1438 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 1439 |
+
"loss": 0.0363,
|
| 1440 |
+
"step": 1440
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 63.74,
|
| 1444 |
+
"learning_rate": 9.785353535353536e-06,
|
| 1445 |
+
"loss": 0.0482,
|
| 1446 |
+
"step": 1450
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 64.0,
|
| 1450 |
+
"eval_accuracy": 0.6346153846153846,
|
| 1451 |
+
"eval_loss": 1.9622400999069214,
|
| 1452 |
+
"eval_runtime": 0.6337,
|
| 1453 |
+
"eval_samples_per_second": 82.064,
|
| 1454 |
+
"eval_steps_per_second": 6.313,
|
| 1455 |
+
"step": 1456
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 64.18,
|
| 1459 |
+
"learning_rate": 9.46969696969697e-06,
|
| 1460 |
+
"loss": 0.071,
|
| 1461 |
+
"step": 1460
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 64.62,
|
| 1465 |
+
"learning_rate": 9.154040404040405e-06,
|
| 1466 |
+
"loss": 0.0646,
|
| 1467 |
+
"step": 1470
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 64.97,
|
| 1471 |
+
"eval_accuracy": 0.6153846153846154,
|
| 1472 |
+
"eval_loss": 1.947584629058838,
|
| 1473 |
+
"eval_runtime": 1.1818,
|
| 1474 |
+
"eval_samples_per_second": 44.001,
|
| 1475 |
+
"eval_steps_per_second": 3.385,
|
| 1476 |
+
"step": 1478
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 65.05,
|
| 1480 |
+
"learning_rate": 8.838383838383838e-06,
|
| 1481 |
+
"loss": 0.0348,
|
| 1482 |
+
"step": 1480
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 65.49,
|
| 1486 |
+
"learning_rate": 8.522727272727273e-06,
|
| 1487 |
+
"loss": 0.0363,
|
| 1488 |
+
"step": 1490
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 65.93,
|
| 1492 |
+
"learning_rate": 8.207070707070708e-06,
|
| 1493 |
+
"loss": 0.0594,
|
| 1494 |
+
"step": 1500
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 65.98,
|
| 1498 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1499 |
+
"eval_loss": 1.5957955121994019,
|
| 1500 |
+
"eval_runtime": 0.6717,
|
| 1501 |
+
"eval_samples_per_second": 77.42,
|
| 1502 |
+
"eval_steps_per_second": 5.955,
|
| 1503 |
+
"step": 1501
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 66.37,
|
| 1507 |
+
"learning_rate": 7.891414141414141e-06,
|
| 1508 |
+
"loss": 0.0375,
|
| 1509 |
+
"step": 1510
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 66.81,
|
| 1513 |
+
"learning_rate": 7.5757575757575764e-06,
|
| 1514 |
+
"loss": 0.0568,
|
| 1515 |
+
"step": 1520
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 66.99,
|
| 1519 |
+
"eval_accuracy": 0.6730769230769231,
|
| 1520 |
+
"eval_loss": 1.8275247812271118,
|
| 1521 |
+
"eval_runtime": 0.7647,
|
| 1522 |
+
"eval_samples_per_second": 68.002,
|
| 1523 |
+
"eval_steps_per_second": 5.231,
|
| 1524 |
+
"step": 1524
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 67.25,
|
| 1528 |
+
"learning_rate": 7.26010101010101e-06,
|
| 1529 |
+
"loss": 0.0443,
|
| 1530 |
+
"step": 1530
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 67.69,
|
| 1534 |
+
"learning_rate": 6.944444444444445e-06,
|
| 1535 |
+
"loss": 0.0662,
|
| 1536 |
+
"step": 1540
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 68.0,
|
| 1540 |
+
"eval_accuracy": 0.6730769230769231,
|
| 1541 |
+
"eval_loss": 1.757631778717041,
|
| 1542 |
+
"eval_runtime": 0.6531,
|
| 1543 |
+
"eval_samples_per_second": 79.615,
|
| 1544 |
+
"eval_steps_per_second": 6.124,
|
| 1545 |
+
"step": 1547
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 68.13,
|
| 1549 |
+
"learning_rate": 6.628787878787879e-06,
|
| 1550 |
+
"loss": 0.0352,
|
| 1551 |
+
"step": 1550
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 68.57,
|
| 1555 |
+
"learning_rate": 6.313131313131314e-06,
|
| 1556 |
+
"loss": 0.0428,
|
| 1557 |
+
"step": 1560
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 68.97,
|
| 1561 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1562 |
+
"eval_loss": 1.9324886798858643,
|
| 1563 |
+
"eval_runtime": 0.7317,
|
| 1564 |
+
"eval_samples_per_second": 71.07,
|
| 1565 |
+
"eval_steps_per_second": 5.467,
|
| 1566 |
+
"step": 1569
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 69.01,
|
| 1570 |
+
"learning_rate": 5.997474747474747e-06,
|
| 1571 |
+
"loss": 0.0549,
|
| 1572 |
+
"step": 1570
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 69.45,
|
| 1576 |
+
"learning_rate": 5.681818181818182e-06,
|
| 1577 |
+
"loss": 0.0571,
|
| 1578 |
+
"step": 1580
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 69.89,
|
| 1582 |
+
"learning_rate": 5.3661616161616165e-06,
|
| 1583 |
+
"loss": 0.0433,
|
| 1584 |
+
"step": 1590
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 69.98,
|
| 1588 |
+
"eval_accuracy": 0.6730769230769231,
|
| 1589 |
+
"eval_loss": 1.8206470012664795,
|
| 1590 |
+
"eval_runtime": 0.6331,
|
| 1591 |
+
"eval_samples_per_second": 82.13,
|
| 1592 |
+
"eval_steps_per_second": 6.318,
|
| 1593 |
+
"step": 1592
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 70.33,
|
| 1597 |
+
"learning_rate": 5.050505050505051e-06,
|
| 1598 |
+
"loss": 0.0477,
|
| 1599 |
+
"step": 1600
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 70.77,
|
| 1603 |
+
"learning_rate": 4.734848484848485e-06,
|
| 1604 |
+
"loss": 0.0511,
|
| 1605 |
+
"step": 1610
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 70.99,
|
| 1609 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1610 |
+
"eval_loss": 1.9029183387756348,
|
| 1611 |
+
"eval_runtime": 0.6361,
|
| 1612 |
+
"eval_samples_per_second": 81.743,
|
| 1613 |
+
"eval_steps_per_second": 6.288,
|
| 1614 |
+
"step": 1615
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 71.21,
|
| 1618 |
+
"learning_rate": 4.419191919191919e-06,
|
| 1619 |
+
"loss": 0.058,
|
| 1620 |
+
"step": 1620
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 71.65,
|
| 1624 |
+
"learning_rate": 4.103535353535354e-06,
|
| 1625 |
+
"loss": 0.0502,
|
| 1626 |
+
"step": 1630
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 72.0,
|
| 1630 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1631 |
+
"eval_loss": 1.8820760250091553,
|
| 1632 |
+
"eval_runtime": 0.6281,
|
| 1633 |
+
"eval_samples_per_second": 82.784,
|
| 1634 |
+
"eval_steps_per_second": 6.368,
|
| 1635 |
+
"step": 1638
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 72.09,
|
| 1639 |
+
"learning_rate": 3.7878787878787882e-06,
|
| 1640 |
+
"loss": 0.0507,
|
| 1641 |
+
"step": 1640
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 72.53,
|
| 1645 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 1646 |
+
"loss": 0.0497,
|
| 1647 |
+
"step": 1650
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 72.97,
|
| 1651 |
+
"learning_rate": 3.156565656565657e-06,
|
| 1652 |
+
"loss": 0.0544,
|
| 1653 |
+
"step": 1660
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 72.97,
|
| 1657 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1658 |
+
"eval_loss": 1.9534863233566284,
|
| 1659 |
+
"eval_runtime": 0.6302,
|
| 1660 |
+
"eval_samples_per_second": 82.519,
|
| 1661 |
+
"eval_steps_per_second": 6.348,
|
| 1662 |
+
"step": 1660
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 73.41,
|
| 1666 |
+
"learning_rate": 2.840909090909091e-06,
|
| 1667 |
+
"loss": 0.0406,
|
| 1668 |
+
"step": 1670
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 73.85,
|
| 1672 |
+
"learning_rate": 2.5252525252525253e-06,
|
| 1673 |
+
"loss": 0.0399,
|
| 1674 |
+
"step": 1680
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 73.98,
|
| 1678 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1679 |
+
"eval_loss": 1.8454902172088623,
|
| 1680 |
+
"eval_runtime": 0.6792,
|
| 1681 |
+
"eval_samples_per_second": 76.566,
|
| 1682 |
+
"eval_steps_per_second": 5.89,
|
| 1683 |
+
"step": 1683
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 74.29,
|
| 1687 |
+
"learning_rate": 2.2095959595959595e-06,
|
| 1688 |
+
"loss": 0.0517,
|
| 1689 |
+
"step": 1690
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 74.73,
|
| 1693 |
+
"learning_rate": 1.8939393939393941e-06,
|
| 1694 |
+
"loss": 0.0561,
|
| 1695 |
+
"step": 1700
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 74.99,
|
| 1699 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1700 |
+
"eval_loss": 1.8289686441421509,
|
| 1701 |
+
"eval_runtime": 0.6441,
|
| 1702 |
+
"eval_samples_per_second": 80.727,
|
| 1703 |
+
"eval_steps_per_second": 6.21,
|
| 1704 |
+
"step": 1706
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 75.16,
|
| 1708 |
+
"learning_rate": 1.5782828282828285e-06,
|
| 1709 |
+
"loss": 0.0487,
|
| 1710 |
+
"step": 1710
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 75.6,
|
| 1714 |
+
"learning_rate": 1.2626262626262627e-06,
|
| 1715 |
+
"loss": 0.041,
|
| 1716 |
+
"step": 1720
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 76.0,
|
| 1720 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1721 |
+
"eval_loss": 1.8427259922027588,
|
| 1722 |
+
"eval_runtime": 0.6382,
|
| 1723 |
+
"eval_samples_per_second": 81.484,
|
| 1724 |
+
"eval_steps_per_second": 6.268,
|
| 1725 |
+
"step": 1729
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 76.04,
|
| 1729 |
+
"learning_rate": 9.469696969696971e-07,
|
| 1730 |
+
"loss": 0.0387,
|
| 1731 |
+
"step": 1730
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 76.48,
|
| 1735 |
+
"learning_rate": 6.313131313131313e-07,
|
| 1736 |
+
"loss": 0.0612,
|
| 1737 |
+
"step": 1740
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 76.92,
|
| 1741 |
+
"learning_rate": 3.1565656565656567e-07,
|
| 1742 |
+
"loss": 0.0582,
|
| 1743 |
+
"step": 1750
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 76.97,
|
| 1747 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1748 |
+
"eval_loss": 1.8591234683990479,
|
| 1749 |
+
"eval_runtime": 0.6637,
|
| 1750 |
+
"eval_samples_per_second": 78.354,
|
| 1751 |
+
"eval_steps_per_second": 6.027,
|
| 1752 |
+
"step": 1751
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 77.36,
|
| 1756 |
+
"learning_rate": 0.0,
|
| 1757 |
+
"loss": 0.0315,
|
| 1758 |
+
"step": 1760
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 77.36,
|
| 1762 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1763 |
+
"eval_loss": 1.8611557483673096,
|
| 1764 |
+
"eval_runtime": 1.1148,
|
| 1765 |
+
"eval_samples_per_second": 46.647,
|
| 1766 |
+
"eval_steps_per_second": 3.588,
|
| 1767 |
+
"step": 1760
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 77.36,
|
| 1771 |
+
"step": 1760,
|
| 1772 |
+
"total_flos": 3.637414425770459e+18,
|
| 1773 |
+
"train_loss": 0.22083052936941386,
|
| 1774 |
+
"train_runtime": 1958.4327,
|
| 1775 |
+
"train_samples_per_second": 59.027,
|
| 1776 |
+
"train_steps_per_second": 0.899
|
| 1777 |
+
}
|
| 1778 |
+
],
|
| 1779 |
+
"logging_steps": 10,
|
| 1780 |
+
"max_steps": 1760,
|
| 1781 |
+
"num_input_tokens_seen": 0,
|
| 1782 |
+
"num_train_epochs": 80,
|
| 1783 |
+
"save_steps": 500,
|
| 1784 |
+
"total_flos": 3.637414425770459e+18,
|
| 1785 |
+
"train_batch_size": 16,
|
| 1786 |
+
"trial_name": null,
|
| 1787 |
+
"trial_params": null
|
| 1788 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a64dc4f9a11a005ec9cd230920c0e7767e85400f0521279c7488f10addff955
|
| 3 |
+
size 4728
|