End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan27_17-36-47_db1093ce036b/events.out.tfevents.1737999760.db1093ce036b.224.13 +3 -0
- train_results.json +8 -0
- trainer_state.json +760 -0
README.md
CHANGED
|
@@ -23,7 +23,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.9166666666666666
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.3267
|
| 37 |
+
- Accuracy: 0.9167
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 71.42857142857143,
|
| 3 |
+
"eval_accuracy": 0.9166666666666666,
|
| 4 |
+
"eval_loss": 0.32666629552841187,
|
| 5 |
+
"eval_runtime": 0.6636,
|
| 6 |
+
"eval_samples_per_second": 216.992,
|
| 7 |
+
"eval_steps_per_second": 4.521,
|
| 8 |
+
"total_flos": 5.956344520589353e+17,
|
| 9 |
+
"train_loss": 0.420122013092041,
|
| 10 |
+
"train_runtime": 326.0769,
|
| 11 |
+
"train_samples_per_second": 130.644,
|
| 12 |
+
"train_steps_per_second": 0.307
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 71.42857142857143,
|
| 3 |
+
"eval_accuracy": 0.9166666666666666,
|
| 4 |
+
"eval_loss": 0.32666629552841187,
|
| 5 |
+
"eval_runtime": 0.6636,
|
| 6 |
+
"eval_samples_per_second": 216.992,
|
| 7 |
+
"eval_steps_per_second": 4.521
|
| 8 |
+
}
|
runs/Jan27_17-36-47_db1093ce036b/events.out.tfevents.1737999760.db1093ce036b.224.13
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aba0b9a87ddf06d3dcb060be2f5daa2663797604169303edcca562e77cafe45f
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 71.42857142857143,
|
| 3 |
+
"total_flos": 5.956344520589353e+17,
|
| 4 |
+
"train_loss": 0.420122013092041,
|
| 5 |
+
"train_runtime": 326.0769,
|
| 6 |
+
"train_samples_per_second": 130.644,
|
| 7 |
+
"train_steps_per_second": 0.307
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.32666629552841187,
|
| 3 |
+
"best_model_checkpoint": "vit-msn-small-beta-fia-manually-enhanced-HSV_test_5/checkpoint-44",
|
| 4 |
+
"epoch": 71.42857142857143,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7142857142857143,
|
| 13 |
+
"eval_accuracy": 0.22916666666666666,
|
| 14 |
+
"eval_loss": 1.1105738878250122,
|
| 15 |
+
"eval_runtime": 0.6997,
|
| 16 |
+
"eval_samples_per_second": 205.812,
|
| 17 |
+
"eval_steps_per_second": 4.288,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.4285714285714286,
|
| 22 |
+
"eval_accuracy": 0.2569444444444444,
|
| 23 |
+
"eval_loss": 1.098416805267334,
|
| 24 |
+
"eval_runtime": 0.6273,
|
| 25 |
+
"eval_samples_per_second": 229.555,
|
| 26 |
+
"eval_steps_per_second": 4.782,
|
| 27 |
+
"step": 2
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.857142857142857,
|
| 31 |
+
"eval_accuracy": 0.4097222222222222,
|
| 32 |
+
"eval_loss": 1.039996862411499,
|
| 33 |
+
"eval_runtime": 0.6547,
|
| 34 |
+
"eval_samples_per_second": 219.941,
|
| 35 |
+
"eval_steps_per_second": 4.582,
|
| 36 |
+
"step": 4
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.571428571428571,
|
| 40 |
+
"eval_accuracy": 0.5486111111111112,
|
| 41 |
+
"eval_loss": 0.99596107006073,
|
| 42 |
+
"eval_runtime": 0.6487,
|
| 43 |
+
"eval_samples_per_second": 221.995,
|
| 44 |
+
"eval_steps_per_second": 4.625,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.7291666666666666,
|
| 50 |
+
"eval_loss": 0.8868050575256348,
|
| 51 |
+
"eval_runtime": 0.7036,
|
| 52 |
+
"eval_samples_per_second": 204.658,
|
| 53 |
+
"eval_steps_per_second": 4.264,
|
| 54 |
+
"step": 7
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 5.714285714285714,
|
| 58 |
+
"eval_accuracy": 0.7777777777777778,
|
| 59 |
+
"eval_loss": 0.8263272047042847,
|
| 60 |
+
"eval_runtime": 0.7254,
|
| 61 |
+
"eval_samples_per_second": 198.509,
|
| 62 |
+
"eval_steps_per_second": 4.136,
|
| 63 |
+
"step": 8
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.428571428571429,
|
| 67 |
+
"eval_accuracy": 0.8055555555555556,
|
| 68 |
+
"eval_loss": 0.7650943994522095,
|
| 69 |
+
"eval_runtime": 0.6223,
|
| 70 |
+
"eval_samples_per_second": 231.4,
|
| 71 |
+
"eval_steps_per_second": 4.821,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.142857142857143,
|
| 76 |
+
"grad_norm": 13.31224536895752,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 0.9808,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 7.857142857142857,
|
| 83 |
+
"eval_accuracy": 0.8125,
|
| 84 |
+
"eval_loss": 0.6520677208900452,
|
| 85 |
+
"eval_runtime": 0.6795,
|
| 86 |
+
"eval_samples_per_second": 211.923,
|
| 87 |
+
"eval_steps_per_second": 4.415,
|
| 88 |
+
"step": 11
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 8.571428571428571,
|
| 92 |
+
"eval_accuracy": 0.8125,
|
| 93 |
+
"eval_loss": 0.605199933052063,
|
| 94 |
+
"eval_runtime": 0.6616,
|
| 95 |
+
"eval_samples_per_second": 217.658,
|
| 96 |
+
"eval_steps_per_second": 4.535,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 10.0,
|
| 101 |
+
"eval_accuracy": 0.8125,
|
| 102 |
+
"eval_loss": 0.538772702217102,
|
| 103 |
+
"eval_runtime": 0.6326,
|
| 104 |
+
"eval_samples_per_second": 227.627,
|
| 105 |
+
"eval_steps_per_second": 4.742,
|
| 106 |
+
"step": 14
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 10.714285714285714,
|
| 110 |
+
"eval_accuracy": 0.8125,
|
| 111 |
+
"eval_loss": 0.5174447894096375,
|
| 112 |
+
"eval_runtime": 0.6152,
|
| 113 |
+
"eval_samples_per_second": 234.055,
|
| 114 |
+
"eval_steps_per_second": 4.876,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 11.428571428571429,
|
| 119 |
+
"eval_accuracy": 0.8125,
|
| 120 |
+
"eval_loss": 0.503182590007782,
|
| 121 |
+
"eval_runtime": 0.6377,
|
| 122 |
+
"eval_samples_per_second": 225.804,
|
| 123 |
+
"eval_steps_per_second": 4.704,
|
| 124 |
+
"step": 16
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 12.857142857142858,
|
| 128 |
+
"eval_accuracy": 0.8125,
|
| 129 |
+
"eval_loss": 0.5022291541099548,
|
| 130 |
+
"eval_runtime": 0.6473,
|
| 131 |
+
"eval_samples_per_second": 222.471,
|
| 132 |
+
"eval_steps_per_second": 4.635,
|
| 133 |
+
"step": 18
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 13.571428571428571,
|
| 137 |
+
"eval_accuracy": 0.8194444444444444,
|
| 138 |
+
"eval_loss": 0.5044423341751099,
|
| 139 |
+
"eval_runtime": 0.6293,
|
| 140 |
+
"eval_samples_per_second": 228.838,
|
| 141 |
+
"eval_steps_per_second": 4.767,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 14.285714285714286,
|
| 146 |
+
"grad_norm": 3.2047011852264404,
|
| 147 |
+
"learning_rate": 8.000000000000001e-06,
|
| 148 |
+
"loss": 0.5431,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 15.0,
|
| 153 |
+
"eval_accuracy": 0.8263888888888888,
|
| 154 |
+
"eval_loss": 0.47730180621147156,
|
| 155 |
+
"eval_runtime": 0.7212,
|
| 156 |
+
"eval_samples_per_second": 199.678,
|
| 157 |
+
"eval_steps_per_second": 4.16,
|
| 158 |
+
"step": 21
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 15.714285714285714,
|
| 162 |
+
"eval_accuracy": 0.8333333333333334,
|
| 163 |
+
"eval_loss": 0.4439104497432709,
|
| 164 |
+
"eval_runtime": 0.6519,
|
| 165 |
+
"eval_samples_per_second": 220.904,
|
| 166 |
+
"eval_steps_per_second": 4.602,
|
| 167 |
+
"step": 22
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 16.428571428571427,
|
| 171 |
+
"eval_accuracy": 0.8402777777777778,
|
| 172 |
+
"eval_loss": 0.41979074478149414,
|
| 173 |
+
"eval_runtime": 0.6167,
|
| 174 |
+
"eval_samples_per_second": 233.497,
|
| 175 |
+
"eval_steps_per_second": 4.865,
|
| 176 |
+
"step": 23
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 17.857142857142858,
|
| 180 |
+
"eval_accuracy": 0.8819444444444444,
|
| 181 |
+
"eval_loss": 0.38726139068603516,
|
| 182 |
+
"eval_runtime": 0.626,
|
| 183 |
+
"eval_samples_per_second": 230.043,
|
| 184 |
+
"eval_steps_per_second": 4.793,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 18.571428571428573,
|
| 189 |
+
"eval_accuracy": 0.8888888888888888,
|
| 190 |
+
"eval_loss": 0.37299442291259766,
|
| 191 |
+
"eval_runtime": 0.6291,
|
| 192 |
+
"eval_samples_per_second": 228.912,
|
| 193 |
+
"eval_steps_per_second": 4.769,
|
| 194 |
+
"step": 26
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.0,
|
| 198 |
+
"eval_accuracy": 0.9027777777777778,
|
| 199 |
+
"eval_loss": 0.3773989677429199,
|
| 200 |
+
"eval_runtime": 0.63,
|
| 201 |
+
"eval_samples_per_second": 228.574,
|
| 202 |
+
"eval_steps_per_second": 4.762,
|
| 203 |
+
"step": 28
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 20.714285714285715,
|
| 207 |
+
"eval_accuracy": 0.9097222222222222,
|
| 208 |
+
"eval_loss": 0.37053972482681274,
|
| 209 |
+
"eval_runtime": 0.6212,
|
| 210 |
+
"eval_samples_per_second": 231.817,
|
| 211 |
+
"eval_steps_per_second": 4.83,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 21.428571428571427,
|
| 216 |
+
"grad_norm": 5.860249996185303,
|
| 217 |
+
"learning_rate": 9.333333333333334e-06,
|
| 218 |
+
"loss": 0.4028,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 21.428571428571427,
|
| 223 |
+
"eval_accuracy": 0.9097222222222222,
|
| 224 |
+
"eval_loss": 0.3586524724960327,
|
| 225 |
+
"eval_runtime": 0.6377,
|
| 226 |
+
"eval_samples_per_second": 225.813,
|
| 227 |
+
"eval_steps_per_second": 4.704,
|
| 228 |
+
"step": 30
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 22.857142857142858,
|
| 232 |
+
"eval_accuracy": 0.8958333333333334,
|
| 233 |
+
"eval_loss": 0.36622118949890137,
|
| 234 |
+
"eval_runtime": 0.6654,
|
| 235 |
+
"eval_samples_per_second": 216.406,
|
| 236 |
+
"eval_steps_per_second": 4.508,
|
| 237 |
+
"step": 32
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 23.571428571428573,
|
| 241 |
+
"eval_accuracy": 0.8680555555555556,
|
| 242 |
+
"eval_loss": 0.37790825963020325,
|
| 243 |
+
"eval_runtime": 0.6384,
|
| 244 |
+
"eval_samples_per_second": 225.558,
|
| 245 |
+
"eval_steps_per_second": 4.699,
|
| 246 |
+
"step": 33
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 25.0,
|
| 250 |
+
"eval_accuracy": 0.8263888888888888,
|
| 251 |
+
"eval_loss": 0.43221160769462585,
|
| 252 |
+
"eval_runtime": 0.6264,
|
| 253 |
+
"eval_samples_per_second": 229.872,
|
| 254 |
+
"eval_steps_per_second": 4.789,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 25.714285714285715,
|
| 259 |
+
"eval_accuracy": 0.8333333333333334,
|
| 260 |
+
"eval_loss": 0.39439037442207336,
|
| 261 |
+
"eval_runtime": 0.6534,
|
| 262 |
+
"eval_samples_per_second": 220.396,
|
| 263 |
+
"eval_steps_per_second": 4.592,
|
| 264 |
+
"step": 36
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 26.428571428571427,
|
| 268 |
+
"eval_accuracy": 0.8888888888888888,
|
| 269 |
+
"eval_loss": 0.3585418462753296,
|
| 270 |
+
"eval_runtime": 0.6327,
|
| 271 |
+
"eval_samples_per_second": 227.579,
|
| 272 |
+
"eval_steps_per_second": 4.741,
|
| 273 |
+
"step": 37
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 27.857142857142858,
|
| 277 |
+
"eval_accuracy": 0.8888888888888888,
|
| 278 |
+
"eval_loss": 0.3607942461967468,
|
| 279 |
+
"eval_runtime": 0.6624,
|
| 280 |
+
"eval_samples_per_second": 217.391,
|
| 281 |
+
"eval_steps_per_second": 4.529,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 28.571428571428573,
|
| 286 |
+
"grad_norm": 3.4132988452911377,
|
| 287 |
+
"learning_rate": 8.000000000000001e-06,
|
| 288 |
+
"loss": 0.3497,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 28.571428571428573,
|
| 293 |
+
"eval_accuracy": 0.8472222222222222,
|
| 294 |
+
"eval_loss": 0.39719662070274353,
|
| 295 |
+
"eval_runtime": 0.643,
|
| 296 |
+
"eval_samples_per_second": 223.955,
|
| 297 |
+
"eval_steps_per_second": 4.666,
|
| 298 |
+
"step": 40
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 30.0,
|
| 302 |
+
"eval_accuracy": 0.8611111111111112,
|
| 303 |
+
"eval_loss": 0.3804582953453064,
|
| 304 |
+
"eval_runtime": 0.6301,
|
| 305 |
+
"eval_samples_per_second": 228.526,
|
| 306 |
+
"eval_steps_per_second": 4.761,
|
| 307 |
+
"step": 42
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 30.714285714285715,
|
| 311 |
+
"eval_accuracy": 0.8819444444444444,
|
| 312 |
+
"eval_loss": 0.3610667586326599,
|
| 313 |
+
"eval_runtime": 0.6248,
|
| 314 |
+
"eval_samples_per_second": 230.471,
|
| 315 |
+
"eval_steps_per_second": 4.801,
|
| 316 |
+
"step": 43
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 31.428571428571427,
|
| 320 |
+
"eval_accuracy": 0.9166666666666666,
|
| 321 |
+
"eval_loss": 0.32666629552841187,
|
| 322 |
+
"eval_runtime": 0.6456,
|
| 323 |
+
"eval_samples_per_second": 223.058,
|
| 324 |
+
"eval_steps_per_second": 4.647,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 32.857142857142854,
|
| 329 |
+
"eval_accuracy": 0.9027777777777778,
|
| 330 |
+
"eval_loss": 0.3402611017227173,
|
| 331 |
+
"eval_runtime": 0.6337,
|
| 332 |
+
"eval_samples_per_second": 227.247,
|
| 333 |
+
"eval_steps_per_second": 4.734,
|
| 334 |
+
"step": 46
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 33.57142857142857,
|
| 338 |
+
"eval_accuracy": 0.875,
|
| 339 |
+
"eval_loss": 0.37514248490333557,
|
| 340 |
+
"eval_runtime": 0.7032,
|
| 341 |
+
"eval_samples_per_second": 204.765,
|
| 342 |
+
"eval_steps_per_second": 4.266,
|
| 343 |
+
"step": 47
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 35.0,
|
| 347 |
+
"eval_accuracy": 0.8680555555555556,
|
| 348 |
+
"eval_loss": 0.3801332414150238,
|
| 349 |
+
"eval_runtime": 0.659,
|
| 350 |
+
"eval_samples_per_second": 218.502,
|
| 351 |
+
"eval_steps_per_second": 4.552,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 35.714285714285715,
|
| 356 |
+
"grad_norm": 6.472348213195801,
|
| 357 |
+
"learning_rate": 6.666666666666667e-06,
|
| 358 |
+
"loss": 0.3278,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 35.714285714285715,
|
| 363 |
+
"eval_accuracy": 0.8958333333333334,
|
| 364 |
+
"eval_loss": 0.34991347789764404,
|
| 365 |
+
"eval_runtime": 0.6712,
|
| 366 |
+
"eval_samples_per_second": 214.545,
|
| 367 |
+
"eval_steps_per_second": 4.47,
|
| 368 |
+
"step": 50
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 36.42857142857143,
|
| 372 |
+
"eval_accuracy": 0.8958333333333334,
|
| 373 |
+
"eval_loss": 0.33839675784111023,
|
| 374 |
+
"eval_runtime": 0.6365,
|
| 375 |
+
"eval_samples_per_second": 226.231,
|
| 376 |
+
"eval_steps_per_second": 4.713,
|
| 377 |
+
"step": 51
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 37.857142857142854,
|
| 381 |
+
"eval_accuracy": 0.8541666666666666,
|
| 382 |
+
"eval_loss": 0.3642105460166931,
|
| 383 |
+
"eval_runtime": 0.6301,
|
| 384 |
+
"eval_samples_per_second": 228.534,
|
| 385 |
+
"eval_steps_per_second": 4.761,
|
| 386 |
+
"step": 53
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 38.57142857142857,
|
| 390 |
+
"eval_accuracy": 0.8194444444444444,
|
| 391 |
+
"eval_loss": 0.3996630907058716,
|
| 392 |
+
"eval_runtime": 0.6609,
|
| 393 |
+
"eval_samples_per_second": 217.89,
|
| 394 |
+
"eval_steps_per_second": 4.539,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 40.0,
|
| 399 |
+
"eval_accuracy": 0.8402777777777778,
|
| 400 |
+
"eval_loss": 0.3843066394329071,
|
| 401 |
+
"eval_runtime": 0.6636,
|
| 402 |
+
"eval_samples_per_second": 216.984,
|
| 403 |
+
"eval_steps_per_second": 4.521,
|
| 404 |
+
"step": 56
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 40.714285714285715,
|
| 408 |
+
"eval_accuracy": 0.8680555555555556,
|
| 409 |
+
"eval_loss": 0.3675690293312073,
|
| 410 |
+
"eval_runtime": 0.6194,
|
| 411 |
+
"eval_samples_per_second": 232.479,
|
| 412 |
+
"eval_steps_per_second": 4.843,
|
| 413 |
+
"step": 57
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 41.42857142857143,
|
| 417 |
+
"eval_accuracy": 0.9027777777777778,
|
| 418 |
+
"eval_loss": 0.3464236557483673,
|
| 419 |
+
"eval_runtime": 0.6267,
|
| 420 |
+
"eval_samples_per_second": 229.775,
|
| 421 |
+
"eval_steps_per_second": 4.787,
|
| 422 |
+
"step": 58
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 42.857142857142854,
|
| 426 |
+
"grad_norm": 6.519013404846191,
|
| 427 |
+
"learning_rate": 5.333333333333334e-06,
|
| 428 |
+
"loss": 0.3334,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 42.857142857142854,
|
| 433 |
+
"eval_accuracy": 0.8819444444444444,
|
| 434 |
+
"eval_loss": 0.36175864934921265,
|
| 435 |
+
"eval_runtime": 0.7106,
|
| 436 |
+
"eval_samples_per_second": 202.636,
|
| 437 |
+
"eval_steps_per_second": 4.222,
|
| 438 |
+
"step": 60
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 43.57142857142857,
|
| 442 |
+
"eval_accuracy": 0.8194444444444444,
|
| 443 |
+
"eval_loss": 0.40056005120277405,
|
| 444 |
+
"eval_runtime": 0.6703,
|
| 445 |
+
"eval_samples_per_second": 214.814,
|
| 446 |
+
"eval_steps_per_second": 4.475,
|
| 447 |
+
"step": 61
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 45.0,
|
| 451 |
+
"eval_accuracy": 0.7638888888888888,
|
| 452 |
+
"eval_loss": 0.49312081933021545,
|
| 453 |
+
"eval_runtime": 0.7051,
|
| 454 |
+
"eval_samples_per_second": 204.23,
|
| 455 |
+
"eval_steps_per_second": 4.255,
|
| 456 |
+
"step": 63
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 45.714285714285715,
|
| 460 |
+
"eval_accuracy": 0.7708333333333334,
|
| 461 |
+
"eval_loss": 0.48445218801498413,
|
| 462 |
+
"eval_runtime": 0.71,
|
| 463 |
+
"eval_samples_per_second": 202.808,
|
| 464 |
+
"eval_steps_per_second": 4.225,
|
| 465 |
+
"step": 64
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 46.42857142857143,
|
| 469 |
+
"eval_accuracy": 0.7916666666666666,
|
| 470 |
+
"eval_loss": 0.4485209286212921,
|
| 471 |
+
"eval_runtime": 0.6303,
|
| 472 |
+
"eval_samples_per_second": 228.459,
|
| 473 |
+
"eval_steps_per_second": 4.76,
|
| 474 |
+
"step": 65
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 47.857142857142854,
|
| 478 |
+
"eval_accuracy": 0.8472222222222222,
|
| 479 |
+
"eval_loss": 0.378328800201416,
|
| 480 |
+
"eval_runtime": 0.6131,
|
| 481 |
+
"eval_samples_per_second": 234.855,
|
| 482 |
+
"eval_steps_per_second": 4.893,
|
| 483 |
+
"step": 67
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 48.57142857142857,
|
| 487 |
+
"eval_accuracy": 0.8472222222222222,
|
| 488 |
+
"eval_loss": 0.37234801054000854,
|
| 489 |
+
"eval_runtime": 0.6727,
|
| 490 |
+
"eval_samples_per_second": 214.05,
|
| 491 |
+
"eval_steps_per_second": 4.459,
|
| 492 |
+
"step": 68
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 50.0,
|
| 496 |
+
"grad_norm": 5.204492092132568,
|
| 497 |
+
"learning_rate": 4.000000000000001e-06,
|
| 498 |
+
"loss": 0.3334,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 50.0,
|
| 503 |
+
"eval_accuracy": 0.8125,
|
| 504 |
+
"eval_loss": 0.407737672328949,
|
| 505 |
+
"eval_runtime": 0.6505,
|
| 506 |
+
"eval_samples_per_second": 221.382,
|
| 507 |
+
"eval_steps_per_second": 4.612,
|
| 508 |
+
"step": 70
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 50.714285714285715,
|
| 512 |
+
"eval_accuracy": 0.7986111111111112,
|
| 513 |
+
"eval_loss": 0.4380877912044525,
|
| 514 |
+
"eval_runtime": 0.7093,
|
| 515 |
+
"eval_samples_per_second": 203.024,
|
| 516 |
+
"eval_steps_per_second": 4.23,
|
| 517 |
+
"step": 71
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 51.42857142857143,
|
| 521 |
+
"eval_accuracy": 0.7847222222222222,
|
| 522 |
+
"eval_loss": 0.46269893646240234,
|
| 523 |
+
"eval_runtime": 0.6731,
|
| 524 |
+
"eval_samples_per_second": 213.937,
|
| 525 |
+
"eval_steps_per_second": 4.457,
|
| 526 |
+
"step": 72
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 52.857142857142854,
|
| 530 |
+
"eval_accuracy": 0.7986111111111112,
|
| 531 |
+
"eval_loss": 0.44445788860321045,
|
| 532 |
+
"eval_runtime": 0.6372,
|
| 533 |
+
"eval_samples_per_second": 225.995,
|
| 534 |
+
"eval_steps_per_second": 4.708,
|
| 535 |
+
"step": 74
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 53.57142857142857,
|
| 539 |
+
"eval_accuracy": 0.8125,
|
| 540 |
+
"eval_loss": 0.41410741209983826,
|
| 541 |
+
"eval_runtime": 0.6728,
|
| 542 |
+
"eval_samples_per_second": 214.026,
|
| 543 |
+
"eval_steps_per_second": 4.459,
|
| 544 |
+
"step": 75
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 55.0,
|
| 548 |
+
"eval_accuracy": 0.8680555555555556,
|
| 549 |
+
"eval_loss": 0.3488573431968689,
|
| 550 |
+
"eval_runtime": 0.6306,
|
| 551 |
+
"eval_samples_per_second": 228.368,
|
| 552 |
+
"eval_steps_per_second": 4.758,
|
| 553 |
+
"step": 77
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 55.714285714285715,
|
| 557 |
+
"eval_accuracy": 0.8958333333333334,
|
| 558 |
+
"eval_loss": 0.33705562353134155,
|
| 559 |
+
"eval_runtime": 0.6859,
|
| 560 |
+
"eval_samples_per_second": 209.945,
|
| 561 |
+
"eval_steps_per_second": 4.374,
|
| 562 |
+
"step": 78
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 56.42857142857143,
|
| 566 |
+
"eval_accuracy": 0.8888888888888888,
|
| 567 |
+
"eval_loss": 0.3358408510684967,
|
| 568 |
+
"eval_runtime": 0.6867,
|
| 569 |
+
"eval_samples_per_second": 209.701,
|
| 570 |
+
"eval_steps_per_second": 4.369,
|
| 571 |
+
"step": 79
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 57.142857142857146,
|
| 575 |
+
"grad_norm": 5.973431587219238,
|
| 576 |
+
"learning_rate": 2.666666666666667e-06,
|
| 577 |
+
"loss": 0.3105,
|
| 578 |
+
"step": 80
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 57.857142857142854,
|
| 582 |
+
"eval_accuracy": 0.8680555555555556,
|
| 583 |
+
"eval_loss": 0.3538711965084076,
|
| 584 |
+
"eval_runtime": 0.7307,
|
| 585 |
+
"eval_samples_per_second": 197.072,
|
| 586 |
+
"eval_steps_per_second": 4.106,
|
| 587 |
+
"step": 81
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 58.57142857142857,
|
| 591 |
+
"eval_accuracy": 0.8541666666666666,
|
| 592 |
+
"eval_loss": 0.3678491413593292,
|
| 593 |
+
"eval_runtime": 0.6126,
|
| 594 |
+
"eval_samples_per_second": 235.055,
|
| 595 |
+
"eval_steps_per_second": 4.897,
|
| 596 |
+
"step": 82
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 60.0,
|
| 600 |
+
"eval_accuracy": 0.8263888888888888,
|
| 601 |
+
"eval_loss": 0.3930552899837494,
|
| 602 |
+
"eval_runtime": 0.633,
|
| 603 |
+
"eval_samples_per_second": 227.478,
|
| 604 |
+
"eval_steps_per_second": 4.739,
|
| 605 |
+
"step": 84
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 60.714285714285715,
|
| 609 |
+
"eval_accuracy": 0.8263888888888888,
|
| 610 |
+
"eval_loss": 0.3938286006450653,
|
| 611 |
+
"eval_runtime": 0.6516,
|
| 612 |
+
"eval_samples_per_second": 220.996,
|
| 613 |
+
"eval_steps_per_second": 4.604,
|
| 614 |
+
"step": 85
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 61.42857142857143,
|
| 618 |
+
"eval_accuracy": 0.8472222222222222,
|
| 619 |
+
"eval_loss": 0.3896949589252472,
|
| 620 |
+
"eval_runtime": 0.6582,
|
| 621 |
+
"eval_samples_per_second": 218.793,
|
| 622 |
+
"eval_steps_per_second": 4.558,
|
| 623 |
+
"step": 86
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 62.857142857142854,
|
| 627 |
+
"eval_accuracy": 0.8611111111111112,
|
| 628 |
+
"eval_loss": 0.3637922406196594,
|
| 629 |
+
"eval_runtime": 0.6651,
|
| 630 |
+
"eval_samples_per_second": 216.505,
|
| 631 |
+
"eval_steps_per_second": 4.511,
|
| 632 |
+
"step": 88
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 63.57142857142857,
|
| 636 |
+
"eval_accuracy": 0.875,
|
| 637 |
+
"eval_loss": 0.34960028529167175,
|
| 638 |
+
"eval_runtime": 0.6331,
|
| 639 |
+
"eval_samples_per_second": 227.443,
|
| 640 |
+
"eval_steps_per_second": 4.738,
|
| 641 |
+
"step": 89
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 64.28571428571429,
|
| 645 |
+
"grad_norm": 6.167888164520264,
|
| 646 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 647 |
+
"loss": 0.3061,
|
| 648 |
+
"step": 90
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 65.0,
|
| 652 |
+
"eval_accuracy": 0.8958333333333334,
|
| 653 |
+
"eval_loss": 0.3304632306098938,
|
| 654 |
+
"eval_runtime": 0.6686,
|
| 655 |
+
"eval_samples_per_second": 215.369,
|
| 656 |
+
"eval_steps_per_second": 4.487,
|
| 657 |
+
"step": 91
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 65.71428571428571,
|
| 661 |
+
"eval_accuracy": 0.9027777777777778,
|
| 662 |
+
"eval_loss": 0.3283728361129761,
|
| 663 |
+
"eval_runtime": 0.6659,
|
| 664 |
+
"eval_samples_per_second": 216.261,
|
| 665 |
+
"eval_steps_per_second": 4.505,
|
| 666 |
+
"step": 92
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 66.42857142857143,
|
| 670 |
+
"eval_accuracy": 0.8958333333333334,
|
| 671 |
+
"eval_loss": 0.3283740282058716,
|
| 672 |
+
"eval_runtime": 0.6699,
|
| 673 |
+
"eval_samples_per_second": 214.972,
|
| 674 |
+
"eval_steps_per_second": 4.479,
|
| 675 |
+
"step": 93
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 67.85714285714286,
|
| 679 |
+
"eval_accuracy": 0.8958333333333334,
|
| 680 |
+
"eval_loss": 0.33374664187431335,
|
| 681 |
+
"eval_runtime": 0.668,
|
| 682 |
+
"eval_samples_per_second": 215.572,
|
| 683 |
+
"eval_steps_per_second": 4.491,
|
| 684 |
+
"step": 95
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 68.57142857142857,
|
| 688 |
+
"eval_accuracy": 0.8888888888888888,
|
| 689 |
+
"eval_loss": 0.33741050958633423,
|
| 690 |
+
"eval_runtime": 0.6191,
|
| 691 |
+
"eval_samples_per_second": 232.594,
|
| 692 |
+
"eval_steps_per_second": 4.846,
|
| 693 |
+
"step": 96
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 70.0,
|
| 697 |
+
"eval_accuracy": 0.875,
|
| 698 |
+
"eval_loss": 0.34418821334838867,
|
| 699 |
+
"eval_runtime": 0.6959,
|
| 700 |
+
"eval_samples_per_second": 206.929,
|
| 701 |
+
"eval_steps_per_second": 4.311,
|
| 702 |
+
"step": 98
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 70.71428571428571,
|
| 706 |
+
"eval_accuracy": 0.875,
|
| 707 |
+
"eval_loss": 0.34521356225013733,
|
| 708 |
+
"eval_runtime": 0.6376,
|
| 709 |
+
"eval_samples_per_second": 225.852,
|
| 710 |
+
"eval_steps_per_second": 4.705,
|
| 711 |
+
"step": 99
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 71.42857142857143,
|
| 715 |
+
"grad_norm": 5.671431541442871,
|
| 716 |
+
"learning_rate": 0.0,
|
| 717 |
+
"loss": 0.3137,
|
| 718 |
+
"step": 100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 71.42857142857143,
|
| 722 |
+
"eval_accuracy": 0.875,
|
| 723 |
+
"eval_loss": 0.3459942042827606,
|
| 724 |
+
"eval_runtime": 0.7141,
|
| 725 |
+
"eval_samples_per_second": 201.642,
|
| 726 |
+
"eval_steps_per_second": 4.201,
|
| 727 |
+
"step": 100
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 71.42857142857143,
|
| 731 |
+
"step": 100,
|
| 732 |
+
"total_flos": 5.956344520589353e+17,
|
| 733 |
+
"train_loss": 0.420122013092041,
|
| 734 |
+
"train_runtime": 326.0769,
|
| 735 |
+
"train_samples_per_second": 130.644,
|
| 736 |
+
"train_steps_per_second": 0.307
|
| 737 |
+
}
|
| 738 |
+
],
|
| 739 |
+
"logging_steps": 10,
|
| 740 |
+
"max_steps": 100,
|
| 741 |
+
"num_input_tokens_seen": 0,
|
| 742 |
+
"num_train_epochs": 100,
|
| 743 |
+
"save_steps": 500,
|
| 744 |
+
"stateful_callbacks": {
|
| 745 |
+
"TrainerControl": {
|
| 746 |
+
"args": {
|
| 747 |
+
"should_epoch_stop": false,
|
| 748 |
+
"should_evaluate": false,
|
| 749 |
+
"should_log": false,
|
| 750 |
+
"should_save": true,
|
| 751 |
+
"should_training_stop": true
|
| 752 |
+
},
|
| 753 |
+
"attributes": {}
|
| 754 |
+
}
|
| 755 |
+
},
|
| 756 |
+
"total_flos": 5.956344520589353e+17,
|
| 757 |
+
"train_batch_size": 64,
|
| 758 |
+
"trial_name": null,
|
| 759 |
+
"trial_params": null
|
| 760 |
+
}
|