End of training
Browse files- README.md +140 -0
- adapter_model.safetensors +1 -1
- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +1140 -0
README.md
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 7 |
+
datasets:
|
| 8 |
+
- mbe
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Mistral-7B-v0.1_mbe_positive
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Mistral-7B-v0.1_mbe_positive
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mbe dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0233
|
| 24 |
+
- Accuracy: 0.6809
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 3e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 16
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: constant
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 52 |
+
- num_epochs: 5.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 58 |
+
| 2.3217 | 0.07 | 10 | 0.7263 | 0.4901 |
|
| 59 |
+
| 0.56 | 0.13 | 20 | 0.6898 | 0.5526 |
|
| 60 |
+
| 0.5281 | 0.2 | 30 | 0.6465 | 0.5888 |
|
| 61 |
+
| 0.994 | 0.27 | 40 | 0.7351 | 0.5987 |
|
| 62 |
+
| 0.4785 | 0.33 | 50 | 0.6004 | 0.6118 |
|
| 63 |
+
| 0.4732 | 0.4 | 60 | 0.5783 | 0.6349 |
|
| 64 |
+
| 0.4466 | 0.47 | 70 | 0.5714 | 0.6414 |
|
| 65 |
+
| 0.8737 | 0.53 | 80 | 0.5673 | 0.6184 |
|
| 66 |
+
| 0.4471 | 0.6 | 90 | 0.5631 | 0.6283 |
|
| 67 |
+
| 0.46 | 0.67 | 100 | 0.5504 | 0.6349 |
|
| 68 |
+
| 0.3294 | 0.73 | 110 | 0.6010 | 0.625 |
|
| 69 |
+
| 0.6526 | 0.8 | 120 | 0.5731 | 0.6283 |
|
| 70 |
+
| 0.3712 | 0.87 | 130 | 0.5379 | 0.6447 |
|
| 71 |
+
| 0.3341 | 0.93 | 140 | 0.5409 | 0.6283 |
|
| 72 |
+
| 0.552 | 1.0 | 150 | 0.5311 | 0.6382 |
|
| 73 |
+
| 0.4681 | 1.07 | 160 | 0.5371 | 0.6414 |
|
| 74 |
+
| 0.3119 | 1.14 | 170 | 0.6172 | 0.6283 |
|
| 75 |
+
| 0.3082 | 1.2 | 180 | 0.5361 | 0.6513 |
|
| 76 |
+
| 0.5217 | 1.27 | 190 | 0.5468 | 0.625 |
|
| 77 |
+
| 0.3888 | 1.34 | 200 | 0.5891 | 0.6316 |
|
| 78 |
+
| 0.2841 | 1.4 | 210 | 0.5429 | 0.6283 |
|
| 79 |
+
| 0.2728 | 1.47 | 220 | 0.5247 | 0.6382 |
|
| 80 |
+
| 0.5563 | 1.54 | 230 | 0.5004 | 0.6513 |
|
| 81 |
+
| 0.2862 | 1.6 | 240 | 0.4741 | 0.6546 |
|
| 82 |
+
| 0.2289 | 1.67 | 250 | 0.5441 | 0.6513 |
|
| 83 |
+
| 0.2481 | 1.74 | 260 | 0.5171 | 0.6513 |
|
| 84 |
+
| 0.329 | 1.8 | 270 | 0.5371 | 0.6546 |
|
| 85 |
+
| 0.1741 | 1.87 | 280 | 0.5412 | 0.6678 |
|
| 86 |
+
| 0.2888 | 1.94 | 290 | 0.5131 | 0.6711 |
|
| 87 |
+
| 0.4157 | 2.0 | 300 | 0.4555 | 0.6447 |
|
| 88 |
+
| 0.1982 | 2.07 | 310 | 0.5670 | 0.6612 |
|
| 89 |
+
| 0.106 | 2.14 | 320 | 0.7943 | 0.6678 |
|
| 90 |
+
| 0.1718 | 2.2 | 330 | 0.7496 | 0.6645 |
|
| 91 |
+
| 0.214 | 2.27 | 340 | 0.6264 | 0.6842 |
|
| 92 |
+
| 0.1571 | 2.34 | 350 | 0.6139 | 0.6316 |
|
| 93 |
+
| 0.1432 | 2.4 | 360 | 0.6199 | 0.6842 |
|
| 94 |
+
| 0.1038 | 2.47 | 370 | 0.6368 | 0.6974 |
|
| 95 |
+
| 0.1728 | 2.54 | 380 | 0.7889 | 0.6678 |
|
| 96 |
+
| 0.14 | 2.6 | 390 | 0.7952 | 0.6546 |
|
| 97 |
+
| 0.1522 | 2.67 | 400 | 0.7745 | 0.6579 |
|
| 98 |
+
| 0.1345 | 2.74 | 410 | 0.7231 | 0.6513 |
|
| 99 |
+
| 0.1587 | 2.8 | 420 | 0.7154 | 0.6480 |
|
| 100 |
+
| 0.1391 | 2.87 | 430 | 0.6923 | 0.6513 |
|
| 101 |
+
| 0.129 | 2.94 | 440 | 0.6484 | 0.6711 |
|
| 102 |
+
| 0.2092 | 3.01 | 450 | 0.5822 | 0.6743 |
|
| 103 |
+
| 0.015 | 3.07 | 460 | 1.1217 | 0.6579 |
|
| 104 |
+
| 0.051 | 3.14 | 470 | 1.5790 | 0.6480 |
|
| 105 |
+
| 0.0999 | 3.21 | 480 | 1.5168 | 0.6678 |
|
| 106 |
+
| 0.1776 | 3.27 | 490 | 1.2342 | 0.6875 |
|
| 107 |
+
| 0.0612 | 3.34 | 500 | 1.0371 | 0.6974 |
|
| 108 |
+
| 0.0858 | 3.41 | 510 | 1.0277 | 0.6776 |
|
| 109 |
+
| 0.0316 | 3.47 | 520 | 1.0387 | 0.6809 |
|
| 110 |
+
| 0.1899 | 3.54 | 530 | 0.8185 | 0.6908 |
|
| 111 |
+
| 0.1517 | 3.61 | 540 | 0.7054 | 0.6842 |
|
| 112 |
+
| 0.0324 | 3.67 | 550 | 0.8505 | 0.6842 |
|
| 113 |
+
| 0.0646 | 3.74 | 560 | 1.0057 | 0.6612 |
|
| 114 |
+
| 0.1038 | 3.81 | 570 | 1.0027 | 0.6645 |
|
| 115 |
+
| 0.0844 | 3.87 | 580 | 0.9926 | 0.6513 |
|
| 116 |
+
| 0.0986 | 3.94 | 590 | 0.9246 | 0.6579 |
|
| 117 |
+
| 0.0627 | 4.01 | 600 | 0.8539 | 0.6546 |
|
| 118 |
+
| 0.0513 | 4.07 | 610 | 0.9247 | 0.6513 |
|
| 119 |
+
| 0.0484 | 4.14 | 620 | 1.1128 | 0.6546 |
|
| 120 |
+
| 0.0244 | 4.21 | 630 | 1.2702 | 0.6480 |
|
| 121 |
+
| 0.0672 | 4.27 | 640 | 1.7169 | 0.6414 |
|
| 122 |
+
| 0.0824 | 4.34 | 650 | 1.6627 | 0.6414 |
|
| 123 |
+
| 0.0068 | 4.41 | 660 | 1.3425 | 0.6349 |
|
| 124 |
+
| 0.044 | 4.47 | 670 | 1.2208 | 0.6612 |
|
| 125 |
+
| 0.0378 | 4.54 | 680 | 1.2891 | 0.6447 |
|
| 126 |
+
| 0.0411 | 4.61 | 690 | 1.3528 | 0.6612 |
|
| 127 |
+
| 0.0215 | 4.67 | 700 | 1.2606 | 0.6678 |
|
| 128 |
+
| 0.0438 | 4.74 | 710 | 1.2515 | 0.6546 |
|
| 129 |
+
| 0.0936 | 4.81 | 720 | 1.0858 | 0.6645 |
|
| 130 |
+
| 0.0305 | 4.87 | 730 | 0.9839 | 0.6579 |
|
| 131 |
+
| 0.0282 | 4.94 | 740 | 1.0233 | 0.6809 |
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
### Framework versions
|
| 135 |
+
|
| 136 |
+
- PEFT 0.7.1
|
| 137 |
+
- Transformers 4.37.2
|
| 138 |
+
- Pytorch 2.1.2+cu121
|
| 139 |
+
- Datasets 2.17.1
|
| 140 |
+
- Tokenizers 0.15.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335605144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5610270074b0aaf10b547d5ac20a829a7b7b37e978e0c038d9fb532068565e5d
|
| 3 |
size 335605144
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.97,
|
| 3 |
+
"train_loss": 0.25739487704614666,
|
| 4 |
+
"train_runtime": 4901.8806,
|
| 5 |
+
"train_samples_per_second": 2.444,
|
| 6 |
+
"train_steps_per_second": 0.152
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.97,
|
| 3 |
+
"train_loss": 0.25739487704614666,
|
| 4 |
+
"train_runtime": 4901.8806,
|
| 5 |
+
"train_samples_per_second": 2.444,
|
| 6 |
+
"train_steps_per_second": 0.152
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.974958263772955,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 745,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 3e-05,
|
| 14 |
+
"loss": 2.3217,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"eval_accuracy": 0.4901315789473684,
|
| 20 |
+
"eval_loss": 0.7262606620788574,
|
| 21 |
+
"eval_runtime": 25.3718,
|
| 22 |
+
"eval_samples_per_second": 11.982,
|
| 23 |
+
"eval_steps_per_second": 2.995,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.13,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.56,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13,
|
| 34 |
+
"eval_accuracy": 0.5526315789473685,
|
| 35 |
+
"eval_loss": 0.6898001432418823,
|
| 36 |
+
"eval_runtime": 25.3761,
|
| 37 |
+
"eval_samples_per_second": 11.98,
|
| 38 |
+
"eval_steps_per_second": 2.995,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.2,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 0.5281,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2,
|
| 49 |
+
"eval_accuracy": 0.5888157894736842,
|
| 50 |
+
"eval_loss": 0.6465093493461609,
|
| 51 |
+
"eval_runtime": 25.3947,
|
| 52 |
+
"eval_samples_per_second": 11.971,
|
| 53 |
+
"eval_steps_per_second": 2.993,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.27,
|
| 58 |
+
"learning_rate": 3e-05,
|
| 59 |
+
"loss": 0.994,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.27,
|
| 64 |
+
"eval_accuracy": 0.5986842105263158,
|
| 65 |
+
"eval_loss": 0.7351367473602295,
|
| 66 |
+
"eval_runtime": 25.4621,
|
| 67 |
+
"eval_samples_per_second": 11.939,
|
| 68 |
+
"eval_steps_per_second": 2.985,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.33,
|
| 73 |
+
"learning_rate": 3e-05,
|
| 74 |
+
"loss": 0.4785,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.33,
|
| 79 |
+
"eval_accuracy": 0.6118421052631579,
|
| 80 |
+
"eval_loss": 0.6004362106323242,
|
| 81 |
+
"eval_runtime": 25.4138,
|
| 82 |
+
"eval_samples_per_second": 11.962,
|
| 83 |
+
"eval_steps_per_second": 2.991,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.4,
|
| 88 |
+
"learning_rate": 3e-05,
|
| 89 |
+
"loss": 0.4732,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.4,
|
| 94 |
+
"eval_accuracy": 0.6348684210526315,
|
| 95 |
+
"eval_loss": 0.5782976746559143,
|
| 96 |
+
"eval_runtime": 25.369,
|
| 97 |
+
"eval_samples_per_second": 11.983,
|
| 98 |
+
"eval_steps_per_second": 2.996,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.47,
|
| 103 |
+
"learning_rate": 3e-05,
|
| 104 |
+
"loss": 0.4466,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.47,
|
| 109 |
+
"eval_accuracy": 0.6414473684210527,
|
| 110 |
+
"eval_loss": 0.5713546872138977,
|
| 111 |
+
"eval_runtime": 25.3858,
|
| 112 |
+
"eval_samples_per_second": 11.975,
|
| 113 |
+
"eval_steps_per_second": 2.994,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.53,
|
| 118 |
+
"learning_rate": 3e-05,
|
| 119 |
+
"loss": 0.8737,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.53,
|
| 124 |
+
"eval_accuracy": 0.618421052631579,
|
| 125 |
+
"eval_loss": 0.567269504070282,
|
| 126 |
+
"eval_runtime": 25.3639,
|
| 127 |
+
"eval_samples_per_second": 11.986,
|
| 128 |
+
"eval_steps_per_second": 2.996,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6,
|
| 133 |
+
"learning_rate": 3e-05,
|
| 134 |
+
"loss": 0.4471,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6,
|
| 139 |
+
"eval_accuracy": 0.6282894736842105,
|
| 140 |
+
"eval_loss": 0.5630530118942261,
|
| 141 |
+
"eval_runtime": 25.3754,
|
| 142 |
+
"eval_samples_per_second": 11.98,
|
| 143 |
+
"eval_steps_per_second": 2.995,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.67,
|
| 148 |
+
"learning_rate": 3e-05,
|
| 149 |
+
"loss": 0.46,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.67,
|
| 154 |
+
"eval_accuracy": 0.6348684210526315,
|
| 155 |
+
"eval_loss": 0.5503756999969482,
|
| 156 |
+
"eval_runtime": 25.3686,
|
| 157 |
+
"eval_samples_per_second": 11.983,
|
| 158 |
+
"eval_steps_per_second": 2.996,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.73,
|
| 163 |
+
"learning_rate": 3e-05,
|
| 164 |
+
"loss": 0.3294,
|
| 165 |
+
"step": 110
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.73,
|
| 169 |
+
"eval_accuracy": 0.625,
|
| 170 |
+
"eval_loss": 0.6009898781776428,
|
| 171 |
+
"eval_runtime": 25.3647,
|
| 172 |
+
"eval_samples_per_second": 11.985,
|
| 173 |
+
"eval_steps_per_second": 2.996,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.8,
|
| 178 |
+
"learning_rate": 3e-05,
|
| 179 |
+
"loss": 0.6526,
|
| 180 |
+
"step": 120
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.8,
|
| 184 |
+
"eval_accuracy": 0.6282894736842105,
|
| 185 |
+
"eval_loss": 0.5730816721916199,
|
| 186 |
+
"eval_runtime": 25.3832,
|
| 187 |
+
"eval_samples_per_second": 11.976,
|
| 188 |
+
"eval_steps_per_second": 2.994,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.87,
|
| 193 |
+
"learning_rate": 3e-05,
|
| 194 |
+
"loss": 0.3712,
|
| 195 |
+
"step": 130
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.87,
|
| 199 |
+
"eval_accuracy": 0.6447368421052632,
|
| 200 |
+
"eval_loss": 0.5378755331039429,
|
| 201 |
+
"eval_runtime": 25.3825,
|
| 202 |
+
"eval_samples_per_second": 11.977,
|
| 203 |
+
"eval_steps_per_second": 2.994,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.93,
|
| 208 |
+
"learning_rate": 3e-05,
|
| 209 |
+
"loss": 0.3341,
|
| 210 |
+
"step": 140
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.93,
|
| 214 |
+
"eval_accuracy": 0.6282894736842105,
|
| 215 |
+
"eval_loss": 0.5408769249916077,
|
| 216 |
+
"eval_runtime": 25.3787,
|
| 217 |
+
"eval_samples_per_second": 11.979,
|
| 218 |
+
"eval_steps_per_second": 2.995,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"learning_rate": 3e-05,
|
| 224 |
+
"loss": 0.552,
|
| 225 |
+
"step": 150
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.0,
|
| 229 |
+
"eval_accuracy": 0.6381578947368421,
|
| 230 |
+
"eval_loss": 0.5310616493225098,
|
| 231 |
+
"eval_runtime": 25.4512,
|
| 232 |
+
"eval_samples_per_second": 11.944,
|
| 233 |
+
"eval_steps_per_second": 2.986,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.07,
|
| 238 |
+
"learning_rate": 3e-05,
|
| 239 |
+
"loss": 0.4681,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.07,
|
| 244 |
+
"eval_accuracy": 0.6414473684210527,
|
| 245 |
+
"eval_loss": 0.5371212959289551,
|
| 246 |
+
"eval_runtime": 25.3633,
|
| 247 |
+
"eval_samples_per_second": 11.986,
|
| 248 |
+
"eval_steps_per_second": 2.996,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.14,
|
| 253 |
+
"learning_rate": 3e-05,
|
| 254 |
+
"loss": 0.3119,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.14,
|
| 259 |
+
"eval_accuracy": 0.6282894736842105,
|
| 260 |
+
"eval_loss": 0.6171860694885254,
|
| 261 |
+
"eval_runtime": 25.3622,
|
| 262 |
+
"eval_samples_per_second": 11.986,
|
| 263 |
+
"eval_steps_per_second": 2.997,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.2,
|
| 268 |
+
"learning_rate": 3e-05,
|
| 269 |
+
"loss": 0.3082,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.2,
|
| 274 |
+
"eval_accuracy": 0.6513157894736842,
|
| 275 |
+
"eval_loss": 0.5360857844352722,
|
| 276 |
+
"eval_runtime": 25.3868,
|
| 277 |
+
"eval_samples_per_second": 11.975,
|
| 278 |
+
"eval_steps_per_second": 2.994,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.27,
|
| 283 |
+
"learning_rate": 3e-05,
|
| 284 |
+
"loss": 0.5217,
|
| 285 |
+
"step": 190
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.27,
|
| 289 |
+
"eval_accuracy": 0.625,
|
| 290 |
+
"eval_loss": 0.5467653870582581,
|
| 291 |
+
"eval_runtime": 25.3846,
|
| 292 |
+
"eval_samples_per_second": 11.976,
|
| 293 |
+
"eval_steps_per_second": 2.994,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.34,
|
| 298 |
+
"learning_rate": 3e-05,
|
| 299 |
+
"loss": 0.3888,
|
| 300 |
+
"step": 200
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.34,
|
| 304 |
+
"eval_accuracy": 0.631578947368421,
|
| 305 |
+
"eval_loss": 0.5891463756561279,
|
| 306 |
+
"eval_runtime": 25.374,
|
| 307 |
+
"eval_samples_per_second": 11.981,
|
| 308 |
+
"eval_steps_per_second": 2.995,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.4,
|
| 313 |
+
"learning_rate": 3e-05,
|
| 314 |
+
"loss": 0.2841,
|
| 315 |
+
"step": 210
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.4,
|
| 319 |
+
"eval_accuracy": 0.6282894736842105,
|
| 320 |
+
"eval_loss": 0.5428625345230103,
|
| 321 |
+
"eval_runtime": 25.3734,
|
| 322 |
+
"eval_samples_per_second": 11.981,
|
| 323 |
+
"eval_steps_per_second": 2.995,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.47,
|
| 328 |
+
"learning_rate": 3e-05,
|
| 329 |
+
"loss": 0.2728,
|
| 330 |
+
"step": 220
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.47,
|
| 334 |
+
"eval_accuracy": 0.6381578947368421,
|
| 335 |
+
"eval_loss": 0.5246651768684387,
|
| 336 |
+
"eval_runtime": 25.3858,
|
| 337 |
+
"eval_samples_per_second": 11.975,
|
| 338 |
+
"eval_steps_per_second": 2.994,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.54,
|
| 343 |
+
"learning_rate": 3e-05,
|
| 344 |
+
"loss": 0.5563,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.54,
|
| 349 |
+
"eval_accuracy": 0.6513157894736842,
|
| 350 |
+
"eval_loss": 0.5003584027290344,
|
| 351 |
+
"eval_runtime": 25.3763,
|
| 352 |
+
"eval_samples_per_second": 11.98,
|
| 353 |
+
"eval_steps_per_second": 2.995,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.6,
|
| 358 |
+
"learning_rate": 3e-05,
|
| 359 |
+
"loss": 0.2862,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.6,
|
| 364 |
+
"eval_accuracy": 0.6546052631578947,
|
| 365 |
+
"eval_loss": 0.4741169810295105,
|
| 366 |
+
"eval_runtime": 25.3852,
|
| 367 |
+
"eval_samples_per_second": 11.975,
|
| 368 |
+
"eval_steps_per_second": 2.994,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.67,
|
| 373 |
+
"learning_rate": 3e-05,
|
| 374 |
+
"loss": 0.2289,
|
| 375 |
+
"step": 250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.67,
|
| 379 |
+
"eval_accuracy": 0.6513157894736842,
|
| 380 |
+
"eval_loss": 0.5441343188285828,
|
| 381 |
+
"eval_runtime": 25.3897,
|
| 382 |
+
"eval_samples_per_second": 11.973,
|
| 383 |
+
"eval_steps_per_second": 2.993,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.74,
|
| 388 |
+
"learning_rate": 3e-05,
|
| 389 |
+
"loss": 0.2481,
|
| 390 |
+
"step": 260
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.74,
|
| 394 |
+
"eval_accuracy": 0.6513157894736842,
|
| 395 |
+
"eval_loss": 0.5170696377754211,
|
| 396 |
+
"eval_runtime": 25.3747,
|
| 397 |
+
"eval_samples_per_second": 11.98,
|
| 398 |
+
"eval_steps_per_second": 2.995,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.8,
|
| 403 |
+
"learning_rate": 3e-05,
|
| 404 |
+
"loss": 0.329,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.8,
|
| 409 |
+
"eval_accuracy": 0.6546052631578947,
|
| 410 |
+
"eval_loss": 0.5371391177177429,
|
| 411 |
+
"eval_runtime": 25.3708,
|
| 412 |
+
"eval_samples_per_second": 11.982,
|
| 413 |
+
"eval_steps_per_second": 2.996,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.87,
|
| 418 |
+
"learning_rate": 3e-05,
|
| 419 |
+
"loss": 0.1741,
|
| 420 |
+
"step": 280
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.87,
|
| 424 |
+
"eval_accuracy": 0.6677631578947368,
|
| 425 |
+
"eval_loss": 0.5411613583564758,
|
| 426 |
+
"eval_runtime": 25.3792,
|
| 427 |
+
"eval_samples_per_second": 11.978,
|
| 428 |
+
"eval_steps_per_second": 2.995,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.94,
|
| 433 |
+
"learning_rate": 3e-05,
|
| 434 |
+
"loss": 0.2888,
|
| 435 |
+
"step": 290
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.94,
|
| 439 |
+
"eval_accuracy": 0.6710526315789473,
|
| 440 |
+
"eval_loss": 0.5130823850631714,
|
| 441 |
+
"eval_runtime": 25.3665,
|
| 442 |
+
"eval_samples_per_second": 11.984,
|
| 443 |
+
"eval_steps_per_second": 2.996,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0,
|
| 448 |
+
"learning_rate": 3e-05,
|
| 449 |
+
"loss": 0.4157,
|
| 450 |
+
"step": 300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.0,
|
| 454 |
+
"eval_accuracy": 0.6447368421052632,
|
| 455 |
+
"eval_loss": 0.45547178387641907,
|
| 456 |
+
"eval_runtime": 25.356,
|
| 457 |
+
"eval_samples_per_second": 11.989,
|
| 458 |
+
"eval_steps_per_second": 2.997,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.07,
|
| 463 |
+
"learning_rate": 3e-05,
|
| 464 |
+
"loss": 0.1982,
|
| 465 |
+
"step": 310
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.07,
|
| 469 |
+
"eval_accuracy": 0.6611842105263158,
|
| 470 |
+
"eval_loss": 0.5670450329780579,
|
| 471 |
+
"eval_runtime": 25.3778,
|
| 472 |
+
"eval_samples_per_second": 11.979,
|
| 473 |
+
"eval_steps_per_second": 2.995,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.14,
|
| 478 |
+
"learning_rate": 3e-05,
|
| 479 |
+
"loss": 0.106,
|
| 480 |
+
"step": 320
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.14,
|
| 484 |
+
"eval_accuracy": 0.6677631578947368,
|
| 485 |
+
"eval_loss": 0.7942893505096436,
|
| 486 |
+
"eval_runtime": 25.3984,
|
| 487 |
+
"eval_samples_per_second": 11.969,
|
| 488 |
+
"eval_steps_per_second": 2.992,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.2,
|
| 493 |
+
"learning_rate": 3e-05,
|
| 494 |
+
"loss": 0.1718,
|
| 495 |
+
"step": 330
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.2,
|
| 499 |
+
"eval_accuracy": 0.6644736842105263,
|
| 500 |
+
"eval_loss": 0.7496399879455566,
|
| 501 |
+
"eval_runtime": 25.3753,
|
| 502 |
+
"eval_samples_per_second": 11.98,
|
| 503 |
+
"eval_steps_per_second": 2.995,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.27,
|
| 508 |
+
"learning_rate": 3e-05,
|
| 509 |
+
"loss": 0.214,
|
| 510 |
+
"step": 340
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.27,
|
| 514 |
+
"eval_accuracy": 0.6842105263157895,
|
| 515 |
+
"eval_loss": 0.626396656036377,
|
| 516 |
+
"eval_runtime": 25.3727,
|
| 517 |
+
"eval_samples_per_second": 11.981,
|
| 518 |
+
"eval_steps_per_second": 2.995,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.34,
|
| 523 |
+
"learning_rate": 3e-05,
|
| 524 |
+
"loss": 0.1571,
|
| 525 |
+
"step": 350
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.34,
|
| 529 |
+
"eval_accuracy": 0.631578947368421,
|
| 530 |
+
"eval_loss": 0.6138848066329956,
|
| 531 |
+
"eval_runtime": 25.3708,
|
| 532 |
+
"eval_samples_per_second": 11.982,
|
| 533 |
+
"eval_steps_per_second": 2.996,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.4,
|
| 538 |
+
"learning_rate": 3e-05,
|
| 539 |
+
"loss": 0.1432,
|
| 540 |
+
"step": 360
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.4,
|
| 544 |
+
"eval_accuracy": 0.6842105263157895,
|
| 545 |
+
"eval_loss": 0.6198970675468445,
|
| 546 |
+
"eval_runtime": 25.3819,
|
| 547 |
+
"eval_samples_per_second": 11.977,
|
| 548 |
+
"eval_steps_per_second": 2.994,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.47,
|
| 553 |
+
"learning_rate": 3e-05,
|
| 554 |
+
"loss": 0.1038,
|
| 555 |
+
"step": 370
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.47,
|
| 559 |
+
"eval_accuracy": 0.6973684210526315,
|
| 560 |
+
"eval_loss": 0.636822521686554,
|
| 561 |
+
"eval_runtime": 25.4286,
|
| 562 |
+
"eval_samples_per_second": 11.955,
|
| 563 |
+
"eval_steps_per_second": 2.989,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.54,
|
| 568 |
+
"learning_rate": 3e-05,
|
| 569 |
+
"loss": 0.1728,
|
| 570 |
+
"step": 380
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.54,
|
| 574 |
+
"eval_accuracy": 0.6677631578947368,
|
| 575 |
+
"eval_loss": 0.7889474630355835,
|
| 576 |
+
"eval_runtime": 25.3888,
|
| 577 |
+
"eval_samples_per_second": 11.974,
|
| 578 |
+
"eval_steps_per_second": 2.993,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.6,
|
| 583 |
+
"learning_rate": 3e-05,
|
| 584 |
+
"loss": 0.14,
|
| 585 |
+
"step": 390
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.6,
|
| 589 |
+
"eval_accuracy": 0.6546052631578947,
|
| 590 |
+
"eval_loss": 0.795179545879364,
|
| 591 |
+
"eval_runtime": 25.3862,
|
| 592 |
+
"eval_samples_per_second": 11.975,
|
| 593 |
+
"eval_steps_per_second": 2.994,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.67,
|
| 598 |
+
"learning_rate": 3e-05,
|
| 599 |
+
"loss": 0.1522,
|
| 600 |
+
"step": 400
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.67,
|
| 604 |
+
"eval_accuracy": 0.6578947368421053,
|
| 605 |
+
"eval_loss": 0.7745038866996765,
|
| 606 |
+
"eval_runtime": 25.3703,
|
| 607 |
+
"eval_samples_per_second": 11.983,
|
| 608 |
+
"eval_steps_per_second": 2.996,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.74,
|
| 613 |
+
"learning_rate": 3e-05,
|
| 614 |
+
"loss": 0.1345,
|
| 615 |
+
"step": 410
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.74,
|
| 619 |
+
"eval_accuracy": 0.6513157894736842,
|
| 620 |
+
"eval_loss": 0.7230806946754456,
|
| 621 |
+
"eval_runtime": 25.3678,
|
| 622 |
+
"eval_samples_per_second": 11.984,
|
| 623 |
+
"eval_steps_per_second": 2.996,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.8,
|
| 628 |
+
"learning_rate": 3e-05,
|
| 629 |
+
"loss": 0.1587,
|
| 630 |
+
"step": 420
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.8,
|
| 634 |
+
"eval_accuracy": 0.6480263157894737,
|
| 635 |
+
"eval_loss": 0.7153956890106201,
|
| 636 |
+
"eval_runtime": 25.3506,
|
| 637 |
+
"eval_samples_per_second": 11.992,
|
| 638 |
+
"eval_steps_per_second": 2.998,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.87,
|
| 643 |
+
"learning_rate": 3e-05,
|
| 644 |
+
"loss": 0.1391,
|
| 645 |
+
"step": 430
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.87,
|
| 649 |
+
"eval_accuracy": 0.6513157894736842,
|
| 650 |
+
"eval_loss": 0.6923157572746277,
|
| 651 |
+
"eval_runtime": 25.3652,
|
| 652 |
+
"eval_samples_per_second": 11.985,
|
| 653 |
+
"eval_steps_per_second": 2.996,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.94,
|
| 658 |
+
"learning_rate": 3e-05,
|
| 659 |
+
"loss": 0.129,
|
| 660 |
+
"step": 440
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.94,
|
| 664 |
+
"eval_accuracy": 0.6710526315789473,
|
| 665 |
+
"eval_loss": 0.6483842730522156,
|
| 666 |
+
"eval_runtime": 25.3639,
|
| 667 |
+
"eval_samples_per_second": 11.986,
|
| 668 |
+
"eval_steps_per_second": 2.996,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.01,
|
| 673 |
+
"learning_rate": 3e-05,
|
| 674 |
+
"loss": 0.2092,
|
| 675 |
+
"step": 450
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.01,
|
| 679 |
+
"eval_accuracy": 0.6743421052631579,
|
| 680 |
+
"eval_loss": 0.5821840167045593,
|
| 681 |
+
"eval_runtime": 25.3814,
|
| 682 |
+
"eval_samples_per_second": 11.977,
|
| 683 |
+
"eval_steps_per_second": 2.994,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.07,
|
| 688 |
+
"learning_rate": 3e-05,
|
| 689 |
+
"loss": 0.015,
|
| 690 |
+
"step": 460
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.07,
|
| 694 |
+
"eval_accuracy": 0.6578947368421053,
|
| 695 |
+
"eval_loss": 1.1217145919799805,
|
| 696 |
+
"eval_runtime": 25.3698,
|
| 697 |
+
"eval_samples_per_second": 11.983,
|
| 698 |
+
"eval_steps_per_second": 2.996,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.14,
|
| 703 |
+
"learning_rate": 3e-05,
|
| 704 |
+
"loss": 0.051,
|
| 705 |
+
"step": 470
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.14,
|
| 709 |
+
"eval_accuracy": 0.6480263157894737,
|
| 710 |
+
"eval_loss": 1.5789867639541626,
|
| 711 |
+
"eval_runtime": 25.3704,
|
| 712 |
+
"eval_samples_per_second": 11.982,
|
| 713 |
+
"eval_steps_per_second": 2.996,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.21,
|
| 718 |
+
"learning_rate": 3e-05,
|
| 719 |
+
"loss": 0.0999,
|
| 720 |
+
"step": 480
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.21,
|
| 724 |
+
"eval_accuracy": 0.6677631578947368,
|
| 725 |
+
"eval_loss": 1.5168237686157227,
|
| 726 |
+
"eval_runtime": 25.3794,
|
| 727 |
+
"eval_samples_per_second": 11.978,
|
| 728 |
+
"eval_steps_per_second": 2.995,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.27,
|
| 733 |
+
"learning_rate": 3e-05,
|
| 734 |
+
"loss": 0.1776,
|
| 735 |
+
"step": 490
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.27,
|
| 739 |
+
"eval_accuracy": 0.6875,
|
| 740 |
+
"eval_loss": 1.2342281341552734,
|
| 741 |
+
"eval_runtime": 25.3944,
|
| 742 |
+
"eval_samples_per_second": 11.971,
|
| 743 |
+
"eval_steps_per_second": 2.993,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.34,
|
| 748 |
+
"learning_rate": 3e-05,
|
| 749 |
+
"loss": 0.0612,
|
| 750 |
+
"step": 500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.34,
|
| 754 |
+
"eval_accuracy": 0.6973684210526315,
|
| 755 |
+
"eval_loss": 1.0370548963546753,
|
| 756 |
+
"eval_runtime": 25.385,
|
| 757 |
+
"eval_samples_per_second": 11.976,
|
| 758 |
+
"eval_steps_per_second": 2.994,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.41,
|
| 763 |
+
"learning_rate": 3e-05,
|
| 764 |
+
"loss": 0.0858,
|
| 765 |
+
"step": 510
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.41,
|
| 769 |
+
"eval_accuracy": 0.6776315789473685,
|
| 770 |
+
"eval_loss": 1.0277096033096313,
|
| 771 |
+
"eval_runtime": 25.386,
|
| 772 |
+
"eval_samples_per_second": 11.975,
|
| 773 |
+
"eval_steps_per_second": 2.994,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.47,
|
| 778 |
+
"learning_rate": 3e-05,
|
| 779 |
+
"loss": 0.0316,
|
| 780 |
+
"step": 520
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.47,
|
| 784 |
+
"eval_accuracy": 0.680921052631579,
|
| 785 |
+
"eval_loss": 1.0386649370193481,
|
| 786 |
+
"eval_runtime": 25.3706,
|
| 787 |
+
"eval_samples_per_second": 11.982,
|
| 788 |
+
"eval_steps_per_second": 2.996,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.54,
|
| 793 |
+
"learning_rate": 3e-05,
|
| 794 |
+
"loss": 0.1899,
|
| 795 |
+
"step": 530
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.54,
|
| 799 |
+
"eval_accuracy": 0.6907894736842105,
|
| 800 |
+
"eval_loss": 0.8184946775436401,
|
| 801 |
+
"eval_runtime": 25.3771,
|
| 802 |
+
"eval_samples_per_second": 11.979,
|
| 803 |
+
"eval_steps_per_second": 2.995,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.61,
|
| 808 |
+
"learning_rate": 3e-05,
|
| 809 |
+
"loss": 0.1517,
|
| 810 |
+
"step": 540
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.61,
|
| 814 |
+
"eval_accuracy": 0.6842105263157895,
|
| 815 |
+
"eval_loss": 0.7053664922714233,
|
| 816 |
+
"eval_runtime": 25.3758,
|
| 817 |
+
"eval_samples_per_second": 11.98,
|
| 818 |
+
"eval_steps_per_second": 2.995,
|
| 819 |
+
"step": 540
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 3.67,
|
| 823 |
+
"learning_rate": 3e-05,
|
| 824 |
+
"loss": 0.0324,
|
| 825 |
+
"step": 550
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.67,
|
| 829 |
+
"eval_accuracy": 0.6842105263157895,
|
| 830 |
+
"eval_loss": 0.8504552245140076,
|
| 831 |
+
"eval_runtime": 25.3714,
|
| 832 |
+
"eval_samples_per_second": 11.982,
|
| 833 |
+
"eval_steps_per_second": 2.995,
|
| 834 |
+
"step": 550
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.74,
|
| 838 |
+
"learning_rate": 3e-05,
|
| 839 |
+
"loss": 0.0646,
|
| 840 |
+
"step": 560
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 3.74,
|
| 844 |
+
"eval_accuracy": 0.6611842105263158,
|
| 845 |
+
"eval_loss": 1.0056827068328857,
|
| 846 |
+
"eval_runtime": 25.3614,
|
| 847 |
+
"eval_samples_per_second": 11.987,
|
| 848 |
+
"eval_steps_per_second": 2.997,
|
| 849 |
+
"step": 560
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.81,
|
| 853 |
+
"learning_rate": 3e-05,
|
| 854 |
+
"loss": 0.1038,
|
| 855 |
+
"step": 570
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.81,
|
| 859 |
+
"eval_accuracy": 0.6644736842105263,
|
| 860 |
+
"eval_loss": 1.0026819705963135,
|
| 861 |
+
"eval_runtime": 25.376,
|
| 862 |
+
"eval_samples_per_second": 11.98,
|
| 863 |
+
"eval_steps_per_second": 2.995,
|
| 864 |
+
"step": 570
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.87,
|
| 868 |
+
"learning_rate": 3e-05,
|
| 869 |
+
"loss": 0.0844,
|
| 870 |
+
"step": 580
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.87,
|
| 874 |
+
"eval_accuracy": 0.6513157894736842,
|
| 875 |
+
"eval_loss": 0.9926165342330933,
|
| 876 |
+
"eval_runtime": 25.3651,
|
| 877 |
+
"eval_samples_per_second": 11.985,
|
| 878 |
+
"eval_steps_per_second": 2.996,
|
| 879 |
+
"step": 580
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 3.94,
|
| 883 |
+
"learning_rate": 3e-05,
|
| 884 |
+
"loss": 0.0986,
|
| 885 |
+
"step": 590
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.94,
|
| 889 |
+
"eval_accuracy": 0.6578947368421053,
|
| 890 |
+
"eval_loss": 0.9245979189872742,
|
| 891 |
+
"eval_runtime": 25.3574,
|
| 892 |
+
"eval_samples_per_second": 11.989,
|
| 893 |
+
"eval_steps_per_second": 2.997,
|
| 894 |
+
"step": 590
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 4.01,
|
| 898 |
+
"learning_rate": 3e-05,
|
| 899 |
+
"loss": 0.0627,
|
| 900 |
+
"step": 600
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 4.01,
|
| 904 |
+
"eval_accuracy": 0.6546052631578947,
|
| 905 |
+
"eval_loss": 0.8538947105407715,
|
| 906 |
+
"eval_runtime": 25.3724,
|
| 907 |
+
"eval_samples_per_second": 11.982,
|
| 908 |
+
"eval_steps_per_second": 2.995,
|
| 909 |
+
"step": 600
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 4.07,
|
| 913 |
+
"learning_rate": 3e-05,
|
| 914 |
+
"loss": 0.0513,
|
| 915 |
+
"step": 610
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 4.07,
|
| 919 |
+
"eval_accuracy": 0.6513157894736842,
|
| 920 |
+
"eval_loss": 0.924721896648407,
|
| 921 |
+
"eval_runtime": 25.4077,
|
| 922 |
+
"eval_samples_per_second": 11.965,
|
| 923 |
+
"eval_steps_per_second": 2.991,
|
| 924 |
+
"step": 610
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 4.14,
|
| 928 |
+
"learning_rate": 3e-05,
|
| 929 |
+
"loss": 0.0484,
|
| 930 |
+
"step": 620
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 4.14,
|
| 934 |
+
"eval_accuracy": 0.6546052631578947,
|
| 935 |
+
"eval_loss": 1.112806797027588,
|
| 936 |
+
"eval_runtime": 25.3865,
|
| 937 |
+
"eval_samples_per_second": 11.975,
|
| 938 |
+
"eval_steps_per_second": 2.994,
|
| 939 |
+
"step": 620
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 4.21,
|
| 943 |
+
"learning_rate": 3e-05,
|
| 944 |
+
"loss": 0.0244,
|
| 945 |
+
"step": 630
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 4.21,
|
| 949 |
+
"eval_accuracy": 0.6480263157894737,
|
| 950 |
+
"eval_loss": 1.2701855897903442,
|
| 951 |
+
"eval_runtime": 25.3744,
|
| 952 |
+
"eval_samples_per_second": 11.981,
|
| 953 |
+
"eval_steps_per_second": 2.995,
|
| 954 |
+
"step": 630
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 4.27,
|
| 958 |
+
"learning_rate": 3e-05,
|
| 959 |
+
"loss": 0.0672,
|
| 960 |
+
"step": 640
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 4.27,
|
| 964 |
+
"eval_accuracy": 0.6414473684210527,
|
| 965 |
+
"eval_loss": 1.716863751411438,
|
| 966 |
+
"eval_runtime": 25.3891,
|
| 967 |
+
"eval_samples_per_second": 11.974,
|
| 968 |
+
"eval_steps_per_second": 2.993,
|
| 969 |
+
"step": 640
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.34,
|
| 973 |
+
"learning_rate": 3e-05,
|
| 974 |
+
"loss": 0.0824,
|
| 975 |
+
"step": 650
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 4.34,
|
| 979 |
+
"eval_accuracy": 0.6414473684210527,
|
| 980 |
+
"eval_loss": 1.662705659866333,
|
| 981 |
+
"eval_runtime": 25.3803,
|
| 982 |
+
"eval_samples_per_second": 11.978,
|
| 983 |
+
"eval_steps_per_second": 2.994,
|
| 984 |
+
"step": 650
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.41,
|
| 988 |
+
"learning_rate": 3e-05,
|
| 989 |
+
"loss": 0.0068,
|
| 990 |
+
"step": 660
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.41,
|
| 994 |
+
"eval_accuracy": 0.6348684210526315,
|
| 995 |
+
"eval_loss": 1.342494010925293,
|
| 996 |
+
"eval_runtime": 25.376,
|
| 997 |
+
"eval_samples_per_second": 11.98,
|
| 998 |
+
"eval_steps_per_second": 2.995,
|
| 999 |
+
"step": 660
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 4.47,
|
| 1003 |
+
"learning_rate": 3e-05,
|
| 1004 |
+
"loss": 0.044,
|
| 1005 |
+
"step": 670
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 4.47,
|
| 1009 |
+
"eval_accuracy": 0.6611842105263158,
|
| 1010 |
+
"eval_loss": 1.2208458185195923,
|
| 1011 |
+
"eval_runtime": 25.3753,
|
| 1012 |
+
"eval_samples_per_second": 11.98,
|
| 1013 |
+
"eval_steps_per_second": 2.995,
|
| 1014 |
+
"step": 670
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 4.54,
|
| 1018 |
+
"learning_rate": 3e-05,
|
| 1019 |
+
"loss": 0.0378,
|
| 1020 |
+
"step": 680
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 4.54,
|
| 1024 |
+
"eval_accuracy": 0.6447368421052632,
|
| 1025 |
+
"eval_loss": 1.289115309715271,
|
| 1026 |
+
"eval_runtime": 25.3905,
|
| 1027 |
+
"eval_samples_per_second": 11.973,
|
| 1028 |
+
"eval_steps_per_second": 2.993,
|
| 1029 |
+
"step": 680
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 4.61,
|
| 1033 |
+
"learning_rate": 3e-05,
|
| 1034 |
+
"loss": 0.0411,
|
| 1035 |
+
"step": 690
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 4.61,
|
| 1039 |
+
"eval_accuracy": 0.6611842105263158,
|
| 1040 |
+
"eval_loss": 1.3528344631195068,
|
| 1041 |
+
"eval_runtime": 25.3678,
|
| 1042 |
+
"eval_samples_per_second": 11.984,
|
| 1043 |
+
"eval_steps_per_second": 2.996,
|
| 1044 |
+
"step": 690
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 4.67,
|
| 1048 |
+
"learning_rate": 3e-05,
|
| 1049 |
+
"loss": 0.0215,
|
| 1050 |
+
"step": 700
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 4.67,
|
| 1054 |
+
"eval_accuracy": 0.6677631578947368,
|
| 1055 |
+
"eval_loss": 1.2606314420700073,
|
| 1056 |
+
"eval_runtime": 25.3852,
|
| 1057 |
+
"eval_samples_per_second": 11.975,
|
| 1058 |
+
"eval_steps_per_second": 2.994,
|
| 1059 |
+
"step": 700
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 4.74,
|
| 1063 |
+
"learning_rate": 3e-05,
|
| 1064 |
+
"loss": 0.0438,
|
| 1065 |
+
"step": 710
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.74,
|
| 1069 |
+
"eval_accuracy": 0.6546052631578947,
|
| 1070 |
+
"eval_loss": 1.2514981031417847,
|
| 1071 |
+
"eval_runtime": 25.3679,
|
| 1072 |
+
"eval_samples_per_second": 11.984,
|
| 1073 |
+
"eval_steps_per_second": 2.996,
|
| 1074 |
+
"step": 710
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 4.81,
|
| 1078 |
+
"learning_rate": 3e-05,
|
| 1079 |
+
"loss": 0.0936,
|
| 1080 |
+
"step": 720
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.81,
|
| 1084 |
+
"eval_accuracy": 0.6644736842105263,
|
| 1085 |
+
"eval_loss": 1.0857858657836914,
|
| 1086 |
+
"eval_runtime": 25.3812,
|
| 1087 |
+
"eval_samples_per_second": 11.977,
|
| 1088 |
+
"eval_steps_per_second": 2.994,
|
| 1089 |
+
"step": 720
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 4.87,
|
| 1093 |
+
"learning_rate": 3e-05,
|
| 1094 |
+
"loss": 0.0305,
|
| 1095 |
+
"step": 730
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.87,
|
| 1099 |
+
"eval_accuracy": 0.6578947368421053,
|
| 1100 |
+
"eval_loss": 0.9838737845420837,
|
| 1101 |
+
"eval_runtime": 25.3673,
|
| 1102 |
+
"eval_samples_per_second": 11.984,
|
| 1103 |
+
"eval_steps_per_second": 2.996,
|
| 1104 |
+
"step": 730
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.94,
|
| 1108 |
+
"learning_rate": 3e-05,
|
| 1109 |
+
"loss": 0.0282,
|
| 1110 |
+
"step": 740
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 4.94,
|
| 1114 |
+
"eval_accuracy": 0.680921052631579,
|
| 1115 |
+
"eval_loss": 1.0233386754989624,
|
| 1116 |
+
"eval_runtime": 25.3685,
|
| 1117 |
+
"eval_samples_per_second": 11.983,
|
| 1118 |
+
"eval_steps_per_second": 2.996,
|
| 1119 |
+
"step": 740
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 4.97,
|
| 1123 |
+
"step": 745,
|
| 1124 |
+
"total_flos": 2.959225892752589e+17,
|
| 1125 |
+
"train_loss": 0.25739487704614666,
|
| 1126 |
+
"train_runtime": 4901.8806,
|
| 1127 |
+
"train_samples_per_second": 2.444,
|
| 1128 |
+
"train_steps_per_second": 0.152
|
| 1129 |
+
}
|
| 1130 |
+
],
|
| 1131 |
+
"logging_steps": 10,
|
| 1132 |
+
"max_steps": 745,
|
| 1133 |
+
"num_input_tokens_seen": 0,
|
| 1134 |
+
"num_train_epochs": 5,
|
| 1135 |
+
"save_steps": 150,
|
| 1136 |
+
"total_flos": 2.959225892752589e+17,
|
| 1137 |
+
"train_batch_size": 4,
|
| 1138 |
+
"trial_name": null,
|
| 1139 |
+
"trial_params": null
|
| 1140 |
+
}
|