End of training
Browse files- README.md +153 -0
- all_results.json +12 -0
- config.json +77 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- runs/Dec11_22-26-08_DESKTOP-SKBE9FB/events.out.tfevents.1733977570.DESKTOP-SKBE9FB.1228.0 +3 -0
- runs/Dec11_22-26-08_DESKTOP-SKBE9FB/events.out.tfevents.1733978953.DESKTOP-SKBE9FB.1228.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1251 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/beit-base-patch16-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: BEiT-DMAE-DA-REVAL-80-35e-05
|
| 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: 0.8913043478260869
|
| 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 |
+
# BEiT-DMAE-DA-REVAL-80-35e-05
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4981
|
| 36 |
+
- Accuracy: 0.8913
|
| 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: 3.5e-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 |
+
- num_epochs: 80
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 1.528 | 0.96 | 11 | 1.2944 | 0.4565 |
|
| 70 |
+
| 1.3955 | 2.0 | 23 | 1.3459 | 0.5 |
|
| 71 |
+
| 1.3036 | 2.96 | 34 | 1.2487 | 0.3696 |
|
| 72 |
+
| 1.1708 | 4.0 | 46 | 1.0742 | 0.5217 |
|
| 73 |
+
| 1.0545 | 4.96 | 57 | 0.9917 | 0.5435 |
|
| 74 |
+
| 0.9352 | 6.0 | 69 | 0.9326 | 0.5435 |
|
| 75 |
+
| 0.7648 | 6.96 | 80 | 0.9982 | 0.4348 |
|
| 76 |
+
| 0.7161 | 8.0 | 92 | 0.8967 | 0.5870 |
|
| 77 |
+
| 0.6157 | 8.96 | 103 | 0.9164 | 0.6087 |
|
| 78 |
+
| 0.6128 | 10.0 | 115 | 0.9261 | 0.6522 |
|
| 79 |
+
| 0.4791 | 10.96 | 126 | 0.7729 | 0.7391 |
|
| 80 |
+
| 0.4494 | 12.0 | 138 | 0.6894 | 0.8043 |
|
| 81 |
+
| 0.4213 | 12.96 | 149 | 0.7138 | 0.8043 |
|
| 82 |
+
| 0.3341 | 14.0 | 161 | 0.9143 | 0.7174 |
|
| 83 |
+
| 0.3114 | 14.96 | 172 | 0.6721 | 0.7609 |
|
| 84 |
+
| 0.322 | 16.0 | 184 | 0.7821 | 0.7609 |
|
| 85 |
+
| 0.2975 | 16.96 | 195 | 0.7998 | 0.7826 |
|
| 86 |
+
| 0.2694 | 18.0 | 207 | 0.6825 | 0.8043 |
|
| 87 |
+
| 0.2104 | 18.96 | 218 | 0.6983 | 0.8043 |
|
| 88 |
+
| 0.2309 | 20.0 | 230 | 0.7812 | 0.7174 |
|
| 89 |
+
| 0.1867 | 20.96 | 241 | 0.7511 | 0.7609 |
|
| 90 |
+
| 0.17 | 22.0 | 253 | 0.9706 | 0.7391 |
|
| 91 |
+
| 0.1915 | 22.96 | 264 | 0.7702 | 0.8043 |
|
| 92 |
+
| 0.2309 | 24.0 | 276 | 0.7152 | 0.8043 |
|
| 93 |
+
| 0.1813 | 24.96 | 287 | 0.7917 | 0.7826 |
|
| 94 |
+
| 0.1399 | 26.0 | 299 | 0.7918 | 0.7391 |
|
| 95 |
+
| 0.1481 | 26.96 | 310 | 0.7052 | 0.8261 |
|
| 96 |
+
| 0.2046 | 28.0 | 322 | 0.5693 | 0.8478 |
|
| 97 |
+
| 0.1912 | 28.96 | 333 | 0.6074 | 0.8261 |
|
| 98 |
+
| 0.1467 | 30.0 | 345 | 0.9355 | 0.7609 |
|
| 99 |
+
| 0.1263 | 30.96 | 356 | 0.6719 | 0.8261 |
|
| 100 |
+
| 0.1357 | 32.0 | 368 | 0.7006 | 0.7826 |
|
| 101 |
+
| 0.1117 | 32.96 | 379 | 0.7690 | 0.7609 |
|
| 102 |
+
| 0.1294 | 34.0 | 391 | 0.9282 | 0.7609 |
|
| 103 |
+
| 0.139 | 34.96 | 402 | 0.7608 | 0.7609 |
|
| 104 |
+
| 0.131 | 36.0 | 414 | 0.8221 | 0.8043 |
|
| 105 |
+
| 0.1237 | 36.96 | 425 | 0.9204 | 0.7391 |
|
| 106 |
+
| 0.1148 | 38.0 | 437 | 0.5724 | 0.8261 |
|
| 107 |
+
| 0.1131 | 38.96 | 448 | 0.9197 | 0.7609 |
|
| 108 |
+
| 0.1171 | 40.0 | 460 | 0.8922 | 0.7174 |
|
| 109 |
+
| 0.0833 | 40.96 | 471 | 0.6172 | 0.8043 |
|
| 110 |
+
| 0.1026 | 42.0 | 483 | 0.6637 | 0.7609 |
|
| 111 |
+
| 0.09 | 42.96 | 494 | 0.8515 | 0.7826 |
|
| 112 |
+
| 0.0894 | 44.0 | 506 | 0.5513 | 0.8696 |
|
| 113 |
+
| 0.0842 | 44.96 | 517 | 0.8008 | 0.8261 |
|
| 114 |
+
| 0.0824 | 46.0 | 529 | 0.6873 | 0.8696 |
|
| 115 |
+
| 0.1004 | 46.96 | 540 | 1.0546 | 0.7826 |
|
| 116 |
+
| 0.0915 | 48.0 | 552 | 0.8237 | 0.7609 |
|
| 117 |
+
| 0.0642 | 48.96 | 563 | 0.4981 | 0.8913 |
|
| 118 |
+
| 0.0872 | 50.0 | 575 | 0.7128 | 0.8696 |
|
| 119 |
+
| 0.0755 | 50.96 | 586 | 0.7991 | 0.8043 |
|
| 120 |
+
| 0.0773 | 52.0 | 598 | 0.8565 | 0.7826 |
|
| 121 |
+
| 0.0853 | 52.96 | 609 | 0.7463 | 0.8478 |
|
| 122 |
+
| 0.0717 | 54.0 | 621 | 0.7527 | 0.8043 |
|
| 123 |
+
| 0.0919 | 54.96 | 632 | 0.6984 | 0.8478 |
|
| 124 |
+
| 0.0913 | 56.0 | 644 | 0.7035 | 0.8043 |
|
| 125 |
+
| 0.0672 | 56.96 | 655 | 0.6481 | 0.8696 |
|
| 126 |
+
| 0.0691 | 58.0 | 667 | 0.7666 | 0.8696 |
|
| 127 |
+
| 0.0733 | 58.96 | 678 | 0.7665 | 0.8478 |
|
| 128 |
+
| 0.0982 | 60.0 | 690 | 0.8573 | 0.8478 |
|
| 129 |
+
| 0.0791 | 60.96 | 701 | 0.7859 | 0.8696 |
|
| 130 |
+
| 0.0559 | 62.0 | 713 | 0.7715 | 0.8261 |
|
| 131 |
+
| 0.0725 | 62.96 | 724 | 0.8548 | 0.8478 |
|
| 132 |
+
| 0.065 | 64.0 | 736 | 0.8533 | 0.8478 |
|
| 133 |
+
| 0.0844 | 64.96 | 747 | 0.8175 | 0.8478 |
|
| 134 |
+
| 0.0664 | 66.0 | 759 | 0.7743 | 0.8261 |
|
| 135 |
+
| 0.0696 | 66.96 | 770 | 0.8106 | 0.8696 |
|
| 136 |
+
| 0.0567 | 68.0 | 782 | 0.7904 | 0.8478 |
|
| 137 |
+
| 0.083 | 68.96 | 793 | 0.8550 | 0.8043 |
|
| 138 |
+
| 0.0385 | 70.0 | 805 | 0.8915 | 0.8261 |
|
| 139 |
+
| 0.0714 | 70.96 | 816 | 0.8631 | 0.8261 |
|
| 140 |
+
| 0.0444 | 72.0 | 828 | 0.8231 | 0.8478 |
|
| 141 |
+
| 0.0496 | 72.96 | 839 | 0.8199 | 0.8478 |
|
| 142 |
+
| 0.0887 | 74.0 | 851 | 0.8304 | 0.8478 |
|
| 143 |
+
| 0.0475 | 74.96 | 862 | 0.8529 | 0.8261 |
|
| 144 |
+
| 0.0639 | 76.0 | 874 | 0.8580 | 0.8261 |
|
| 145 |
+
| 0.0704 | 76.52 | 880 | 0.8589 | 0.8261 |
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
### Framework versions
|
| 149 |
+
|
| 150 |
+
- Transformers 4.36.2
|
| 151 |
+
- Pytorch 2.1.2+cu118
|
| 152 |
+
- Datasets 2.16.1
|
| 153 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 76.52,
|
| 3 |
+
"eval_accuracy": 0.8913043478260869,
|
| 4 |
+
"eval_loss": 0.4981374740600586,
|
| 5 |
+
"eval_runtime": 0.8272,
|
| 6 |
+
"eval_samples_per_second": 55.61,
|
| 7 |
+
"eval_steps_per_second": 3.627,
|
| 8 |
+
"train_loss": 0.24412418752908707,
|
| 9 |
+
"train_runtime": 1381.4229,
|
| 10 |
+
"train_samples_per_second": 41.812,
|
| 11 |
+
"train_steps_per_second": 0.637
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/beit-base-patch16-224",
|
| 3 |
+
"add_fpn": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BeitForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"auxiliary_channels": 256,
|
| 9 |
+
"auxiliary_concat_input": false,
|
| 10 |
+
"auxiliary_loss_weight": 0.4,
|
| 11 |
+
"auxiliary_num_convs": 1,
|
| 12 |
+
"drop_path_rate": 0.1,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "avanzada",
|
| 18 |
+
"1": "leve",
|
| 19 |
+
"2": "moderada",
|
| 20 |
+
"3": "no dmae"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"avanzada": 0,
|
| 27 |
+
"leve": 1,
|
| 28 |
+
"moderada": 2,
|
| 29 |
+
"no dmae": 3
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"layer_scale_init_value": 0.1,
|
| 33 |
+
"model_type": "beit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"out_features": [
|
| 38 |
+
"stage12"
|
| 39 |
+
],
|
| 40 |
+
"out_indices": [
|
| 41 |
+
12
|
| 42 |
+
],
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pool_scales": [
|
| 45 |
+
1,
|
| 46 |
+
2,
|
| 47 |
+
3,
|
| 48 |
+
6
|
| 49 |
+
],
|
| 50 |
+
"problem_type": "single_label_classification",
|
| 51 |
+
"reshape_hidden_states": true,
|
| 52 |
+
"semantic_loss_ignore_index": 255,
|
| 53 |
+
"stage_names": [
|
| 54 |
+
"stem",
|
| 55 |
+
"stage1",
|
| 56 |
+
"stage2",
|
| 57 |
+
"stage3",
|
| 58 |
+
"stage4",
|
| 59 |
+
"stage5",
|
| 60 |
+
"stage6",
|
| 61 |
+
"stage7",
|
| 62 |
+
"stage8",
|
| 63 |
+
"stage9",
|
| 64 |
+
"stage10",
|
| 65 |
+
"stage11",
|
| 66 |
+
"stage12"
|
| 67 |
+
],
|
| 68 |
+
"torch_dtype": "float32",
|
| 69 |
+
"transformers_version": "4.36.2",
|
| 70 |
+
"use_absolute_position_embeddings": false,
|
| 71 |
+
"use_auxiliary_head": true,
|
| 72 |
+
"use_mask_token": false,
|
| 73 |
+
"use_mean_pooling": true,
|
| 74 |
+
"use_relative_position_bias": true,
|
| 75 |
+
"use_shared_relative_position_bias": false,
|
| 76 |
+
"vocab_size": 8192
|
| 77 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 76.52,
|
| 3 |
+
"eval_accuracy": 0.8913043478260869,
|
| 4 |
+
"eval_loss": 0.4981374740600586,
|
| 5 |
+
"eval_runtime": 0.8272,
|
| 6 |
+
"eval_samples_per_second": 55.61,
|
| 7 |
+
"eval_steps_per_second": 3.627
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6596dd40893feb0a4c220d9f805fa9efda3e3d009dca6de6d068f78fe11f23b
|
| 3 |
+
size 343086480
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": false,
|
| 7 |
+
"do_normalize": true,
|
| 8 |
+
"do_reduce_labels": false,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BeitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.5,
|
| 19 |
+
0.5,
|
| 20 |
+
0.5
|
| 21 |
+
],
|
| 22 |
+
"resample": 2,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"height": 224,
|
| 26 |
+
"width": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
runs/Dec11_22-26-08_DESKTOP-SKBE9FB/events.out.tfevents.1733977570.DESKTOP-SKBE9FB.1228.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38e212abc0bfd8b75015b3db0883591e6ea934c265ec6123d337238eceb86386
|
| 3 |
+
size 44254
|
runs/Dec11_22-26-08_DESKTOP-SKBE9FB/events.out.tfevents.1733978953.DESKTOP-SKBE9FB.1228.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d4e25fcf0e44b243b13effeed7446abc40499afdd5da26ca7afd7e5fb7f21c1
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 76.52,
|
| 3 |
+
"train_loss": 0.24412418752908707,
|
| 4 |
+
"train_runtime": 1381.4229,
|
| 5 |
+
"train_samples_per_second": 41.812,
|
| 6 |
+
"train_steps_per_second": 0.637
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8913043478260869,
|
| 3 |
+
"best_model_checkpoint": "BEiT-DMAE-DA-REVAL-80-35e-05\\checkpoint-563",
|
| 4 |
+
"epoch": 76.52173913043478,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 880,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"learning_rate": 3.460227272727272e-05,
|
| 14 |
+
"loss": 1.528,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.96,
|
| 19 |
+
"eval_accuracy": 0.45652173913043476,
|
| 20 |
+
"eval_loss": 1.294417142868042,
|
| 21 |
+
"eval_runtime": 0.959,
|
| 22 |
+
"eval_samples_per_second": 47.967,
|
| 23 |
+
"eval_steps_per_second": 3.128,
|
| 24 |
+
"step": 11
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.74,
|
| 28 |
+
"learning_rate": 3.420454545454545e-05,
|
| 29 |
+
"loss": 1.3955,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.5,
|
| 35 |
+
"eval_loss": 1.3459346294403076,
|
| 36 |
+
"eval_runtime": 0.6587,
|
| 37 |
+
"eval_samples_per_second": 69.839,
|
| 38 |
+
"eval_steps_per_second": 4.555,
|
| 39 |
+
"step": 23
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.61,
|
| 43 |
+
"learning_rate": 3.380681818181818e-05,
|
| 44 |
+
"loss": 1.3036,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.96,
|
| 49 |
+
"eval_accuracy": 0.3695652173913043,
|
| 50 |
+
"eval_loss": 1.2487155199050903,
|
| 51 |
+
"eval_runtime": 0.6542,
|
| 52 |
+
"eval_samples_per_second": 70.319,
|
| 53 |
+
"eval_steps_per_second": 4.586,
|
| 54 |
+
"step": 34
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.48,
|
| 58 |
+
"learning_rate": 3.340909090909091e-05,
|
| 59 |
+
"loss": 1.1708,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"eval_accuracy": 0.5217391304347826,
|
| 65 |
+
"eval_loss": 1.0741910934448242,
|
| 66 |
+
"eval_runtime": 0.6982,
|
| 67 |
+
"eval_samples_per_second": 65.888,
|
| 68 |
+
"eval_steps_per_second": 4.297,
|
| 69 |
+
"step": 46
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.35,
|
| 73 |
+
"learning_rate": 3.3011363636363635e-05,
|
| 74 |
+
"loss": 1.0545,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.96,
|
| 79 |
+
"eval_accuracy": 0.5434782608695652,
|
| 80 |
+
"eval_loss": 0.9917401671409607,
|
| 81 |
+
"eval_runtime": 0.7157,
|
| 82 |
+
"eval_samples_per_second": 64.276,
|
| 83 |
+
"eval_steps_per_second": 4.192,
|
| 84 |
+
"step": 57
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.22,
|
| 88 |
+
"learning_rate": 3.261363636363636e-05,
|
| 89 |
+
"loss": 0.9352,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.0,
|
| 94 |
+
"eval_accuracy": 0.5434782608695652,
|
| 95 |
+
"eval_loss": 0.9326199293136597,
|
| 96 |
+
"eval_runtime": 0.6573,
|
| 97 |
+
"eval_samples_per_second": 69.98,
|
| 98 |
+
"eval_steps_per_second": 4.564,
|
| 99 |
+
"step": 69
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.09,
|
| 103 |
+
"learning_rate": 3.221590909090909e-05,
|
| 104 |
+
"loss": 0.8446,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.96,
|
| 109 |
+
"learning_rate": 3.1818181818181814e-05,
|
| 110 |
+
"loss": 0.7648,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.96,
|
| 115 |
+
"eval_accuracy": 0.43478260869565216,
|
| 116 |
+
"eval_loss": 0.9982470870018005,
|
| 117 |
+
"eval_runtime": 0.6256,
|
| 118 |
+
"eval_samples_per_second": 73.524,
|
| 119 |
+
"eval_steps_per_second": 4.795,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 7.83,
|
| 124 |
+
"learning_rate": 3.142045454545454e-05,
|
| 125 |
+
"loss": 0.7161,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.5869565217391305,
|
| 131 |
+
"eval_loss": 0.8967475891113281,
|
| 132 |
+
"eval_runtime": 0.7002,
|
| 133 |
+
"eval_samples_per_second": 65.7,
|
| 134 |
+
"eval_steps_per_second": 4.285,
|
| 135 |
+
"step": 92
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.7,
|
| 139 |
+
"learning_rate": 3.102272727272727e-05,
|
| 140 |
+
"loss": 0.6157,
|
| 141 |
+
"step": 100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.96,
|
| 145 |
+
"eval_accuracy": 0.6086956521739131,
|
| 146 |
+
"eval_loss": 0.9164350032806396,
|
| 147 |
+
"eval_runtime": 0.7232,
|
| 148 |
+
"eval_samples_per_second": 63.61,
|
| 149 |
+
"eval_steps_per_second": 4.148,
|
| 150 |
+
"step": 103
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.57,
|
| 154 |
+
"learning_rate": 3.0625e-05,
|
| 155 |
+
"loss": 0.6128,
|
| 156 |
+
"step": 110
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 10.0,
|
| 160 |
+
"eval_accuracy": 0.6521739130434783,
|
| 161 |
+
"eval_loss": 0.9261461496353149,
|
| 162 |
+
"eval_runtime": 0.6497,
|
| 163 |
+
"eval_samples_per_second": 70.807,
|
| 164 |
+
"eval_steps_per_second": 4.618,
|
| 165 |
+
"step": 115
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 10.43,
|
| 169 |
+
"learning_rate": 3.0227272727272725e-05,
|
| 170 |
+
"loss": 0.4791,
|
| 171 |
+
"step": 120
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 10.96,
|
| 175 |
+
"eval_accuracy": 0.7391304347826086,
|
| 176 |
+
"eval_loss": 0.7729063630104065,
|
| 177 |
+
"eval_runtime": 0.7422,
|
| 178 |
+
"eval_samples_per_second": 61.981,
|
| 179 |
+
"eval_steps_per_second": 4.042,
|
| 180 |
+
"step": 126
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 11.3,
|
| 184 |
+
"learning_rate": 2.982954545454545e-05,
|
| 185 |
+
"loss": 0.4494,
|
| 186 |
+
"step": 130
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 12.0,
|
| 190 |
+
"eval_accuracy": 0.8043478260869565,
|
| 191 |
+
"eval_loss": 0.6893649101257324,
|
| 192 |
+
"eval_runtime": 0.7172,
|
| 193 |
+
"eval_samples_per_second": 64.142,
|
| 194 |
+
"eval_steps_per_second": 4.183,
|
| 195 |
+
"step": 138
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.17,
|
| 199 |
+
"learning_rate": 2.943181818181818e-05,
|
| 200 |
+
"loss": 0.4213,
|
| 201 |
+
"step": 140
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.96,
|
| 205 |
+
"eval_accuracy": 0.8043478260869565,
|
| 206 |
+
"eval_loss": 0.7137573957443237,
|
| 207 |
+
"eval_runtime": 0.6156,
|
| 208 |
+
"eval_samples_per_second": 74.718,
|
| 209 |
+
"eval_steps_per_second": 4.873,
|
| 210 |
+
"step": 149
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 13.04,
|
| 214 |
+
"learning_rate": 2.9034090909090907e-05,
|
| 215 |
+
"loss": 0.3843,
|
| 216 |
+
"step": 150
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 13.91,
|
| 220 |
+
"learning_rate": 2.8636363636363637e-05,
|
| 221 |
+
"loss": 0.3341,
|
| 222 |
+
"step": 160
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 14.0,
|
| 226 |
+
"eval_accuracy": 0.717391304347826,
|
| 227 |
+
"eval_loss": 0.9143244624137878,
|
| 228 |
+
"eval_runtime": 0.6832,
|
| 229 |
+
"eval_samples_per_second": 67.335,
|
| 230 |
+
"eval_steps_per_second": 4.391,
|
| 231 |
+
"step": 161
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 14.78,
|
| 235 |
+
"learning_rate": 2.823863636363636e-05,
|
| 236 |
+
"loss": 0.3114,
|
| 237 |
+
"step": 170
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 14.96,
|
| 241 |
+
"eval_accuracy": 0.7608695652173914,
|
| 242 |
+
"eval_loss": 0.6721171736717224,
|
| 243 |
+
"eval_runtime": 0.7027,
|
| 244 |
+
"eval_samples_per_second": 65.466,
|
| 245 |
+
"eval_steps_per_second": 4.269,
|
| 246 |
+
"step": 172
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.65,
|
| 250 |
+
"learning_rate": 2.7840909090909086e-05,
|
| 251 |
+
"loss": 0.322,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 16.0,
|
| 256 |
+
"eval_accuracy": 0.7608695652173914,
|
| 257 |
+
"eval_loss": 0.7820727229118347,
|
| 258 |
+
"eval_runtime": 0.6701,
|
| 259 |
+
"eval_samples_per_second": 68.641,
|
| 260 |
+
"eval_steps_per_second": 4.477,
|
| 261 |
+
"step": 184
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 16.52,
|
| 265 |
+
"learning_rate": 2.7443181818181816e-05,
|
| 266 |
+
"loss": 0.2975,
|
| 267 |
+
"step": 190
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 16.96,
|
| 271 |
+
"eval_accuracy": 0.782608695652174,
|
| 272 |
+
"eval_loss": 0.7998351454734802,
|
| 273 |
+
"eval_runtime": 0.6641,
|
| 274 |
+
"eval_samples_per_second": 69.262,
|
| 275 |
+
"eval_steps_per_second": 4.517,
|
| 276 |
+
"step": 195
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 17.39,
|
| 280 |
+
"learning_rate": 2.7045454545454542e-05,
|
| 281 |
+
"loss": 0.2694,
|
| 282 |
+
"step": 200
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 18.0,
|
| 286 |
+
"eval_accuracy": 0.8043478260869565,
|
| 287 |
+
"eval_loss": 0.682524561882019,
|
| 288 |
+
"eval_runtime": 0.6627,
|
| 289 |
+
"eval_samples_per_second": 69.418,
|
| 290 |
+
"eval_steps_per_second": 4.527,
|
| 291 |
+
"step": 207
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 18.26,
|
| 295 |
+
"learning_rate": 2.664772727272727e-05,
|
| 296 |
+
"loss": 0.2104,
|
| 297 |
+
"step": 210
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.96,
|
| 301 |
+
"eval_accuracy": 0.8043478260869565,
|
| 302 |
+
"eval_loss": 0.698331892490387,
|
| 303 |
+
"eval_runtime": 0.6571,
|
| 304 |
+
"eval_samples_per_second": 70.0,
|
| 305 |
+
"eval_steps_per_second": 4.565,
|
| 306 |
+
"step": 218
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 19.13,
|
| 310 |
+
"learning_rate": 2.6249999999999998e-05,
|
| 311 |
+
"loss": 0.2204,
|
| 312 |
+
"step": 220
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 20.0,
|
| 316 |
+
"learning_rate": 2.5852272727272724e-05,
|
| 317 |
+
"loss": 0.2309,
|
| 318 |
+
"step": 230
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 20.0,
|
| 322 |
+
"eval_accuracy": 0.717391304347826,
|
| 323 |
+
"eval_loss": 0.7812390327453613,
|
| 324 |
+
"eval_runtime": 0.6722,
|
| 325 |
+
"eval_samples_per_second": 68.429,
|
| 326 |
+
"eval_steps_per_second": 4.463,
|
| 327 |
+
"step": 230
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 20.87,
|
| 331 |
+
"learning_rate": 2.5454545454545454e-05,
|
| 332 |
+
"loss": 0.1867,
|
| 333 |
+
"step": 240
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 20.96,
|
| 337 |
+
"eval_accuracy": 0.7608695652173914,
|
| 338 |
+
"eval_loss": 0.751146137714386,
|
| 339 |
+
"eval_runtime": 0.7132,
|
| 340 |
+
"eval_samples_per_second": 64.5,
|
| 341 |
+
"eval_steps_per_second": 4.207,
|
| 342 |
+
"step": 241
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 21.74,
|
| 346 |
+
"learning_rate": 2.505681818181818e-05,
|
| 347 |
+
"loss": 0.17,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 22.0,
|
| 352 |
+
"eval_accuracy": 0.7391304347826086,
|
| 353 |
+
"eval_loss": 0.970604419708252,
|
| 354 |
+
"eval_runtime": 0.7257,
|
| 355 |
+
"eval_samples_per_second": 63.389,
|
| 356 |
+
"eval_steps_per_second": 4.134,
|
| 357 |
+
"step": 253
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 22.61,
|
| 361 |
+
"learning_rate": 2.465909090909091e-05,
|
| 362 |
+
"loss": 0.1915,
|
| 363 |
+
"step": 260
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 22.96,
|
| 367 |
+
"eval_accuracy": 0.8043478260869565,
|
| 368 |
+
"eval_loss": 0.770175576210022,
|
| 369 |
+
"eval_runtime": 0.6742,
|
| 370 |
+
"eval_samples_per_second": 68.229,
|
| 371 |
+
"eval_steps_per_second": 4.45,
|
| 372 |
+
"step": 264
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 23.48,
|
| 376 |
+
"learning_rate": 2.4261363636363636e-05,
|
| 377 |
+
"loss": 0.2309,
|
| 378 |
+
"step": 270
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 24.0,
|
| 382 |
+
"eval_accuracy": 0.8043478260869565,
|
| 383 |
+
"eval_loss": 0.7151906490325928,
|
| 384 |
+
"eval_runtime": 0.6942,
|
| 385 |
+
"eval_samples_per_second": 66.268,
|
| 386 |
+
"eval_steps_per_second": 4.322,
|
| 387 |
+
"step": 276
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 24.35,
|
| 391 |
+
"learning_rate": 2.386363636363636e-05,
|
| 392 |
+
"loss": 0.1813,
|
| 393 |
+
"step": 280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 24.96,
|
| 397 |
+
"eval_accuracy": 0.782608695652174,
|
| 398 |
+
"eval_loss": 0.7917236089706421,
|
| 399 |
+
"eval_runtime": 0.6527,
|
| 400 |
+
"eval_samples_per_second": 70.481,
|
| 401 |
+
"eval_steps_per_second": 4.597,
|
| 402 |
+
"step": 287
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 25.22,
|
| 406 |
+
"learning_rate": 2.3465909090909088e-05,
|
| 407 |
+
"loss": 0.1399,
|
| 408 |
+
"step": 290
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 26.0,
|
| 412 |
+
"eval_accuracy": 0.7391304347826086,
|
| 413 |
+
"eval_loss": 0.7917895913124084,
|
| 414 |
+
"eval_runtime": 0.7092,
|
| 415 |
+
"eval_samples_per_second": 64.864,
|
| 416 |
+
"eval_steps_per_second": 4.23,
|
| 417 |
+
"step": 299
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 26.09,
|
| 421 |
+
"learning_rate": 2.3068181818181814e-05,
|
| 422 |
+
"loss": 0.1551,
|
| 423 |
+
"step": 300
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 26.96,
|
| 427 |
+
"learning_rate": 2.2670454545454544e-05,
|
| 428 |
+
"loss": 0.1481,
|
| 429 |
+
"step": 310
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 26.96,
|
| 433 |
+
"eval_accuracy": 0.8260869565217391,
|
| 434 |
+
"eval_loss": 0.7051936984062195,
|
| 435 |
+
"eval_runtime": 0.6687,
|
| 436 |
+
"eval_samples_per_second": 68.795,
|
| 437 |
+
"eval_steps_per_second": 4.487,
|
| 438 |
+
"step": 310
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 27.83,
|
| 442 |
+
"learning_rate": 2.227272727272727e-05,
|
| 443 |
+
"loss": 0.2046,
|
| 444 |
+
"step": 320
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 28.0,
|
| 448 |
+
"eval_accuracy": 0.8478260869565217,
|
| 449 |
+
"eval_loss": 0.5693252682685852,
|
| 450 |
+
"eval_runtime": 0.6682,
|
| 451 |
+
"eval_samples_per_second": 68.845,
|
| 452 |
+
"eval_steps_per_second": 4.49,
|
| 453 |
+
"step": 322
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 28.7,
|
| 457 |
+
"learning_rate": 2.1874999999999996e-05,
|
| 458 |
+
"loss": 0.1912,
|
| 459 |
+
"step": 330
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 28.96,
|
| 463 |
+
"eval_accuracy": 0.8260869565217391,
|
| 464 |
+
"eval_loss": 0.6074328422546387,
|
| 465 |
+
"eval_runtime": 0.6471,
|
| 466 |
+
"eval_samples_per_second": 71.081,
|
| 467 |
+
"eval_steps_per_second": 4.636,
|
| 468 |
+
"step": 333
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 29.57,
|
| 472 |
+
"learning_rate": 2.1477272727272726e-05,
|
| 473 |
+
"loss": 0.1467,
|
| 474 |
+
"step": 340
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 30.0,
|
| 478 |
+
"eval_accuracy": 0.7608695652173914,
|
| 479 |
+
"eval_loss": 0.9355303049087524,
|
| 480 |
+
"eval_runtime": 0.6607,
|
| 481 |
+
"eval_samples_per_second": 69.628,
|
| 482 |
+
"eval_steps_per_second": 4.541,
|
| 483 |
+
"step": 345
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 30.43,
|
| 487 |
+
"learning_rate": 2.1079545454545452e-05,
|
| 488 |
+
"loss": 0.1263,
|
| 489 |
+
"step": 350
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 30.96,
|
| 493 |
+
"eval_accuracy": 0.8260869565217391,
|
| 494 |
+
"eval_loss": 0.6719444394111633,
|
| 495 |
+
"eval_runtime": 0.7092,
|
| 496 |
+
"eval_samples_per_second": 64.865,
|
| 497 |
+
"eval_steps_per_second": 4.23,
|
| 498 |
+
"step": 356
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 31.3,
|
| 502 |
+
"learning_rate": 2.0681818181818182e-05,
|
| 503 |
+
"loss": 0.1357,
|
| 504 |
+
"step": 360
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 32.0,
|
| 508 |
+
"eval_accuracy": 0.782608695652174,
|
| 509 |
+
"eval_loss": 0.7006427049636841,
|
| 510 |
+
"eval_runtime": 0.6992,
|
| 511 |
+
"eval_samples_per_second": 65.792,
|
| 512 |
+
"eval_steps_per_second": 4.291,
|
| 513 |
+
"step": 368
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 32.17,
|
| 517 |
+
"learning_rate": 2.0284090909090908e-05,
|
| 518 |
+
"loss": 0.1117,
|
| 519 |
+
"step": 370
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 32.96,
|
| 523 |
+
"eval_accuracy": 0.7608695652173914,
|
| 524 |
+
"eval_loss": 0.7689698934555054,
|
| 525 |
+
"eval_runtime": 0.6541,
|
| 526 |
+
"eval_samples_per_second": 70.321,
|
| 527 |
+
"eval_steps_per_second": 4.586,
|
| 528 |
+
"step": 379
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 33.04,
|
| 532 |
+
"learning_rate": 1.9886363636363638e-05,
|
| 533 |
+
"loss": 0.1583,
|
| 534 |
+
"step": 380
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 33.91,
|
| 538 |
+
"learning_rate": 1.948863636363636e-05,
|
| 539 |
+
"loss": 0.1294,
|
| 540 |
+
"step": 390
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 34.0,
|
| 544 |
+
"eval_accuracy": 0.7608695652173914,
|
| 545 |
+
"eval_loss": 0.928158164024353,
|
| 546 |
+
"eval_runtime": 0.6376,
|
| 547 |
+
"eval_samples_per_second": 72.14,
|
| 548 |
+
"eval_steps_per_second": 4.705,
|
| 549 |
+
"step": 391
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 34.78,
|
| 553 |
+
"learning_rate": 1.9090909090909087e-05,
|
| 554 |
+
"loss": 0.139,
|
| 555 |
+
"step": 400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 34.96,
|
| 559 |
+
"eval_accuracy": 0.7608695652173914,
|
| 560 |
+
"eval_loss": 0.7608460187911987,
|
| 561 |
+
"eval_runtime": 0.7022,
|
| 562 |
+
"eval_samples_per_second": 65.511,
|
| 563 |
+
"eval_steps_per_second": 4.272,
|
| 564 |
+
"step": 402
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 35.65,
|
| 568 |
+
"learning_rate": 1.8693181818181816e-05,
|
| 569 |
+
"loss": 0.131,
|
| 570 |
+
"step": 410
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 36.0,
|
| 574 |
+
"eval_accuracy": 0.8043478260869565,
|
| 575 |
+
"eval_loss": 0.8220712542533875,
|
| 576 |
+
"eval_runtime": 0.6507,
|
| 577 |
+
"eval_samples_per_second": 70.688,
|
| 578 |
+
"eval_steps_per_second": 4.61,
|
| 579 |
+
"step": 414
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 36.52,
|
| 583 |
+
"learning_rate": 1.8295454545454543e-05,
|
| 584 |
+
"loss": 0.1237,
|
| 585 |
+
"step": 420
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 36.96,
|
| 589 |
+
"eval_accuracy": 0.7391304347826086,
|
| 590 |
+
"eval_loss": 0.9203805327415466,
|
| 591 |
+
"eval_runtime": 0.6632,
|
| 592 |
+
"eval_samples_per_second": 69.365,
|
| 593 |
+
"eval_steps_per_second": 4.524,
|
| 594 |
+
"step": 425
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 37.39,
|
| 598 |
+
"learning_rate": 1.7897727272727272e-05,
|
| 599 |
+
"loss": 0.1148,
|
| 600 |
+
"step": 430
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 38.0,
|
| 604 |
+
"eval_accuracy": 0.8260869565217391,
|
| 605 |
+
"eval_loss": 0.5723962187767029,
|
| 606 |
+
"eval_runtime": 0.6677,
|
| 607 |
+
"eval_samples_per_second": 68.897,
|
| 608 |
+
"eval_steps_per_second": 4.493,
|
| 609 |
+
"step": 437
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 38.26,
|
| 613 |
+
"learning_rate": 1.75e-05,
|
| 614 |
+
"loss": 0.1131,
|
| 615 |
+
"step": 440
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 38.96,
|
| 619 |
+
"eval_accuracy": 0.7608695652173914,
|
| 620 |
+
"eval_loss": 0.9196888208389282,
|
| 621 |
+
"eval_runtime": 0.6641,
|
| 622 |
+
"eval_samples_per_second": 69.262,
|
| 623 |
+
"eval_steps_per_second": 4.517,
|
| 624 |
+
"step": 448
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 39.13,
|
| 628 |
+
"learning_rate": 1.7102272727272725e-05,
|
| 629 |
+
"loss": 0.1219,
|
| 630 |
+
"step": 450
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 40.0,
|
| 634 |
+
"learning_rate": 1.6704545454545454e-05,
|
| 635 |
+
"loss": 0.1171,
|
| 636 |
+
"step": 460
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 40.0,
|
| 640 |
+
"eval_accuracy": 0.717391304347826,
|
| 641 |
+
"eval_loss": 0.8921728730201721,
|
| 642 |
+
"eval_runtime": 0.6682,
|
| 643 |
+
"eval_samples_per_second": 68.845,
|
| 644 |
+
"eval_steps_per_second": 4.49,
|
| 645 |
+
"step": 460
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 40.87,
|
| 649 |
+
"learning_rate": 1.630681818181818e-05,
|
| 650 |
+
"loss": 0.0833,
|
| 651 |
+
"step": 470
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 40.96,
|
| 655 |
+
"eval_accuracy": 0.8043478260869565,
|
| 656 |
+
"eval_loss": 0.6171940565109253,
|
| 657 |
+
"eval_runtime": 0.6882,
|
| 658 |
+
"eval_samples_per_second": 66.844,
|
| 659 |
+
"eval_steps_per_second": 4.359,
|
| 660 |
+
"step": 471
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 41.74,
|
| 664 |
+
"learning_rate": 1.5909090909090907e-05,
|
| 665 |
+
"loss": 0.1026,
|
| 666 |
+
"step": 480
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 42.0,
|
| 670 |
+
"eval_accuracy": 0.7608695652173914,
|
| 671 |
+
"eval_loss": 0.6637086272239685,
|
| 672 |
+
"eval_runtime": 0.6681,
|
| 673 |
+
"eval_samples_per_second": 68.847,
|
| 674 |
+
"eval_steps_per_second": 4.49,
|
| 675 |
+
"step": 483
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 42.61,
|
| 679 |
+
"learning_rate": 1.5511363636363636e-05,
|
| 680 |
+
"loss": 0.09,
|
| 681 |
+
"step": 490
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 42.96,
|
| 685 |
+
"eval_accuracy": 0.782608695652174,
|
| 686 |
+
"eval_loss": 0.8515200614929199,
|
| 687 |
+
"eval_runtime": 0.6752,
|
| 688 |
+
"eval_samples_per_second": 68.133,
|
| 689 |
+
"eval_steps_per_second": 4.443,
|
| 690 |
+
"step": 494
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 43.48,
|
| 694 |
+
"learning_rate": 1.5113636363636363e-05,
|
| 695 |
+
"loss": 0.0894,
|
| 696 |
+
"step": 500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 44.0,
|
| 700 |
+
"eval_accuracy": 0.8695652173913043,
|
| 701 |
+
"eval_loss": 0.5513039231300354,
|
| 702 |
+
"eval_runtime": 0.6732,
|
| 703 |
+
"eval_samples_per_second": 68.335,
|
| 704 |
+
"eval_steps_per_second": 4.457,
|
| 705 |
+
"step": 506
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 44.35,
|
| 709 |
+
"learning_rate": 1.471590909090909e-05,
|
| 710 |
+
"loss": 0.0842,
|
| 711 |
+
"step": 510
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 44.96,
|
| 715 |
+
"eval_accuracy": 0.8260869565217391,
|
| 716 |
+
"eval_loss": 0.8007767796516418,
|
| 717 |
+
"eval_runtime": 0.7037,
|
| 718 |
+
"eval_samples_per_second": 65.372,
|
| 719 |
+
"eval_steps_per_second": 4.263,
|
| 720 |
+
"step": 517
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 45.22,
|
| 724 |
+
"learning_rate": 1.4318181818181818e-05,
|
| 725 |
+
"loss": 0.0824,
|
| 726 |
+
"step": 520
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 46.0,
|
| 730 |
+
"eval_accuracy": 0.8695652173913043,
|
| 731 |
+
"eval_loss": 0.6872851848602295,
|
| 732 |
+
"eval_runtime": 0.6532,
|
| 733 |
+
"eval_samples_per_second": 70.427,
|
| 734 |
+
"eval_steps_per_second": 4.593,
|
| 735 |
+
"step": 529
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 46.09,
|
| 739 |
+
"learning_rate": 1.3920454545454543e-05,
|
| 740 |
+
"loss": 0.0827,
|
| 741 |
+
"step": 530
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 46.96,
|
| 745 |
+
"learning_rate": 1.3522727272727271e-05,
|
| 746 |
+
"loss": 0.1004,
|
| 747 |
+
"step": 540
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 46.96,
|
| 751 |
+
"eval_accuracy": 0.782608695652174,
|
| 752 |
+
"eval_loss": 1.0545523166656494,
|
| 753 |
+
"eval_runtime": 0.6481,
|
| 754 |
+
"eval_samples_per_second": 70.972,
|
| 755 |
+
"eval_steps_per_second": 4.629,
|
| 756 |
+
"step": 540
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 47.83,
|
| 760 |
+
"learning_rate": 1.3124999999999999e-05,
|
| 761 |
+
"loss": 0.0915,
|
| 762 |
+
"step": 550
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 48.0,
|
| 766 |
+
"eval_accuracy": 0.7608695652173914,
|
| 767 |
+
"eval_loss": 0.8237115740776062,
|
| 768 |
+
"eval_runtime": 0.6266,
|
| 769 |
+
"eval_samples_per_second": 73.406,
|
| 770 |
+
"eval_steps_per_second": 4.787,
|
| 771 |
+
"step": 552
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 48.7,
|
| 775 |
+
"learning_rate": 1.2727272727272727e-05,
|
| 776 |
+
"loss": 0.0642,
|
| 777 |
+
"step": 560
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 48.96,
|
| 781 |
+
"eval_accuracy": 0.8913043478260869,
|
| 782 |
+
"eval_loss": 0.4981374740600586,
|
| 783 |
+
"eval_runtime": 0.6371,
|
| 784 |
+
"eval_samples_per_second": 72.197,
|
| 785 |
+
"eval_steps_per_second": 4.709,
|
| 786 |
+
"step": 563
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 49.57,
|
| 790 |
+
"learning_rate": 1.2329545454545455e-05,
|
| 791 |
+
"loss": 0.0872,
|
| 792 |
+
"step": 570
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 50.0,
|
| 796 |
+
"eval_accuracy": 0.8695652173913043,
|
| 797 |
+
"eval_loss": 0.7127761840820312,
|
| 798 |
+
"eval_runtime": 0.6437,
|
| 799 |
+
"eval_samples_per_second": 71.467,
|
| 800 |
+
"eval_steps_per_second": 4.661,
|
| 801 |
+
"step": 575
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 50.43,
|
| 805 |
+
"learning_rate": 1.193181818181818e-05,
|
| 806 |
+
"loss": 0.0755,
|
| 807 |
+
"step": 580
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 50.96,
|
| 811 |
+
"eval_accuracy": 0.8043478260869565,
|
| 812 |
+
"eval_loss": 0.7990968823432922,
|
| 813 |
+
"eval_runtime": 0.6897,
|
| 814 |
+
"eval_samples_per_second": 66.699,
|
| 815 |
+
"eval_steps_per_second": 4.35,
|
| 816 |
+
"step": 586
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 51.3,
|
| 820 |
+
"learning_rate": 1.1534090909090907e-05,
|
| 821 |
+
"loss": 0.0773,
|
| 822 |
+
"step": 590
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 52.0,
|
| 826 |
+
"eval_accuracy": 0.782608695652174,
|
| 827 |
+
"eval_loss": 0.856543242931366,
|
| 828 |
+
"eval_runtime": 0.6842,
|
| 829 |
+
"eval_samples_per_second": 67.237,
|
| 830 |
+
"eval_steps_per_second": 4.385,
|
| 831 |
+
"step": 598
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 52.17,
|
| 835 |
+
"learning_rate": 1.1136363636363635e-05,
|
| 836 |
+
"loss": 0.0853,
|
| 837 |
+
"step": 600
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 52.96,
|
| 841 |
+
"eval_accuracy": 0.8478260869565217,
|
| 842 |
+
"eval_loss": 0.7462709546089172,
|
| 843 |
+
"eval_runtime": 0.6571,
|
| 844 |
+
"eval_samples_per_second": 70.0,
|
| 845 |
+
"eval_steps_per_second": 4.565,
|
| 846 |
+
"step": 609
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 53.04,
|
| 850 |
+
"learning_rate": 1.0738636363636363e-05,
|
| 851 |
+
"loss": 0.0857,
|
| 852 |
+
"step": 610
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 53.91,
|
| 856 |
+
"learning_rate": 1.0340909090909091e-05,
|
| 857 |
+
"loss": 0.0717,
|
| 858 |
+
"step": 620
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 54.0,
|
| 862 |
+
"eval_accuracy": 0.8043478260869565,
|
| 863 |
+
"eval_loss": 0.7526757717132568,
|
| 864 |
+
"eval_runtime": 0.7192,
|
| 865 |
+
"eval_samples_per_second": 63.962,
|
| 866 |
+
"eval_steps_per_second": 4.171,
|
| 867 |
+
"step": 621
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 54.78,
|
| 871 |
+
"learning_rate": 9.943181818181819e-06,
|
| 872 |
+
"loss": 0.0919,
|
| 873 |
+
"step": 630
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 54.96,
|
| 877 |
+
"eval_accuracy": 0.8478260869565217,
|
| 878 |
+
"eval_loss": 0.6983631253242493,
|
| 879 |
+
"eval_runtime": 0.6431,
|
| 880 |
+
"eval_samples_per_second": 71.523,
|
| 881 |
+
"eval_steps_per_second": 4.665,
|
| 882 |
+
"step": 632
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 55.65,
|
| 886 |
+
"learning_rate": 9.545454545454543e-06,
|
| 887 |
+
"loss": 0.0913,
|
| 888 |
+
"step": 640
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 56.0,
|
| 892 |
+
"eval_accuracy": 0.8043478260869565,
|
| 893 |
+
"eval_loss": 0.7034562826156616,
|
| 894 |
+
"eval_runtime": 0.6912,
|
| 895 |
+
"eval_samples_per_second": 66.555,
|
| 896 |
+
"eval_steps_per_second": 4.341,
|
| 897 |
+
"step": 644
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 56.52,
|
| 901 |
+
"learning_rate": 9.147727272727271e-06,
|
| 902 |
+
"loss": 0.0672,
|
| 903 |
+
"step": 650
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 56.96,
|
| 907 |
+
"eval_accuracy": 0.8695652173913043,
|
| 908 |
+
"eval_loss": 0.6480595469474792,
|
| 909 |
+
"eval_runtime": 0.7292,
|
| 910 |
+
"eval_samples_per_second": 63.086,
|
| 911 |
+
"eval_steps_per_second": 4.114,
|
| 912 |
+
"step": 655
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 57.39,
|
| 916 |
+
"learning_rate": 8.75e-06,
|
| 917 |
+
"loss": 0.0691,
|
| 918 |
+
"step": 660
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 58.0,
|
| 922 |
+
"eval_accuracy": 0.8695652173913043,
|
| 923 |
+
"eval_loss": 0.7666171789169312,
|
| 924 |
+
"eval_runtime": 0.6391,
|
| 925 |
+
"eval_samples_per_second": 71.971,
|
| 926 |
+
"eval_steps_per_second": 4.694,
|
| 927 |
+
"step": 667
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 58.26,
|
| 931 |
+
"learning_rate": 8.352272727272727e-06,
|
| 932 |
+
"loss": 0.0733,
|
| 933 |
+
"step": 670
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 58.96,
|
| 937 |
+
"eval_accuracy": 0.8478260869565217,
|
| 938 |
+
"eval_loss": 0.7665241360664368,
|
| 939 |
+
"eval_runtime": 0.6431,
|
| 940 |
+
"eval_samples_per_second": 71.524,
|
| 941 |
+
"eval_steps_per_second": 4.665,
|
| 942 |
+
"step": 678
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 59.13,
|
| 946 |
+
"learning_rate": 7.954545454545453e-06,
|
| 947 |
+
"loss": 0.0984,
|
| 948 |
+
"step": 680
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 60.0,
|
| 952 |
+
"learning_rate": 7.556818181818181e-06,
|
| 953 |
+
"loss": 0.0982,
|
| 954 |
+
"step": 690
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 60.0,
|
| 958 |
+
"eval_accuracy": 0.8478260869565217,
|
| 959 |
+
"eval_loss": 0.857338011264801,
|
| 960 |
+
"eval_runtime": 0.6657,
|
| 961 |
+
"eval_samples_per_second": 69.105,
|
| 962 |
+
"eval_steps_per_second": 4.507,
|
| 963 |
+
"step": 690
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 60.87,
|
| 967 |
+
"learning_rate": 7.159090909090909e-06,
|
| 968 |
+
"loss": 0.0791,
|
| 969 |
+
"step": 700
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 60.96,
|
| 973 |
+
"eval_accuracy": 0.8695652173913043,
|
| 974 |
+
"eval_loss": 0.7858647704124451,
|
| 975 |
+
"eval_runtime": 0.6367,
|
| 976 |
+
"eval_samples_per_second": 72.253,
|
| 977 |
+
"eval_steps_per_second": 4.712,
|
| 978 |
+
"step": 701
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 61.74,
|
| 982 |
+
"learning_rate": 6.7613636363636355e-06,
|
| 983 |
+
"loss": 0.0559,
|
| 984 |
+
"step": 710
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 62.0,
|
| 988 |
+
"eval_accuracy": 0.8260869565217391,
|
| 989 |
+
"eval_loss": 0.7714826464653015,
|
| 990 |
+
"eval_runtime": 0.6571,
|
| 991 |
+
"eval_samples_per_second": 70.0,
|
| 992 |
+
"eval_steps_per_second": 4.565,
|
| 993 |
+
"step": 713
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 62.61,
|
| 997 |
+
"learning_rate": 6.363636363636363e-06,
|
| 998 |
+
"loss": 0.0725,
|
| 999 |
+
"step": 720
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 62.96,
|
| 1003 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1004 |
+
"eval_loss": 0.8547795414924622,
|
| 1005 |
+
"eval_runtime": 0.6541,
|
| 1006 |
+
"eval_samples_per_second": 70.321,
|
| 1007 |
+
"eval_steps_per_second": 4.586,
|
| 1008 |
+
"step": 724
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 63.48,
|
| 1012 |
+
"learning_rate": 5.96590909090909e-06,
|
| 1013 |
+
"loss": 0.065,
|
| 1014 |
+
"step": 730
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 64.0,
|
| 1018 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1019 |
+
"eval_loss": 0.8533302545547485,
|
| 1020 |
+
"eval_runtime": 0.6612,
|
| 1021 |
+
"eval_samples_per_second": 69.575,
|
| 1022 |
+
"eval_steps_per_second": 4.537,
|
| 1023 |
+
"step": 736
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 64.35,
|
| 1027 |
+
"learning_rate": 5.5681818181818175e-06,
|
| 1028 |
+
"loss": 0.0844,
|
| 1029 |
+
"step": 740
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 64.96,
|
| 1033 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1034 |
+
"eval_loss": 0.8175135850906372,
|
| 1035 |
+
"eval_runtime": 0.6431,
|
| 1036 |
+
"eval_samples_per_second": 71.524,
|
| 1037 |
+
"eval_steps_per_second": 4.665,
|
| 1038 |
+
"step": 747
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 65.22,
|
| 1042 |
+
"learning_rate": 5.1704545454545455e-06,
|
| 1043 |
+
"loss": 0.0664,
|
| 1044 |
+
"step": 750
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 66.0,
|
| 1048 |
+
"eval_accuracy": 0.8260869565217391,
|
| 1049 |
+
"eval_loss": 0.7742665410041809,
|
| 1050 |
+
"eval_runtime": 0.6437,
|
| 1051 |
+
"eval_samples_per_second": 71.467,
|
| 1052 |
+
"eval_steps_per_second": 4.661,
|
| 1053 |
+
"step": 759
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 66.09,
|
| 1057 |
+
"learning_rate": 4.772727272727272e-06,
|
| 1058 |
+
"loss": 0.0601,
|
| 1059 |
+
"step": 760
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 66.96,
|
| 1063 |
+
"learning_rate": 4.375e-06,
|
| 1064 |
+
"loss": 0.0696,
|
| 1065 |
+
"step": 770
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 66.96,
|
| 1069 |
+
"eval_accuracy": 0.8695652173913043,
|
| 1070 |
+
"eval_loss": 0.8106241822242737,
|
| 1071 |
+
"eval_runtime": 0.6692,
|
| 1072 |
+
"eval_samples_per_second": 68.742,
|
| 1073 |
+
"eval_steps_per_second": 4.483,
|
| 1074 |
+
"step": 770
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 67.83,
|
| 1078 |
+
"learning_rate": 3.977272727272727e-06,
|
| 1079 |
+
"loss": 0.0567,
|
| 1080 |
+
"step": 780
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 68.0,
|
| 1084 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1085 |
+
"eval_loss": 0.7903584241867065,
|
| 1086 |
+
"eval_runtime": 0.7197,
|
| 1087 |
+
"eval_samples_per_second": 63.918,
|
| 1088 |
+
"eval_steps_per_second": 4.169,
|
| 1089 |
+
"step": 782
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 68.7,
|
| 1093 |
+
"learning_rate": 3.5795454545454546e-06,
|
| 1094 |
+
"loss": 0.083,
|
| 1095 |
+
"step": 790
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 68.96,
|
| 1099 |
+
"eval_accuracy": 0.8043478260869565,
|
| 1100 |
+
"eval_loss": 0.854982852935791,
|
| 1101 |
+
"eval_runtime": 0.7112,
|
| 1102 |
+
"eval_samples_per_second": 64.681,
|
| 1103 |
+
"eval_steps_per_second": 4.218,
|
| 1104 |
+
"step": 793
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 69.57,
|
| 1108 |
+
"learning_rate": 3.1818181818181817e-06,
|
| 1109 |
+
"loss": 0.0385,
|
| 1110 |
+
"step": 800
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 70.0,
|
| 1114 |
+
"eval_accuracy": 0.8260869565217391,
|
| 1115 |
+
"eval_loss": 0.8915210366249084,
|
| 1116 |
+
"eval_runtime": 0.7182,
|
| 1117 |
+
"eval_samples_per_second": 64.053,
|
| 1118 |
+
"eval_steps_per_second": 4.177,
|
| 1119 |
+
"step": 805
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 70.43,
|
| 1123 |
+
"learning_rate": 2.7840909090909088e-06,
|
| 1124 |
+
"loss": 0.0714,
|
| 1125 |
+
"step": 810
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 70.96,
|
| 1129 |
+
"eval_accuracy": 0.8260869565217391,
|
| 1130 |
+
"eval_loss": 0.8631047606468201,
|
| 1131 |
+
"eval_runtime": 0.6702,
|
| 1132 |
+
"eval_samples_per_second": 68.639,
|
| 1133 |
+
"eval_steps_per_second": 4.476,
|
| 1134 |
+
"step": 816
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 71.3,
|
| 1138 |
+
"learning_rate": 2.386363636363636e-06,
|
| 1139 |
+
"loss": 0.0444,
|
| 1140 |
+
"step": 820
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 72.0,
|
| 1144 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1145 |
+
"eval_loss": 0.82310551404953,
|
| 1146 |
+
"eval_runtime": 0.6397,
|
| 1147 |
+
"eval_samples_per_second": 71.913,
|
| 1148 |
+
"eval_steps_per_second": 4.69,
|
| 1149 |
+
"step": 828
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 72.17,
|
| 1153 |
+
"learning_rate": 1.9886363636363633e-06,
|
| 1154 |
+
"loss": 0.0496,
|
| 1155 |
+
"step": 830
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 72.96,
|
| 1159 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1160 |
+
"eval_loss": 0.8199043869972229,
|
| 1161 |
+
"eval_runtime": 0.6597,
|
| 1162 |
+
"eval_samples_per_second": 69.733,
|
| 1163 |
+
"eval_steps_per_second": 4.548,
|
| 1164 |
+
"step": 839
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 73.04,
|
| 1168 |
+
"learning_rate": 1.5909090909090908e-06,
|
| 1169 |
+
"loss": 0.0333,
|
| 1170 |
+
"step": 840
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 73.91,
|
| 1174 |
+
"learning_rate": 1.193181818181818e-06,
|
| 1175 |
+
"loss": 0.0887,
|
| 1176 |
+
"step": 850
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 74.0,
|
| 1180 |
+
"eval_accuracy": 0.8478260869565217,
|
| 1181 |
+
"eval_loss": 0.8303984999656677,
|
| 1182 |
+
"eval_runtime": 0.6507,
|
| 1183 |
+
"eval_samples_per_second": 70.698,
|
| 1184 |
+
"eval_steps_per_second": 4.611,
|
| 1185 |
+
"step": 851
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 74.78,
|
| 1189 |
+
"learning_rate": 7.954545454545454e-07,
|
| 1190 |
+
"loss": 0.0475,
|
| 1191 |
+
"step": 860
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 74.96,
|
| 1195 |
+
"eval_accuracy": 0.8260869565217391,
|
| 1196 |
+
"eval_loss": 0.8528614640235901,
|
| 1197 |
+
"eval_runtime": 0.6557,
|
| 1198 |
+
"eval_samples_per_second": 70.159,
|
| 1199 |
+
"eval_steps_per_second": 4.576,
|
| 1200 |
+
"step": 862
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 75.65,
|
| 1204 |
+
"learning_rate": 3.977272727272727e-07,
|
| 1205 |
+
"loss": 0.0639,
|
| 1206 |
+
"step": 870
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 76.0,
|
| 1210 |
+
"eval_accuracy": 0.8260869565217391,
|
| 1211 |
+
"eval_loss": 0.8579635620117188,
|
| 1212 |
+
"eval_runtime": 0.6582,
|
| 1213 |
+
"eval_samples_per_second": 69.891,
|
| 1214 |
+
"eval_steps_per_second": 4.558,
|
| 1215 |
+
"step": 874
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 76.52,
|
| 1219 |
+
"learning_rate": 0.0,
|
| 1220 |
+
"loss": 0.0704,
|
| 1221 |
+
"step": 880
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 76.52,
|
| 1225 |
+
"eval_accuracy": 0.8260869565217391,
|
| 1226 |
+
"eval_loss": 0.8589013814926147,
|
| 1227 |
+
"eval_runtime": 0.6641,
|
| 1228 |
+
"eval_samples_per_second": 69.264,
|
| 1229 |
+
"eval_steps_per_second": 4.517,
|
| 1230 |
+
"step": 880
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 76.52,
|
| 1234 |
+
"step": 880,
|
| 1235 |
+
"total_flos": 4.2801440000281805e+18,
|
| 1236 |
+
"train_loss": 0.24412418752908707,
|
| 1237 |
+
"train_runtime": 1381.4229,
|
| 1238 |
+
"train_samples_per_second": 41.812,
|
| 1239 |
+
"train_steps_per_second": 0.637
|
| 1240 |
+
}
|
| 1241 |
+
],
|
| 1242 |
+
"logging_steps": 10,
|
| 1243 |
+
"max_steps": 880,
|
| 1244 |
+
"num_input_tokens_seen": 0,
|
| 1245 |
+
"num_train_epochs": 80,
|
| 1246 |
+
"save_steps": 500,
|
| 1247 |
+
"total_flos": 4.2801440000281805e+18,
|
| 1248 |
+
"train_batch_size": 16,
|
| 1249 |
+
"trial_name": null,
|
| 1250 |
+
"trial_params": null
|
| 1251 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8c3f27ccb9408557df581877eda2a835278bdb1388c9cff802b3538992be73a
|
| 3 |
+
size 4728
|