Model save
Browse files- README.md +92 -0
- model.safetensors +1 -1
- trainer_state.json +2274 -0
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: MCG-NJU/videomae-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: videomae-surf-analytics-runpod4
|
| 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-surf-analytics-runpod4
|
| 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: 0.7259
|
| 22 |
+
- Accuracy: 0.9016
|
| 23 |
+
- F1: 0.9021
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 5e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- training_steps: 2760
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 54 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
|
| 55 |
+
| 1.2463 | 0.0337 | 93 | 1.2389 | 0.4344 | 0.2949 |
|
| 56 |
+
| 1.024 | 1.0337 | 186 | 1.0343 | 0.5492 | 0.5254 |
|
| 57 |
+
| 0.6932 | 2.0337 | 279 | 0.8280 | 0.6639 | 0.6360 |
|
| 58 |
+
| 0.4467 | 3.0337 | 372 | 0.7665 | 0.7459 | 0.7338 |
|
| 59 |
+
| 0.4449 | 4.0337 | 465 | 0.8715 | 0.7131 | 0.6741 |
|
| 60 |
+
| 0.1371 | 5.0337 | 558 | 1.0560 | 0.7295 | 0.7158 |
|
| 61 |
+
| 0.1789 | 6.0337 | 651 | 0.8218 | 0.7869 | 0.7877 |
|
| 62 |
+
| 0.2125 | 7.0337 | 744 | 0.7612 | 0.7869 | 0.7812 |
|
| 63 |
+
| 0.1561 | 8.0337 | 837 | 0.6051 | 0.8525 | 0.8498 |
|
| 64 |
+
| 0.2297 | 9.0337 | 930 | 0.6321 | 0.8770 | 0.8766 |
|
| 65 |
+
| 0.0692 | 10.0337 | 1023 | 0.7128 | 0.8443 | 0.8455 |
|
| 66 |
+
| 0.0495 | 11.0337 | 1116 | 0.7738 | 0.8361 | 0.8353 |
|
| 67 |
+
| 0.1059 | 12.0337 | 1209 | 0.6213 | 0.8525 | 0.8524 |
|
| 68 |
+
| 0.1672 | 13.0337 | 1302 | 0.7888 | 0.8443 | 0.8409 |
|
| 69 |
+
| 0.0178 | 14.0337 | 1395 | 0.6488 | 0.8689 | 0.8658 |
|
| 70 |
+
| 0.0165 | 15.0337 | 1488 | 0.6845 | 0.8770 | 0.8773 |
|
| 71 |
+
| 0.0166 | 16.0337 | 1581 | 0.8649 | 0.8525 | 0.8445 |
|
| 72 |
+
| 0.0014 | 17.0337 | 1674 | 0.7866 | 0.8525 | 0.8516 |
|
| 73 |
+
| 0.0473 | 18.0337 | 1767 | 0.6390 | 0.8770 | 0.8776 |
|
| 74 |
+
| 0.0441 | 19.0337 | 1860 | 0.8235 | 0.8361 | 0.8342 |
|
| 75 |
+
| 0.0006 | 20.0337 | 1953 | 0.6014 | 0.8852 | 0.8856 |
|
| 76 |
+
| 0.0005 | 21.0337 | 2046 | 0.7581 | 0.8689 | 0.8672 |
|
| 77 |
+
| 0.0032 | 22.0337 | 2139 | 0.6454 | 0.8770 | 0.8772 |
|
| 78 |
+
| 0.0565 | 23.0337 | 2232 | 0.8096 | 0.8525 | 0.8542 |
|
| 79 |
+
| 0.011 | 24.0337 | 2325 | 0.6807 | 0.8852 | 0.8858 |
|
| 80 |
+
| 0.0146 | 25.0337 | 2418 | 0.7754 | 0.8689 | 0.8696 |
|
| 81 |
+
| 0.0004 | 26.0337 | 2511 | 0.7246 | 0.8852 | 0.8857 |
|
| 82 |
+
| 0.0004 | 27.0337 | 2604 | 0.7165 | 0.8934 | 0.8942 |
|
| 83 |
+
| 0.0003 | 28.0337 | 2697 | 0.7232 | 0.9016 | 0.9021 |
|
| 84 |
+
| 0.0177 | 29.0228 | 2760 | 0.7259 | 0.9016 | 0.9021 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.41.2
|
| 90 |
+
- Pytorch 2.3.1+cu121
|
| 91 |
+
- Datasets 2.19.2
|
| 92 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344943528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a0d32932f833cdc9432629e3cdd01bd83ad86ece67a76f09ef1c2f71fbad53
|
| 3 |
size 344943528
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.90210919178688,
|
| 3 |
+
"best_model_checkpoint": "videomae-surf-analytics-runpod4/checkpoint-2697",
|
| 4 |
+
"epoch": 29.02282608695652,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2760,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0036231884057971015,
|
| 13 |
+
"grad_norm": 9.726770401000977,
|
| 14 |
+
"learning_rate": 1.8115942028985508e-06,
|
| 15 |
+
"loss": 1.3861,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.007246376811594203,
|
| 20 |
+
"grad_norm": 8.901580810546875,
|
| 21 |
+
"learning_rate": 3.6231884057971017e-06,
|
| 22 |
+
"loss": 1.3917,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.010869565217391304,
|
| 27 |
+
"grad_norm": 5.0848612785339355,
|
| 28 |
+
"learning_rate": 5.4347826086956525e-06,
|
| 29 |
+
"loss": 1.3179,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.014492753623188406,
|
| 34 |
+
"grad_norm": 8.99917221069336,
|
| 35 |
+
"learning_rate": 7.246376811594203e-06,
|
| 36 |
+
"loss": 1.2512,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.018115942028985508,
|
| 41 |
+
"grad_norm": 11.607219696044922,
|
| 42 |
+
"learning_rate": 9.057971014492753e-06,
|
| 43 |
+
"loss": 1.2267,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.021739130434782608,
|
| 48 |
+
"grad_norm": 6.150553226470947,
|
| 49 |
+
"learning_rate": 1.0869565217391305e-05,
|
| 50 |
+
"loss": 1.2952,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.025362318840579712,
|
| 55 |
+
"grad_norm": 7.3294358253479,
|
| 56 |
+
"learning_rate": 1.2681159420289857e-05,
|
| 57 |
+
"loss": 1.0431,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.028985507246376812,
|
| 62 |
+
"grad_norm": 4.637725830078125,
|
| 63 |
+
"learning_rate": 1.4492753623188407e-05,
|
| 64 |
+
"loss": 1.2039,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03260869565217391,
|
| 69 |
+
"grad_norm": 7.160071849822998,
|
| 70 |
+
"learning_rate": 1.630434782608696e-05,
|
| 71 |
+
"loss": 1.2463,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03369565217391304,
|
| 76 |
+
"eval_accuracy": 0.4344262295081967,
|
| 77 |
+
"eval_f1": 0.29487747520534413,
|
| 78 |
+
"eval_loss": 1.2388594150543213,
|
| 79 |
+
"eval_runtime": 42.3507,
|
| 80 |
+
"eval_samples_per_second": 2.881,
|
| 81 |
+
"eval_steps_per_second": 0.378,
|
| 82 |
+
"step": 93
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.002536231884058,
|
| 86 |
+
"grad_norm": 4.499807834625244,
|
| 87 |
+
"learning_rate": 1.8115942028985507e-05,
|
| 88 |
+
"loss": 1.1553,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.0061594202898552,
|
| 93 |
+
"grad_norm": 5.520775318145752,
|
| 94 |
+
"learning_rate": 1.992753623188406e-05,
|
| 95 |
+
"loss": 1.1873,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.0097826086956523,
|
| 100 |
+
"grad_norm": 7.460188388824463,
|
| 101 |
+
"learning_rate": 2.173913043478261e-05,
|
| 102 |
+
"loss": 1.0111,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.0134057971014492,
|
| 107 |
+
"grad_norm": 7.1730875968933105,
|
| 108 |
+
"learning_rate": 2.355072463768116e-05,
|
| 109 |
+
"loss": 1.0118,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0170289855072463,
|
| 114 |
+
"grad_norm": 6.370150566101074,
|
| 115 |
+
"learning_rate": 2.5362318840579714e-05,
|
| 116 |
+
"loss": 0.9757,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0206521739130434,
|
| 121 |
+
"grad_norm": 12.998475074768066,
|
| 122 |
+
"learning_rate": 2.7173913043478262e-05,
|
| 123 |
+
"loss": 0.9456,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.0242753623188405,
|
| 128 |
+
"grad_norm": 19.65399169921875,
|
| 129 |
+
"learning_rate": 2.8985507246376814e-05,
|
| 130 |
+
"loss": 1.0014,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.0278985507246376,
|
| 135 |
+
"grad_norm": 11.76526927947998,
|
| 136 |
+
"learning_rate": 3.079710144927536e-05,
|
| 137 |
+
"loss": 1.0805,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.0315217391304348,
|
| 142 |
+
"grad_norm": 8.409660339355469,
|
| 143 |
+
"learning_rate": 3.260869565217392e-05,
|
| 144 |
+
"loss": 1.024,
|
| 145 |
+
"step": 180
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.0336956521739131,
|
| 149 |
+
"eval_accuracy": 0.5491803278688525,
|
| 150 |
+
"eval_f1": 0.5254458656098001,
|
| 151 |
+
"eval_loss": 1.0342785120010376,
|
| 152 |
+
"eval_runtime": 42.2598,
|
| 153 |
+
"eval_samples_per_second": 2.887,
|
| 154 |
+
"eval_steps_per_second": 0.379,
|
| 155 |
+
"step": 186
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.0014492753623188,
|
| 159 |
+
"grad_norm": 8.813424110412598,
|
| 160 |
+
"learning_rate": 3.4420289855072465e-05,
|
| 161 |
+
"loss": 0.9424,
|
| 162 |
+
"step": 190
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.005072463768116,
|
| 166 |
+
"grad_norm": 18.248958587646484,
|
| 167 |
+
"learning_rate": 3.6231884057971014e-05,
|
| 168 |
+
"loss": 0.8009,
|
| 169 |
+
"step": 200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.008695652173913,
|
| 173 |
+
"grad_norm": 9.742342948913574,
|
| 174 |
+
"learning_rate": 3.804347826086957e-05,
|
| 175 |
+
"loss": 0.6643,
|
| 176 |
+
"step": 210
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.0123188405797103,
|
| 180 |
+
"grad_norm": 10.787181854248047,
|
| 181 |
+
"learning_rate": 3.985507246376812e-05,
|
| 182 |
+
"loss": 1.0492,
|
| 183 |
+
"step": 220
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.0159420289855072,
|
| 187 |
+
"grad_norm": 10.376043319702148,
|
| 188 |
+
"learning_rate": 4.166666666666667e-05,
|
| 189 |
+
"loss": 0.6274,
|
| 190 |
+
"step": 230
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.0195652173913046,
|
| 194 |
+
"grad_norm": 8.305957794189453,
|
| 195 |
+
"learning_rate": 4.347826086956522e-05,
|
| 196 |
+
"loss": 0.7027,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.0231884057971015,
|
| 201 |
+
"grad_norm": 13.777029991149902,
|
| 202 |
+
"learning_rate": 4.528985507246377e-05,
|
| 203 |
+
"loss": 0.6191,
|
| 204 |
+
"step": 250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.0268115942028984,
|
| 208 |
+
"grad_norm": 10.486043930053711,
|
| 209 |
+
"learning_rate": 4.710144927536232e-05,
|
| 210 |
+
"loss": 0.8711,
|
| 211 |
+
"step": 260
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.0304347826086957,
|
| 215 |
+
"grad_norm": 5.285229682922363,
|
| 216 |
+
"learning_rate": 4.891304347826087e-05,
|
| 217 |
+
"loss": 0.6932,
|
| 218 |
+
"step": 270
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.033695652173913,
|
| 222 |
+
"eval_accuracy": 0.6639344262295082,
|
| 223 |
+
"eval_f1": 0.6359864440646367,
|
| 224 |
+
"eval_loss": 0.8279891610145569,
|
| 225 |
+
"eval_runtime": 36.4539,
|
| 226 |
+
"eval_samples_per_second": 3.347,
|
| 227 |
+
"eval_steps_per_second": 0.439,
|
| 228 |
+
"step": 279
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.0003623188405797,
|
| 232 |
+
"grad_norm": 7.227272033691406,
|
| 233 |
+
"learning_rate": 4.99194847020934e-05,
|
| 234 |
+
"loss": 0.8223,
|
| 235 |
+
"step": 280
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.003985507246377,
|
| 239 |
+
"grad_norm": 6.091291427612305,
|
| 240 |
+
"learning_rate": 4.9718196457326895e-05,
|
| 241 |
+
"loss": 0.7407,
|
| 242 |
+
"step": 290
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.007608695652174,
|
| 246 |
+
"grad_norm": 12.283949851989746,
|
| 247 |
+
"learning_rate": 4.9516908212560386e-05,
|
| 248 |
+
"loss": 0.5408,
|
| 249 |
+
"step": 300
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.011231884057971,
|
| 253 |
+
"grad_norm": 12.24530029296875,
|
| 254 |
+
"learning_rate": 4.9315619967793884e-05,
|
| 255 |
+
"loss": 0.5201,
|
| 256 |
+
"step": 310
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.014855072463768,
|
| 260 |
+
"grad_norm": 13.709362983703613,
|
| 261 |
+
"learning_rate": 4.911433172302738e-05,
|
| 262 |
+
"loss": 0.5266,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.018478260869565,
|
| 267 |
+
"grad_norm": 8.324898719787598,
|
| 268 |
+
"learning_rate": 4.891304347826087e-05,
|
| 269 |
+
"loss": 0.5397,
|
| 270 |
+
"step": 330
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.0221014492753624,
|
| 274 |
+
"grad_norm": 13.807954788208008,
|
| 275 |
+
"learning_rate": 4.871175523349436e-05,
|
| 276 |
+
"loss": 0.5297,
|
| 277 |
+
"step": 340
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 3.0257246376811593,
|
| 281 |
+
"grad_norm": 12.566025733947754,
|
| 282 |
+
"learning_rate": 4.851046698872786e-05,
|
| 283 |
+
"loss": 0.4034,
|
| 284 |
+
"step": 350
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.0293478260869566,
|
| 288 |
+
"grad_norm": 15.83183479309082,
|
| 289 |
+
"learning_rate": 4.830917874396135e-05,
|
| 290 |
+
"loss": 0.4654,
|
| 291 |
+
"step": 360
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.0329710144927535,
|
| 295 |
+
"grad_norm": 1.7397154569625854,
|
| 296 |
+
"learning_rate": 4.810789049919485e-05,
|
| 297 |
+
"loss": 0.4467,
|
| 298 |
+
"step": 370
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.033695652173913,
|
| 302 |
+
"eval_accuracy": 0.7459016393442623,
|
| 303 |
+
"eval_f1": 0.7338377280393545,
|
| 304 |
+
"eval_loss": 0.7664637565612793,
|
| 305 |
+
"eval_runtime": 36.3739,
|
| 306 |
+
"eval_samples_per_second": 3.354,
|
| 307 |
+
"eval_steps_per_second": 0.44,
|
| 308 |
+
"step": 372
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.0028985507246375,
|
| 312 |
+
"grad_norm": 2.2322423458099365,
|
| 313 |
+
"learning_rate": 4.790660225442835e-05,
|
| 314 |
+
"loss": 0.3515,
|
| 315 |
+
"step": 380
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.006521739130434,
|
| 319 |
+
"grad_norm": 17.386234283447266,
|
| 320 |
+
"learning_rate": 4.770531400966184e-05,
|
| 321 |
+
"loss": 0.2997,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.010144927536232,
|
| 326 |
+
"grad_norm": 11.770244598388672,
|
| 327 |
+
"learning_rate": 4.7504025764895335e-05,
|
| 328 |
+
"loss": 0.2963,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.013768115942029,
|
| 333 |
+
"grad_norm": 17.996971130371094,
|
| 334 |
+
"learning_rate": 4.7302737520128826e-05,
|
| 335 |
+
"loss": 0.2062,
|
| 336 |
+
"step": 410
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.017391304347826,
|
| 340 |
+
"grad_norm": 0.812595009803772,
|
| 341 |
+
"learning_rate": 4.710144927536232e-05,
|
| 342 |
+
"loss": 0.1948,
|
| 343 |
+
"step": 420
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.021014492753623,
|
| 347 |
+
"grad_norm": 9.69245433807373,
|
| 348 |
+
"learning_rate": 4.6900161030595815e-05,
|
| 349 |
+
"loss": 0.5129,
|
| 350 |
+
"step": 430
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.024637681159421,
|
| 354 |
+
"grad_norm": 9.770214080810547,
|
| 355 |
+
"learning_rate": 4.669887278582931e-05,
|
| 356 |
+
"loss": 0.3938,
|
| 357 |
+
"step": 440
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.028260869565218,
|
| 361 |
+
"grad_norm": 16.608795166015625,
|
| 362 |
+
"learning_rate": 4.64975845410628e-05,
|
| 363 |
+
"loss": 0.3251,
|
| 364 |
+
"step": 450
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.0318840579710145,
|
| 368 |
+
"grad_norm": 14.123062133789062,
|
| 369 |
+
"learning_rate": 4.62962962962963e-05,
|
| 370 |
+
"loss": 0.4449,
|
| 371 |
+
"step": 460
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 4.033695652173913,
|
| 375 |
+
"eval_accuracy": 0.7131147540983607,
|
| 376 |
+
"eval_f1": 0.6741469908968126,
|
| 377 |
+
"eval_loss": 0.871498703956604,
|
| 378 |
+
"eval_runtime": 36.9705,
|
| 379 |
+
"eval_samples_per_second": 3.3,
|
| 380 |
+
"eval_steps_per_second": 0.433,
|
| 381 |
+
"step": 465
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 5.0018115942028984,
|
| 385 |
+
"grad_norm": 6.473958969116211,
|
| 386 |
+
"learning_rate": 4.609500805152979e-05,
|
| 387 |
+
"loss": 0.1426,
|
| 388 |
+
"step": 470
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.005434782608695,
|
| 392 |
+
"grad_norm": 0.1059931218624115,
|
| 393 |
+
"learning_rate": 4.589371980676328e-05,
|
| 394 |
+
"loss": 0.1327,
|
| 395 |
+
"step": 480
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.009057971014493,
|
| 399 |
+
"grad_norm": 0.7832779884338379,
|
| 400 |
+
"learning_rate": 4.569243156199678e-05,
|
| 401 |
+
"loss": 0.1692,
|
| 402 |
+
"step": 490
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.01268115942029,
|
| 406 |
+
"grad_norm": 12.166410446166992,
|
| 407 |
+
"learning_rate": 4.549114331723028e-05,
|
| 408 |
+
"loss": 0.2135,
|
| 409 |
+
"step": 500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 5.016304347826087,
|
| 413 |
+
"grad_norm": 4.051369667053223,
|
| 414 |
+
"learning_rate": 4.528985507246377e-05,
|
| 415 |
+
"loss": 0.2939,
|
| 416 |
+
"step": 510
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.019927536231884,
|
| 420 |
+
"grad_norm": 1.8354891538619995,
|
| 421 |
+
"learning_rate": 4.5088566827697266e-05,
|
| 422 |
+
"loss": 0.2449,
|
| 423 |
+
"step": 520
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.023550724637682,
|
| 427 |
+
"grad_norm": 0.3607825040817261,
|
| 428 |
+
"learning_rate": 4.488727858293076e-05,
|
| 429 |
+
"loss": 0.0841,
|
| 430 |
+
"step": 530
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 5.0271739130434785,
|
| 434 |
+
"grad_norm": 7.8428239822387695,
|
| 435 |
+
"learning_rate": 4.4685990338164255e-05,
|
| 436 |
+
"loss": 0.4005,
|
| 437 |
+
"step": 540
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.030797101449275,
|
| 441 |
+
"grad_norm": 0.2001497596502304,
|
| 442 |
+
"learning_rate": 4.4484702093397746e-05,
|
| 443 |
+
"loss": 0.1371,
|
| 444 |
+
"step": 550
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.033695652173913,
|
| 448 |
+
"eval_accuracy": 0.7295081967213115,
|
| 449 |
+
"eval_f1": 0.7157775700184823,
|
| 450 |
+
"eval_loss": 1.0560429096221924,
|
| 451 |
+
"eval_runtime": 42.0495,
|
| 452 |
+
"eval_samples_per_second": 2.901,
|
| 453 |
+
"eval_steps_per_second": 0.381,
|
| 454 |
+
"step": 558
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 6.000724637681159,
|
| 458 |
+
"grad_norm": 0.06493417173624039,
|
| 459 |
+
"learning_rate": 4.428341384863124e-05,
|
| 460 |
+
"loss": 0.2275,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 6.004347826086956,
|
| 465 |
+
"grad_norm": 11.751331329345703,
|
| 466 |
+
"learning_rate": 4.408212560386474e-05,
|
| 467 |
+
"loss": 0.2252,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 6.007971014492754,
|
| 472 |
+
"grad_norm": 19.441425323486328,
|
| 473 |
+
"learning_rate": 4.388083735909823e-05,
|
| 474 |
+
"loss": 0.2761,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 6.011594202898551,
|
| 479 |
+
"grad_norm": 0.09549690037965775,
|
| 480 |
+
"learning_rate": 4.367954911433172e-05,
|
| 481 |
+
"loss": 0.2724,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.015217391304348,
|
| 486 |
+
"grad_norm": 12.359782218933105,
|
| 487 |
+
"learning_rate": 4.347826086956522e-05,
|
| 488 |
+
"loss": 0.1888,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 6.018840579710145,
|
| 493 |
+
"grad_norm": 20.348411560058594,
|
| 494 |
+
"learning_rate": 4.327697262479871e-05,
|
| 495 |
+
"loss": 0.4012,
|
| 496 |
+
"step": 610
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 6.022463768115942,
|
| 500 |
+
"grad_norm": 0.05766362324357033,
|
| 501 |
+
"learning_rate": 4.307568438003221e-05,
|
| 502 |
+
"loss": 0.1362,
|
| 503 |
+
"step": 620
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.026086956521739,
|
| 507 |
+
"grad_norm": 18.2602481842041,
|
| 508 |
+
"learning_rate": 4.2874396135265707e-05,
|
| 509 |
+
"loss": 0.1788,
|
| 510 |
+
"step": 630
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 6.029710144927536,
|
| 514 |
+
"grad_norm": 0.44831833243370056,
|
| 515 |
+
"learning_rate": 4.26731078904992e-05,
|
| 516 |
+
"loss": 0.1337,
|
| 517 |
+
"step": 640
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 6.033333333333333,
|
| 521 |
+
"grad_norm": 13.512539863586426,
|
| 522 |
+
"learning_rate": 4.247181964573269e-05,
|
| 523 |
+
"loss": 0.1789,
|
| 524 |
+
"step": 650
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.033695652173913,
|
| 528 |
+
"eval_accuracy": 0.7868852459016393,
|
| 529 |
+
"eval_f1": 0.7876811278368901,
|
| 530 |
+
"eval_loss": 0.8218082189559937,
|
| 531 |
+
"eval_runtime": 41.3621,
|
| 532 |
+
"eval_samples_per_second": 2.95,
|
| 533 |
+
"eval_steps_per_second": 0.387,
|
| 534 |
+
"step": 651
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.003260869565217,
|
| 538 |
+
"grad_norm": 0.31983035802841187,
|
| 539 |
+
"learning_rate": 4.2270531400966186e-05,
|
| 540 |
+
"loss": 0.1123,
|
| 541 |
+
"step": 660
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.006884057971014,
|
| 545 |
+
"grad_norm": 3.5525496006011963,
|
| 546 |
+
"learning_rate": 4.206924315619968e-05,
|
| 547 |
+
"loss": 0.1231,
|
| 548 |
+
"step": 670
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.010507246376812,
|
| 552 |
+
"grad_norm": 17.89982795715332,
|
| 553 |
+
"learning_rate": 4.1867954911433174e-05,
|
| 554 |
+
"loss": 0.1998,
|
| 555 |
+
"step": 680
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.014130434782609,
|
| 559 |
+
"grad_norm": 14.844808578491211,
|
| 560 |
+
"learning_rate": 4.166666666666667e-05,
|
| 561 |
+
"loss": 0.0988,
|
| 562 |
+
"step": 690
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.017753623188406,
|
| 566 |
+
"grad_norm": 1.0570082664489746,
|
| 567 |
+
"learning_rate": 4.146537842190016e-05,
|
| 568 |
+
"loss": 0.1069,
|
| 569 |
+
"step": 700
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.021376811594203,
|
| 573 |
+
"grad_norm": 58.255123138427734,
|
| 574 |
+
"learning_rate": 4.126409017713366e-05,
|
| 575 |
+
"loss": 0.2484,
|
| 576 |
+
"step": 710
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.025,
|
| 580 |
+
"grad_norm": 0.30179139971733093,
|
| 581 |
+
"learning_rate": 4.106280193236715e-05,
|
| 582 |
+
"loss": 0.0665,
|
| 583 |
+
"step": 720
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.028623188405797,
|
| 587 |
+
"grad_norm": 36.053836822509766,
|
| 588 |
+
"learning_rate": 4.086151368760064e-05,
|
| 589 |
+
"loss": 0.2122,
|
| 590 |
+
"step": 730
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.032246376811594,
|
| 594 |
+
"grad_norm": 0.23371699452400208,
|
| 595 |
+
"learning_rate": 4.066022544283414e-05,
|
| 596 |
+
"loss": 0.2125,
|
| 597 |
+
"step": 740
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.033695652173913,
|
| 601 |
+
"eval_accuracy": 0.7868852459016393,
|
| 602 |
+
"eval_f1": 0.7812358925016187,
|
| 603 |
+
"eval_loss": 0.7612058520317078,
|
| 604 |
+
"eval_runtime": 38.7607,
|
| 605 |
+
"eval_samples_per_second": 3.148,
|
| 606 |
+
"eval_steps_per_second": 0.413,
|
| 607 |
+
"step": 744
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 8.002173913043478,
|
| 611 |
+
"grad_norm": 0.2972787022590637,
|
| 612 |
+
"learning_rate": 4.045893719806764e-05,
|
| 613 |
+
"loss": 0.0607,
|
| 614 |
+
"step": 750
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 8.005797101449275,
|
| 618 |
+
"grad_norm": 0.18866966664791107,
|
| 619 |
+
"learning_rate": 4.025764895330113e-05,
|
| 620 |
+
"loss": 0.1634,
|
| 621 |
+
"step": 760
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 8.009420289855072,
|
| 625 |
+
"grad_norm": 0.39748045802116394,
|
| 626 |
+
"learning_rate": 4.0056360708534626e-05,
|
| 627 |
+
"loss": 0.0266,
|
| 628 |
+
"step": 770
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 8.013043478260869,
|
| 632 |
+
"grad_norm": 8.73737907409668,
|
| 633 |
+
"learning_rate": 3.985507246376812e-05,
|
| 634 |
+
"loss": 0.0885,
|
| 635 |
+
"step": 780
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 8.016666666666667,
|
| 639 |
+
"grad_norm": 0.15234462916851044,
|
| 640 |
+
"learning_rate": 3.965378421900161e-05,
|
| 641 |
+
"loss": 0.0031,
|
| 642 |
+
"step": 790
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 8.020289855072464,
|
| 646 |
+
"grad_norm": 12.640290260314941,
|
| 647 |
+
"learning_rate": 3.9452495974235105e-05,
|
| 648 |
+
"loss": 0.2264,
|
| 649 |
+
"step": 800
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 8.023913043478261,
|
| 653 |
+
"grad_norm": 0.857113778591156,
|
| 654 |
+
"learning_rate": 3.92512077294686e-05,
|
| 655 |
+
"loss": 0.2147,
|
| 656 |
+
"step": 810
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 8.027536231884058,
|
| 660 |
+
"grad_norm": 22.054996490478516,
|
| 661 |
+
"learning_rate": 3.9049919484702094e-05,
|
| 662 |
+
"loss": 0.1488,
|
| 663 |
+
"step": 820
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 8.031159420289855,
|
| 667 |
+
"grad_norm": 0.0397706963121891,
|
| 668 |
+
"learning_rate": 3.884863123993559e-05,
|
| 669 |
+
"loss": 0.1561,
|
| 670 |
+
"step": 830
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 8.033695652173913,
|
| 674 |
+
"eval_accuracy": 0.8524590163934426,
|
| 675 |
+
"eval_f1": 0.8498439299955695,
|
| 676 |
+
"eval_loss": 0.6051312685012817,
|
| 677 |
+
"eval_runtime": 37.4453,
|
| 678 |
+
"eval_samples_per_second": 3.258,
|
| 679 |
+
"eval_steps_per_second": 0.427,
|
| 680 |
+
"step": 837
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 9.001086956521739,
|
| 684 |
+
"grad_norm": 21.391626358032227,
|
| 685 |
+
"learning_rate": 3.864734299516908e-05,
|
| 686 |
+
"loss": 0.0403,
|
| 687 |
+
"step": 840
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 9.004710144927536,
|
| 691 |
+
"grad_norm": 29.436418533325195,
|
| 692 |
+
"learning_rate": 3.844605475040258e-05,
|
| 693 |
+
"loss": 0.0919,
|
| 694 |
+
"step": 850
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 9.008333333333333,
|
| 698 |
+
"grad_norm": 0.7489465475082397,
|
| 699 |
+
"learning_rate": 3.824476650563607e-05,
|
| 700 |
+
"loss": 0.1226,
|
| 701 |
+
"step": 860
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 9.01195652173913,
|
| 705 |
+
"grad_norm": 0.17123177647590637,
|
| 706 |
+
"learning_rate": 3.804347826086957e-05,
|
| 707 |
+
"loss": 0.1048,
|
| 708 |
+
"step": 870
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 9.015579710144927,
|
| 712 |
+
"grad_norm": 0.16690145432949066,
|
| 713 |
+
"learning_rate": 3.784219001610306e-05,
|
| 714 |
+
"loss": 0.019,
|
| 715 |
+
"step": 880
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 9.019202898550725,
|
| 719 |
+
"grad_norm": 0.029665417969226837,
|
| 720 |
+
"learning_rate": 3.764090177133656e-05,
|
| 721 |
+
"loss": 0.0916,
|
| 722 |
+
"step": 890
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 9.022826086956522,
|
| 726 |
+
"grad_norm": 0.02787993662059307,
|
| 727 |
+
"learning_rate": 3.743961352657005e-05,
|
| 728 |
+
"loss": 0.1313,
|
| 729 |
+
"step": 900
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 9.02644927536232,
|
| 733 |
+
"grad_norm": 0.020100735127925873,
|
| 734 |
+
"learning_rate": 3.7238325281803546e-05,
|
| 735 |
+
"loss": 0.0665,
|
| 736 |
+
"step": 910
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 9.030072463768116,
|
| 740 |
+
"grad_norm": 0.46395331621170044,
|
| 741 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 742 |
+
"loss": 0.1576,
|
| 743 |
+
"step": 920
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 9.033695652173913,
|
| 747 |
+
"grad_norm": 15.341463088989258,
|
| 748 |
+
"learning_rate": 3.6835748792270534e-05,
|
| 749 |
+
"loss": 0.2297,
|
| 750 |
+
"step": 930
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 9.033695652173913,
|
| 754 |
+
"eval_accuracy": 0.8770491803278688,
|
| 755 |
+
"eval_f1": 0.8766394106755289,
|
| 756 |
+
"eval_loss": 0.6320860385894775,
|
| 757 |
+
"eval_runtime": 36.4362,
|
| 758 |
+
"eval_samples_per_second": 3.348,
|
| 759 |
+
"eval_steps_per_second": 0.439,
|
| 760 |
+
"step": 930
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 10.003623188405797,
|
| 764 |
+
"grad_norm": 0.1273241639137268,
|
| 765 |
+
"learning_rate": 3.663446054750403e-05,
|
| 766 |
+
"loss": 0.023,
|
| 767 |
+
"step": 940
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 10.007246376811594,
|
| 771 |
+
"grad_norm": 7.185577869415283,
|
| 772 |
+
"learning_rate": 3.643317230273752e-05,
|
| 773 |
+
"loss": 0.0476,
|
| 774 |
+
"step": 950
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 10.01086956521739,
|
| 778 |
+
"grad_norm": 0.06820656359195709,
|
| 779 |
+
"learning_rate": 3.6231884057971014e-05,
|
| 780 |
+
"loss": 0.098,
|
| 781 |
+
"step": 960
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 10.014492753623188,
|
| 785 |
+
"grad_norm": 3.738891124725342,
|
| 786 |
+
"learning_rate": 3.603059581320451e-05,
|
| 787 |
+
"loss": 0.0214,
|
| 788 |
+
"step": 970
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 10.018115942028986,
|
| 792 |
+
"grad_norm": 0.026407288387417793,
|
| 793 |
+
"learning_rate": 3.5829307568438e-05,
|
| 794 |
+
"loss": 0.0211,
|
| 795 |
+
"step": 980
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 10.021739130434783,
|
| 799 |
+
"grad_norm": 0.013281815685331821,
|
| 800 |
+
"learning_rate": 3.56280193236715e-05,
|
| 801 |
+
"loss": 0.0539,
|
| 802 |
+
"step": 990
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 10.02536231884058,
|
| 806 |
+
"grad_norm": 0.016630737110972404,
|
| 807 |
+
"learning_rate": 3.5426731078905e-05,
|
| 808 |
+
"loss": 0.0013,
|
| 809 |
+
"step": 1000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 10.028985507246377,
|
| 813 |
+
"grad_norm": 0.013293278403580189,
|
| 814 |
+
"learning_rate": 3.522544283413849e-05,
|
| 815 |
+
"loss": 0.0542,
|
| 816 |
+
"step": 1010
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 10.032608695652174,
|
| 820 |
+
"grad_norm": 0.021008765324950218,
|
| 821 |
+
"learning_rate": 3.502415458937198e-05,
|
| 822 |
+
"loss": 0.0692,
|
| 823 |
+
"step": 1020
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 10.033695652173913,
|
| 827 |
+
"eval_accuracy": 0.8442622950819673,
|
| 828 |
+
"eval_f1": 0.8454522438128995,
|
| 829 |
+
"eval_loss": 0.7127842903137207,
|
| 830 |
+
"eval_runtime": 37.7495,
|
| 831 |
+
"eval_samples_per_second": 3.232,
|
| 832 |
+
"eval_steps_per_second": 0.424,
|
| 833 |
+
"step": 1023
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 11.002536231884058,
|
| 837 |
+
"grad_norm": 1.3483757972717285,
|
| 838 |
+
"learning_rate": 3.482286634460548e-05,
|
| 839 |
+
"loss": 0.0038,
|
| 840 |
+
"step": 1030
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 11.006159420289855,
|
| 844 |
+
"grad_norm": 3.5823521614074707,
|
| 845 |
+
"learning_rate": 3.462157809983897e-05,
|
| 846 |
+
"loss": 0.0591,
|
| 847 |
+
"step": 1040
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 11.009782608695652,
|
| 851 |
+
"grad_norm": 0.010481027886271477,
|
| 852 |
+
"learning_rate": 3.4420289855072465e-05,
|
| 853 |
+
"loss": 0.1033,
|
| 854 |
+
"step": 1050
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 11.013405797101449,
|
| 858 |
+
"grad_norm": 0.022550148889422417,
|
| 859 |
+
"learning_rate": 3.421900161030596e-05,
|
| 860 |
+
"loss": 0.073,
|
| 861 |
+
"step": 1060
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 11.017028985507247,
|
| 865 |
+
"grad_norm": 0.22509634494781494,
|
| 866 |
+
"learning_rate": 3.4017713365539454e-05,
|
| 867 |
+
"loss": 0.0726,
|
| 868 |
+
"step": 1070
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 11.020652173913044,
|
| 872 |
+
"grad_norm": 0.409952849149704,
|
| 873 |
+
"learning_rate": 3.381642512077295e-05,
|
| 874 |
+
"loss": 0.02,
|
| 875 |
+
"step": 1080
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 11.024275362318841,
|
| 879 |
+
"grad_norm": 0.022929221391677856,
|
| 880 |
+
"learning_rate": 3.361513687600644e-05,
|
| 881 |
+
"loss": 0.0079,
|
| 882 |
+
"step": 1090
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 11.027898550724638,
|
| 886 |
+
"grad_norm": 0.009896630421280861,
|
| 887 |
+
"learning_rate": 3.341384863123993e-05,
|
| 888 |
+
"loss": 0.0277,
|
| 889 |
+
"step": 1100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 11.031521739130435,
|
| 893 |
+
"grad_norm": 0.04593189060688019,
|
| 894 |
+
"learning_rate": 3.321256038647343e-05,
|
| 895 |
+
"loss": 0.0495,
|
| 896 |
+
"step": 1110
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 11.033695652173913,
|
| 900 |
+
"eval_accuracy": 0.8360655737704918,
|
| 901 |
+
"eval_f1": 0.8352522796879587,
|
| 902 |
+
"eval_loss": 0.7737651467323303,
|
| 903 |
+
"eval_runtime": 37.723,
|
| 904 |
+
"eval_samples_per_second": 3.234,
|
| 905 |
+
"eval_steps_per_second": 0.424,
|
| 906 |
+
"step": 1116
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 12.001449275362319,
|
| 910 |
+
"grad_norm": 0.4977063536643982,
|
| 911 |
+
"learning_rate": 3.301127214170693e-05,
|
| 912 |
+
"loss": 0.068,
|
| 913 |
+
"step": 1120
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 12.005072463768116,
|
| 917 |
+
"grad_norm": 9.698254585266113,
|
| 918 |
+
"learning_rate": 3.280998389694042e-05,
|
| 919 |
+
"loss": 0.0108,
|
| 920 |
+
"step": 1130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 12.008695652173913,
|
| 924 |
+
"grad_norm": 37.918338775634766,
|
| 925 |
+
"learning_rate": 3.260869565217392e-05,
|
| 926 |
+
"loss": 0.0108,
|
| 927 |
+
"step": 1140
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 12.01231884057971,
|
| 931 |
+
"grad_norm": 0.012104889377951622,
|
| 932 |
+
"learning_rate": 3.240740740740741e-05,
|
| 933 |
+
"loss": 0.0524,
|
| 934 |
+
"step": 1150
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 12.015942028985508,
|
| 938 |
+
"grad_norm": 40.3338623046875,
|
| 939 |
+
"learning_rate": 3.22061191626409e-05,
|
| 940 |
+
"loss": 0.0867,
|
| 941 |
+
"step": 1160
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 12.019565217391305,
|
| 945 |
+
"grad_norm": 37.17512130737305,
|
| 946 |
+
"learning_rate": 3.2004830917874396e-05,
|
| 947 |
+
"loss": 0.058,
|
| 948 |
+
"step": 1170
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 12.023188405797102,
|
| 952 |
+
"grad_norm": 0.11629298329353333,
|
| 953 |
+
"learning_rate": 3.1803542673107894e-05,
|
| 954 |
+
"loss": 0.0826,
|
| 955 |
+
"step": 1180
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 12.026811594202899,
|
| 959 |
+
"grad_norm": 0.01565568707883358,
|
| 960 |
+
"learning_rate": 3.1602254428341385e-05,
|
| 961 |
+
"loss": 0.1293,
|
| 962 |
+
"step": 1190
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 12.030434782608696,
|
| 966 |
+
"grad_norm": 0.0614808052778244,
|
| 967 |
+
"learning_rate": 3.140096618357488e-05,
|
| 968 |
+
"loss": 0.1059,
|
| 969 |
+
"step": 1200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 12.033695652173913,
|
| 973 |
+
"eval_accuracy": 0.8524590163934426,
|
| 974 |
+
"eval_f1": 0.8524029704357573,
|
| 975 |
+
"eval_loss": 0.6213375329971313,
|
| 976 |
+
"eval_runtime": 37.3424,
|
| 977 |
+
"eval_samples_per_second": 3.267,
|
| 978 |
+
"eval_steps_per_second": 0.428,
|
| 979 |
+
"step": 1209
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 13.00036231884058,
|
| 983 |
+
"grad_norm": 0.01347822230309248,
|
| 984 |
+
"learning_rate": 3.119967793880837e-05,
|
| 985 |
+
"loss": 0.002,
|
| 986 |
+
"step": 1210
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 13.003985507246377,
|
| 990 |
+
"grad_norm": 0.02086636610329151,
|
| 991 |
+
"learning_rate": 3.099838969404187e-05,
|
| 992 |
+
"loss": 0.0658,
|
| 993 |
+
"step": 1220
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 13.007608695652173,
|
| 997 |
+
"grad_norm": 0.18250229954719543,
|
| 998 |
+
"learning_rate": 3.079710144927536e-05,
|
| 999 |
+
"loss": 0.018,
|
| 1000 |
+
"step": 1230
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 13.01123188405797,
|
| 1004 |
+
"grad_norm": 0.01864694245159626,
|
| 1005 |
+
"learning_rate": 3.059581320450886e-05,
|
| 1006 |
+
"loss": 0.0016,
|
| 1007 |
+
"step": 1240
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 13.014855072463767,
|
| 1011 |
+
"grad_norm": 0.03139445558190346,
|
| 1012 |
+
"learning_rate": 3.0394524959742354e-05,
|
| 1013 |
+
"loss": 0.0011,
|
| 1014 |
+
"step": 1250
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 13.018478260869566,
|
| 1018 |
+
"grad_norm": 0.013789031654596329,
|
| 1019 |
+
"learning_rate": 3.0193236714975848e-05,
|
| 1020 |
+
"loss": 0.0016,
|
| 1021 |
+
"step": 1260
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 13.022101449275363,
|
| 1025 |
+
"grad_norm": 0.03744020313024521,
|
| 1026 |
+
"learning_rate": 2.9991948470209342e-05,
|
| 1027 |
+
"loss": 0.001,
|
| 1028 |
+
"step": 1270
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 13.02572463768116,
|
| 1032 |
+
"grad_norm": 0.007898851297795773,
|
| 1033 |
+
"learning_rate": 2.9790660225442833e-05,
|
| 1034 |
+
"loss": 0.0106,
|
| 1035 |
+
"step": 1280
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 13.029347826086957,
|
| 1039 |
+
"grad_norm": 3.897127866744995,
|
| 1040 |
+
"learning_rate": 2.9589371980676327e-05,
|
| 1041 |
+
"loss": 0.0454,
|
| 1042 |
+
"step": 1290
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 13.032971014492754,
|
| 1046 |
+
"grad_norm": 0.009393475018441677,
|
| 1047 |
+
"learning_rate": 2.938808373590982e-05,
|
| 1048 |
+
"loss": 0.1672,
|
| 1049 |
+
"step": 1300
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 13.033695652173913,
|
| 1053 |
+
"eval_accuracy": 0.8442622950819673,
|
| 1054 |
+
"eval_f1": 0.8408580352564015,
|
| 1055 |
+
"eval_loss": 0.7887758612632751,
|
| 1056 |
+
"eval_runtime": 37.7507,
|
| 1057 |
+
"eval_samples_per_second": 3.232,
|
| 1058 |
+
"eval_steps_per_second": 0.424,
|
| 1059 |
+
"step": 1302
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 14.002898550724638,
|
| 1063 |
+
"grad_norm": 0.034189604222774506,
|
| 1064 |
+
"learning_rate": 2.918679549114332e-05,
|
| 1065 |
+
"loss": 0.044,
|
| 1066 |
+
"step": 1310
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 14.006521739130434,
|
| 1070 |
+
"grad_norm": 0.02449285238981247,
|
| 1071 |
+
"learning_rate": 2.8985507246376814e-05,
|
| 1072 |
+
"loss": 0.0904,
|
| 1073 |
+
"step": 1320
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 14.010144927536231,
|
| 1077 |
+
"grad_norm": 0.027986012399196625,
|
| 1078 |
+
"learning_rate": 2.8784219001610308e-05,
|
| 1079 |
+
"loss": 0.0059,
|
| 1080 |
+
"step": 1330
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 14.013768115942028,
|
| 1084 |
+
"grad_norm": 0.017405090853571892,
|
| 1085 |
+
"learning_rate": 2.8582930756843802e-05,
|
| 1086 |
+
"loss": 0.0016,
|
| 1087 |
+
"step": 1340
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 14.017391304347827,
|
| 1091 |
+
"grad_norm": 0.009259097278118134,
|
| 1092 |
+
"learning_rate": 2.8381642512077293e-05,
|
| 1093 |
+
"loss": 0.1116,
|
| 1094 |
+
"step": 1350
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 14.021014492753624,
|
| 1098 |
+
"grad_norm": 0.27058884501457214,
|
| 1099 |
+
"learning_rate": 2.8180354267310787e-05,
|
| 1100 |
+
"loss": 0.0011,
|
| 1101 |
+
"step": 1360
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 14.02463768115942,
|
| 1105 |
+
"grad_norm": 0.04683419317007065,
|
| 1106 |
+
"learning_rate": 2.7979066022544288e-05,
|
| 1107 |
+
"loss": 0.0022,
|
| 1108 |
+
"step": 1370
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 14.028260869565218,
|
| 1112 |
+
"grad_norm": 0.011938877403736115,
|
| 1113 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1114 |
+
"loss": 0.092,
|
| 1115 |
+
"step": 1380
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 14.031884057971014,
|
| 1119 |
+
"grad_norm": 0.020922021940350533,
|
| 1120 |
+
"learning_rate": 2.7576489533011273e-05,
|
| 1121 |
+
"loss": 0.0178,
|
| 1122 |
+
"step": 1390
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 14.033695652173913,
|
| 1126 |
+
"eval_accuracy": 0.8688524590163934,
|
| 1127 |
+
"eval_f1": 0.8657779177289288,
|
| 1128 |
+
"eval_loss": 0.6488391757011414,
|
| 1129 |
+
"eval_runtime": 37.3683,
|
| 1130 |
+
"eval_samples_per_second": 3.265,
|
| 1131 |
+
"eval_steps_per_second": 0.428,
|
| 1132 |
+
"step": 1395
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 15.001811594202898,
|
| 1136 |
+
"grad_norm": 0.014293194748461246,
|
| 1137 |
+
"learning_rate": 2.7375201288244768e-05,
|
| 1138 |
+
"loss": 0.0616,
|
| 1139 |
+
"step": 1400
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 15.005434782608695,
|
| 1143 |
+
"grad_norm": 0.012990676797926426,
|
| 1144 |
+
"learning_rate": 2.7173913043478262e-05,
|
| 1145 |
+
"loss": 0.0038,
|
| 1146 |
+
"step": 1410
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 15.009057971014492,
|
| 1150 |
+
"grad_norm": 0.021259872242808342,
|
| 1151 |
+
"learning_rate": 2.6972624798711753e-05,
|
| 1152 |
+
"loss": 0.0008,
|
| 1153 |
+
"step": 1420
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 15.01268115942029,
|
| 1157 |
+
"grad_norm": 0.02497517503798008,
|
| 1158 |
+
"learning_rate": 2.6771336553945254e-05,
|
| 1159 |
+
"loss": 0.0016,
|
| 1160 |
+
"step": 1430
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 15.016304347826088,
|
| 1164 |
+
"grad_norm": 7.305609703063965,
|
| 1165 |
+
"learning_rate": 2.6570048309178748e-05,
|
| 1166 |
+
"loss": 0.1195,
|
| 1167 |
+
"step": 1440
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 15.019927536231885,
|
| 1171 |
+
"grad_norm": 65.574462890625,
|
| 1172 |
+
"learning_rate": 2.636876006441224e-05,
|
| 1173 |
+
"loss": 0.0579,
|
| 1174 |
+
"step": 1450
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 15.023550724637682,
|
| 1178 |
+
"grad_norm": 0.010529917664825916,
|
| 1179 |
+
"learning_rate": 2.6167471819645733e-05,
|
| 1180 |
+
"loss": 0.0296,
|
| 1181 |
+
"step": 1460
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 15.027173913043478,
|
| 1185 |
+
"grad_norm": 0.010935317724943161,
|
| 1186 |
+
"learning_rate": 2.5966183574879227e-05,
|
| 1187 |
+
"loss": 0.0616,
|
| 1188 |
+
"step": 1470
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 15.030797101449275,
|
| 1192 |
+
"grad_norm": 0.03048408031463623,
|
| 1193 |
+
"learning_rate": 2.576489533011272e-05,
|
| 1194 |
+
"loss": 0.0165,
|
| 1195 |
+
"step": 1480
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 15.033695652173913,
|
| 1199 |
+
"eval_accuracy": 0.8770491803278688,
|
| 1200 |
+
"eval_f1": 0.8772784869363629,
|
| 1201 |
+
"eval_loss": 0.68454909324646,
|
| 1202 |
+
"eval_runtime": 38.539,
|
| 1203 |
+
"eval_samples_per_second": 3.166,
|
| 1204 |
+
"eval_steps_per_second": 0.415,
|
| 1205 |
+
"step": 1488
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 16.00072463768116,
|
| 1209 |
+
"grad_norm": 0.026206759735941887,
|
| 1210 |
+
"learning_rate": 2.556360708534622e-05,
|
| 1211 |
+
"loss": 0.0027,
|
| 1212 |
+
"step": 1490
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 16.004347826086956,
|
| 1216 |
+
"grad_norm": 0.17636388540267944,
|
| 1217 |
+
"learning_rate": 2.5362318840579714e-05,
|
| 1218 |
+
"loss": 0.0013,
|
| 1219 |
+
"step": 1500
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 16.007971014492753,
|
| 1223 |
+
"grad_norm": 0.009907973930239677,
|
| 1224 |
+
"learning_rate": 2.5161030595813208e-05,
|
| 1225 |
+
"loss": 0.0008,
|
| 1226 |
+
"step": 1510
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 16.01159420289855,
|
| 1230 |
+
"grad_norm": 0.007697808090597391,
|
| 1231 |
+
"learning_rate": 2.49597423510467e-05,
|
| 1232 |
+
"loss": 0.0012,
|
| 1233 |
+
"step": 1520
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 16.015217391304347,
|
| 1237 |
+
"grad_norm": 0.012929815798997879,
|
| 1238 |
+
"learning_rate": 2.4758454106280193e-05,
|
| 1239 |
+
"loss": 0.0008,
|
| 1240 |
+
"step": 1530
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 16.018840579710144,
|
| 1244 |
+
"grad_norm": 0.03589075058698654,
|
| 1245 |
+
"learning_rate": 2.455716586151369e-05,
|
| 1246 |
+
"loss": 0.0006,
|
| 1247 |
+
"step": 1540
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 16.02246376811594,
|
| 1251 |
+
"grad_norm": 0.012779805809259415,
|
| 1252 |
+
"learning_rate": 2.435587761674718e-05,
|
| 1253 |
+
"loss": 0.1136,
|
| 1254 |
+
"step": 1550
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 16.026086956521738,
|
| 1258 |
+
"grad_norm": 51.02324676513672,
|
| 1259 |
+
"learning_rate": 2.4154589371980676e-05,
|
| 1260 |
+
"loss": 0.1051,
|
| 1261 |
+
"step": 1560
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 16.029710144927535,
|
| 1265 |
+
"grad_norm": 0.01224570907652378,
|
| 1266 |
+
"learning_rate": 2.3953301127214173e-05,
|
| 1267 |
+
"loss": 0.0355,
|
| 1268 |
+
"step": 1570
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 16.033333333333335,
|
| 1272 |
+
"grad_norm": 0.1042768731713295,
|
| 1273 |
+
"learning_rate": 2.3752012882447668e-05,
|
| 1274 |
+
"loss": 0.0166,
|
| 1275 |
+
"step": 1580
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 16.033695652173915,
|
| 1279 |
+
"eval_accuracy": 0.8524590163934426,
|
| 1280 |
+
"eval_f1": 0.8445057204972595,
|
| 1281 |
+
"eval_loss": 0.8649476766586304,
|
| 1282 |
+
"eval_runtime": 42.3787,
|
| 1283 |
+
"eval_samples_per_second": 2.879,
|
| 1284 |
+
"eval_steps_per_second": 0.378,
|
| 1285 |
+
"step": 1581
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 17.003260869565217,
|
| 1289 |
+
"grad_norm": 0.007085030898451805,
|
| 1290 |
+
"learning_rate": 2.355072463768116e-05,
|
| 1291 |
+
"loss": 0.0251,
|
| 1292 |
+
"step": 1590
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 17.006884057971014,
|
| 1296 |
+
"grad_norm": 0.015758316963911057,
|
| 1297 |
+
"learning_rate": 2.3349436392914656e-05,
|
| 1298 |
+
"loss": 0.0598,
|
| 1299 |
+
"step": 1600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 17.01050724637681,
|
| 1303 |
+
"grad_norm": 0.0069606369361281395,
|
| 1304 |
+
"learning_rate": 2.314814814814815e-05,
|
| 1305 |
+
"loss": 0.004,
|
| 1306 |
+
"step": 1610
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 17.014130434782608,
|
| 1310 |
+
"grad_norm": 0.008627723902463913,
|
| 1311 |
+
"learning_rate": 2.294685990338164e-05,
|
| 1312 |
+
"loss": 0.0065,
|
| 1313 |
+
"step": 1620
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 17.017753623188405,
|
| 1317 |
+
"grad_norm": 0.009509687311947346,
|
| 1318 |
+
"learning_rate": 2.274557165861514e-05,
|
| 1319 |
+
"loss": 0.0005,
|
| 1320 |
+
"step": 1630
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 17.0213768115942,
|
| 1324 |
+
"grad_norm": 0.014063004404306412,
|
| 1325 |
+
"learning_rate": 2.2544283413848633e-05,
|
| 1326 |
+
"loss": 0.0011,
|
| 1327 |
+
"step": 1640
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 17.025,
|
| 1331 |
+
"grad_norm": 14.068120956420898,
|
| 1332 |
+
"learning_rate": 2.2342995169082127e-05,
|
| 1333 |
+
"loss": 0.0636,
|
| 1334 |
+
"step": 1650
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 17.028623188405795,
|
| 1338 |
+
"grad_norm": 0.08216149359941483,
|
| 1339 |
+
"learning_rate": 2.214170692431562e-05,
|
| 1340 |
+
"loss": 0.1043,
|
| 1341 |
+
"step": 1660
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 17.032246376811596,
|
| 1345 |
+
"grad_norm": 0.14345373213291168,
|
| 1346 |
+
"learning_rate": 2.1940418679549116e-05,
|
| 1347 |
+
"loss": 0.0014,
|
| 1348 |
+
"step": 1670
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 17.033695652173915,
|
| 1352 |
+
"eval_accuracy": 0.8524590163934426,
|
| 1353 |
+
"eval_f1": 0.8516181034534225,
|
| 1354 |
+
"eval_loss": 0.7865917086601257,
|
| 1355 |
+
"eval_runtime": 40.0693,
|
| 1356 |
+
"eval_samples_per_second": 3.045,
|
| 1357 |
+
"eval_steps_per_second": 0.399,
|
| 1358 |
+
"step": 1674
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 18.002173913043478,
|
| 1362 |
+
"grad_norm": 0.006833807565271854,
|
| 1363 |
+
"learning_rate": 2.173913043478261e-05,
|
| 1364 |
+
"loss": 0.0039,
|
| 1365 |
+
"step": 1680
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 18.005797101449275,
|
| 1369 |
+
"grad_norm": 0.014425553381443024,
|
| 1370 |
+
"learning_rate": 2.1537842190016104e-05,
|
| 1371 |
+
"loss": 0.022,
|
| 1372 |
+
"step": 1690
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 18.009420289855072,
|
| 1376 |
+
"grad_norm": 0.05315766856074333,
|
| 1377 |
+
"learning_rate": 2.13365539452496e-05,
|
| 1378 |
+
"loss": 0.0055,
|
| 1379 |
+
"step": 1700
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 18.01304347826087,
|
| 1383 |
+
"grad_norm": 0.006013238336890936,
|
| 1384 |
+
"learning_rate": 2.1135265700483093e-05,
|
| 1385 |
+
"loss": 0.0725,
|
| 1386 |
+
"step": 1710
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 18.016666666666666,
|
| 1390 |
+
"grad_norm": 0.009230862371623516,
|
| 1391 |
+
"learning_rate": 2.0933977455716587e-05,
|
| 1392 |
+
"loss": 0.0005,
|
| 1393 |
+
"step": 1720
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 18.020289855072463,
|
| 1397 |
+
"grad_norm": 0.007369612343609333,
|
| 1398 |
+
"learning_rate": 2.073268921095008e-05,
|
| 1399 |
+
"loss": 0.0005,
|
| 1400 |
+
"step": 1730
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 18.02391304347826,
|
| 1404 |
+
"grad_norm": 0.005340999457985163,
|
| 1405 |
+
"learning_rate": 2.0531400966183576e-05,
|
| 1406 |
+
"loss": 0.0043,
|
| 1407 |
+
"step": 1740
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 18.027536231884056,
|
| 1411 |
+
"grad_norm": 5.2305498123168945,
|
| 1412 |
+
"learning_rate": 2.033011272141707e-05,
|
| 1413 |
+
"loss": 0.0677,
|
| 1414 |
+
"step": 1750
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 18.031159420289853,
|
| 1418 |
+
"grad_norm": 0.008544102311134338,
|
| 1419 |
+
"learning_rate": 2.0128824476650564e-05,
|
| 1420 |
+
"loss": 0.0473,
|
| 1421 |
+
"step": 1760
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 18.033695652173915,
|
| 1425 |
+
"eval_accuracy": 0.8770491803278688,
|
| 1426 |
+
"eval_f1": 0.8776382319776725,
|
| 1427 |
+
"eval_loss": 0.6390149593353271,
|
| 1428 |
+
"eval_runtime": 38.4182,
|
| 1429 |
+
"eval_samples_per_second": 3.176,
|
| 1430 |
+
"eval_steps_per_second": 0.416,
|
| 1431 |
+
"step": 1767
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 19.00108695652174,
|
| 1435 |
+
"grad_norm": 0.007366463541984558,
|
| 1436 |
+
"learning_rate": 1.992753623188406e-05,
|
| 1437 |
+
"loss": 0.0005,
|
| 1438 |
+
"step": 1770
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 19.004710144927536,
|
| 1442 |
+
"grad_norm": 2.3047983646392822,
|
| 1443 |
+
"learning_rate": 1.9726247987117553e-05,
|
| 1444 |
+
"loss": 0.0185,
|
| 1445 |
+
"step": 1780
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 19.008333333333333,
|
| 1449 |
+
"grad_norm": 0.005975569132715464,
|
| 1450 |
+
"learning_rate": 1.9524959742351047e-05,
|
| 1451 |
+
"loss": 0.0007,
|
| 1452 |
+
"step": 1790
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 19.01195652173913,
|
| 1456 |
+
"grad_norm": 0.007045724429190159,
|
| 1457 |
+
"learning_rate": 1.932367149758454e-05,
|
| 1458 |
+
"loss": 0.0008,
|
| 1459 |
+
"step": 1800
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 19.015579710144927,
|
| 1463 |
+
"grad_norm": 0.005632986314594746,
|
| 1464 |
+
"learning_rate": 1.9122383252818036e-05,
|
| 1465 |
+
"loss": 0.001,
|
| 1466 |
+
"step": 1810
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 19.019202898550724,
|
| 1470 |
+
"grad_norm": 0.0067955972626805305,
|
| 1471 |
+
"learning_rate": 1.892109500805153e-05,
|
| 1472 |
+
"loss": 0.0006,
|
| 1473 |
+
"step": 1820
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 19.02282608695652,
|
| 1477 |
+
"grad_norm": 0.0061930399388074875,
|
| 1478 |
+
"learning_rate": 1.8719806763285024e-05,
|
| 1479 |
+
"loss": 0.0154,
|
| 1480 |
+
"step": 1830
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 19.026449275362317,
|
| 1484 |
+
"grad_norm": 0.005985133349895477,
|
| 1485 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1486 |
+
"loss": 0.0029,
|
| 1487 |
+
"step": 1840
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 19.030072463768114,
|
| 1491 |
+
"grad_norm": 0.005963871255517006,
|
| 1492 |
+
"learning_rate": 1.8317230273752016e-05,
|
| 1493 |
+
"loss": 0.0407,
|
| 1494 |
+
"step": 1850
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 19.033695652173915,
|
| 1498 |
+
"grad_norm": 0.004762581083923578,
|
| 1499 |
+
"learning_rate": 1.8115942028985507e-05,
|
| 1500 |
+
"loss": 0.0441,
|
| 1501 |
+
"step": 1860
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 19.033695652173915,
|
| 1505 |
+
"eval_accuracy": 0.8360655737704918,
|
| 1506 |
+
"eval_f1": 0.834206674473068,
|
| 1507 |
+
"eval_loss": 0.8234833478927612,
|
| 1508 |
+
"eval_runtime": 37.3263,
|
| 1509 |
+
"eval_samples_per_second": 3.268,
|
| 1510 |
+
"eval_steps_per_second": 0.429,
|
| 1511 |
+
"step": 1860
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 20.003623188405797,
|
| 1515 |
+
"grad_norm": 0.12766918540000916,
|
| 1516 |
+
"learning_rate": 1.7914653784219e-05,
|
| 1517 |
+
"loss": 0.0067,
|
| 1518 |
+
"step": 1870
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 20.007246376811594,
|
| 1522 |
+
"grad_norm": 0.031153714284300804,
|
| 1523 |
+
"learning_rate": 1.77133655394525e-05,
|
| 1524 |
+
"loss": 0.0007,
|
| 1525 |
+
"step": 1880
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 20.01086956521739,
|
| 1529 |
+
"grad_norm": 0.0049373493529856205,
|
| 1530 |
+
"learning_rate": 1.751207729468599e-05,
|
| 1531 |
+
"loss": 0.0148,
|
| 1532 |
+
"step": 1890
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 20.014492753623188,
|
| 1536 |
+
"grad_norm": 0.04706621542572975,
|
| 1537 |
+
"learning_rate": 1.7310789049919484e-05,
|
| 1538 |
+
"loss": 0.0516,
|
| 1539 |
+
"step": 1900
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 20.018115942028984,
|
| 1543 |
+
"grad_norm": 0.011202222667634487,
|
| 1544 |
+
"learning_rate": 1.710950080515298e-05,
|
| 1545 |
+
"loss": 0.0073,
|
| 1546 |
+
"step": 1910
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 20.02173913043478,
|
| 1550 |
+
"grad_norm": 0.004066763911396265,
|
| 1551 |
+
"learning_rate": 1.6908212560386476e-05,
|
| 1552 |
+
"loss": 0.0065,
|
| 1553 |
+
"step": 1920
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 20.02536231884058,
|
| 1557 |
+
"grad_norm": 0.5498021245002747,
|
| 1558 |
+
"learning_rate": 1.6706924315619967e-05,
|
| 1559 |
+
"loss": 0.0549,
|
| 1560 |
+
"step": 1930
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 20.028985507246375,
|
| 1564 |
+
"grad_norm": 0.011782179586589336,
|
| 1565 |
+
"learning_rate": 1.6505636070853464e-05,
|
| 1566 |
+
"loss": 0.0009,
|
| 1567 |
+
"step": 1940
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 20.032608695652176,
|
| 1571 |
+
"grad_norm": 0.0048751975409686565,
|
| 1572 |
+
"learning_rate": 1.630434782608696e-05,
|
| 1573 |
+
"loss": 0.0006,
|
| 1574 |
+
"step": 1950
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 20.033695652173915,
|
| 1578 |
+
"eval_accuracy": 0.8852459016393442,
|
| 1579 |
+
"eval_f1": 0.88558791751199,
|
| 1580 |
+
"eval_loss": 0.6014039516448975,
|
| 1581 |
+
"eval_runtime": 37.9636,
|
| 1582 |
+
"eval_samples_per_second": 3.214,
|
| 1583 |
+
"eval_steps_per_second": 0.421,
|
| 1584 |
+
"step": 1953
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 21.002536231884058,
|
| 1588 |
+
"grad_norm": 0.009569565765559673,
|
| 1589 |
+
"learning_rate": 1.610305958132045e-05,
|
| 1590 |
+
"loss": 0.0004,
|
| 1591 |
+
"step": 1960
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 21.006159420289855,
|
| 1595 |
+
"grad_norm": 0.0038696015253663063,
|
| 1596 |
+
"learning_rate": 1.5901771336553947e-05,
|
| 1597 |
+
"loss": 0.0005,
|
| 1598 |
+
"step": 1970
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 21.00978260869565,
|
| 1602 |
+
"grad_norm": 0.012325268238782883,
|
| 1603 |
+
"learning_rate": 1.570048309178744e-05,
|
| 1604 |
+
"loss": 0.0248,
|
| 1605 |
+
"step": 1980
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 21.01340579710145,
|
| 1609 |
+
"grad_norm": 0.927451491355896,
|
| 1610 |
+
"learning_rate": 1.5499194847020936e-05,
|
| 1611 |
+
"loss": 0.0384,
|
| 1612 |
+
"step": 1990
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 21.017028985507245,
|
| 1616 |
+
"grad_norm": 0.005916436202824116,
|
| 1617 |
+
"learning_rate": 1.529790660225443e-05,
|
| 1618 |
+
"loss": 0.0004,
|
| 1619 |
+
"step": 2000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 21.020652173913042,
|
| 1623 |
+
"grad_norm": 0.00484825111925602,
|
| 1624 |
+
"learning_rate": 1.5096618357487924e-05,
|
| 1625 |
+
"loss": 0.0028,
|
| 1626 |
+
"step": 2010
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 21.02427536231884,
|
| 1630 |
+
"grad_norm": 0.05984441190958023,
|
| 1631 |
+
"learning_rate": 1.4895330112721417e-05,
|
| 1632 |
+
"loss": 0.0635,
|
| 1633 |
+
"step": 2020
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 21.027898550724636,
|
| 1637 |
+
"grad_norm": 0.006016437895596027,
|
| 1638 |
+
"learning_rate": 1.469404186795491e-05,
|
| 1639 |
+
"loss": 0.0005,
|
| 1640 |
+
"step": 2030
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 21.031521739130437,
|
| 1644 |
+
"grad_norm": 0.006119464058429003,
|
| 1645 |
+
"learning_rate": 1.4492753623188407e-05,
|
| 1646 |
+
"loss": 0.0005,
|
| 1647 |
+
"step": 2040
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 21.033695652173915,
|
| 1651 |
+
"eval_accuracy": 0.8688524590163934,
|
| 1652 |
+
"eval_f1": 0.8672487891684085,
|
| 1653 |
+
"eval_loss": 0.758141815662384,
|
| 1654 |
+
"eval_runtime": 38.1916,
|
| 1655 |
+
"eval_samples_per_second": 3.194,
|
| 1656 |
+
"eval_steps_per_second": 0.419,
|
| 1657 |
+
"step": 2046
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 22.00144927536232,
|
| 1661 |
+
"grad_norm": 0.008889817632734776,
|
| 1662 |
+
"learning_rate": 1.4291465378421901e-05,
|
| 1663 |
+
"loss": 0.0009,
|
| 1664 |
+
"step": 2050
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 22.005072463768116,
|
| 1668 |
+
"grad_norm": 0.004777275491505861,
|
| 1669 |
+
"learning_rate": 1.4090177133655394e-05,
|
| 1670 |
+
"loss": 0.0159,
|
| 1671 |
+
"step": 2060
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 22.008695652173913,
|
| 1675 |
+
"grad_norm": 0.005355835892260075,
|
| 1676 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1677 |
+
"loss": 0.0066,
|
| 1678 |
+
"step": 2070
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 22.01231884057971,
|
| 1682 |
+
"grad_norm": 0.006906128488481045,
|
| 1683 |
+
"learning_rate": 1.3687600644122384e-05,
|
| 1684 |
+
"loss": 0.0005,
|
| 1685 |
+
"step": 2080
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 22.015942028985506,
|
| 1689 |
+
"grad_norm": 0.0049617839977145195,
|
| 1690 |
+
"learning_rate": 1.3486312399355876e-05,
|
| 1691 |
+
"loss": 0.0007,
|
| 1692 |
+
"step": 2090
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 22.019565217391303,
|
| 1696 |
+
"grad_norm": 0.004387282766401768,
|
| 1697 |
+
"learning_rate": 1.3285024154589374e-05,
|
| 1698 |
+
"loss": 0.0004,
|
| 1699 |
+
"step": 2100
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 22.0231884057971,
|
| 1703 |
+
"grad_norm": 0.004814252723008394,
|
| 1704 |
+
"learning_rate": 1.3083735909822867e-05,
|
| 1705 |
+
"loss": 0.0041,
|
| 1706 |
+
"step": 2110
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 22.026811594202897,
|
| 1710 |
+
"grad_norm": 0.007489080540835857,
|
| 1711 |
+
"learning_rate": 1.288244766505636e-05,
|
| 1712 |
+
"loss": 0.0442,
|
| 1713 |
+
"step": 2120
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 22.030434782608694,
|
| 1717 |
+
"grad_norm": 0.00951230525970459,
|
| 1718 |
+
"learning_rate": 1.2681159420289857e-05,
|
| 1719 |
+
"loss": 0.0032,
|
| 1720 |
+
"step": 2130
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 22.033695652173915,
|
| 1724 |
+
"eval_accuracy": 0.8770491803278688,
|
| 1725 |
+
"eval_f1": 0.8771730619791396,
|
| 1726 |
+
"eval_loss": 0.6454241871833801,
|
| 1727 |
+
"eval_runtime": 37.8713,
|
| 1728 |
+
"eval_samples_per_second": 3.221,
|
| 1729 |
+
"eval_steps_per_second": 0.422,
|
| 1730 |
+
"step": 2139
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 23.00036231884058,
|
| 1734 |
+
"grad_norm": 0.005327664315700531,
|
| 1735 |
+
"learning_rate": 1.247987117552335e-05,
|
| 1736 |
+
"loss": 0.027,
|
| 1737 |
+
"step": 2140
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 23.003985507246377,
|
| 1741 |
+
"grad_norm": 0.006378709804266691,
|
| 1742 |
+
"learning_rate": 1.2278582930756845e-05,
|
| 1743 |
+
"loss": 0.0005,
|
| 1744 |
+
"step": 2150
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 23.007608695652173,
|
| 1748 |
+
"grad_norm": 0.004449001979082823,
|
| 1749 |
+
"learning_rate": 1.2077294685990338e-05,
|
| 1750 |
+
"loss": 0.0166,
|
| 1751 |
+
"step": 2160
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 23.01123188405797,
|
| 1755 |
+
"grad_norm": 0.011220560409128666,
|
| 1756 |
+
"learning_rate": 1.1876006441223834e-05,
|
| 1757 |
+
"loss": 0.013,
|
| 1758 |
+
"step": 2170
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 23.014855072463767,
|
| 1762 |
+
"grad_norm": 0.007521830964833498,
|
| 1763 |
+
"learning_rate": 1.1674718196457328e-05,
|
| 1764 |
+
"loss": 0.0004,
|
| 1765 |
+
"step": 2180
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 23.018478260869564,
|
| 1769 |
+
"grad_norm": 0.06200418993830681,
|
| 1770 |
+
"learning_rate": 1.147342995169082e-05,
|
| 1771 |
+
"loss": 0.0204,
|
| 1772 |
+
"step": 2190
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 23.02210144927536,
|
| 1776 |
+
"grad_norm": 0.005162249319255352,
|
| 1777 |
+
"learning_rate": 1.1272141706924317e-05,
|
| 1778 |
+
"loss": 0.0005,
|
| 1779 |
+
"step": 2200
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 23.025724637681158,
|
| 1783 |
+
"grad_norm": 0.004768849816173315,
|
| 1784 |
+
"learning_rate": 1.107085346215781e-05,
|
| 1785 |
+
"loss": 0.0963,
|
| 1786 |
+
"step": 2210
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 23.029347826086955,
|
| 1790 |
+
"grad_norm": 0.006896668113768101,
|
| 1791 |
+
"learning_rate": 1.0869565217391305e-05,
|
| 1792 |
+
"loss": 0.0209,
|
| 1793 |
+
"step": 2220
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 23.032971014492755,
|
| 1797 |
+
"grad_norm": 0.5598499178886414,
|
| 1798 |
+
"learning_rate": 1.06682769726248e-05,
|
| 1799 |
+
"loss": 0.0565,
|
| 1800 |
+
"step": 2230
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 23.033695652173915,
|
| 1804 |
+
"eval_accuracy": 0.8524590163934426,
|
| 1805 |
+
"eval_f1": 0.8542214345493033,
|
| 1806 |
+
"eval_loss": 0.8096156120300293,
|
| 1807 |
+
"eval_runtime": 39.1323,
|
| 1808 |
+
"eval_samples_per_second": 3.118,
|
| 1809 |
+
"eval_steps_per_second": 0.409,
|
| 1810 |
+
"step": 2232
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 24.002898550724638,
|
| 1814 |
+
"grad_norm": 0.017325986176729202,
|
| 1815 |
+
"learning_rate": 1.0466988727858294e-05,
|
| 1816 |
+
"loss": 0.0005,
|
| 1817 |
+
"step": 2240
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 24.006521739130434,
|
| 1821 |
+
"grad_norm": 0.2567996382713318,
|
| 1822 |
+
"learning_rate": 1.0265700483091788e-05,
|
| 1823 |
+
"loss": 0.011,
|
| 1824 |
+
"step": 2250
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 24.01014492753623,
|
| 1828 |
+
"grad_norm": 0.008284560404717922,
|
| 1829 |
+
"learning_rate": 1.0064412238325282e-05,
|
| 1830 |
+
"loss": 0.0105,
|
| 1831 |
+
"step": 2260
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 24.013768115942028,
|
| 1835 |
+
"grad_norm": 0.021722067147493362,
|
| 1836 |
+
"learning_rate": 9.863123993558776e-06,
|
| 1837 |
+
"loss": 0.0129,
|
| 1838 |
+
"step": 2270
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 24.017391304347825,
|
| 1842 |
+
"grad_norm": 0.01306977029889822,
|
| 1843 |
+
"learning_rate": 9.66183574879227e-06,
|
| 1844 |
+
"loss": 0.093,
|
| 1845 |
+
"step": 2280
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 24.021014492753622,
|
| 1849 |
+
"grad_norm": 0.006157809402793646,
|
| 1850 |
+
"learning_rate": 9.460547504025765e-06,
|
| 1851 |
+
"loss": 0.0005,
|
| 1852 |
+
"step": 2290
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 24.02463768115942,
|
| 1856 |
+
"grad_norm": 0.006750662811100483,
|
| 1857 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1858 |
+
"loss": 0.0004,
|
| 1859 |
+
"step": 2300
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 24.028260869565216,
|
| 1863 |
+
"grad_norm": 0.004828326869755983,
|
| 1864 |
+
"learning_rate": 9.057971014492753e-06,
|
| 1865 |
+
"loss": 0.0095,
|
| 1866 |
+
"step": 2310
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 24.031884057971016,
|
| 1870 |
+
"grad_norm": 1.7074612379074097,
|
| 1871 |
+
"learning_rate": 8.85668276972625e-06,
|
| 1872 |
+
"loss": 0.011,
|
| 1873 |
+
"step": 2320
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 24.033695652173915,
|
| 1877 |
+
"eval_accuracy": 0.8852459016393442,
|
| 1878 |
+
"eval_f1": 0.8858382568953512,
|
| 1879 |
+
"eval_loss": 0.6807242631912231,
|
| 1880 |
+
"eval_runtime": 41.3656,
|
| 1881 |
+
"eval_samples_per_second": 2.949,
|
| 1882 |
+
"eval_steps_per_second": 0.387,
|
| 1883 |
+
"step": 2325
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 25.0018115942029,
|
| 1887 |
+
"grad_norm": 0.0043255784548819065,
|
| 1888 |
+
"learning_rate": 8.655394524959742e-06,
|
| 1889 |
+
"loss": 0.0022,
|
| 1890 |
+
"step": 2330
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 25.005434782608695,
|
| 1894 |
+
"grad_norm": 0.007067692466080189,
|
| 1895 |
+
"learning_rate": 8.454106280193238e-06,
|
| 1896 |
+
"loss": 0.0073,
|
| 1897 |
+
"step": 2340
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 25.009057971014492,
|
| 1901 |
+
"grad_norm": 1.005963683128357,
|
| 1902 |
+
"learning_rate": 8.252818035426732e-06,
|
| 1903 |
+
"loss": 0.0011,
|
| 1904 |
+
"step": 2350
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 25.01268115942029,
|
| 1908 |
+
"grad_norm": 0.004243878182023764,
|
| 1909 |
+
"learning_rate": 8.051529790660225e-06,
|
| 1910 |
+
"loss": 0.0004,
|
| 1911 |
+
"step": 2360
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 25.016304347826086,
|
| 1915 |
+
"grad_norm": 0.0035646618343889713,
|
| 1916 |
+
"learning_rate": 7.85024154589372e-06,
|
| 1917 |
+
"loss": 0.0004,
|
| 1918 |
+
"step": 2370
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 25.019927536231883,
|
| 1922 |
+
"grad_norm": 0.004057039972394705,
|
| 1923 |
+
"learning_rate": 7.648953301127215e-06,
|
| 1924 |
+
"loss": 0.0004,
|
| 1925 |
+
"step": 2380
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 25.02355072463768,
|
| 1929 |
+
"grad_norm": 0.010123531334102154,
|
| 1930 |
+
"learning_rate": 7.447665056360708e-06,
|
| 1931 |
+
"loss": 0.0025,
|
| 1932 |
+
"step": 2390
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 25.027173913043477,
|
| 1936 |
+
"grad_norm": 1.058449387550354,
|
| 1937 |
+
"learning_rate": 7.246376811594203e-06,
|
| 1938 |
+
"loss": 0.0228,
|
| 1939 |
+
"step": 2400
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 25.030797101449274,
|
| 1943 |
+
"grad_norm": 2.1814162731170654,
|
| 1944 |
+
"learning_rate": 7.045088566827697e-06,
|
| 1945 |
+
"loss": 0.0146,
|
| 1946 |
+
"step": 2410
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 25.033695652173915,
|
| 1950 |
+
"eval_accuracy": 0.8688524590163934,
|
| 1951 |
+
"eval_f1": 0.8695984040246334,
|
| 1952 |
+
"eval_loss": 0.7754350900650024,
|
| 1953 |
+
"eval_runtime": 41.8119,
|
| 1954 |
+
"eval_samples_per_second": 2.918,
|
| 1955 |
+
"eval_steps_per_second": 0.383,
|
| 1956 |
+
"step": 2418
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 26.00072463768116,
|
| 1960 |
+
"grad_norm": 0.00446619326248765,
|
| 1961 |
+
"learning_rate": 6.843800322061192e-06,
|
| 1962 |
+
"loss": 0.0469,
|
| 1963 |
+
"step": 2420
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 26.004347826086956,
|
| 1967 |
+
"grad_norm": 0.005227618385106325,
|
| 1968 |
+
"learning_rate": 6.642512077294687e-06,
|
| 1969 |
+
"loss": 0.0105,
|
| 1970 |
+
"step": 2430
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 26.007971014492753,
|
| 1974 |
+
"grad_norm": 2.0163729190826416,
|
| 1975 |
+
"learning_rate": 6.44122383252818e-06,
|
| 1976 |
+
"loss": 0.0116,
|
| 1977 |
+
"step": 2440
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 26.01159420289855,
|
| 1981 |
+
"grad_norm": 0.0069722458720207214,
|
| 1982 |
+
"learning_rate": 6.239935587761675e-06,
|
| 1983 |
+
"loss": 0.0079,
|
| 1984 |
+
"step": 2450
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 26.015217391304347,
|
| 1988 |
+
"grad_norm": 0.006805983372032642,
|
| 1989 |
+
"learning_rate": 6.038647342995169e-06,
|
| 1990 |
+
"loss": 0.0004,
|
| 1991 |
+
"step": 2460
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 26.018840579710144,
|
| 1995 |
+
"grad_norm": 0.005044913850724697,
|
| 1996 |
+
"learning_rate": 5.837359098228664e-06,
|
| 1997 |
+
"loss": 0.0036,
|
| 1998 |
+
"step": 2470
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 26.02246376811594,
|
| 2002 |
+
"grad_norm": 0.005564519669860601,
|
| 2003 |
+
"learning_rate": 5.636070853462158e-06,
|
| 2004 |
+
"loss": 0.0003,
|
| 2005 |
+
"step": 2480
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 26.026086956521738,
|
| 2009 |
+
"grad_norm": 0.003706958144903183,
|
| 2010 |
+
"learning_rate": 5.4347826086956525e-06,
|
| 2011 |
+
"loss": 0.0004,
|
| 2012 |
+
"step": 2490
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 26.029710144927535,
|
| 2016 |
+
"grad_norm": 0.02714346908032894,
|
| 2017 |
+
"learning_rate": 5.233494363929147e-06,
|
| 2018 |
+
"loss": 0.0191,
|
| 2019 |
+
"step": 2500
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 26.033333333333335,
|
| 2023 |
+
"grad_norm": 0.008597085252404213,
|
| 2024 |
+
"learning_rate": 5.032206119162641e-06,
|
| 2025 |
+
"loss": 0.0004,
|
| 2026 |
+
"step": 2510
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 26.033695652173915,
|
| 2030 |
+
"eval_accuracy": 0.8852459016393442,
|
| 2031 |
+
"eval_f1": 0.885748980830948,
|
| 2032 |
+
"eval_loss": 0.7246056199073792,
|
| 2033 |
+
"eval_runtime": 39.2721,
|
| 2034 |
+
"eval_samples_per_second": 3.107,
|
| 2035 |
+
"eval_steps_per_second": 0.407,
|
| 2036 |
+
"step": 2511
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 27.003260869565217,
|
| 2040 |
+
"grad_norm": 0.004729451611638069,
|
| 2041 |
+
"learning_rate": 4.830917874396135e-06,
|
| 2042 |
+
"loss": 0.0004,
|
| 2043 |
+
"step": 2520
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 27.006884057971014,
|
| 2047 |
+
"grad_norm": 0.0047379061579704285,
|
| 2048 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 2049 |
+
"loss": 0.0169,
|
| 2050 |
+
"step": 2530
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 27.01050724637681,
|
| 2054 |
+
"grad_norm": 0.0059508224949240685,
|
| 2055 |
+
"learning_rate": 4.428341384863125e-06,
|
| 2056 |
+
"loss": 0.0003,
|
| 2057 |
+
"step": 2540
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 27.014130434782608,
|
| 2061 |
+
"grad_norm": 0.004985982086509466,
|
| 2062 |
+
"learning_rate": 4.227053140096619e-06,
|
| 2063 |
+
"loss": 0.0004,
|
| 2064 |
+
"step": 2550
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 27.017753623188405,
|
| 2068 |
+
"grad_norm": 0.004285223316401243,
|
| 2069 |
+
"learning_rate": 4.025764895330112e-06,
|
| 2070 |
+
"loss": 0.0064,
|
| 2071 |
+
"step": 2560
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 27.0213768115942,
|
| 2075 |
+
"grad_norm": 0.00481518916785717,
|
| 2076 |
+
"learning_rate": 3.8244766505636074e-06,
|
| 2077 |
+
"loss": 0.0036,
|
| 2078 |
+
"step": 2570
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 27.025,
|
| 2082 |
+
"grad_norm": 0.005598173942416906,
|
| 2083 |
+
"learning_rate": 3.6231884057971017e-06,
|
| 2084 |
+
"loss": 0.0265,
|
| 2085 |
+
"step": 2580
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 27.028623188405795,
|
| 2089 |
+
"grad_norm": 0.005482200998812914,
|
| 2090 |
+
"learning_rate": 3.421900161030596e-06,
|
| 2091 |
+
"loss": 0.0003,
|
| 2092 |
+
"step": 2590
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 27.032246376811596,
|
| 2096 |
+
"grad_norm": 0.0035128567833453417,
|
| 2097 |
+
"learning_rate": 3.22061191626409e-06,
|
| 2098 |
+
"loss": 0.0004,
|
| 2099 |
+
"step": 2600
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 27.033695652173915,
|
| 2103 |
+
"eval_accuracy": 0.8934426229508197,
|
| 2104 |
+
"eval_f1": 0.8942102524069736,
|
| 2105 |
+
"eval_loss": 0.7165006995201111,
|
| 2106 |
+
"eval_runtime": 37.9801,
|
| 2107 |
+
"eval_samples_per_second": 3.212,
|
| 2108 |
+
"eval_steps_per_second": 0.421,
|
| 2109 |
+
"step": 2604
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 28.002173913043478,
|
| 2113 |
+
"grad_norm": 0.004918423481285572,
|
| 2114 |
+
"learning_rate": 3.0193236714975845e-06,
|
| 2115 |
+
"loss": 0.0003,
|
| 2116 |
+
"step": 2610
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 28.005797101449275,
|
| 2120 |
+
"grad_norm": 0.00445589842274785,
|
| 2121 |
+
"learning_rate": 2.818035426731079e-06,
|
| 2122 |
+
"loss": 0.0096,
|
| 2123 |
+
"step": 2620
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 28.009420289855072,
|
| 2127 |
+
"grad_norm": 0.0045196604914963245,
|
| 2128 |
+
"learning_rate": 2.6167471819645734e-06,
|
| 2129 |
+
"loss": 0.0159,
|
| 2130 |
+
"step": 2630
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 28.01304347826087,
|
| 2134 |
+
"grad_norm": 0.005592667497694492,
|
| 2135 |
+
"learning_rate": 2.4154589371980677e-06,
|
| 2136 |
+
"loss": 0.0135,
|
| 2137 |
+
"step": 2640
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 28.016666666666666,
|
| 2141 |
+
"grad_norm": 0.004337575286626816,
|
| 2142 |
+
"learning_rate": 2.2141706924315623e-06,
|
| 2143 |
+
"loss": 0.0003,
|
| 2144 |
+
"step": 2650
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 28.020289855072463,
|
| 2148 |
+
"grad_norm": 0.014842136763036251,
|
| 2149 |
+
"learning_rate": 2.012882447665056e-06,
|
| 2150 |
+
"loss": 0.0004,
|
| 2151 |
+
"step": 2660
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 28.02391304347826,
|
| 2155 |
+
"grad_norm": 2.614138603210449,
|
| 2156 |
+
"learning_rate": 1.8115942028985508e-06,
|
| 2157 |
+
"loss": 0.0216,
|
| 2158 |
+
"step": 2670
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 28.027536231884056,
|
| 2162 |
+
"grad_norm": 0.004238471854478121,
|
| 2163 |
+
"learning_rate": 1.610305958132045e-06,
|
| 2164 |
+
"loss": 0.0048,
|
| 2165 |
+
"step": 2680
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 28.031159420289853,
|
| 2169 |
+
"grad_norm": 0.006333829369395971,
|
| 2170 |
+
"learning_rate": 1.4090177133655396e-06,
|
| 2171 |
+
"loss": 0.0003,
|
| 2172 |
+
"step": 2690
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 28.033695652173915,
|
| 2176 |
+
"eval_accuracy": 0.9016393442622951,
|
| 2177 |
+
"eval_f1": 0.90210919178688,
|
| 2178 |
+
"eval_loss": 0.723217248916626,
|
| 2179 |
+
"eval_runtime": 42.3468,
|
| 2180 |
+
"eval_samples_per_second": 2.881,
|
| 2181 |
+
"eval_steps_per_second": 0.378,
|
| 2182 |
+
"step": 2697
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 29.00108695652174,
|
| 2186 |
+
"grad_norm": 0.00406339205801487,
|
| 2187 |
+
"learning_rate": 1.2077294685990338e-06,
|
| 2188 |
+
"loss": 0.0003,
|
| 2189 |
+
"step": 2700
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 29.004710144927536,
|
| 2193 |
+
"grad_norm": 0.00470451544970274,
|
| 2194 |
+
"learning_rate": 1.006441223832528e-06,
|
| 2195 |
+
"loss": 0.0052,
|
| 2196 |
+
"step": 2710
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 29.008333333333333,
|
| 2200 |
+
"grad_norm": 0.0051088836044073105,
|
| 2201 |
+
"learning_rate": 8.051529790660226e-07,
|
| 2202 |
+
"loss": 0.0003,
|
| 2203 |
+
"step": 2720
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 29.01195652173913,
|
| 2207 |
+
"grad_norm": 0.00631117494776845,
|
| 2208 |
+
"learning_rate": 6.038647342995169e-07,
|
| 2209 |
+
"loss": 0.0054,
|
| 2210 |
+
"step": 2730
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 29.015579710144927,
|
| 2214 |
+
"grad_norm": 0.006218273192644119,
|
| 2215 |
+
"learning_rate": 4.025764895330113e-07,
|
| 2216 |
+
"loss": 0.0003,
|
| 2217 |
+
"step": 2740
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 29.019202898550724,
|
| 2221 |
+
"grad_norm": 0.004932409152388573,
|
| 2222 |
+
"learning_rate": 2.0128824476650564e-07,
|
| 2223 |
+
"loss": 0.0043,
|
| 2224 |
+
"step": 2750
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 29.02282608695652,
|
| 2228 |
+
"grad_norm": 0.00396711053326726,
|
| 2229 |
+
"learning_rate": 0.0,
|
| 2230 |
+
"loss": 0.0177,
|
| 2231 |
+
"step": 2760
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 29.02282608695652,
|
| 2235 |
+
"eval_accuracy": 0.9016393442622951,
|
| 2236 |
+
"eval_f1": 0.90210919178688,
|
| 2237 |
+
"eval_loss": 0.7259094715118408,
|
| 2238 |
+
"eval_runtime": 42.2094,
|
| 2239 |
+
"eval_samples_per_second": 2.89,
|
| 2240 |
+
"eval_steps_per_second": 0.379,
|
| 2241 |
+
"step": 2760
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 29.02282608695652,
|
| 2245 |
+
"step": 2760,
|
| 2246 |
+
"total_flos": 2.7405187314155127e+19,
|
| 2247 |
+
"train_loss": 0.1748103732693657,
|
| 2248 |
+
"train_runtime": 10578.7771,
|
| 2249 |
+
"train_samples_per_second": 2.087,
|
| 2250 |
+
"train_steps_per_second": 0.261
|
| 2251 |
+
}
|
| 2252 |
+
],
|
| 2253 |
+
"logging_steps": 10,
|
| 2254 |
+
"max_steps": 2760,
|
| 2255 |
+
"num_input_tokens_seen": 0,
|
| 2256 |
+
"num_train_epochs": 9223372036854775807,
|
| 2257 |
+
"save_steps": 500,
|
| 2258 |
+
"stateful_callbacks": {
|
| 2259 |
+
"TrainerControl": {
|
| 2260 |
+
"args": {
|
| 2261 |
+
"should_epoch_stop": false,
|
| 2262 |
+
"should_evaluate": false,
|
| 2263 |
+
"should_log": false,
|
| 2264 |
+
"should_save": true,
|
| 2265 |
+
"should_training_stop": true
|
| 2266 |
+
},
|
| 2267 |
+
"attributes": {}
|
| 2268 |
+
}
|
| 2269 |
+
},
|
| 2270 |
+
"total_flos": 2.7405187314155127e+19,
|
| 2271 |
+
"train_batch_size": 8,
|
| 2272 |
+
"trial_name": null,
|
| 2273 |
+
"trial_params": null
|
| 2274 |
+
}
|