Commit
•
f498af0
1
Parent(s):
d9e4e15
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base-960h
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-base-960h-EMOPIA-10sec-full-100epoc
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wav2vec2-base-960h-EMOPIA-10sec-full-100epoc
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.5358
|
| 22 |
+
- Accuracy: 0.8737
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 100
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 54 |
+
| 1.2276 | 1.0 | 2248 | 1.3142 | 0.5730 |
|
| 55 |
+
| 1.4493 | 2.0 | 4496 | 1.5339 | 0.5907 |
|
| 56 |
+
| 1.4328 | 3.0 | 6744 | 1.5229 | 0.6584 |
|
| 57 |
+
| 1.3839 | 4.0 | 8992 | 1.3336 | 0.6922 |
|
| 58 |
+
| 1.4591 | 5.0 | 11240 | 1.4407 | 0.6762 |
|
| 59 |
+
| 1.3609 | 6.0 | 13488 | 1.1341 | 0.7117 |
|
| 60 |
+
| 1.222 | 7.0 | 15736 | 1.5204 | 0.7028 |
|
| 61 |
+
| 1.1713 | 8.0 | 17984 | 1.3222 | 0.7473 |
|
| 62 |
+
| 1.1414 | 9.0 | 20232 | 1.3233 | 0.7562 |
|
| 63 |
+
| 1.0977 | 10.0 | 22480 | 1.3587 | 0.7384 |
|
| 64 |
+
| 0.9768 | 11.0 | 24728 | 1.3482 | 0.7633 |
|
| 65 |
+
| 0.9219 | 12.0 | 26976 | 1.3743 | 0.7580 |
|
| 66 |
+
| 0.8636 | 13.0 | 29224 | 1.1195 | 0.8167 |
|
| 67 |
+
| 0.8543 | 14.0 | 31472 | 1.1716 | 0.8043 |
|
| 68 |
+
| 0.8053 | 15.0 | 33720 | 1.2033 | 0.8114 |
|
| 69 |
+
| 0.7718 | 16.0 | 35968 | 1.2491 | 0.7989 |
|
| 70 |
+
| 0.6904 | 17.0 | 38216 | 1.0851 | 0.8363 |
|
| 71 |
+
| 0.6545 | 18.0 | 40464 | 1.2963 | 0.8007 |
|
| 72 |
+
| 0.6858 | 19.0 | 42712 | 1.3231 | 0.8078 |
|
| 73 |
+
| 0.6444 | 20.0 | 44960 | 1.1918 | 0.8238 |
|
| 74 |
+
| 0.6166 | 21.0 | 47208 | 1.1358 | 0.8345 |
|
| 75 |
+
| 0.5437 | 22.0 | 49456 | 1.2446 | 0.8256 |
|
| 76 |
+
| 0.4719 | 23.0 | 51704 | 1.4120 | 0.8149 |
|
| 77 |
+
| 0.4802 | 24.0 | 53952 | 1.2611 | 0.8203 |
|
| 78 |
+
| 0.484 | 25.0 | 56200 | 1.2840 | 0.8363 |
|
| 79 |
+
| 0.3649 | 26.0 | 58448 | 1.2421 | 0.8434 |
|
| 80 |
+
| 0.4146 | 27.0 | 60696 | 1.3465 | 0.8292 |
|
| 81 |
+
| 0.3998 | 28.0 | 62944 | 1.2309 | 0.8505 |
|
| 82 |
+
| 0.4113 | 29.0 | 65192 | 1.1663 | 0.8523 |
|
| 83 |
+
| 0.3385 | 30.0 | 67440 | 1.2567 | 0.8470 |
|
| 84 |
+
| 0.3188 | 31.0 | 69688 | 1.2581 | 0.8434 |
|
| 85 |
+
| 0.3203 | 32.0 | 71936 | 1.2454 | 0.8541 |
|
| 86 |
+
| 0.2766 | 33.0 | 74184 | 1.2542 | 0.8523 |
|
| 87 |
+
| 0.2505 | 34.0 | 76432 | 1.5897 | 0.8149 |
|
| 88 |
+
| 0.2777 | 35.0 | 78680 | 1.3483 | 0.8363 |
|
| 89 |
+
| 0.2816 | 36.0 | 80928 | 1.2510 | 0.8523 |
|
| 90 |
+
| 0.2728 | 37.0 | 83176 | 1.4422 | 0.8327 |
|
| 91 |
+
| 0.255 | 38.0 | 85424 | 1.2928 | 0.8488 |
|
| 92 |
+
| 0.2172 | 39.0 | 87672 | 1.4022 | 0.8452 |
|
| 93 |
+
| 0.2204 | 40.0 | 89920 | 1.4114 | 0.8381 |
|
| 94 |
+
| 0.2232 | 41.0 | 92168 | 1.4324 | 0.8416 |
|
| 95 |
+
| 0.2301 | 42.0 | 94416 | 1.3528 | 0.8488 |
|
| 96 |
+
| 0.1751 | 43.0 | 96664 | 1.4649 | 0.8434 |
|
| 97 |
+
| 0.1982 | 44.0 | 98912 | 1.2216 | 0.8754 |
|
| 98 |
+
| 0.1803 | 45.0 | 101160 | 1.4569 | 0.8452 |
|
| 99 |
+
| 0.1582 | 46.0 | 103408 | 1.3650 | 0.8665 |
|
| 100 |
+
| 0.1837 | 47.0 | 105656 | 1.2877 | 0.8541 |
|
| 101 |
+
| 0.1458 | 48.0 | 107904 | 1.7389 | 0.8310 |
|
| 102 |
+
| 0.1664 | 49.0 | 110152 | 1.4001 | 0.8541 |
|
| 103 |
+
| 0.1473 | 50.0 | 112400 | 1.2979 | 0.8701 |
|
| 104 |
+
| 0.1341 | 51.0 | 114648 | 1.5705 | 0.8470 |
|
| 105 |
+
| 0.1603 | 52.0 | 116896 | 1.6043 | 0.8381 |
|
| 106 |
+
| 0.1133 | 53.0 | 119144 | 1.6194 | 0.8452 |
|
| 107 |
+
| 0.107 | 54.0 | 121392 | 1.4173 | 0.8630 |
|
| 108 |
+
| 0.116 | 55.0 | 123640 | 1.5268 | 0.8541 |
|
| 109 |
+
| 0.0988 | 56.0 | 125888 | 1.6092 | 0.8523 |
|
| 110 |
+
| 0.139 | 57.0 | 128136 | 1.4312 | 0.8648 |
|
| 111 |
+
| 0.0798 | 58.0 | 130384 | 1.7888 | 0.8327 |
|
| 112 |
+
| 0.0776 | 59.0 | 132632 | 1.5457 | 0.8665 |
|
| 113 |
+
| 0.1288 | 60.0 | 134880 | 1.4554 | 0.8630 |
|
| 114 |
+
| 0.0828 | 61.0 | 137128 | 1.7078 | 0.8559 |
|
| 115 |
+
| 0.0823 | 62.0 | 139376 | 1.4734 | 0.8754 |
|
| 116 |
+
| 0.0803 | 63.0 | 141624 | 1.6007 | 0.8594 |
|
| 117 |
+
| 0.0947 | 64.0 | 143872 | 1.4467 | 0.8701 |
|
| 118 |
+
| 0.0916 | 65.0 | 146120 | 1.4410 | 0.8737 |
|
| 119 |
+
| 0.0814 | 66.0 | 148368 | 1.7116 | 0.8470 |
|
| 120 |
+
| 0.0938 | 67.0 | 150616 | 1.5838 | 0.8630 |
|
| 121 |
+
| 0.066 | 68.0 | 152864 | 1.6458 | 0.8559 |
|
| 122 |
+
| 0.096 | 69.0 | 155112 | 1.6926 | 0.8559 |
|
| 123 |
+
| 0.0638 | 70.0 | 157360 | 1.5233 | 0.8630 |
|
| 124 |
+
| 0.063 | 71.0 | 159608 | 1.5641 | 0.8594 |
|
| 125 |
+
| 0.0758 | 72.0 | 161856 | 1.6767 | 0.8505 |
|
| 126 |
+
| 0.0579 | 73.0 | 164104 | 1.5338 | 0.8630 |
|
| 127 |
+
| 0.0379 | 74.0 | 166352 | 1.6348 | 0.8630 |
|
| 128 |
+
| 0.0351 | 75.0 | 168600 | 1.7037 | 0.8559 |
|
| 129 |
+
| 0.0472 | 76.0 | 170848 | 1.5682 | 0.8754 |
|
| 130 |
+
| 0.0253 | 77.0 | 173096 | 1.7067 | 0.8559 |
|
| 131 |
+
| 0.073 | 78.0 | 175344 | 1.4460 | 0.8754 |
|
| 132 |
+
| 0.049 | 79.0 | 177592 | 1.5897 | 0.8594 |
|
| 133 |
+
| 0.0503 | 80.0 | 179840 | 1.6017 | 0.8648 |
|
| 134 |
+
| 0.0497 | 81.0 | 182088 | 1.5319 | 0.8683 |
|
| 135 |
+
| 0.0553 | 82.0 | 184336 | 1.5479 | 0.8612 |
|
| 136 |
+
| 0.0416 | 83.0 | 186584 | 1.5556 | 0.8577 |
|
| 137 |
+
| 0.0641 | 84.0 | 188832 | 1.5675 | 0.8594 |
|
| 138 |
+
| 0.0425 | 85.0 | 191080 | 1.6854 | 0.8559 |
|
| 139 |
+
| 0.0311 | 86.0 | 193328 | 1.4628 | 0.8737 |
|
| 140 |
+
| 0.0456 | 87.0 | 195576 | 1.5069 | 0.8701 |
|
| 141 |
+
| 0.0224 | 88.0 | 197824 | 1.6130 | 0.8665 |
|
| 142 |
+
| 0.0345 | 89.0 | 200072 | 1.5750 | 0.8701 |
|
| 143 |
+
| 0.041 | 90.0 | 202320 | 1.5230 | 0.8719 |
|
| 144 |
+
| 0.0165 | 91.0 | 204568 | 1.6564 | 0.8594 |
|
| 145 |
+
| 0.0478 | 92.0 | 206816 | 1.5940 | 0.8630 |
|
| 146 |
+
| 0.032 | 93.0 | 209064 | 1.4741 | 0.8808 |
|
| 147 |
+
| 0.0433 | 94.0 | 211312 | 1.5333 | 0.8719 |
|
| 148 |
+
| 0.0243 | 95.0 | 213560 | 1.5165 | 0.8719 |
|
| 149 |
+
| 0.0165 | 96.0 | 215808 | 1.5775 | 0.8683 |
|
| 150 |
+
| 0.0177 | 97.0 | 218056 | 1.5302 | 0.8772 |
|
| 151 |
+
| 0.0253 | 98.0 | 220304 | 1.5424 | 0.8754 |
|
| 152 |
+
| 0.0224 | 99.0 | 222552 | 1.5462 | 0.8719 |
|
| 153 |
+
| 0.0213 | 100.0 | 224800 | 1.5358 | 0.8737 |
|
| 154 |
+
|
| 155 |
+
|
| 156 |
+
### Framework versions
|
| 157 |
+
|
| 158 |
+
- Transformers 4.45.2
|
| 159 |
+
- Pytorch 2.4.1+cu118
|
| 160 |
+
- Datasets 3.0.1
|
| 161 |
+
- Tokenizers 0.20.0
|
config.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSpeechClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "group",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.1,
|
| 56 |
+
"finetuning_task": "facebook/wav2vec2-base-960h",
|
| 57 |
+
"gradient_checkpointing": false,
|
| 58 |
+
"hidden_act": "gelu",
|
| 59 |
+
"hidden_dropout": 0.1,
|
| 60 |
+
"hidden_dropout_prob": 0.1,
|
| 61 |
+
"hidden_size": 768,
|
| 62 |
+
"id2label": {
|
| 63 |
+
"0": "Q1",
|
| 64 |
+
"1": "Q2",
|
| 65 |
+
"2": "Q3",
|
| 66 |
+
"3": "Q4"
|
| 67 |
+
},
|
| 68 |
+
"initializer_range": 0.02,
|
| 69 |
+
"intermediate_size": 3072,
|
| 70 |
+
"label2id": {
|
| 71 |
+
"Q1": 0,
|
| 72 |
+
"Q2": 1,
|
| 73 |
+
"Q3": 2,
|
| 74 |
+
"Q4": 3
|
| 75 |
+
},
|
| 76 |
+
"layer_norm_eps": 1e-05,
|
| 77 |
+
"layerdrop": 0.1,
|
| 78 |
+
"mask_feature_length": 10,
|
| 79 |
+
"mask_feature_min_masks": 0,
|
| 80 |
+
"mask_feature_prob": 0.0,
|
| 81 |
+
"mask_time_length": 10,
|
| 82 |
+
"mask_time_min_masks": 2,
|
| 83 |
+
"mask_time_prob": 0.05,
|
| 84 |
+
"model_type": "wav2vec2",
|
| 85 |
+
"num_adapter_layers": 3,
|
| 86 |
+
"num_attention_heads": 12,
|
| 87 |
+
"num_codevector_groups": 2,
|
| 88 |
+
"num_codevectors_per_group": 320,
|
| 89 |
+
"num_conv_pos_embedding_groups": 16,
|
| 90 |
+
"num_conv_pos_embeddings": 128,
|
| 91 |
+
"num_feat_extract_layers": 7,
|
| 92 |
+
"num_hidden_layers": 12,
|
| 93 |
+
"num_negatives": 100,
|
| 94 |
+
"output_hidden_size": 768,
|
| 95 |
+
"pad_token_id": 0,
|
| 96 |
+
"pooling_mode": "mean",
|
| 97 |
+
"problem_type": "single_label_classification",
|
| 98 |
+
"proj_codevector_dim": 256,
|
| 99 |
+
"tdnn_dilation": [
|
| 100 |
+
1,
|
| 101 |
+
2,
|
| 102 |
+
3,
|
| 103 |
+
1,
|
| 104 |
+
1
|
| 105 |
+
],
|
| 106 |
+
"tdnn_dim": [
|
| 107 |
+
512,
|
| 108 |
+
512,
|
| 109 |
+
512,
|
| 110 |
+
512,
|
| 111 |
+
1500
|
| 112 |
+
],
|
| 113 |
+
"tdnn_kernel": [
|
| 114 |
+
5,
|
| 115 |
+
3,
|
| 116 |
+
3,
|
| 117 |
+
1,
|
| 118 |
+
1
|
| 119 |
+
],
|
| 120 |
+
"torch_dtype": "float32",
|
| 121 |
+
"transformers_version": "4.45.2",
|
| 122 |
+
"use_weighted_layer_sum": false,
|
| 123 |
+
"vocab_size": 32,
|
| 124 |
+
"xvector_output_dim": 512
|
| 125 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c68d3b1a2e460fb99cbce9243e70a09b0d12d580ee82d25e5de3643f3764cc0
|
| 3 |
+
size 379887584
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
runs/Oct08_13-55-12_ip-172-16-45-83.ap-northeast-1.compute.internal/events.out.tfevents.1728395848.ip-172-16-45-83.ap-northeast-1.compute.internal
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc72a36024f165d17c797288fe0613db2e107d8d8071ce4ce5f49f99b19ec853
|
| 3 |
+
size 61377
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1642 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 224800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 17.773962020874023,
|
| 14 |
+
"learning_rate": 9.900311387900357e-06,
|
| 15 |
+
"loss": 1.2276,
|
| 16 |
+
"step": 2248
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.5729537606239319,
|
| 21 |
+
"eval_loss": 1.3142218589782715,
|
| 22 |
+
"eval_runtime": 43.9858,
|
| 23 |
+
"eval_samples_per_second": 12.777,
|
| 24 |
+
"eval_steps_per_second": 12.777,
|
| 25 |
+
"step": 2248
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 33.84526824951172,
|
| 30 |
+
"learning_rate": 9.800355871886121e-06,
|
| 31 |
+
"loss": 1.4493,
|
| 32 |
+
"step": 4496
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.5907473564147949,
|
| 37 |
+
"eval_loss": 1.5339363813400269,
|
| 38 |
+
"eval_runtime": 44.2068,
|
| 39 |
+
"eval_samples_per_second": 12.713,
|
| 40 |
+
"eval_steps_per_second": 12.713,
|
| 41 |
+
"step": 4496
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 0.590007483959198,
|
| 46 |
+
"learning_rate": 9.700400355871887e-06,
|
| 47 |
+
"loss": 1.4328,
|
| 48 |
+
"step": 6744
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.6583629846572876,
|
| 53 |
+
"eval_loss": 1.5228670835494995,
|
| 54 |
+
"eval_runtime": 44.2648,
|
| 55 |
+
"eval_samples_per_second": 12.696,
|
| 56 |
+
"eval_steps_per_second": 12.696,
|
| 57 |
+
"step": 6744
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 27.285722732543945,
|
| 62 |
+
"learning_rate": 9.600533807829182e-06,
|
| 63 |
+
"loss": 1.3839,
|
| 64 |
+
"step": 8992
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.6921707987785339,
|
| 69 |
+
"eval_loss": 1.333614706993103,
|
| 70 |
+
"eval_runtime": 44.2465,
|
| 71 |
+
"eval_samples_per_second": 12.702,
|
| 72 |
+
"eval_steps_per_second": 12.702,
|
| 73 |
+
"step": 8992
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 28.629926681518555,
|
| 78 |
+
"learning_rate": 9.500533807829183e-06,
|
| 79 |
+
"loss": 1.4591,
|
| 80 |
+
"step": 11240
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.6761565804481506,
|
| 85 |
+
"eval_loss": 1.4407259225845337,
|
| 86 |
+
"eval_runtime": 44.1453,
|
| 87 |
+
"eval_samples_per_second": 12.731,
|
| 88 |
+
"eval_steps_per_second": 12.731,
|
| 89 |
+
"step": 11240
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 14.747943878173828,
|
| 94 |
+
"learning_rate": 9.400533807829182e-06,
|
| 95 |
+
"loss": 1.3609,
|
| 96 |
+
"step": 13488
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.7117437720298767,
|
| 101 |
+
"eval_loss": 1.1341328620910645,
|
| 102 |
+
"eval_runtime": 44.9034,
|
| 103 |
+
"eval_samples_per_second": 12.516,
|
| 104 |
+
"eval_steps_per_second": 12.516,
|
| 105 |
+
"step": 13488
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 44.90867233276367,
|
| 110 |
+
"learning_rate": 9.300578291814948e-06,
|
| 111 |
+
"loss": 1.222,
|
| 112 |
+
"step": 15736
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.7028470039367676,
|
| 117 |
+
"eval_loss": 1.5203638076782227,
|
| 118 |
+
"eval_runtime": 44.0645,
|
| 119 |
+
"eval_samples_per_second": 12.754,
|
| 120 |
+
"eval_steps_per_second": 12.754,
|
| 121 |
+
"step": 15736
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 0.5433468818664551,
|
| 126 |
+
"learning_rate": 9.200622775800714e-06,
|
| 127 |
+
"loss": 1.1713,
|
| 128 |
+
"step": 17984
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.7473309636116028,
|
| 133 |
+
"eval_loss": 1.3221626281738281,
|
| 134 |
+
"eval_runtime": 44.4952,
|
| 135 |
+
"eval_samples_per_second": 12.631,
|
| 136 |
+
"eval_steps_per_second": 12.631,
|
| 137 |
+
"step": 17984
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.0,
|
| 141 |
+
"grad_norm": 0.15495184063911438,
|
| 142 |
+
"learning_rate": 9.100622775800713e-06,
|
| 143 |
+
"loss": 1.1414,
|
| 144 |
+
"step": 20232
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.0,
|
| 148 |
+
"eval_accuracy": 0.7562277317047119,
|
| 149 |
+
"eval_loss": 1.3233251571655273,
|
| 150 |
+
"eval_runtime": 44.534,
|
| 151 |
+
"eval_samples_per_second": 12.62,
|
| 152 |
+
"eval_steps_per_second": 12.62,
|
| 153 |
+
"step": 20232
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"grad_norm": 0.034351445734500885,
|
| 158 |
+
"learning_rate": 9.000711743772242e-06,
|
| 159 |
+
"loss": 1.0977,
|
| 160 |
+
"step": 22480
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 10.0,
|
| 164 |
+
"eval_accuracy": 0.7384341359138489,
|
| 165 |
+
"eval_loss": 1.3587311506271362,
|
| 166 |
+
"eval_runtime": 44.5493,
|
| 167 |
+
"eval_samples_per_second": 12.615,
|
| 168 |
+
"eval_steps_per_second": 12.615,
|
| 169 |
+
"step": 22480
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 11.0,
|
| 173 |
+
"grad_norm": 0.17834441363811493,
|
| 174 |
+
"learning_rate": 8.900711743772243e-06,
|
| 175 |
+
"loss": 0.9768,
|
| 176 |
+
"step": 24728
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.0,
|
| 180 |
+
"eval_accuracy": 0.7633451819419861,
|
| 181 |
+
"eval_loss": 1.348164677619934,
|
| 182 |
+
"eval_runtime": 44.2727,
|
| 183 |
+
"eval_samples_per_second": 12.694,
|
| 184 |
+
"eval_steps_per_second": 12.694,
|
| 185 |
+
"step": 24728
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 12.0,
|
| 189 |
+
"grad_norm": 0.0854184553027153,
|
| 190 |
+
"learning_rate": 8.800800711743773e-06,
|
| 191 |
+
"loss": 0.9219,
|
| 192 |
+
"step": 26976
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.7580071091651917,
|
| 197 |
+
"eval_loss": 1.3742923736572266,
|
| 198 |
+
"eval_runtime": 44.1709,
|
| 199 |
+
"eval_samples_per_second": 12.723,
|
| 200 |
+
"eval_steps_per_second": 12.723,
|
| 201 |
+
"step": 26976
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"grad_norm": 1.15831458568573,
|
| 206 |
+
"learning_rate": 8.700800711743772e-06,
|
| 207 |
+
"loss": 0.8636,
|
| 208 |
+
"step": 29224
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 13.0,
|
| 212 |
+
"eval_accuracy": 0.8167259693145752,
|
| 213 |
+
"eval_loss": 1.1195218563079834,
|
| 214 |
+
"eval_runtime": 44.3771,
|
| 215 |
+
"eval_samples_per_second": 12.664,
|
| 216 |
+
"eval_steps_per_second": 12.664,
|
| 217 |
+
"step": 29224
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"grad_norm": 658.5977172851562,
|
| 222 |
+
"learning_rate": 8.600845195729538e-06,
|
| 223 |
+
"loss": 0.8543,
|
| 224 |
+
"step": 31472
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.0,
|
| 228 |
+
"eval_accuracy": 0.8042704463005066,
|
| 229 |
+
"eval_loss": 1.171613097190857,
|
| 230 |
+
"eval_runtime": 43.8385,
|
| 231 |
+
"eval_samples_per_second": 12.82,
|
| 232 |
+
"eval_steps_per_second": 12.82,
|
| 233 |
+
"step": 31472
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"grad_norm": 1.0300912857055664,
|
| 238 |
+
"learning_rate": 8.500934163701069e-06,
|
| 239 |
+
"loss": 0.8053,
|
| 240 |
+
"step": 33720
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.0,
|
| 244 |
+
"eval_accuracy": 0.8113878965377808,
|
| 245 |
+
"eval_loss": 1.2032980918884277,
|
| 246 |
+
"eval_runtime": 44.439,
|
| 247 |
+
"eval_samples_per_second": 12.647,
|
| 248 |
+
"eval_steps_per_second": 12.647,
|
| 249 |
+
"step": 33720
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"grad_norm": 0.1946033537387848,
|
| 254 |
+
"learning_rate": 8.400978647686834e-06,
|
| 255 |
+
"loss": 0.7718,
|
| 256 |
+
"step": 35968
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.7989323735237122,
|
| 261 |
+
"eval_loss": 1.249149203300476,
|
| 262 |
+
"eval_runtime": 46.8737,
|
| 263 |
+
"eval_samples_per_second": 11.99,
|
| 264 |
+
"eval_steps_per_second": 11.99,
|
| 265 |
+
"step": 35968
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 17.0,
|
| 269 |
+
"grad_norm": 0.08109813928604126,
|
| 270 |
+
"learning_rate": 8.300978647686834e-06,
|
| 271 |
+
"loss": 0.6904,
|
| 272 |
+
"step": 38216
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.0,
|
| 276 |
+
"eval_accuracy": 0.836298942565918,
|
| 277 |
+
"eval_loss": 1.0850577354431152,
|
| 278 |
+
"eval_runtime": 46.9201,
|
| 279 |
+
"eval_samples_per_second": 11.978,
|
| 280 |
+
"eval_steps_per_second": 11.978,
|
| 281 |
+
"step": 38216
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.0,
|
| 285 |
+
"grad_norm": 0.05036694556474686,
|
| 286 |
+
"learning_rate": 8.2010231316726e-06,
|
| 287 |
+
"loss": 0.6545,
|
| 288 |
+
"step": 40464
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.0,
|
| 292 |
+
"eval_accuracy": 0.8007117509841919,
|
| 293 |
+
"eval_loss": 1.2962548732757568,
|
| 294 |
+
"eval_runtime": 44.6234,
|
| 295 |
+
"eval_samples_per_second": 12.594,
|
| 296 |
+
"eval_steps_per_second": 12.594,
|
| 297 |
+
"step": 40464
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"grad_norm": 0.5516142249107361,
|
| 302 |
+
"learning_rate": 8.101023131672599e-06,
|
| 303 |
+
"loss": 0.6858,
|
| 304 |
+
"step": 42712
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 19.0,
|
| 308 |
+
"eval_accuracy": 0.8078292012214661,
|
| 309 |
+
"eval_loss": 1.3231106996536255,
|
| 310 |
+
"eval_runtime": 45.2364,
|
| 311 |
+
"eval_samples_per_second": 12.424,
|
| 312 |
+
"eval_steps_per_second": 12.424,
|
| 313 |
+
"step": 42712
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"grad_norm": 21.766986846923828,
|
| 318 |
+
"learning_rate": 8.001067615658363e-06,
|
| 319 |
+
"loss": 0.6444,
|
| 320 |
+
"step": 44960
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.8238434195518494,
|
| 325 |
+
"eval_loss": 1.1918330192565918,
|
| 326 |
+
"eval_runtime": 45.4969,
|
| 327 |
+
"eval_samples_per_second": 12.352,
|
| 328 |
+
"eval_steps_per_second": 12.352,
|
| 329 |
+
"step": 44960
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 21.0,
|
| 333 |
+
"grad_norm": 0.047945111989974976,
|
| 334 |
+
"learning_rate": 7.90111209964413e-06,
|
| 335 |
+
"loss": 0.6166,
|
| 336 |
+
"step": 47208
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 21.0,
|
| 340 |
+
"eval_accuracy": 0.8345195651054382,
|
| 341 |
+
"eval_loss": 1.1358013153076172,
|
| 342 |
+
"eval_runtime": 44.2578,
|
| 343 |
+
"eval_samples_per_second": 12.698,
|
| 344 |
+
"eval_steps_per_second": 12.698,
|
| 345 |
+
"step": 47208
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"grad_norm": 0.016365328803658485,
|
| 350 |
+
"learning_rate": 7.801156583629894e-06,
|
| 351 |
+
"loss": 0.5437,
|
| 352 |
+
"step": 49456
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 22.0,
|
| 356 |
+
"eval_accuracy": 0.8256227970123291,
|
| 357 |
+
"eval_loss": 1.2446305751800537,
|
| 358 |
+
"eval_runtime": 44.445,
|
| 359 |
+
"eval_samples_per_second": 12.645,
|
| 360 |
+
"eval_steps_per_second": 12.645,
|
| 361 |
+
"step": 49456
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 23.0,
|
| 365 |
+
"grad_norm": 0.040828485041856766,
|
| 366 |
+
"learning_rate": 7.701156583629893e-06,
|
| 367 |
+
"loss": 0.4719,
|
| 368 |
+
"step": 51704
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 23.0,
|
| 372 |
+
"eval_accuracy": 0.8149465918540955,
|
| 373 |
+
"eval_loss": 1.4120286703109741,
|
| 374 |
+
"eval_runtime": 44.091,
|
| 375 |
+
"eval_samples_per_second": 12.746,
|
| 376 |
+
"eval_steps_per_second": 12.746,
|
| 377 |
+
"step": 51704
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 24.0,
|
| 381 |
+
"grad_norm": 1.33746337890625,
|
| 382 |
+
"learning_rate": 7.601201067615659e-06,
|
| 383 |
+
"loss": 0.4802,
|
| 384 |
+
"step": 53952
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 24.0,
|
| 388 |
+
"eval_accuracy": 0.8202847242355347,
|
| 389 |
+
"eval_loss": 1.2611161470413208,
|
| 390 |
+
"eval_runtime": 44.1951,
|
| 391 |
+
"eval_samples_per_second": 12.716,
|
| 392 |
+
"eval_steps_per_second": 12.716,
|
| 393 |
+
"step": 53952
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 25.0,
|
| 397 |
+
"grad_norm": 95.64888763427734,
|
| 398 |
+
"learning_rate": 7.501290035587189e-06,
|
| 399 |
+
"loss": 0.484,
|
| 400 |
+
"step": 56200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.0,
|
| 404 |
+
"eval_accuracy": 0.836298942565918,
|
| 405 |
+
"eval_loss": 1.2840217351913452,
|
| 406 |
+
"eval_runtime": 44.2468,
|
| 407 |
+
"eval_samples_per_second": 12.701,
|
| 408 |
+
"eval_steps_per_second": 12.701,
|
| 409 |
+
"step": 56200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 26.0,
|
| 413 |
+
"grad_norm": 0.019676001742482185,
|
| 414 |
+
"learning_rate": 7.40129003558719e-06,
|
| 415 |
+
"loss": 0.3649,
|
| 416 |
+
"step": 58448
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 26.0,
|
| 420 |
+
"eval_accuracy": 0.8434163928031921,
|
| 421 |
+
"eval_loss": 1.2421414852142334,
|
| 422 |
+
"eval_runtime": 44.4397,
|
| 423 |
+
"eval_samples_per_second": 12.646,
|
| 424 |
+
"eval_steps_per_second": 12.646,
|
| 425 |
+
"step": 58448
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 27.0,
|
| 429 |
+
"grad_norm": 0.01975702866911888,
|
| 430 |
+
"learning_rate": 7.301379003558719e-06,
|
| 431 |
+
"loss": 0.4146,
|
| 432 |
+
"step": 60696
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 27.0,
|
| 436 |
+
"eval_accuracy": 0.8291814923286438,
|
| 437 |
+
"eval_loss": 1.3464977741241455,
|
| 438 |
+
"eval_runtime": 43.9971,
|
| 439 |
+
"eval_samples_per_second": 12.774,
|
| 440 |
+
"eval_steps_per_second": 12.774,
|
| 441 |
+
"step": 60696
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 28.0,
|
| 445 |
+
"grad_norm": 0.0131510766223073,
|
| 446 |
+
"learning_rate": 7.201423487544484e-06,
|
| 447 |
+
"loss": 0.3998,
|
| 448 |
+
"step": 62944
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 28.0,
|
| 452 |
+
"eval_accuracy": 0.8505337834358215,
|
| 453 |
+
"eval_loss": 1.2309142351150513,
|
| 454 |
+
"eval_runtime": 44.0844,
|
| 455 |
+
"eval_samples_per_second": 12.748,
|
| 456 |
+
"eval_steps_per_second": 12.748,
|
| 457 |
+
"step": 62944
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 29.0,
|
| 461 |
+
"grad_norm": 0.043094441294670105,
|
| 462 |
+
"learning_rate": 7.101423487544484e-06,
|
| 463 |
+
"loss": 0.4113,
|
| 464 |
+
"step": 65192
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 29.0,
|
| 468 |
+
"eval_accuracy": 0.8523131608963013,
|
| 469 |
+
"eval_loss": 1.166311264038086,
|
| 470 |
+
"eval_runtime": 45.2787,
|
| 471 |
+
"eval_samples_per_second": 12.412,
|
| 472 |
+
"eval_steps_per_second": 12.412,
|
| 473 |
+
"step": 65192
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 30.0,
|
| 477 |
+
"grad_norm": 0.04462951049208641,
|
| 478 |
+
"learning_rate": 7.001467971530249e-06,
|
| 479 |
+
"loss": 0.3385,
|
| 480 |
+
"step": 67440
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 30.0,
|
| 484 |
+
"eval_accuracy": 0.8469750881195068,
|
| 485 |
+
"eval_loss": 1.2566747665405273,
|
| 486 |
+
"eval_runtime": 43.6729,
|
| 487 |
+
"eval_samples_per_second": 12.868,
|
| 488 |
+
"eval_steps_per_second": 12.868,
|
| 489 |
+
"step": 67440
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 31.0,
|
| 493 |
+
"grad_norm": 0.003071392187848687,
|
| 494 |
+
"learning_rate": 6.901512455516015e-06,
|
| 495 |
+
"loss": 0.3188,
|
| 496 |
+
"step": 69688
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 31.0,
|
| 500 |
+
"eval_accuracy": 0.8434163928031921,
|
| 501 |
+
"eval_loss": 1.2580705881118774,
|
| 502 |
+
"eval_runtime": 45.193,
|
| 503 |
+
"eval_samples_per_second": 12.436,
|
| 504 |
+
"eval_steps_per_second": 12.436,
|
| 505 |
+
"step": 69688
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 32.0,
|
| 509 |
+
"grad_norm": 0.051271870732307434,
|
| 510 |
+
"learning_rate": 6.80155693950178e-06,
|
| 511 |
+
"loss": 0.3203,
|
| 512 |
+
"step": 71936
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 32.0,
|
| 516 |
+
"eval_accuracy": 0.854092538356781,
|
| 517 |
+
"eval_loss": 1.2454197406768799,
|
| 518 |
+
"eval_runtime": 43.9824,
|
| 519 |
+
"eval_samples_per_second": 12.778,
|
| 520 |
+
"eval_steps_per_second": 12.778,
|
| 521 |
+
"step": 71936
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 33.0,
|
| 525 |
+
"grad_norm": 0.003354266518726945,
|
| 526 |
+
"learning_rate": 6.701645907473309e-06,
|
| 527 |
+
"loss": 0.2766,
|
| 528 |
+
"step": 74184
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 33.0,
|
| 532 |
+
"eval_accuracy": 0.8523131608963013,
|
| 533 |
+
"eval_loss": 1.2542338371276855,
|
| 534 |
+
"eval_runtime": 44.114,
|
| 535 |
+
"eval_samples_per_second": 12.74,
|
| 536 |
+
"eval_steps_per_second": 12.74,
|
| 537 |
+
"step": 74184
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 34.0,
|
| 541 |
+
"grad_norm": 0.0016816665884107351,
|
| 542 |
+
"learning_rate": 6.6016459074733095e-06,
|
| 543 |
+
"loss": 0.2505,
|
| 544 |
+
"step": 76432
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 34.0,
|
| 548 |
+
"eval_accuracy": 0.8149465918540955,
|
| 549 |
+
"eval_loss": 1.5897480249404907,
|
| 550 |
+
"eval_runtime": 44.5247,
|
| 551 |
+
"eval_samples_per_second": 12.622,
|
| 552 |
+
"eval_steps_per_second": 12.622,
|
| 553 |
+
"step": 76432
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 35.0,
|
| 557 |
+
"grad_norm": 0.0018826358718797565,
|
| 558 |
+
"learning_rate": 6.501690391459075e-06,
|
| 559 |
+
"loss": 0.2777,
|
| 560 |
+
"step": 78680
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 35.0,
|
| 564 |
+
"eval_accuracy": 0.836298942565918,
|
| 565 |
+
"eval_loss": 1.348265528678894,
|
| 566 |
+
"eval_runtime": 44.5684,
|
| 567 |
+
"eval_samples_per_second": 12.61,
|
| 568 |
+
"eval_steps_per_second": 12.61,
|
| 569 |
+
"step": 78680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 36.0,
|
| 573 |
+
"grad_norm": 0.0017322949133813381,
|
| 574 |
+
"learning_rate": 6.40173487544484e-06,
|
| 575 |
+
"loss": 0.2816,
|
| 576 |
+
"step": 80928
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 36.0,
|
| 580 |
+
"eval_accuracy": 0.8523131608963013,
|
| 581 |
+
"eval_loss": 1.2510393857955933,
|
| 582 |
+
"eval_runtime": 44.2735,
|
| 583 |
+
"eval_samples_per_second": 12.694,
|
| 584 |
+
"eval_steps_per_second": 12.694,
|
| 585 |
+
"step": 80928
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 37.0,
|
| 589 |
+
"grad_norm": 0.002890912117436528,
|
| 590 |
+
"learning_rate": 6.301779359430605e-06,
|
| 591 |
+
"loss": 0.2728,
|
| 592 |
+
"step": 83176
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 37.0,
|
| 596 |
+
"eval_accuracy": 0.8327401876449585,
|
| 597 |
+
"eval_loss": 1.4422318935394287,
|
| 598 |
+
"eval_runtime": 45.8456,
|
| 599 |
+
"eval_samples_per_second": 12.259,
|
| 600 |
+
"eval_steps_per_second": 12.259,
|
| 601 |
+
"step": 83176
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 38.0,
|
| 605 |
+
"grad_norm": 0.021676644682884216,
|
| 606 |
+
"learning_rate": 6.20182384341637e-06,
|
| 607 |
+
"loss": 0.255,
|
| 608 |
+
"step": 85424
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 38.0,
|
| 612 |
+
"eval_accuracy": 0.8487544655799866,
|
| 613 |
+
"eval_loss": 1.2928466796875,
|
| 614 |
+
"eval_runtime": 44.6873,
|
| 615 |
+
"eval_samples_per_second": 12.576,
|
| 616 |
+
"eval_steps_per_second": 12.576,
|
| 617 |
+
"step": 85424
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 39.0,
|
| 621 |
+
"grad_norm": 0.06743878126144409,
|
| 622 |
+
"learning_rate": 6.10182384341637e-06,
|
| 623 |
+
"loss": 0.2172,
|
| 624 |
+
"step": 87672
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 39.0,
|
| 628 |
+
"eval_accuracy": 0.8451957106590271,
|
| 629 |
+
"eval_loss": 1.4022176265716553,
|
| 630 |
+
"eval_runtime": 44.9479,
|
| 631 |
+
"eval_samples_per_second": 12.503,
|
| 632 |
+
"eval_steps_per_second": 12.503,
|
| 633 |
+
"step": 87672
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 40.0,
|
| 637 |
+
"grad_norm": 0.0027778081130236387,
|
| 638 |
+
"learning_rate": 6.001823843416371e-06,
|
| 639 |
+
"loss": 0.2204,
|
| 640 |
+
"step": 89920
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 40.0,
|
| 644 |
+
"eval_accuracy": 0.8380783200263977,
|
| 645 |
+
"eval_loss": 1.4114270210266113,
|
| 646 |
+
"eval_runtime": 44.0198,
|
| 647 |
+
"eval_samples_per_second": 12.767,
|
| 648 |
+
"eval_steps_per_second": 12.767,
|
| 649 |
+
"step": 89920
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 41.0,
|
| 653 |
+
"grad_norm": 0.007720357272773981,
|
| 654 |
+
"learning_rate": 5.901912811387901e-06,
|
| 655 |
+
"loss": 0.2232,
|
| 656 |
+
"step": 92168
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 41.0,
|
| 660 |
+
"eval_accuracy": 0.8416370153427124,
|
| 661 |
+
"eval_loss": 1.4324493408203125,
|
| 662 |
+
"eval_runtime": 43.6963,
|
| 663 |
+
"eval_samples_per_second": 12.861,
|
| 664 |
+
"eval_steps_per_second": 12.861,
|
| 665 |
+
"step": 92168
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 42.0,
|
| 669 |
+
"grad_norm": 0.007710450328886509,
|
| 670 |
+
"learning_rate": 5.8019572953736655e-06,
|
| 671 |
+
"loss": 0.2301,
|
| 672 |
+
"step": 94416
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 42.0,
|
| 676 |
+
"eval_accuracy": 0.8487544655799866,
|
| 677 |
+
"eval_loss": 1.3528090715408325,
|
| 678 |
+
"eval_runtime": 45.0443,
|
| 679 |
+
"eval_samples_per_second": 12.477,
|
| 680 |
+
"eval_steps_per_second": 12.477,
|
| 681 |
+
"step": 94416
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 43.0,
|
| 685 |
+
"grad_norm": 0.00038957124343141913,
|
| 686 |
+
"learning_rate": 5.70200177935943e-06,
|
| 687 |
+
"loss": 0.1751,
|
| 688 |
+
"step": 96664
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 43.0,
|
| 692 |
+
"eval_accuracy": 0.8434163928031921,
|
| 693 |
+
"eval_loss": 1.4648776054382324,
|
| 694 |
+
"eval_runtime": 44.1086,
|
| 695 |
+
"eval_samples_per_second": 12.741,
|
| 696 |
+
"eval_steps_per_second": 12.741,
|
| 697 |
+
"step": 96664
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 44.0,
|
| 701 |
+
"grad_norm": 0.0042132362723350525,
|
| 702 |
+
"learning_rate": 5.602046263345197e-06,
|
| 703 |
+
"loss": 0.1982,
|
| 704 |
+
"step": 98912
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 44.0,
|
| 708 |
+
"eval_accuracy": 0.8754448294639587,
|
| 709 |
+
"eval_loss": 1.221611499786377,
|
| 710 |
+
"eval_runtime": 44.0087,
|
| 711 |
+
"eval_samples_per_second": 12.77,
|
| 712 |
+
"eval_steps_per_second": 12.77,
|
| 713 |
+
"step": 98912
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 45.0,
|
| 717 |
+
"grad_norm": 0.011830995790660381,
|
| 718 |
+
"learning_rate": 5.502046263345196e-06,
|
| 719 |
+
"loss": 0.1803,
|
| 720 |
+
"step": 101160
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 45.0,
|
| 724 |
+
"eval_accuracy": 0.8451957106590271,
|
| 725 |
+
"eval_loss": 1.4569214582443237,
|
| 726 |
+
"eval_runtime": 44.6868,
|
| 727 |
+
"eval_samples_per_second": 12.576,
|
| 728 |
+
"eval_steps_per_second": 12.576,
|
| 729 |
+
"step": 101160
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 46.0,
|
| 733 |
+
"grad_norm": 0.0046292925253510475,
|
| 734 |
+
"learning_rate": 5.402090747330961e-06,
|
| 735 |
+
"loss": 0.1582,
|
| 736 |
+
"step": 103408
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 46.0,
|
| 740 |
+
"eval_accuracy": 0.8665480613708496,
|
| 741 |
+
"eval_loss": 1.365021824836731,
|
| 742 |
+
"eval_runtime": 43.9986,
|
| 743 |
+
"eval_samples_per_second": 12.773,
|
| 744 |
+
"eval_steps_per_second": 12.773,
|
| 745 |
+
"step": 103408
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 47.0,
|
| 749 |
+
"grad_norm": 0.041185297071933746,
|
| 750 |
+
"learning_rate": 5.302135231316726e-06,
|
| 751 |
+
"loss": 0.1837,
|
| 752 |
+
"step": 105656
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 47.0,
|
| 756 |
+
"eval_accuracy": 0.854092538356781,
|
| 757 |
+
"eval_loss": 1.2877007722854614,
|
| 758 |
+
"eval_runtime": 44.0731,
|
| 759 |
+
"eval_samples_per_second": 12.752,
|
| 760 |
+
"eval_steps_per_second": 12.752,
|
| 761 |
+
"step": 105656
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 48.0,
|
| 765 |
+
"grad_norm": 0.04080544412136078,
|
| 766 |
+
"learning_rate": 5.202179715302491e-06,
|
| 767 |
+
"loss": 0.1458,
|
| 768 |
+
"step": 107904
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 48.0,
|
| 772 |
+
"eval_accuracy": 0.8309608697891235,
|
| 773 |
+
"eval_loss": 1.7388625144958496,
|
| 774 |
+
"eval_runtime": 45.0509,
|
| 775 |
+
"eval_samples_per_second": 12.475,
|
| 776 |
+
"eval_steps_per_second": 12.475,
|
| 777 |
+
"step": 107904
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 49.0,
|
| 781 |
+
"grad_norm": 0.003914756700396538,
|
| 782 |
+
"learning_rate": 5.1022241992882574e-06,
|
| 783 |
+
"loss": 0.1664,
|
| 784 |
+
"step": 110152
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 49.0,
|
| 788 |
+
"eval_accuracy": 0.854092538356781,
|
| 789 |
+
"eval_loss": 1.4000823497772217,
|
| 790 |
+
"eval_runtime": 44.2826,
|
| 791 |
+
"eval_samples_per_second": 12.691,
|
| 792 |
+
"eval_steps_per_second": 12.691,
|
| 793 |
+
"step": 110152
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 50.0,
|
| 797 |
+
"grad_norm": 0.0011822431115433574,
|
| 798 |
+
"learning_rate": 5.002268683274022e-06,
|
| 799 |
+
"loss": 0.1473,
|
| 800 |
+
"step": 112400
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 50.0,
|
| 804 |
+
"eval_accuracy": 0.8701067566871643,
|
| 805 |
+
"eval_loss": 1.2979094982147217,
|
| 806 |
+
"eval_runtime": 44.3693,
|
| 807 |
+
"eval_samples_per_second": 12.666,
|
| 808 |
+
"eval_steps_per_second": 12.666,
|
| 809 |
+
"step": 112400
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 51.0,
|
| 813 |
+
"grad_norm": 0.0008859778754413128,
|
| 814 |
+
"learning_rate": 4.9022686832740216e-06,
|
| 815 |
+
"loss": 0.1341,
|
| 816 |
+
"step": 114648
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 51.0,
|
| 820 |
+
"eval_accuracy": 0.8469750881195068,
|
| 821 |
+
"eval_loss": 1.570462942123413,
|
| 822 |
+
"eval_runtime": 44.0624,
|
| 823 |
+
"eval_samples_per_second": 12.755,
|
| 824 |
+
"eval_steps_per_second": 12.755,
|
| 825 |
+
"step": 114648
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 52.0,
|
| 829 |
+
"grad_norm": 0.0008422972168773413,
|
| 830 |
+
"learning_rate": 4.8023131672597865e-06,
|
| 831 |
+
"loss": 0.1603,
|
| 832 |
+
"step": 116896
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 52.0,
|
| 836 |
+
"eval_accuracy": 0.8380783200263977,
|
| 837 |
+
"eval_loss": 1.6043403148651123,
|
| 838 |
+
"eval_runtime": 44.715,
|
| 839 |
+
"eval_samples_per_second": 12.568,
|
| 840 |
+
"eval_steps_per_second": 12.568,
|
| 841 |
+
"step": 116896
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 53.0,
|
| 845 |
+
"grad_norm": 0.1126694455742836,
|
| 846 |
+
"learning_rate": 4.702357651245552e-06,
|
| 847 |
+
"loss": 0.1133,
|
| 848 |
+
"step": 119144
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 53.0,
|
| 852 |
+
"eval_accuracy": 0.8451957106590271,
|
| 853 |
+
"eval_loss": 1.6194249391555786,
|
| 854 |
+
"eval_runtime": 44.3847,
|
| 855 |
+
"eval_samples_per_second": 12.662,
|
| 856 |
+
"eval_steps_per_second": 12.662,
|
| 857 |
+
"step": 119144
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 54.0,
|
| 861 |
+
"grad_norm": 0.0018404704751446843,
|
| 862 |
+
"learning_rate": 4.602402135231317e-06,
|
| 863 |
+
"loss": 0.107,
|
| 864 |
+
"step": 121392
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 54.0,
|
| 868 |
+
"eval_accuracy": 0.8629893064498901,
|
| 869 |
+
"eval_loss": 1.4172945022583008,
|
| 870 |
+
"eval_runtime": 45.9409,
|
| 871 |
+
"eval_samples_per_second": 12.233,
|
| 872 |
+
"eval_steps_per_second": 12.233,
|
| 873 |
+
"step": 121392
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 55.0,
|
| 877 |
+
"grad_norm": 0.0005189430085010827,
|
| 878 |
+
"learning_rate": 4.502402135231317e-06,
|
| 879 |
+
"loss": 0.116,
|
| 880 |
+
"step": 123640
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 55.0,
|
| 884 |
+
"eval_accuracy": 0.854092538356781,
|
| 885 |
+
"eval_loss": 1.526777982711792,
|
| 886 |
+
"eval_runtime": 44.5269,
|
| 887 |
+
"eval_samples_per_second": 12.622,
|
| 888 |
+
"eval_steps_per_second": 12.622,
|
| 889 |
+
"step": 123640
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 56.0,
|
| 893 |
+
"grad_norm": 0.000902254250831902,
|
| 894 |
+
"learning_rate": 4.402446619217082e-06,
|
| 895 |
+
"loss": 0.0988,
|
| 896 |
+
"step": 125888
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 56.0,
|
| 900 |
+
"eval_accuracy": 0.8523131608963013,
|
| 901 |
+
"eval_loss": 1.6091721057891846,
|
| 902 |
+
"eval_runtime": 44.4807,
|
| 903 |
+
"eval_samples_per_second": 12.635,
|
| 904 |
+
"eval_steps_per_second": 12.635,
|
| 905 |
+
"step": 125888
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 57.0,
|
| 909 |
+
"grad_norm": 0.04167209565639496,
|
| 910 |
+
"learning_rate": 4.302491103202847e-06,
|
| 911 |
+
"loss": 0.139,
|
| 912 |
+
"step": 128136
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 57.0,
|
| 916 |
+
"eval_accuracy": 0.8647686839103699,
|
| 917 |
+
"eval_loss": 1.4311786890029907,
|
| 918 |
+
"eval_runtime": 44.6921,
|
| 919 |
+
"eval_samples_per_second": 12.575,
|
| 920 |
+
"eval_steps_per_second": 12.575,
|
| 921 |
+
"step": 128136
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 58.0,
|
| 925 |
+
"grad_norm": 0.0009059112053364515,
|
| 926 |
+
"learning_rate": 4.202535587188613e-06,
|
| 927 |
+
"loss": 0.0798,
|
| 928 |
+
"step": 130384
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 58.0,
|
| 932 |
+
"eval_accuracy": 0.8327401876449585,
|
| 933 |
+
"eval_loss": 1.7888070344924927,
|
| 934 |
+
"eval_runtime": 46.1517,
|
| 935 |
+
"eval_samples_per_second": 12.177,
|
| 936 |
+
"eval_steps_per_second": 12.177,
|
| 937 |
+
"step": 130384
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 59.0,
|
| 941 |
+
"grad_norm": 0.00021046701294835657,
|
| 942 |
+
"learning_rate": 4.102535587188613e-06,
|
| 943 |
+
"loss": 0.0776,
|
| 944 |
+
"step": 132632
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 59.0,
|
| 948 |
+
"eval_accuracy": 0.8665480613708496,
|
| 949 |
+
"eval_loss": 1.5457098484039307,
|
| 950 |
+
"eval_runtime": 44.2018,
|
| 951 |
+
"eval_samples_per_second": 12.714,
|
| 952 |
+
"eval_steps_per_second": 12.714,
|
| 953 |
+
"step": 132632
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 60.0,
|
| 957 |
+
"grad_norm": 0.0024244808591902256,
|
| 958 |
+
"learning_rate": 4.002580071174378e-06,
|
| 959 |
+
"loss": 0.1288,
|
| 960 |
+
"step": 134880
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 60.0,
|
| 964 |
+
"eval_accuracy": 0.8629893064498901,
|
| 965 |
+
"eval_loss": 1.4553505182266235,
|
| 966 |
+
"eval_runtime": 43.9122,
|
| 967 |
+
"eval_samples_per_second": 12.798,
|
| 968 |
+
"eval_steps_per_second": 12.798,
|
| 969 |
+
"step": 134880
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 61.0,
|
| 973 |
+
"grad_norm": 0.0004949413705617189,
|
| 974 |
+
"learning_rate": 3.9026245551601425e-06,
|
| 975 |
+
"loss": 0.0828,
|
| 976 |
+
"step": 137128
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 61.0,
|
| 980 |
+
"eval_accuracy": 0.8558719158172607,
|
| 981 |
+
"eval_loss": 1.7077866792678833,
|
| 982 |
+
"eval_runtime": 44.3471,
|
| 983 |
+
"eval_samples_per_second": 12.673,
|
| 984 |
+
"eval_steps_per_second": 12.673,
|
| 985 |
+
"step": 137128
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 62.0,
|
| 989 |
+
"grad_norm": 0.00021063751773908734,
|
| 990 |
+
"learning_rate": 3.8026690391459074e-06,
|
| 991 |
+
"loss": 0.0823,
|
| 992 |
+
"step": 139376
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 62.0,
|
| 996 |
+
"eval_accuracy": 0.8754448294639587,
|
| 997 |
+
"eval_loss": 1.4733619689941406,
|
| 998 |
+
"eval_runtime": 44.2713,
|
| 999 |
+
"eval_samples_per_second": 12.694,
|
| 1000 |
+
"eval_steps_per_second": 12.694,
|
| 1001 |
+
"step": 139376
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 63.0,
|
| 1005 |
+
"grad_norm": 0.0006752557819709182,
|
| 1006 |
+
"learning_rate": 3.702713523131673e-06,
|
| 1007 |
+
"loss": 0.0803,
|
| 1008 |
+
"step": 141624
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 63.0,
|
| 1012 |
+
"eval_accuracy": 0.8594306111335754,
|
| 1013 |
+
"eval_loss": 1.6007416248321533,
|
| 1014 |
+
"eval_runtime": 44.5589,
|
| 1015 |
+
"eval_samples_per_second": 12.613,
|
| 1016 |
+
"eval_steps_per_second": 12.613,
|
| 1017 |
+
"step": 141624
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 64.0,
|
| 1021 |
+
"grad_norm": 0.0015100333839654922,
|
| 1022 |
+
"learning_rate": 3.602758007117438e-06,
|
| 1023 |
+
"loss": 0.0947,
|
| 1024 |
+
"step": 143872
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 64.0,
|
| 1028 |
+
"eval_accuracy": 0.8701067566871643,
|
| 1029 |
+
"eval_loss": 1.4466949701309204,
|
| 1030 |
+
"eval_runtime": 44.6568,
|
| 1031 |
+
"eval_samples_per_second": 12.585,
|
| 1032 |
+
"eval_steps_per_second": 12.585,
|
| 1033 |
+
"step": 143872
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 65.0,
|
| 1037 |
+
"grad_norm": 0.0003055017732549459,
|
| 1038 |
+
"learning_rate": 3.5028024911032033e-06,
|
| 1039 |
+
"loss": 0.0916,
|
| 1040 |
+
"step": 146120
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 65.0,
|
| 1044 |
+
"eval_accuracy": 0.873665452003479,
|
| 1045 |
+
"eval_loss": 1.4410454034805298,
|
| 1046 |
+
"eval_runtime": 44.5129,
|
| 1047 |
+
"eval_samples_per_second": 12.626,
|
| 1048 |
+
"eval_steps_per_second": 12.626,
|
| 1049 |
+
"step": 146120
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 66.0,
|
| 1053 |
+
"grad_norm": 0.0007535702898167074,
|
| 1054 |
+
"learning_rate": 3.402846975088968e-06,
|
| 1055 |
+
"loss": 0.0814,
|
| 1056 |
+
"step": 148368
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 66.0,
|
| 1060 |
+
"eval_accuracy": 0.8469750881195068,
|
| 1061 |
+
"eval_loss": 1.711586356163025,
|
| 1062 |
+
"eval_runtime": 44.7221,
|
| 1063 |
+
"eval_samples_per_second": 12.566,
|
| 1064 |
+
"eval_steps_per_second": 12.566,
|
| 1065 |
+
"step": 148368
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 67.0,
|
| 1069 |
+
"grad_norm": NaN,
|
| 1070 |
+
"learning_rate": 3.3028914590747335e-06,
|
| 1071 |
+
"loss": 0.0938,
|
| 1072 |
+
"step": 150616
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 67.0,
|
| 1076 |
+
"eval_accuracy": 0.8629893064498901,
|
| 1077 |
+
"eval_loss": 1.5838223695755005,
|
| 1078 |
+
"eval_runtime": 44.5452,
|
| 1079 |
+
"eval_samples_per_second": 12.616,
|
| 1080 |
+
"eval_steps_per_second": 12.616,
|
| 1081 |
+
"step": 150616
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 68.0,
|
| 1085 |
+
"grad_norm": 0.00016811703972052783,
|
| 1086 |
+
"learning_rate": 3.2028914590747336e-06,
|
| 1087 |
+
"loss": 0.066,
|
| 1088 |
+
"step": 152864
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 68.0,
|
| 1092 |
+
"eval_accuracy": 0.8558719158172607,
|
| 1093 |
+
"eval_loss": 1.645817518234253,
|
| 1094 |
+
"eval_runtime": 44.4578,
|
| 1095 |
+
"eval_samples_per_second": 12.641,
|
| 1096 |
+
"eval_steps_per_second": 12.641,
|
| 1097 |
+
"step": 152864
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 69.0,
|
| 1101 |
+
"grad_norm": 0.0004475938912946731,
|
| 1102 |
+
"learning_rate": 3.102935943060498e-06,
|
| 1103 |
+
"loss": 0.096,
|
| 1104 |
+
"step": 155112
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 69.0,
|
| 1108 |
+
"eval_accuracy": 0.8558719158172607,
|
| 1109 |
+
"eval_loss": 1.6925562620162964,
|
| 1110 |
+
"eval_runtime": 44.7853,
|
| 1111 |
+
"eval_samples_per_second": 12.549,
|
| 1112 |
+
"eval_steps_per_second": 12.549,
|
| 1113 |
+
"step": 155112
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 70.0,
|
| 1117 |
+
"grad_norm": 0.005046023055911064,
|
| 1118 |
+
"learning_rate": 3.0030249110320286e-06,
|
| 1119 |
+
"loss": 0.0638,
|
| 1120 |
+
"step": 157360
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 70.0,
|
| 1124 |
+
"eval_accuracy": 0.8629893064498901,
|
| 1125 |
+
"eval_loss": 1.5232763290405273,
|
| 1126 |
+
"eval_runtime": 44.8809,
|
| 1127 |
+
"eval_samples_per_second": 12.522,
|
| 1128 |
+
"eval_steps_per_second": 12.522,
|
| 1129 |
+
"step": 157360
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 71.0,
|
| 1133 |
+
"grad_norm": 0.00024611467961221933,
|
| 1134 |
+
"learning_rate": 2.9030249110320287e-06,
|
| 1135 |
+
"loss": 0.063,
|
| 1136 |
+
"step": 159608
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 71.0,
|
| 1140 |
+
"eval_accuracy": 0.8594306111335754,
|
| 1141 |
+
"eval_loss": 1.5641191005706787,
|
| 1142 |
+
"eval_runtime": 44.3769,
|
| 1143 |
+
"eval_samples_per_second": 12.664,
|
| 1144 |
+
"eval_steps_per_second": 12.664,
|
| 1145 |
+
"step": 159608
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 72.0,
|
| 1149 |
+
"grad_norm": 0.001299203373491764,
|
| 1150 |
+
"learning_rate": 2.8030249110320284e-06,
|
| 1151 |
+
"loss": 0.0758,
|
| 1152 |
+
"step": 161856
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 72.0,
|
| 1156 |
+
"eval_accuracy": 0.8505337834358215,
|
| 1157 |
+
"eval_loss": 1.6766804456710815,
|
| 1158 |
+
"eval_runtime": 44.9521,
|
| 1159 |
+
"eval_samples_per_second": 12.502,
|
| 1160 |
+
"eval_steps_per_second": 12.502,
|
| 1161 |
+
"step": 161856
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 73.0,
|
| 1165 |
+
"grad_norm": 0.00021305486734490842,
|
| 1166 |
+
"learning_rate": 2.7030693950177937e-06,
|
| 1167 |
+
"loss": 0.0579,
|
| 1168 |
+
"step": 164104
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 73.0,
|
| 1172 |
+
"eval_accuracy": 0.8629893064498901,
|
| 1173 |
+
"eval_loss": 1.5338364839553833,
|
| 1174 |
+
"eval_runtime": 46.2439,
|
| 1175 |
+
"eval_samples_per_second": 12.153,
|
| 1176 |
+
"eval_steps_per_second": 12.153,
|
| 1177 |
+
"step": 164104
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 74.0,
|
| 1181 |
+
"grad_norm": 0.0005646486533805728,
|
| 1182 |
+
"learning_rate": 2.6031138790035586e-06,
|
| 1183 |
+
"loss": 0.0379,
|
| 1184 |
+
"step": 166352
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 74.0,
|
| 1188 |
+
"eval_accuracy": 0.8629893064498901,
|
| 1189 |
+
"eval_loss": 1.6348403692245483,
|
| 1190 |
+
"eval_runtime": 44.783,
|
| 1191 |
+
"eval_samples_per_second": 12.549,
|
| 1192 |
+
"eval_steps_per_second": 12.549,
|
| 1193 |
+
"step": 166352
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 75.0,
|
| 1197 |
+
"grad_norm": 0.00010759654833236709,
|
| 1198 |
+
"learning_rate": 2.5031583629893243e-06,
|
| 1199 |
+
"loss": 0.0351,
|
| 1200 |
+
"step": 168600
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 75.0,
|
| 1204 |
+
"eval_accuracy": 0.8558719158172607,
|
| 1205 |
+
"eval_loss": 1.70370352268219,
|
| 1206 |
+
"eval_runtime": 47.2555,
|
| 1207 |
+
"eval_samples_per_second": 11.893,
|
| 1208 |
+
"eval_steps_per_second": 11.893,
|
| 1209 |
+
"step": 168600
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 76.0,
|
| 1213 |
+
"grad_norm": 0.000321146595524624,
|
| 1214 |
+
"learning_rate": 2.403202846975089e-06,
|
| 1215 |
+
"loss": 0.0472,
|
| 1216 |
+
"step": 170848
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 76.0,
|
| 1220 |
+
"eval_accuracy": 0.8754448294639587,
|
| 1221 |
+
"eval_loss": 1.5681896209716797,
|
| 1222 |
+
"eval_runtime": 44.4779,
|
| 1223 |
+
"eval_samples_per_second": 12.635,
|
| 1224 |
+
"eval_steps_per_second": 12.635,
|
| 1225 |
+
"step": 170848
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 77.0,
|
| 1229 |
+
"grad_norm": 0.00014101610577199608,
|
| 1230 |
+
"learning_rate": 2.3032028469750893e-06,
|
| 1231 |
+
"loss": 0.0253,
|
| 1232 |
+
"step": 173096
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 77.0,
|
| 1236 |
+
"eval_accuracy": 0.8558719158172607,
|
| 1237 |
+
"eval_loss": 1.7067368030548096,
|
| 1238 |
+
"eval_runtime": 44.3009,
|
| 1239 |
+
"eval_samples_per_second": 12.686,
|
| 1240 |
+
"eval_steps_per_second": 12.686,
|
| 1241 |
+
"step": 173096
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 78.0,
|
| 1245 |
+
"grad_norm": 0.0002290535339852795,
|
| 1246 |
+
"learning_rate": 2.203247330960854e-06,
|
| 1247 |
+
"loss": 0.073,
|
| 1248 |
+
"step": 175344
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 78.0,
|
| 1252 |
+
"eval_accuracy": 0.8754448294639587,
|
| 1253 |
+
"eval_loss": 1.4460408687591553,
|
| 1254 |
+
"eval_runtime": 44.9156,
|
| 1255 |
+
"eval_samples_per_second": 12.512,
|
| 1256 |
+
"eval_steps_per_second": 12.512,
|
| 1257 |
+
"step": 175344
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 79.0,
|
| 1261 |
+
"grad_norm": 0.0008211834938265383,
|
| 1262 |
+
"learning_rate": 2.1032918149466195e-06,
|
| 1263 |
+
"loss": 0.049,
|
| 1264 |
+
"step": 177592
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 79.0,
|
| 1268 |
+
"eval_accuracy": 0.8594306111335754,
|
| 1269 |
+
"eval_loss": 1.5897014141082764,
|
| 1270 |
+
"eval_runtime": 44.349,
|
| 1271 |
+
"eval_samples_per_second": 12.672,
|
| 1272 |
+
"eval_steps_per_second": 12.672,
|
| 1273 |
+
"step": 177592
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 80.0,
|
| 1277 |
+
"grad_norm": 0.0002687973901629448,
|
| 1278 |
+
"learning_rate": 2.003291814946619e-06,
|
| 1279 |
+
"loss": 0.0503,
|
| 1280 |
+
"step": 179840
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 80.0,
|
| 1284 |
+
"eval_accuracy": 0.8647686839103699,
|
| 1285 |
+
"eval_loss": 1.601679801940918,
|
| 1286 |
+
"eval_runtime": 44.9732,
|
| 1287 |
+
"eval_samples_per_second": 12.496,
|
| 1288 |
+
"eval_steps_per_second": 12.496,
|
| 1289 |
+
"step": 179840
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 81.0,
|
| 1293 |
+
"grad_norm": 0.00014994025696069002,
|
| 1294 |
+
"learning_rate": 1.9033807829181496e-06,
|
| 1295 |
+
"loss": 0.0497,
|
| 1296 |
+
"step": 182088
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 81.0,
|
| 1300 |
+
"eval_accuracy": 0.8683273792266846,
|
| 1301 |
+
"eval_loss": 1.5318866968154907,
|
| 1302 |
+
"eval_runtime": 44.556,
|
| 1303 |
+
"eval_samples_per_second": 12.613,
|
| 1304 |
+
"eval_steps_per_second": 12.613,
|
| 1305 |
+
"step": 182088
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 82.0,
|
| 1309 |
+
"grad_norm": 0.00014429475413635373,
|
| 1310 |
+
"learning_rate": 1.8034697508896797e-06,
|
| 1311 |
+
"loss": 0.0553,
|
| 1312 |
+
"step": 184336
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 82.0,
|
| 1316 |
+
"eval_accuracy": 0.8612099885940552,
|
| 1317 |
+
"eval_loss": 1.5479316711425781,
|
| 1318 |
+
"eval_runtime": 44.3184,
|
| 1319 |
+
"eval_samples_per_second": 12.681,
|
| 1320 |
+
"eval_steps_per_second": 12.681,
|
| 1321 |
+
"step": 184336
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 83.0,
|
| 1325 |
+
"grad_norm": 0.0028621815145015717,
|
| 1326 |
+
"learning_rate": 1.70346975088968e-06,
|
| 1327 |
+
"loss": 0.0416,
|
| 1328 |
+
"step": 186584
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 83.0,
|
| 1332 |
+
"eval_accuracy": 0.8576512336730957,
|
| 1333 |
+
"eval_loss": 1.5556381940841675,
|
| 1334 |
+
"eval_runtime": 44.9266,
|
| 1335 |
+
"eval_samples_per_second": 12.509,
|
| 1336 |
+
"eval_steps_per_second": 12.509,
|
| 1337 |
+
"step": 186584
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 84.0,
|
| 1341 |
+
"grad_norm": 0.0002136415132554248,
|
| 1342 |
+
"learning_rate": 1.60346975088968e-06,
|
| 1343 |
+
"loss": 0.0641,
|
| 1344 |
+
"step": 188832
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 84.0,
|
| 1348 |
+
"eval_accuracy": 0.8594306111335754,
|
| 1349 |
+
"eval_loss": 1.5674761533737183,
|
| 1350 |
+
"eval_runtime": 44.2532,
|
| 1351 |
+
"eval_samples_per_second": 12.7,
|
| 1352 |
+
"eval_steps_per_second": 12.7,
|
| 1353 |
+
"step": 188832
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 85.0,
|
| 1357 |
+
"grad_norm": 0.00014172360533848405,
|
| 1358 |
+
"learning_rate": 1.503514234875445e-06,
|
| 1359 |
+
"loss": 0.0425,
|
| 1360 |
+
"step": 191080
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 85.0,
|
| 1364 |
+
"eval_accuracy": 0.8558719158172607,
|
| 1365 |
+
"eval_loss": 1.6853959560394287,
|
| 1366 |
+
"eval_runtime": 44.7377,
|
| 1367 |
+
"eval_samples_per_second": 12.562,
|
| 1368 |
+
"eval_steps_per_second": 12.562,
|
| 1369 |
+
"step": 191080
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 86.0,
|
| 1373 |
+
"grad_norm": 0.0003552982525434345,
|
| 1374 |
+
"learning_rate": 1.403514234875445e-06,
|
| 1375 |
+
"loss": 0.0311,
|
| 1376 |
+
"step": 193328
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 86.0,
|
| 1380 |
+
"eval_accuracy": 0.873665452003479,
|
| 1381 |
+
"eval_loss": 1.4628252983093262,
|
| 1382 |
+
"eval_runtime": 44.4922,
|
| 1383 |
+
"eval_samples_per_second": 12.631,
|
| 1384 |
+
"eval_steps_per_second": 12.631,
|
| 1385 |
+
"step": 193328
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 87.0,
|
| 1389 |
+
"grad_norm": 0.00020055480126757175,
|
| 1390 |
+
"learning_rate": 1.3036032028469752e-06,
|
| 1391 |
+
"loss": 0.0456,
|
| 1392 |
+
"step": 195576
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 87.0,
|
| 1396 |
+
"eval_accuracy": 0.8701067566871643,
|
| 1397 |
+
"eval_loss": 1.5069490671157837,
|
| 1398 |
+
"eval_runtime": 44.3942,
|
| 1399 |
+
"eval_samples_per_second": 12.659,
|
| 1400 |
+
"eval_steps_per_second": 12.659,
|
| 1401 |
+
"step": 195576
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 88.0,
|
| 1405 |
+
"grad_norm": 0.0007724438328295946,
|
| 1406 |
+
"learning_rate": 1.2036032028469751e-06,
|
| 1407 |
+
"loss": 0.0224,
|
| 1408 |
+
"step": 197824
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 88.0,
|
| 1412 |
+
"eval_accuracy": 0.8665480613708496,
|
| 1413 |
+
"eval_loss": 1.612963080406189,
|
| 1414 |
+
"eval_runtime": 44.8107,
|
| 1415 |
+
"eval_samples_per_second": 12.542,
|
| 1416 |
+
"eval_steps_per_second": 12.542,
|
| 1417 |
+
"step": 197824
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 89.0,
|
| 1421 |
+
"grad_norm": 0.00014038340304978192,
|
| 1422 |
+
"learning_rate": 1.1036476868327404e-06,
|
| 1423 |
+
"loss": 0.0345,
|
| 1424 |
+
"step": 200072
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 89.0,
|
| 1428 |
+
"eval_accuracy": 0.8701067566871643,
|
| 1429 |
+
"eval_loss": 1.5750340223312378,
|
| 1430 |
+
"eval_runtime": 44.6873,
|
| 1431 |
+
"eval_samples_per_second": 12.576,
|
| 1432 |
+
"eval_steps_per_second": 12.576,
|
| 1433 |
+
"step": 200072
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 90.0,
|
| 1437 |
+
"grad_norm": 6.56926931696944e-05,
|
| 1438 |
+
"learning_rate": 1.0036476868327403e-06,
|
| 1439 |
+
"loss": 0.041,
|
| 1440 |
+
"step": 202320
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 90.0,
|
| 1444 |
+
"eval_accuracy": 0.871886134147644,
|
| 1445 |
+
"eval_loss": 1.5229840278625488,
|
| 1446 |
+
"eval_runtime": 44.4416,
|
| 1447 |
+
"eval_samples_per_second": 12.646,
|
| 1448 |
+
"eval_steps_per_second": 12.646,
|
| 1449 |
+
"step": 202320
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 91.0,
|
| 1453 |
+
"grad_norm": 0.00015356726362369955,
|
| 1454 |
+
"learning_rate": 9.036921708185054e-07,
|
| 1455 |
+
"loss": 0.0165,
|
| 1456 |
+
"step": 204568
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 91.0,
|
| 1460 |
+
"eval_accuracy": 0.8594306111335754,
|
| 1461 |
+
"eval_loss": 1.6564196348190308,
|
| 1462 |
+
"eval_runtime": 44.2201,
|
| 1463 |
+
"eval_samples_per_second": 12.709,
|
| 1464 |
+
"eval_steps_per_second": 12.709,
|
| 1465 |
+
"step": 204568
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 92.0,
|
| 1469 |
+
"grad_norm": 8.38369523989968e-05,
|
| 1470 |
+
"learning_rate": 8.037811387900357e-07,
|
| 1471 |
+
"loss": 0.0478,
|
| 1472 |
+
"step": 206816
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 92.0,
|
| 1476 |
+
"eval_accuracy": 0.8629893064498901,
|
| 1477 |
+
"eval_loss": 1.5940439701080322,
|
| 1478 |
+
"eval_runtime": 44.433,
|
| 1479 |
+
"eval_samples_per_second": 12.648,
|
| 1480 |
+
"eval_steps_per_second": 12.648,
|
| 1481 |
+
"step": 206816
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 93.0,
|
| 1485 |
+
"grad_norm": 0.0002615041739773005,
|
| 1486 |
+
"learning_rate": 7.037811387900356e-07,
|
| 1487 |
+
"loss": 0.032,
|
| 1488 |
+
"step": 209064
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 93.0,
|
| 1492 |
+
"eval_accuracy": 0.8807829022407532,
|
| 1493 |
+
"eval_loss": 1.4740957021713257,
|
| 1494 |
+
"eval_runtime": 44.2628,
|
| 1495 |
+
"eval_samples_per_second": 12.697,
|
| 1496 |
+
"eval_steps_per_second": 12.697,
|
| 1497 |
+
"step": 209064
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 94.0,
|
| 1501 |
+
"grad_norm": 6.115555286407471,
|
| 1502 |
+
"learning_rate": 6.037811387900357e-07,
|
| 1503 |
+
"loss": 0.0433,
|
| 1504 |
+
"step": 211312
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 94.0,
|
| 1508 |
+
"eval_accuracy": 0.871886134147644,
|
| 1509 |
+
"eval_loss": 1.5333490371704102,
|
| 1510 |
+
"eval_runtime": 44.3613,
|
| 1511 |
+
"eval_samples_per_second": 12.669,
|
| 1512 |
+
"eval_steps_per_second": 12.669,
|
| 1513 |
+
"step": 211312
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 95.0,
|
| 1517 |
+
"grad_norm": 0.003299184376373887,
|
| 1518 |
+
"learning_rate": 5.038256227758007e-07,
|
| 1519 |
+
"loss": 0.0243,
|
| 1520 |
+
"step": 213560
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 95.0,
|
| 1524 |
+
"eval_accuracy": 0.871886134147644,
|
| 1525 |
+
"eval_loss": 1.5164633989334106,
|
| 1526 |
+
"eval_runtime": 44.7905,
|
| 1527 |
+
"eval_samples_per_second": 12.547,
|
| 1528 |
+
"eval_steps_per_second": 12.547,
|
| 1529 |
+
"step": 213560
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 96.0,
|
| 1533 |
+
"grad_norm": 5.206004061619751e-05,
|
| 1534 |
+
"learning_rate": 4.038701067615659e-07,
|
| 1535 |
+
"loss": 0.0165,
|
| 1536 |
+
"step": 215808
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 96.0,
|
| 1540 |
+
"eval_accuracy": 0.8683273792266846,
|
| 1541 |
+
"eval_loss": 1.5774868726730347,
|
| 1542 |
+
"eval_runtime": 44.4019,
|
| 1543 |
+
"eval_samples_per_second": 12.657,
|
| 1544 |
+
"eval_steps_per_second": 12.657,
|
| 1545 |
+
"step": 215808
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 97.0,
|
| 1549 |
+
"grad_norm": 0.0002649713715072721,
|
| 1550 |
+
"learning_rate": 3.03914590747331e-07,
|
| 1551 |
+
"loss": 0.0177,
|
| 1552 |
+
"step": 218056
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 97.0,
|
| 1556 |
+
"eval_accuracy": 0.8772242069244385,
|
| 1557 |
+
"eval_loss": 1.5302330255508423,
|
| 1558 |
+
"eval_runtime": 44.581,
|
| 1559 |
+
"eval_samples_per_second": 12.606,
|
| 1560 |
+
"eval_steps_per_second": 12.606,
|
| 1561 |
+
"step": 218056
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 98.0,
|
| 1565 |
+
"grad_norm": 5.933016291237436e-05,
|
| 1566 |
+
"learning_rate": 2.039590747330961e-07,
|
| 1567 |
+
"loss": 0.0253,
|
| 1568 |
+
"step": 220304
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 98.0,
|
| 1572 |
+
"eval_accuracy": 0.8754448294639587,
|
| 1573 |
+
"eval_loss": 1.5424113273620605,
|
| 1574 |
+
"eval_runtime": 44.8846,
|
| 1575 |
+
"eval_samples_per_second": 12.521,
|
| 1576 |
+
"eval_steps_per_second": 12.521,
|
| 1577 |
+
"step": 220304
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 99.0,
|
| 1581 |
+
"grad_norm": 7.96098611317575e-05,
|
| 1582 |
+
"learning_rate": 1.0400355871886121e-07,
|
| 1583 |
+
"loss": 0.0224,
|
| 1584 |
+
"step": 222552
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 99.0,
|
| 1588 |
+
"eval_accuracy": 0.871886134147644,
|
| 1589 |
+
"eval_loss": 1.5461581945419312,
|
| 1590 |
+
"eval_runtime": 44.4094,
|
| 1591 |
+
"eval_samples_per_second": 12.655,
|
| 1592 |
+
"eval_steps_per_second": 12.655,
|
| 1593 |
+
"step": 222552
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 100.0,
|
| 1597 |
+
"grad_norm": 0.00019997352501377463,
|
| 1598 |
+
"learning_rate": 4.0925266903914596e-09,
|
| 1599 |
+
"loss": 0.0213,
|
| 1600 |
+
"step": 224800
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 100.0,
|
| 1604 |
+
"eval_accuracy": 0.873665452003479,
|
| 1605 |
+
"eval_loss": 1.5357913970947266,
|
| 1606 |
+
"eval_runtime": 44.4377,
|
| 1607 |
+
"eval_samples_per_second": 12.647,
|
| 1608 |
+
"eval_steps_per_second": 12.647,
|
| 1609 |
+
"step": 224800
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 100.0,
|
| 1613 |
+
"step": 224800,
|
| 1614 |
+
"total_flos": 2.049428872704e+19,
|
| 1615 |
+
"train_loss": 0.33036238875677576,
|
| 1616 |
+
"train_runtime": 38665.4857,
|
| 1617 |
+
"train_samples_per_second": 5.814,
|
| 1618 |
+
"train_steps_per_second": 5.814
|
| 1619 |
+
}
|
| 1620 |
+
],
|
| 1621 |
+
"logging_steps": 35,
|
| 1622 |
+
"max_steps": 224800,
|
| 1623 |
+
"num_input_tokens_seen": 0,
|
| 1624 |
+
"num_train_epochs": 100,
|
| 1625 |
+
"save_steps": 500,
|
| 1626 |
+
"stateful_callbacks": {
|
| 1627 |
+
"TrainerControl": {
|
| 1628 |
+
"args": {
|
| 1629 |
+
"should_epoch_stop": false,
|
| 1630 |
+
"should_evaluate": false,
|
| 1631 |
+
"should_log": false,
|
| 1632 |
+
"should_save": false,
|
| 1633 |
+
"should_training_stop": false
|
| 1634 |
+
},
|
| 1635 |
+
"attributes": {}
|
| 1636 |
+
}
|
| 1637 |
+
},
|
| 1638 |
+
"total_flos": 2.049428872704e+19,
|
| 1639 |
+
"train_batch_size": 1,
|
| 1640 |
+
"trial_name": null,
|
| 1641 |
+
"trial_params": null
|
| 1642 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a034c8c5e04c1e9b7c65444f39fe6cc427be19d9730c9ab345e878d95d74d3
|
| 3 |
+
size 5304
|