Model save
Browse files- README.md +115 -0
- model.safetensors +1 -1
- trainer_state.json +867 -0
README.md
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: MCG-NJU/videomae-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: VideoMAE_Base_wlasl_100_longtail_200
|
| 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 |
+
# VideoMAE_Base_wlasl_100_longtail_200
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.9736
|
| 22 |
+
- Accuracy: 0.4822
|
| 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: 5e-05
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- training_steps: 36000
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 57 |
+
| 18.7021 | 0.005 | 180 | 4.6442 | 0.0118 |
|
| 58 |
+
| 18.6026 | 1.0050 | 360 | 4.6319 | 0.0118 |
|
| 59 |
+
| 18.5393 | 2.0050 | 540 | 4.6238 | 0.0178 |
|
| 60 |
+
| 18.3789 | 3.0050 | 721 | 4.6170 | 0.0178 |
|
| 61 |
+
| 18.3763 | 4.005 | 901 | 4.6237 | 0.0178 |
|
| 62 |
+
| 18.334 | 5.0050 | 1081 | 4.6342 | 0.0296 |
|
| 63 |
+
| 18.1779 | 6.0050 | 1261 | 4.6036 | 0.0296 |
|
| 64 |
+
| 17.9948 | 7.0050 | 1442 | 4.5903 | 0.0266 |
|
| 65 |
+
| 17.9333 | 8.005 | 1622 | 4.6144 | 0.0237 |
|
| 66 |
+
| 17.7505 | 9.0050 | 1802 | 4.5865 | 0.0118 |
|
| 67 |
+
| 17.4917 | 10.0050 | 1982 | 4.5626 | 0.0207 |
|
| 68 |
+
| 16.9821 | 11.0050 | 2163 | 4.3615 | 0.0444 |
|
| 69 |
+
| 16.2362 | 12.005 | 2343 | 4.1515 | 0.0533 |
|
| 70 |
+
| 15.2255 | 13.0050 | 2523 | 3.9603 | 0.0740 |
|
| 71 |
+
| 14.0646 | 14.0050 | 2703 | 3.7594 | 0.0828 |
|
| 72 |
+
| 12.8642 | 15.0050 | 2884 | 3.4154 | 0.1420 |
|
| 73 |
+
| 11.6502 | 16.005 | 3064 | 3.3917 | 0.1627 |
|
| 74 |
+
| 10.332 | 17.0050 | 3244 | 3.0359 | 0.2249 |
|
| 75 |
+
| 8.9465 | 18.0050 | 3424 | 2.8625 | 0.2840 |
|
| 76 |
+
| 7.6629 | 19.0050 | 3605 | 2.8202 | 0.3107 |
|
| 77 |
+
| 6.2517 | 20.005 | 3785 | 2.6478 | 0.3343 |
|
| 78 |
+
| 5.1876 | 21.0050 | 3965 | 2.4982 | 0.3728 |
|
| 79 |
+
| 4.0929 | 22.0050 | 4145 | 2.3891 | 0.3876 |
|
| 80 |
+
| 3.0425 | 23.0050 | 4326 | 2.2212 | 0.4083 |
|
| 81 |
+
| 2.3667 | 24.005 | 4506 | 2.1609 | 0.4586 |
|
| 82 |
+
| 1.7821 | 25.0050 | 4686 | 2.2471 | 0.4260 |
|
| 83 |
+
| 1.4215 | 26.0050 | 4866 | 2.2263 | 0.4675 |
|
| 84 |
+
| 1.1324 | 27.0050 | 5047 | 2.2360 | 0.4556 |
|
| 85 |
+
| 0.9114 | 28.005 | 5227 | 2.2021 | 0.4852 |
|
| 86 |
+
| 0.6966 | 29.0050 | 5407 | 2.3123 | 0.4408 |
|
| 87 |
+
| 0.5676 | 30.0050 | 5587 | 2.1198 | 0.5355 |
|
| 88 |
+
| 0.4494 | 31.0050 | 5768 | 2.2495 | 0.4911 |
|
| 89 |
+
| 0.3321 | 32.005 | 5948 | 2.2658 | 0.5089 |
|
| 90 |
+
| 0.227 | 33.0050 | 6128 | 2.4423 | 0.4882 |
|
| 91 |
+
| 0.2203 | 34.0050 | 6308 | 2.4358 | 0.4763 |
|
| 92 |
+
| 0.2643 | 35.0050 | 6489 | 2.5521 | 0.4675 |
|
| 93 |
+
| 0.111 | 36.005 | 6669 | 2.5787 | 0.4882 |
|
| 94 |
+
| 0.1009 | 37.0050 | 6849 | 2.4022 | 0.5059 |
|
| 95 |
+
| 0.1275 | 38.0050 | 7029 | 2.5451 | 0.5 |
|
| 96 |
+
| 0.1874 | 39.0050 | 7210 | 2.8339 | 0.4586 |
|
| 97 |
+
| 0.1695 | 40.005 | 7390 | 3.0320 | 0.4320 |
|
| 98 |
+
| 0.1735 | 41.0050 | 7570 | 2.6961 | 0.4941 |
|
| 99 |
+
| 0.1299 | 42.0050 | 7750 | 2.9589 | 0.4675 |
|
| 100 |
+
| 0.1399 | 43.0050 | 7931 | 2.6799 | 0.5325 |
|
| 101 |
+
| 0.118 | 44.005 | 8111 | 2.8731 | 0.5 |
|
| 102 |
+
| 0.1583 | 45.0050 | 8291 | 2.8757 | 0.4970 |
|
| 103 |
+
| 0.1667 | 46.0050 | 8471 | 2.9294 | 0.4941 |
|
| 104 |
+
| 0.202 | 47.0050 | 8652 | 3.1443 | 0.4615 |
|
| 105 |
+
| 0.1301 | 48.005 | 8832 | 2.8941 | 0.5207 |
|
| 106 |
+
| 0.2298 | 49.0050 | 9012 | 3.1270 | 0.4704 |
|
| 107 |
+
| 0.1858 | 50.0050 | 9192 | 2.9736 | 0.4822 |
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
### Framework versions
|
| 111 |
+
|
| 112 |
+
- Transformers 4.46.1
|
| 113 |
+
- Pytorch 2.5.1+cu124
|
| 114 |
+
- Datasets 3.1.0
|
| 115 |
+
- Tokenizers 0.20.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 345238832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c753d4a48065c56dcb9bb2c9257349b57e033e91fed6aa52b1066f88b6ec00d
|
| 3 |
size 345238832
|
trainer_state.json
ADDED
|
@@ -0,0 +1,867 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5355029585798816,
|
| 3 |
+
"best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/VideoMAE_Base_wlasl_100_longtail_200/checkpoint-5587",
|
| 4 |
+
"epoch": 50.00498611111111,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9192,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005,
|
| 13 |
+
"grad_norm": 57.62034225463867,
|
| 14 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 15 |
+
"loss": 18.7021,
|
| 16 |
+
"step": 180
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.005,
|
| 20 |
+
"eval_accuracy": 0.011834319526627219,
|
| 21 |
+
"eval_loss": 4.644242286682129,
|
| 22 |
+
"eval_runtime": 29.4341,
|
| 23 |
+
"eval_samples_per_second": 11.483,
|
| 24 |
+
"eval_steps_per_second": 5.742,
|
| 25 |
+
"step": 180
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.0049930555555555,
|
| 29 |
+
"grad_norm": 63.21147155761719,
|
| 30 |
+
"learning_rate": 4.9444444444444444e-06,
|
| 31 |
+
"loss": 18.6026,
|
| 32 |
+
"step": 360
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0049930555555555,
|
| 36 |
+
"eval_accuracy": 0.011834319526627219,
|
| 37 |
+
"eval_loss": 4.631899356842041,
|
| 38 |
+
"eval_runtime": 29.7352,
|
| 39 |
+
"eval_samples_per_second": 11.367,
|
| 40 |
+
"eval_steps_per_second": 5.684,
|
| 41 |
+
"step": 360
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.004986111111111,
|
| 45 |
+
"grad_norm": 34.4942741394043,
|
| 46 |
+
"learning_rate": 7.444444444444444e-06,
|
| 47 |
+
"loss": 18.5393,
|
| 48 |
+
"step": 540
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.004986111111111,
|
| 52 |
+
"eval_accuracy": 0.01775147928994083,
|
| 53 |
+
"eval_loss": 4.623769283294678,
|
| 54 |
+
"eval_runtime": 31.652,
|
| 55 |
+
"eval_samples_per_second": 10.679,
|
| 56 |
+
"eval_steps_per_second": 5.339,
|
| 57 |
+
"step": 540
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.0050069444444443,
|
| 61 |
+
"grad_norm": 30.521425247192383,
|
| 62 |
+
"learning_rate": 9.958333333333333e-06,
|
| 63 |
+
"loss": 18.3789,
|
| 64 |
+
"step": 721
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.0050069444444443,
|
| 68 |
+
"eval_accuracy": 0.01775147928994083,
|
| 69 |
+
"eval_loss": 4.617008209228516,
|
| 70 |
+
"eval_runtime": 28.7672,
|
| 71 |
+
"eval_samples_per_second": 11.749,
|
| 72 |
+
"eval_steps_per_second": 5.875,
|
| 73 |
+
"step": 721
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.005,
|
| 77 |
+
"grad_norm": 32.52579116821289,
|
| 78 |
+
"learning_rate": 1.2458333333333334e-05,
|
| 79 |
+
"loss": 18.3763,
|
| 80 |
+
"step": 901
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.005,
|
| 84 |
+
"eval_accuracy": 0.01775147928994083,
|
| 85 |
+
"eval_loss": 4.6236653327941895,
|
| 86 |
+
"eval_runtime": 30.9057,
|
| 87 |
+
"eval_samples_per_second": 10.936,
|
| 88 |
+
"eval_steps_per_second": 5.468,
|
| 89 |
+
"step": 901
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0049930555555555,
|
| 93 |
+
"grad_norm": 34.23224639892578,
|
| 94 |
+
"learning_rate": 1.4958333333333336e-05,
|
| 95 |
+
"loss": 18.334,
|
| 96 |
+
"step": 1081
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0049930555555555,
|
| 100 |
+
"eval_accuracy": 0.029585798816568046,
|
| 101 |
+
"eval_loss": 4.634205341339111,
|
| 102 |
+
"eval_runtime": 28.5668,
|
| 103 |
+
"eval_samples_per_second": 11.832,
|
| 104 |
+
"eval_steps_per_second": 5.916,
|
| 105 |
+
"step": 1081
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.004986111111111,
|
| 109 |
+
"grad_norm": 35.624855041503906,
|
| 110 |
+
"learning_rate": 1.7458333333333335e-05,
|
| 111 |
+
"loss": 18.1779,
|
| 112 |
+
"step": 1261
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.004986111111111,
|
| 116 |
+
"eval_accuracy": 0.029585798816568046,
|
| 117 |
+
"eval_loss": 4.603573322296143,
|
| 118 |
+
"eval_runtime": 28.2523,
|
| 119 |
+
"eval_samples_per_second": 11.964,
|
| 120 |
+
"eval_steps_per_second": 5.982,
|
| 121 |
+
"step": 1261
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.005006944444444,
|
| 125 |
+
"grad_norm": 48.291839599609375,
|
| 126 |
+
"learning_rate": 1.9972222222222223e-05,
|
| 127 |
+
"loss": 17.9948,
|
| 128 |
+
"step": 1442
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.005006944444444,
|
| 132 |
+
"eval_accuracy": 0.026627218934911243,
|
| 133 |
+
"eval_loss": 4.590323448181152,
|
| 134 |
+
"eval_runtime": 29.8277,
|
| 135 |
+
"eval_samples_per_second": 11.332,
|
| 136 |
+
"eval_steps_per_second": 5.666,
|
| 137 |
+
"step": 1442
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 8.005,
|
| 141 |
+
"grad_norm": 36.94101333618164,
|
| 142 |
+
"learning_rate": 2.2472222222222223e-05,
|
| 143 |
+
"loss": 17.9333,
|
| 144 |
+
"step": 1622
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.005,
|
| 148 |
+
"eval_accuracy": 0.023668639053254437,
|
| 149 |
+
"eval_loss": 4.614376068115234,
|
| 150 |
+
"eval_runtime": 27.5145,
|
| 151 |
+
"eval_samples_per_second": 12.284,
|
| 152 |
+
"eval_steps_per_second": 6.142,
|
| 153 |
+
"step": 1622
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.004993055555556,
|
| 157 |
+
"grad_norm": 35.89722442626953,
|
| 158 |
+
"learning_rate": 2.4972222222222226e-05,
|
| 159 |
+
"loss": 17.7505,
|
| 160 |
+
"step": 1802
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.004993055555556,
|
| 164 |
+
"eval_accuracy": 0.011834319526627219,
|
| 165 |
+
"eval_loss": 4.586489200592041,
|
| 166 |
+
"eval_runtime": 29.1474,
|
| 167 |
+
"eval_samples_per_second": 11.596,
|
| 168 |
+
"eval_steps_per_second": 5.798,
|
| 169 |
+
"step": 1802
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 10.00498611111111,
|
| 173 |
+
"grad_norm": 36.66941452026367,
|
| 174 |
+
"learning_rate": 2.7472222222222222e-05,
|
| 175 |
+
"loss": 17.4917,
|
| 176 |
+
"step": 1982
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.00498611111111,
|
| 180 |
+
"eval_accuracy": 0.020710059171597635,
|
| 181 |
+
"eval_loss": 4.562595367431641,
|
| 182 |
+
"eval_runtime": 27.9047,
|
| 183 |
+
"eval_samples_per_second": 12.113,
|
| 184 |
+
"eval_steps_per_second": 6.056,
|
| 185 |
+
"step": 1982
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 11.005006944444444,
|
| 189 |
+
"grad_norm": 35.883052825927734,
|
| 190 |
+
"learning_rate": 2.9986111111111116e-05,
|
| 191 |
+
"loss": 16.9821,
|
| 192 |
+
"step": 2163
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 11.005006944444444,
|
| 196 |
+
"eval_accuracy": 0.04437869822485207,
|
| 197 |
+
"eval_loss": 4.36150598526001,
|
| 198 |
+
"eval_runtime": 25.3334,
|
| 199 |
+
"eval_samples_per_second": 13.342,
|
| 200 |
+
"eval_steps_per_second": 6.671,
|
| 201 |
+
"step": 2163
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.005,
|
| 205 |
+
"grad_norm": 48.5424690246582,
|
| 206 |
+
"learning_rate": 3.248611111111111e-05,
|
| 207 |
+
"loss": 16.2362,
|
| 208 |
+
"step": 2343
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 12.005,
|
| 212 |
+
"eval_accuracy": 0.05325443786982249,
|
| 213 |
+
"eval_loss": 4.151459693908691,
|
| 214 |
+
"eval_runtime": 23.9608,
|
| 215 |
+
"eval_samples_per_second": 14.106,
|
| 216 |
+
"eval_steps_per_second": 7.053,
|
| 217 |
+
"step": 2343
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 13.004993055555556,
|
| 221 |
+
"grad_norm": 41.33076095581055,
|
| 222 |
+
"learning_rate": 3.4986111111111116e-05,
|
| 223 |
+
"loss": 15.2255,
|
| 224 |
+
"step": 2523
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.004993055555556,
|
| 228 |
+
"eval_accuracy": 0.07396449704142012,
|
| 229 |
+
"eval_loss": 3.960317850112915,
|
| 230 |
+
"eval_runtime": 18.4092,
|
| 231 |
+
"eval_samples_per_second": 18.36,
|
| 232 |
+
"eval_steps_per_second": 9.18,
|
| 233 |
+
"step": 2523
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 14.00498611111111,
|
| 237 |
+
"grad_norm": 55.07318115234375,
|
| 238 |
+
"learning_rate": 3.748611111111111e-05,
|
| 239 |
+
"loss": 14.0646,
|
| 240 |
+
"step": 2703
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.00498611111111,
|
| 244 |
+
"eval_accuracy": 0.08284023668639054,
|
| 245 |
+
"eval_loss": 3.7594428062438965,
|
| 246 |
+
"eval_runtime": 28.2986,
|
| 247 |
+
"eval_samples_per_second": 11.944,
|
| 248 |
+
"eval_steps_per_second": 5.972,
|
| 249 |
+
"step": 2703
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 15.005006944444444,
|
| 253 |
+
"grad_norm": 41.32450485229492,
|
| 254 |
+
"learning_rate": 4e-05,
|
| 255 |
+
"loss": 12.8642,
|
| 256 |
+
"step": 2884
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 15.005006944444444,
|
| 260 |
+
"eval_accuracy": 0.14201183431952663,
|
| 261 |
+
"eval_loss": 3.4153764247894287,
|
| 262 |
+
"eval_runtime": 26.9752,
|
| 263 |
+
"eval_samples_per_second": 12.53,
|
| 264 |
+
"eval_steps_per_second": 6.265,
|
| 265 |
+
"step": 2884
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 16.005,
|
| 269 |
+
"grad_norm": 81.92693328857422,
|
| 270 |
+
"learning_rate": 4.25e-05,
|
| 271 |
+
"loss": 11.6502,
|
| 272 |
+
"step": 3064
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 16.005,
|
| 276 |
+
"eval_accuracy": 0.16272189349112426,
|
| 277 |
+
"eval_loss": 3.39172625541687,
|
| 278 |
+
"eval_runtime": 27.2787,
|
| 279 |
+
"eval_samples_per_second": 12.391,
|
| 280 |
+
"eval_steps_per_second": 6.195,
|
| 281 |
+
"step": 3064
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 17.004993055555556,
|
| 285 |
+
"grad_norm": 57.80864334106445,
|
| 286 |
+
"learning_rate": 4.5e-05,
|
| 287 |
+
"loss": 10.332,
|
| 288 |
+
"step": 3244
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 17.004993055555556,
|
| 292 |
+
"eval_accuracy": 0.22485207100591717,
|
| 293 |
+
"eval_loss": 3.0358824729919434,
|
| 294 |
+
"eval_runtime": 28.8309,
|
| 295 |
+
"eval_samples_per_second": 11.724,
|
| 296 |
+
"eval_steps_per_second": 5.862,
|
| 297 |
+
"step": 3244
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.004986111111112,
|
| 301 |
+
"grad_norm": 57.51765060424805,
|
| 302 |
+
"learning_rate": 4.75e-05,
|
| 303 |
+
"loss": 8.9465,
|
| 304 |
+
"step": 3424
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 18.004986111111112,
|
| 308 |
+
"eval_accuracy": 0.28402366863905326,
|
| 309 |
+
"eval_loss": 2.8625123500823975,
|
| 310 |
+
"eval_runtime": 26.3032,
|
| 311 |
+
"eval_samples_per_second": 12.85,
|
| 312 |
+
"eval_steps_per_second": 6.425,
|
| 313 |
+
"step": 3424
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 19.005006944444446,
|
| 317 |
+
"grad_norm": 61.120155334472656,
|
| 318 |
+
"learning_rate": 5e-05,
|
| 319 |
+
"loss": 7.6629,
|
| 320 |
+
"step": 3605
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 19.005006944444446,
|
| 324 |
+
"eval_accuracy": 0.3106508875739645,
|
| 325 |
+
"eval_loss": 2.820160388946533,
|
| 326 |
+
"eval_runtime": 25.9784,
|
| 327 |
+
"eval_samples_per_second": 13.011,
|
| 328 |
+
"eval_steps_per_second": 6.505,
|
| 329 |
+
"step": 3605
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 20.005,
|
| 333 |
+
"grad_norm": 66.28811645507812,
|
| 334 |
+
"learning_rate": 4.972222222222223e-05,
|
| 335 |
+
"loss": 6.2517,
|
| 336 |
+
"step": 3785
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 20.005,
|
| 340 |
+
"eval_accuracy": 0.3343195266272189,
|
| 341 |
+
"eval_loss": 2.647813320159912,
|
| 342 |
+
"eval_runtime": 28.2017,
|
| 343 |
+
"eval_samples_per_second": 11.985,
|
| 344 |
+
"eval_steps_per_second": 5.993,
|
| 345 |
+
"step": 3785
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 21.004993055555556,
|
| 349 |
+
"grad_norm": 83.8398666381836,
|
| 350 |
+
"learning_rate": 4.9444444444444446e-05,
|
| 351 |
+
"loss": 5.1876,
|
| 352 |
+
"step": 3965
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 21.004993055555556,
|
| 356 |
+
"eval_accuracy": 0.3727810650887574,
|
| 357 |
+
"eval_loss": 2.4981963634490967,
|
| 358 |
+
"eval_runtime": 29.7423,
|
| 359 |
+
"eval_samples_per_second": 11.364,
|
| 360 |
+
"eval_steps_per_second": 5.682,
|
| 361 |
+
"step": 3965
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 22.004986111111112,
|
| 365 |
+
"grad_norm": 70.95669555664062,
|
| 366 |
+
"learning_rate": 4.9166666666666665e-05,
|
| 367 |
+
"loss": 4.0929,
|
| 368 |
+
"step": 4145
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 22.004986111111112,
|
| 372 |
+
"eval_accuracy": 0.3875739644970414,
|
| 373 |
+
"eval_loss": 2.389131546020508,
|
| 374 |
+
"eval_runtime": 29.0106,
|
| 375 |
+
"eval_samples_per_second": 11.651,
|
| 376 |
+
"eval_steps_per_second": 5.825,
|
| 377 |
+
"step": 4145
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 23.005006944444446,
|
| 381 |
+
"grad_norm": 73.58196258544922,
|
| 382 |
+
"learning_rate": 4.8887345679012346e-05,
|
| 383 |
+
"loss": 3.0425,
|
| 384 |
+
"step": 4326
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 23.005006944444446,
|
| 388 |
+
"eval_accuracy": 0.40828402366863903,
|
| 389 |
+
"eval_loss": 2.2211599349975586,
|
| 390 |
+
"eval_runtime": 29.3983,
|
| 391 |
+
"eval_samples_per_second": 11.497,
|
| 392 |
+
"eval_steps_per_second": 5.749,
|
| 393 |
+
"step": 4326
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 24.005,
|
| 397 |
+
"grad_norm": 38.20242691040039,
|
| 398 |
+
"learning_rate": 4.860956790123457e-05,
|
| 399 |
+
"loss": 2.3667,
|
| 400 |
+
"step": 4506
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 24.005,
|
| 404 |
+
"eval_accuracy": 0.45857988165680474,
|
| 405 |
+
"eval_loss": 2.1608965396881104,
|
| 406 |
+
"eval_runtime": 26.1013,
|
| 407 |
+
"eval_samples_per_second": 12.95,
|
| 408 |
+
"eval_steps_per_second": 6.475,
|
| 409 |
+
"step": 4506
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 25.004993055555556,
|
| 413 |
+
"grad_norm": 55.99176025390625,
|
| 414 |
+
"learning_rate": 4.8331790123456797e-05,
|
| 415 |
+
"loss": 1.7821,
|
| 416 |
+
"step": 4686
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 25.004993055555556,
|
| 420 |
+
"eval_accuracy": 0.4260355029585799,
|
| 421 |
+
"eval_loss": 2.2471060752868652,
|
| 422 |
+
"eval_runtime": 29.7721,
|
| 423 |
+
"eval_samples_per_second": 11.353,
|
| 424 |
+
"eval_steps_per_second": 5.676,
|
| 425 |
+
"step": 4686
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 26.004986111111112,
|
| 429 |
+
"grad_norm": 37.733924865722656,
|
| 430 |
+
"learning_rate": 4.8054012345679015e-05,
|
| 431 |
+
"loss": 1.4215,
|
| 432 |
+
"step": 4866
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 26.004986111111112,
|
| 436 |
+
"eval_accuracy": 0.46745562130177515,
|
| 437 |
+
"eval_loss": 2.2263102531433105,
|
| 438 |
+
"eval_runtime": 28.251,
|
| 439 |
+
"eval_samples_per_second": 11.964,
|
| 440 |
+
"eval_steps_per_second": 5.982,
|
| 441 |
+
"step": 4866
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 27.005006944444446,
|
| 445 |
+
"grad_norm": 23.38159942626953,
|
| 446 |
+
"learning_rate": 4.777469135802469e-05,
|
| 447 |
+
"loss": 1.1324,
|
| 448 |
+
"step": 5047
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 27.005006944444446,
|
| 452 |
+
"eval_accuracy": 0.4556213017751479,
|
| 453 |
+
"eval_loss": 2.235961437225342,
|
| 454 |
+
"eval_runtime": 29.6258,
|
| 455 |
+
"eval_samples_per_second": 11.409,
|
| 456 |
+
"eval_steps_per_second": 5.704,
|
| 457 |
+
"step": 5047
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 28.005,
|
| 461 |
+
"grad_norm": 37.854759216308594,
|
| 462 |
+
"learning_rate": 4.7496913580246915e-05,
|
| 463 |
+
"loss": 0.9114,
|
| 464 |
+
"step": 5227
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 28.005,
|
| 468 |
+
"eval_accuracy": 0.48520710059171596,
|
| 469 |
+
"eval_loss": 2.202089548110962,
|
| 470 |
+
"eval_runtime": 30.2271,
|
| 471 |
+
"eval_samples_per_second": 11.182,
|
| 472 |
+
"eval_steps_per_second": 5.591,
|
| 473 |
+
"step": 5227
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 29.004993055555556,
|
| 477 |
+
"grad_norm": 11.60957145690918,
|
| 478 |
+
"learning_rate": 4.721913580246914e-05,
|
| 479 |
+
"loss": 0.6966,
|
| 480 |
+
"step": 5407
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 29.004993055555556,
|
| 484 |
+
"eval_accuracy": 0.4408284023668639,
|
| 485 |
+
"eval_loss": 2.312260627746582,
|
| 486 |
+
"eval_runtime": 27.0737,
|
| 487 |
+
"eval_samples_per_second": 12.484,
|
| 488 |
+
"eval_steps_per_second": 6.242,
|
| 489 |
+
"step": 5407
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 30.004986111111112,
|
| 493 |
+
"grad_norm": 11.04503345489502,
|
| 494 |
+
"learning_rate": 4.694135802469136e-05,
|
| 495 |
+
"loss": 0.5676,
|
| 496 |
+
"step": 5587
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 30.004986111111112,
|
| 500 |
+
"eval_accuracy": 0.5355029585798816,
|
| 501 |
+
"eval_loss": 2.119814395904541,
|
| 502 |
+
"eval_runtime": 26.3784,
|
| 503 |
+
"eval_samples_per_second": 12.814,
|
| 504 |
+
"eval_steps_per_second": 6.407,
|
| 505 |
+
"step": 5587
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 31.005006944444446,
|
| 509 |
+
"grad_norm": 23.7001895904541,
|
| 510 |
+
"learning_rate": 4.666203703703704e-05,
|
| 511 |
+
"loss": 0.4494,
|
| 512 |
+
"step": 5768
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 31.005006944444446,
|
| 516 |
+
"eval_accuracy": 0.4911242603550296,
|
| 517 |
+
"eval_loss": 2.2495245933532715,
|
| 518 |
+
"eval_runtime": 26.6338,
|
| 519 |
+
"eval_samples_per_second": 12.691,
|
| 520 |
+
"eval_steps_per_second": 6.345,
|
| 521 |
+
"step": 5768
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 32.005,
|
| 525 |
+
"grad_norm": 8.150625228881836,
|
| 526 |
+
"learning_rate": 4.638425925925926e-05,
|
| 527 |
+
"loss": 0.3321,
|
| 528 |
+
"step": 5948
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 32.005,
|
| 532 |
+
"eval_accuracy": 0.5088757396449705,
|
| 533 |
+
"eval_loss": 2.2658286094665527,
|
| 534 |
+
"eval_runtime": 12.0221,
|
| 535 |
+
"eval_samples_per_second": 28.115,
|
| 536 |
+
"eval_steps_per_second": 14.057,
|
| 537 |
+
"step": 5948
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 33.00499305555556,
|
| 541 |
+
"grad_norm": 4.771080017089844,
|
| 542 |
+
"learning_rate": 4.6106481481481484e-05,
|
| 543 |
+
"loss": 0.227,
|
| 544 |
+
"step": 6128
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 33.00499305555556,
|
| 548 |
+
"eval_accuracy": 0.4881656804733728,
|
| 549 |
+
"eval_loss": 2.442265033721924,
|
| 550 |
+
"eval_runtime": 28.4938,
|
| 551 |
+
"eval_samples_per_second": 11.862,
|
| 552 |
+
"eval_steps_per_second": 5.931,
|
| 553 |
+
"step": 6128
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 34.00498611111111,
|
| 557 |
+
"grad_norm": 31.75286293029785,
|
| 558 |
+
"learning_rate": 4.582870370370371e-05,
|
| 559 |
+
"loss": 0.2203,
|
| 560 |
+
"step": 6308
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 34.00498611111111,
|
| 564 |
+
"eval_accuracy": 0.47633136094674555,
|
| 565 |
+
"eval_loss": 2.435835123062134,
|
| 566 |
+
"eval_runtime": 12.5987,
|
| 567 |
+
"eval_samples_per_second": 26.828,
|
| 568 |
+
"eval_steps_per_second": 13.414,
|
| 569 |
+
"step": 6308
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 35.005006944444446,
|
| 573 |
+
"grad_norm": 17.9893798828125,
|
| 574 |
+
"learning_rate": 4.5549382716049384e-05,
|
| 575 |
+
"loss": 0.2643,
|
| 576 |
+
"step": 6489
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 35.005006944444446,
|
| 580 |
+
"eval_accuracy": 0.46745562130177515,
|
| 581 |
+
"eval_loss": 2.552072525024414,
|
| 582 |
+
"eval_runtime": 11.7733,
|
| 583 |
+
"eval_samples_per_second": 28.709,
|
| 584 |
+
"eval_steps_per_second": 14.354,
|
| 585 |
+
"step": 6489
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 36.005,
|
| 589 |
+
"grad_norm": 1.910334825515747,
|
| 590 |
+
"learning_rate": 4.527160493827161e-05,
|
| 591 |
+
"loss": 0.111,
|
| 592 |
+
"step": 6669
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 36.005,
|
| 596 |
+
"eval_accuracy": 0.4881656804733728,
|
| 597 |
+
"eval_loss": 2.578749895095825,
|
| 598 |
+
"eval_runtime": 11.8894,
|
| 599 |
+
"eval_samples_per_second": 28.429,
|
| 600 |
+
"eval_steps_per_second": 14.214,
|
| 601 |
+
"step": 6669
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 37.00499305555556,
|
| 605 |
+
"grad_norm": 0.18931302428245544,
|
| 606 |
+
"learning_rate": 4.499382716049383e-05,
|
| 607 |
+
"loss": 0.1009,
|
| 608 |
+
"step": 6849
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 37.00499305555556,
|
| 612 |
+
"eval_accuracy": 0.5059171597633136,
|
| 613 |
+
"eval_loss": 2.402237892150879,
|
| 614 |
+
"eval_runtime": 21.2587,
|
| 615 |
+
"eval_samples_per_second": 15.899,
|
| 616 |
+
"eval_steps_per_second": 7.95,
|
| 617 |
+
"step": 6849
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 38.00498611111111,
|
| 621 |
+
"grad_norm": 0.6850244998931885,
|
| 622 |
+
"learning_rate": 4.4717592592592597e-05,
|
| 623 |
+
"loss": 0.1275,
|
| 624 |
+
"step": 7029
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 38.00498611111111,
|
| 628 |
+
"eval_accuracy": 0.5,
|
| 629 |
+
"eval_loss": 2.5450520515441895,
|
| 630 |
+
"eval_runtime": 29.372,
|
| 631 |
+
"eval_samples_per_second": 11.508,
|
| 632 |
+
"eval_steps_per_second": 5.754,
|
| 633 |
+
"step": 7029
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 39.005006944444446,
|
| 637 |
+
"grad_norm": 1.1550191640853882,
|
| 638 |
+
"learning_rate": 4.443827160493828e-05,
|
| 639 |
+
"loss": 0.1874,
|
| 640 |
+
"step": 7210
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 39.005006944444446,
|
| 644 |
+
"eval_accuracy": 0.45857988165680474,
|
| 645 |
+
"eval_loss": 2.8338911533355713,
|
| 646 |
+
"eval_runtime": 27.5638,
|
| 647 |
+
"eval_samples_per_second": 12.262,
|
| 648 |
+
"eval_steps_per_second": 6.131,
|
| 649 |
+
"step": 7210
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 40.005,
|
| 653 |
+
"grad_norm": 0.09220674633979797,
|
| 654 |
+
"learning_rate": 4.4160493827160497e-05,
|
| 655 |
+
"loss": 0.1695,
|
| 656 |
+
"step": 7390
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 40.005,
|
| 660 |
+
"eval_accuracy": 0.4319526627218935,
|
| 661 |
+
"eval_loss": 3.031979560852051,
|
| 662 |
+
"eval_runtime": 28.426,
|
| 663 |
+
"eval_samples_per_second": 11.891,
|
| 664 |
+
"eval_steps_per_second": 5.945,
|
| 665 |
+
"step": 7390
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 41.00499305555556,
|
| 669 |
+
"grad_norm": 0.9716654419898987,
|
| 670 |
+
"learning_rate": 4.3882716049382715e-05,
|
| 671 |
+
"loss": 0.1735,
|
| 672 |
+
"step": 7570
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 41.00499305555556,
|
| 676 |
+
"eval_accuracy": 0.4940828402366864,
|
| 677 |
+
"eval_loss": 2.696147918701172,
|
| 678 |
+
"eval_runtime": 24.5611,
|
| 679 |
+
"eval_samples_per_second": 13.762,
|
| 680 |
+
"eval_steps_per_second": 6.881,
|
| 681 |
+
"step": 7570
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 42.00498611111111,
|
| 685 |
+
"grad_norm": 1.0446219444274902,
|
| 686 |
+
"learning_rate": 4.360493827160494e-05,
|
| 687 |
+
"loss": 0.1299,
|
| 688 |
+
"step": 7750
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 42.00498611111111,
|
| 692 |
+
"eval_accuracy": 0.46745562130177515,
|
| 693 |
+
"eval_loss": 2.9589343070983887,
|
| 694 |
+
"eval_runtime": 27.9316,
|
| 695 |
+
"eval_samples_per_second": 12.101,
|
| 696 |
+
"eval_steps_per_second": 6.051,
|
| 697 |
+
"step": 7750
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 43.005006944444446,
|
| 701 |
+
"grad_norm": 37.8647346496582,
|
| 702 |
+
"learning_rate": 4.332561728395062e-05,
|
| 703 |
+
"loss": 0.1399,
|
| 704 |
+
"step": 7931
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 43.005006944444446,
|
| 708 |
+
"eval_accuracy": 0.5325443786982249,
|
| 709 |
+
"eval_loss": 2.6799256801605225,
|
| 710 |
+
"eval_runtime": 29.2099,
|
| 711 |
+
"eval_samples_per_second": 11.571,
|
| 712 |
+
"eval_steps_per_second": 5.786,
|
| 713 |
+
"step": 7931
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 44.005,
|
| 717 |
+
"grad_norm": 8.789149284362793,
|
| 718 |
+
"learning_rate": 4.304783950617284e-05,
|
| 719 |
+
"loss": 0.118,
|
| 720 |
+
"step": 8111
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 44.005,
|
| 724 |
+
"eval_accuracy": 0.5,
|
| 725 |
+
"eval_loss": 2.8731420040130615,
|
| 726 |
+
"eval_runtime": 26.167,
|
| 727 |
+
"eval_samples_per_second": 12.917,
|
| 728 |
+
"eval_steps_per_second": 6.459,
|
| 729 |
+
"step": 8111
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 45.00499305555556,
|
| 733 |
+
"grad_norm": 10.257121086120605,
|
| 734 |
+
"learning_rate": 4.277006172839506e-05,
|
| 735 |
+
"loss": 0.1583,
|
| 736 |
+
"step": 8291
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 45.00499305555556,
|
| 740 |
+
"eval_accuracy": 0.4970414201183432,
|
| 741 |
+
"eval_loss": 2.875749349594116,
|
| 742 |
+
"eval_runtime": 26.8437,
|
| 743 |
+
"eval_samples_per_second": 12.591,
|
| 744 |
+
"eval_steps_per_second": 6.296,
|
| 745 |
+
"step": 8291
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 46.00498611111111,
|
| 749 |
+
"grad_norm": 5.601294040679932,
|
| 750 |
+
"learning_rate": 4.2492283950617284e-05,
|
| 751 |
+
"loss": 0.1667,
|
| 752 |
+
"step": 8471
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 46.00498611111111,
|
| 756 |
+
"eval_accuracy": 0.4940828402366864,
|
| 757 |
+
"eval_loss": 2.9293906688690186,
|
| 758 |
+
"eval_runtime": 28.8864,
|
| 759 |
+
"eval_samples_per_second": 11.701,
|
| 760 |
+
"eval_steps_per_second": 5.85,
|
| 761 |
+
"step": 8471
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 47.005006944444446,
|
| 765 |
+
"grad_norm": 0.18206937611103058,
|
| 766 |
+
"learning_rate": 4.2212962962962965e-05,
|
| 767 |
+
"loss": 0.202,
|
| 768 |
+
"step": 8652
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 47.005006944444446,
|
| 772 |
+
"eval_accuracy": 0.46153846153846156,
|
| 773 |
+
"eval_loss": 3.144300937652588,
|
| 774 |
+
"eval_runtime": 29.5485,
|
| 775 |
+
"eval_samples_per_second": 11.439,
|
| 776 |
+
"eval_steps_per_second": 5.719,
|
| 777 |
+
"step": 8652
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 48.005,
|
| 781 |
+
"grad_norm": 0.22736448049545288,
|
| 782 |
+
"learning_rate": 4.193518518518519e-05,
|
| 783 |
+
"loss": 0.1301,
|
| 784 |
+
"step": 8832
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 48.005,
|
| 788 |
+
"eval_accuracy": 0.5207100591715976,
|
| 789 |
+
"eval_loss": 2.8941469192504883,
|
| 790 |
+
"eval_runtime": 29.2679,
|
| 791 |
+
"eval_samples_per_second": 11.549,
|
| 792 |
+
"eval_steps_per_second": 5.774,
|
| 793 |
+
"step": 8832
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 49.00499305555556,
|
| 797 |
+
"grad_norm": 11.593667030334473,
|
| 798 |
+
"learning_rate": 4.165895061728395e-05,
|
| 799 |
+
"loss": 0.2298,
|
| 800 |
+
"step": 9012
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 49.00499305555556,
|
| 804 |
+
"eval_accuracy": 0.47041420118343197,
|
| 805 |
+
"eval_loss": 3.1270129680633545,
|
| 806 |
+
"eval_runtime": 26.2692,
|
| 807 |
+
"eval_samples_per_second": 12.867,
|
| 808 |
+
"eval_steps_per_second": 6.433,
|
| 809 |
+
"step": 9012
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 50.00498611111111,
|
| 813 |
+
"grad_norm": 9.116874694824219,
|
| 814 |
+
"learning_rate": 4.138117283950618e-05,
|
| 815 |
+
"loss": 0.1858,
|
| 816 |
+
"step": 9192
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 50.00498611111111,
|
| 820 |
+
"eval_accuracy": 0.4822485207100592,
|
| 821 |
+
"eval_loss": 2.973588228225708,
|
| 822 |
+
"eval_runtime": 28.2275,
|
| 823 |
+
"eval_samples_per_second": 11.974,
|
| 824 |
+
"eval_steps_per_second": 5.987,
|
| 825 |
+
"step": 9192
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 50.00498611111111,
|
| 829 |
+
"step": 9192,
|
| 830 |
+
"total_flos": 9.171817168536207e+19,
|
| 831 |
+
"train_loss": 6.774725560419864,
|
| 832 |
+
"train_runtime": 9513.7238,
|
| 833 |
+
"train_samples_per_second": 30.272,
|
| 834 |
+
"train_steps_per_second": 3.784
|
| 835 |
+
}
|
| 836 |
+
],
|
| 837 |
+
"logging_steps": 500,
|
| 838 |
+
"max_steps": 36000,
|
| 839 |
+
"num_input_tokens_seen": 0,
|
| 840 |
+
"num_train_epochs": 9223372036854775807,
|
| 841 |
+
"save_steps": 500,
|
| 842 |
+
"stateful_callbacks": {
|
| 843 |
+
"EarlyStoppingCallback": {
|
| 844 |
+
"args": {
|
| 845 |
+
"early_stopping_patience": 20,
|
| 846 |
+
"early_stopping_threshold": 0.0
|
| 847 |
+
},
|
| 848 |
+
"attributes": {
|
| 849 |
+
"early_stopping_patience_counter": 20
|
| 850 |
+
}
|
| 851 |
+
},
|
| 852 |
+
"TrainerControl": {
|
| 853 |
+
"args": {
|
| 854 |
+
"should_epoch_stop": false,
|
| 855 |
+
"should_evaluate": false,
|
| 856 |
+
"should_log": false,
|
| 857 |
+
"should_save": true,
|
| 858 |
+
"should_training_stop": true
|
| 859 |
+
},
|
| 860 |
+
"attributes": {}
|
| 861 |
+
}
|
| 862 |
+
},
|
| 863 |
+
"total_flos": 9.171817168536207e+19,
|
| 864 |
+
"train_batch_size": 2,
|
| 865 |
+
"trial_name": null,
|
| 866 |
+
"trial_params": null
|
| 867 |
+
}
|