Commit
•
1584927
1
Parent(s):
1390c3d
End of training
Browse files- README.md +1 -1
- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +820 -0
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
- Accuracy: 0.6146
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5240
|
| 21 |
- Accuracy: 0.6146
|
| 22 |
|
| 23 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.042022792022792,
|
| 3 |
+
"eval_accuracy": 0.6146341463414634,
|
| 4 |
+
"eval_loss": 1.5239903926849365,
|
| 5 |
+
"eval_runtime": 17.6083,
|
| 6 |
+
"eval_samples_per_second": 11.642,
|
| 7 |
+
"eval_steps_per_second": 0.738
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.042022792022792,
|
| 3 |
+
"eval_accuracy": 0.6146341463414634,
|
| 4 |
+
"eval_loss": 1.5239903926849365,
|
| 5 |
+
"eval_runtime": 17.6083,
|
| 6 |
+
"eval_samples_per_second": 11.642,
|
| 7 |
+
"eval_steps_per_second": 0.738
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,820 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6601941747572816,
|
| 3 |
+
"best_model_checkpoint": "videomae-large-finetuned-right-hand-conflab-v1/checkpoint-708",
|
| 4 |
+
"epoch": 14.042022792022792,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 885,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.007122507122507123,
|
| 13 |
+
"grad_norm": 12.899408340454102,
|
| 14 |
+
"learning_rate": 3.5460992907801423e-06,
|
| 15 |
+
"loss": 2.0965,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.014245014245014245,
|
| 20 |
+
"grad_norm": 9.095556259155273,
|
| 21 |
+
"learning_rate": 7.092198581560285e-06,
|
| 22 |
+
"loss": 2.1002,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.021367521367521368,
|
| 27 |
+
"grad_norm": 11.837288856506348,
|
| 28 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 29 |
+
"loss": 1.9683,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02849002849002849,
|
| 34 |
+
"grad_norm": 8.063945770263672,
|
| 35 |
+
"learning_rate": 1.418439716312057e-05,
|
| 36 |
+
"loss": 1.9838,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03561253561253561,
|
| 41 |
+
"grad_norm": 7.636847972869873,
|
| 42 |
+
"learning_rate": 1.773049645390071e-05,
|
| 43 |
+
"loss": 2.0232,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04202279202279202,
|
| 48 |
+
"eval_accuracy": 0.1941747572815534,
|
| 49 |
+
"eval_loss": 1.9421881437301636,
|
| 50 |
+
"eval_runtime": 24.149,
|
| 51 |
+
"eval_samples_per_second": 8.53,
|
| 52 |
+
"eval_steps_per_second": 0.538,
|
| 53 |
+
"step": 59
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.0007122507122508,
|
| 57 |
+
"grad_norm": 7.21124267578125,
|
| 58 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 59 |
+
"loss": 1.981,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.0078347578347577,
|
| 64 |
+
"grad_norm": 8.352581977844238,
|
| 65 |
+
"learning_rate": 2.4822695035460995e-05,
|
| 66 |
+
"loss": 1.9465,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.014957264957265,
|
| 71 |
+
"grad_norm": 8.361379623413086,
|
| 72 |
+
"learning_rate": 2.836879432624114e-05,
|
| 73 |
+
"loss": 1.962,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.022079772079772,
|
| 78 |
+
"grad_norm": 5.388889312744141,
|
| 79 |
+
"learning_rate": 3.191489361702128e-05,
|
| 80 |
+
"loss": 1.976,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0292022792022792,
|
| 85 |
+
"grad_norm": 5.553725719451904,
|
| 86 |
+
"learning_rate": 3.546099290780142e-05,
|
| 87 |
+
"loss": 2.0058,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0363247863247864,
|
| 92 |
+
"grad_norm": 6.278877258300781,
|
| 93 |
+
"learning_rate": 3.900709219858156e-05,
|
| 94 |
+
"loss": 1.8426,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.042022792022792,
|
| 99 |
+
"eval_accuracy": 0.33980582524271846,
|
| 100 |
+
"eval_loss": 1.7418017387390137,
|
| 101 |
+
"eval_runtime": 19.8724,
|
| 102 |
+
"eval_samples_per_second": 10.366,
|
| 103 |
+
"eval_steps_per_second": 0.654,
|
| 104 |
+
"step": 118
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0014245014245016,
|
| 108 |
+
"grad_norm": 5.7616729736328125,
|
| 109 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 110 |
+
"loss": 1.9192,
|
| 111 |
+
"step": 120
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.0085470085470085,
|
| 115 |
+
"grad_norm": 6.886305332183838,
|
| 116 |
+
"learning_rate": 4.609929078014185e-05,
|
| 117 |
+
"loss": 1.8077,
|
| 118 |
+
"step": 130
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.0156695156695155,
|
| 122 |
+
"grad_norm": 12.934743881225586,
|
| 123 |
+
"learning_rate": 4.964539007092199e-05,
|
| 124 |
+
"loss": 1.6519,
|
| 125 |
+
"step": 140
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.022792022792023,
|
| 129 |
+
"grad_norm": 9.393815994262695,
|
| 130 |
+
"learning_rate": 4.96437054631829e-05,
|
| 131 |
+
"loss": 1.6934,
|
| 132 |
+
"step": 150
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.02991452991453,
|
| 136 |
+
"grad_norm": 10.663277626037598,
|
| 137 |
+
"learning_rate": 4.924782264449723e-05,
|
| 138 |
+
"loss": 1.7591,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.037037037037037,
|
| 143 |
+
"grad_norm": 6.719297885894775,
|
| 144 |
+
"learning_rate": 4.885193982581156e-05,
|
| 145 |
+
"loss": 1.7424,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.042022792022792,
|
| 150 |
+
"eval_accuracy": 0.4174757281553398,
|
| 151 |
+
"eval_loss": 1.6896483898162842,
|
| 152 |
+
"eval_runtime": 17.8016,
|
| 153 |
+
"eval_samples_per_second": 11.572,
|
| 154 |
+
"eval_steps_per_second": 0.73,
|
| 155 |
+
"step": 177
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.002136752136752,
|
| 159 |
+
"grad_norm": 5.332315921783447,
|
| 160 |
+
"learning_rate": 4.845605700712589e-05,
|
| 161 |
+
"loss": 1.7511,
|
| 162 |
+
"step": 180
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.009259259259259,
|
| 166 |
+
"grad_norm": 9.056990623474121,
|
| 167 |
+
"learning_rate": 4.806017418844022e-05,
|
| 168 |
+
"loss": 1.6771,
|
| 169 |
+
"step": 190
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.0163817663817665,
|
| 173 |
+
"grad_norm": 10.588340759277344,
|
| 174 |
+
"learning_rate": 4.766429136975455e-05,
|
| 175 |
+
"loss": 1.4029,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.0235042735042734,
|
| 180 |
+
"grad_norm": 17.486988067626953,
|
| 181 |
+
"learning_rate": 4.7268408551068886e-05,
|
| 182 |
+
"loss": 1.4862,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.030626780626781,
|
| 187 |
+
"grad_norm": 7.175242900848389,
|
| 188 |
+
"learning_rate": 4.687252573238321e-05,
|
| 189 |
+
"loss": 1.4282,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.0377492877492878,
|
| 194 |
+
"grad_norm": 8.013775825500488,
|
| 195 |
+
"learning_rate": 4.647664291369755e-05,
|
| 196 |
+
"loss": 1.2206,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.042022792022792,
|
| 201 |
+
"eval_accuracy": 0.44660194174757284,
|
| 202 |
+
"eval_loss": 1.628009557723999,
|
| 203 |
+
"eval_runtime": 21.5993,
|
| 204 |
+
"eval_samples_per_second": 9.537,
|
| 205 |
+
"eval_steps_per_second": 0.602,
|
| 206 |
+
"step": 236
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.002849002849003,
|
| 210 |
+
"grad_norm": 8.972482681274414,
|
| 211 |
+
"learning_rate": 4.6080760095011874e-05,
|
| 212 |
+
"loss": 1.6023,
|
| 213 |
+
"step": 240
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.00997150997151,
|
| 217 |
+
"grad_norm": 7.669183731079102,
|
| 218 |
+
"learning_rate": 4.568487727632621e-05,
|
| 219 |
+
"loss": 1.1725,
|
| 220 |
+
"step": 250
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.017094017094017,
|
| 224 |
+
"grad_norm": 7.465898513793945,
|
| 225 |
+
"learning_rate": 4.528899445764054e-05,
|
| 226 |
+
"loss": 1.2957,
|
| 227 |
+
"step": 260
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.024216524216524,
|
| 231 |
+
"grad_norm": 5.810666561126709,
|
| 232 |
+
"learning_rate": 4.4893111638954874e-05,
|
| 233 |
+
"loss": 1.3387,
|
| 234 |
+
"step": 270
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.031339031339031,
|
| 238 |
+
"grad_norm": 8.172585487365723,
|
| 239 |
+
"learning_rate": 4.44972288202692e-05,
|
| 240 |
+
"loss": 1.2668,
|
| 241 |
+
"step": 280
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.038461538461538,
|
| 245 |
+
"grad_norm": 7.007075309753418,
|
| 246 |
+
"learning_rate": 4.4101346001583535e-05,
|
| 247 |
+
"loss": 1.0738,
|
| 248 |
+
"step": 290
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.042022792022792,
|
| 252 |
+
"eval_accuracy": 0.5825242718446602,
|
| 253 |
+
"eval_loss": 1.2310322523117065,
|
| 254 |
+
"eval_runtime": 18.9007,
|
| 255 |
+
"eval_samples_per_second": 10.899,
|
| 256 |
+
"eval_steps_per_second": 0.688,
|
| 257 |
+
"step": 295
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.003561253561253,
|
| 261 |
+
"grad_norm": 4.775450229644775,
|
| 262 |
+
"learning_rate": 4.370546318289787e-05,
|
| 263 |
+
"loss": 1.0455,
|
| 264 |
+
"step": 300
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.010683760683761,
|
| 268 |
+
"grad_norm": 9.440917015075684,
|
| 269 |
+
"learning_rate": 4.3309580364212195e-05,
|
| 270 |
+
"loss": 0.99,
|
| 271 |
+
"step": 310
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.017806267806268,
|
| 275 |
+
"grad_norm": 5.092905521392822,
|
| 276 |
+
"learning_rate": 4.291369754552653e-05,
|
| 277 |
+
"loss": 0.9873,
|
| 278 |
+
"step": 320
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.0249287749287745,
|
| 282 |
+
"grad_norm": 8.457822799682617,
|
| 283 |
+
"learning_rate": 4.2517814726840856e-05,
|
| 284 |
+
"loss": 0.8012,
|
| 285 |
+
"step": 330
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.032051282051282,
|
| 289 |
+
"grad_norm": 6.717366695404053,
|
| 290 |
+
"learning_rate": 4.212193190815519e-05,
|
| 291 |
+
"loss": 0.9262,
|
| 292 |
+
"step": 340
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 5.039173789173789,
|
| 296 |
+
"grad_norm": 6.962019920349121,
|
| 297 |
+
"learning_rate": 4.172604908946952e-05,
|
| 298 |
+
"loss": 1.0054,
|
| 299 |
+
"step": 350
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.042022792022792,
|
| 303 |
+
"eval_accuracy": 0.558252427184466,
|
| 304 |
+
"eval_loss": 1.3242673873901367,
|
| 305 |
+
"eval_runtime": 20.0158,
|
| 306 |
+
"eval_samples_per_second": 10.292,
|
| 307 |
+
"eval_steps_per_second": 0.649,
|
| 308 |
+
"step": 354
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.004273504273504,
|
| 312 |
+
"grad_norm": 17.063520431518555,
|
| 313 |
+
"learning_rate": 4.133016627078385e-05,
|
| 314 |
+
"loss": 0.8909,
|
| 315 |
+
"step": 360
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.011396011396012,
|
| 319 |
+
"grad_norm": 8.150900840759277,
|
| 320 |
+
"learning_rate": 4.093428345209818e-05,
|
| 321 |
+
"loss": 0.89,
|
| 322 |
+
"step": 370
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 6.018518518518518,
|
| 326 |
+
"grad_norm": 8.059175491333008,
|
| 327 |
+
"learning_rate": 4.053840063341251e-05,
|
| 328 |
+
"loss": 0.7925,
|
| 329 |
+
"step": 380
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 6.0256410256410255,
|
| 333 |
+
"grad_norm": 7.513158798217773,
|
| 334 |
+
"learning_rate": 4.0142517814726843e-05,
|
| 335 |
+
"loss": 0.853,
|
| 336 |
+
"step": 390
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 6.032763532763533,
|
| 340 |
+
"grad_norm": 6.1937971115112305,
|
| 341 |
+
"learning_rate": 3.974663499604117e-05,
|
| 342 |
+
"loss": 0.7338,
|
| 343 |
+
"step": 400
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 6.0398860398860394,
|
| 347 |
+
"grad_norm": 5.745666980743408,
|
| 348 |
+
"learning_rate": 3.9350752177355504e-05,
|
| 349 |
+
"loss": 0.782,
|
| 350 |
+
"step": 410
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.042022792022792,
|
| 354 |
+
"eval_accuracy": 0.6359223300970874,
|
| 355 |
+
"eval_loss": 1.1890981197357178,
|
| 356 |
+
"eval_runtime": 19.1994,
|
| 357 |
+
"eval_samples_per_second": 10.73,
|
| 358 |
+
"eval_steps_per_second": 0.677,
|
| 359 |
+
"step": 413
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.004985754985755,
|
| 363 |
+
"grad_norm": 7.788235187530518,
|
| 364 |
+
"learning_rate": 3.895486935866984e-05,
|
| 365 |
+
"loss": 0.745,
|
| 366 |
+
"step": 420
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.012108262108262,
|
| 370 |
+
"grad_norm": 8.95632553100586,
|
| 371 |
+
"learning_rate": 3.8558986539984164e-05,
|
| 372 |
+
"loss": 0.6315,
|
| 373 |
+
"step": 430
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 7.019230769230769,
|
| 377 |
+
"grad_norm": 9.59426498413086,
|
| 378 |
+
"learning_rate": 3.81631037212985e-05,
|
| 379 |
+
"loss": 0.6792,
|
| 380 |
+
"step": 440
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.0263532763532766,
|
| 384 |
+
"grad_norm": 7.637509822845459,
|
| 385 |
+
"learning_rate": 3.7767220902612825e-05,
|
| 386 |
+
"loss": 0.5733,
|
| 387 |
+
"step": 450
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.033475783475783,
|
| 391 |
+
"grad_norm": 10.775083541870117,
|
| 392 |
+
"learning_rate": 3.737133808392716e-05,
|
| 393 |
+
"loss": 0.7303,
|
| 394 |
+
"step": 460
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 7.0405982905982905,
|
| 398 |
+
"grad_norm": 6.580932140350342,
|
| 399 |
+
"learning_rate": 3.6975455265241485e-05,
|
| 400 |
+
"loss": 0.599,
|
| 401 |
+
"step": 470
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.042022792022792,
|
| 405 |
+
"eval_accuracy": 0.6504854368932039,
|
| 406 |
+
"eval_loss": 1.193009376525879,
|
| 407 |
+
"eval_runtime": 20.2931,
|
| 408 |
+
"eval_samples_per_second": 10.151,
|
| 409 |
+
"eval_steps_per_second": 0.641,
|
| 410 |
+
"step": 472
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.005698005698006,
|
| 414 |
+
"grad_norm": 8.682097434997559,
|
| 415 |
+
"learning_rate": 3.657957244655582e-05,
|
| 416 |
+
"loss": 0.4704,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.012820512820513,
|
| 421 |
+
"grad_norm": 8.527168273925781,
|
| 422 |
+
"learning_rate": 3.618368962787015e-05,
|
| 423 |
+
"loss": 0.6392,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 8.01994301994302,
|
| 428 |
+
"grad_norm": 6.198835849761963,
|
| 429 |
+
"learning_rate": 3.578780680918448e-05,
|
| 430 |
+
"loss": 0.3972,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 8.027065527065528,
|
| 435 |
+
"grad_norm": 6.177005290985107,
|
| 436 |
+
"learning_rate": 3.539192399049881e-05,
|
| 437 |
+
"loss": 0.4873,
|
| 438 |
+
"step": 510
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 8.034188034188034,
|
| 442 |
+
"grad_norm": 9.330336570739746,
|
| 443 |
+
"learning_rate": 3.4996041171813146e-05,
|
| 444 |
+
"loss": 0.4534,
|
| 445 |
+
"step": 520
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 8.04131054131054,
|
| 449 |
+
"grad_norm": 5.25494384765625,
|
| 450 |
+
"learning_rate": 3.460015835312748e-05,
|
| 451 |
+
"loss": 0.6782,
|
| 452 |
+
"step": 530
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.042022792022792,
|
| 456 |
+
"eval_accuracy": 0.6359223300970874,
|
| 457 |
+
"eval_loss": 1.2866381406784058,
|
| 458 |
+
"eval_runtime": 19.101,
|
| 459 |
+
"eval_samples_per_second": 10.785,
|
| 460 |
+
"eval_steps_per_second": 0.681,
|
| 461 |
+
"step": 531
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 9.006410256410257,
|
| 465 |
+
"grad_norm": 5.766805648803711,
|
| 466 |
+
"learning_rate": 3.4204275534441806e-05,
|
| 467 |
+
"loss": 0.392,
|
| 468 |
+
"step": 540
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 9.013532763532764,
|
| 472 |
+
"grad_norm": 11.340324401855469,
|
| 473 |
+
"learning_rate": 3.380839271575614e-05,
|
| 474 |
+
"loss": 0.4548,
|
| 475 |
+
"step": 550
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 9.02065527065527,
|
| 479 |
+
"grad_norm": 10.191842079162598,
|
| 480 |
+
"learning_rate": 3.3412509897070474e-05,
|
| 481 |
+
"loss": 0.3105,
|
| 482 |
+
"step": 560
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.027777777777779,
|
| 486 |
+
"grad_norm": 5.949177265167236,
|
| 487 |
+
"learning_rate": 3.30166270783848e-05,
|
| 488 |
+
"loss": 0.4979,
|
| 489 |
+
"step": 570
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.034900284900285,
|
| 493 |
+
"grad_norm": 11.043278694152832,
|
| 494 |
+
"learning_rate": 3.2620744259699134e-05,
|
| 495 |
+
"loss": 0.3972,
|
| 496 |
+
"step": 580
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 9.042022792022792,
|
| 500 |
+
"grad_norm": 16.354900360107422,
|
| 501 |
+
"learning_rate": 3.222486144101346e-05,
|
| 502 |
+
"loss": 0.3033,
|
| 503 |
+
"step": 590
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.042022792022792,
|
| 507 |
+
"eval_accuracy": 0.5776699029126213,
|
| 508 |
+
"eval_loss": 1.423584222793579,
|
| 509 |
+
"eval_runtime": 20.9024,
|
| 510 |
+
"eval_samples_per_second": 9.855,
|
| 511 |
+
"eval_steps_per_second": 0.622,
|
| 512 |
+
"step": 590
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 10.007122507122507,
|
| 516 |
+
"grad_norm": 1.9087872505187988,
|
| 517 |
+
"learning_rate": 3.1828978622327794e-05,
|
| 518 |
+
"loss": 0.1958,
|
| 519 |
+
"step": 600
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 10.014245014245015,
|
| 523 |
+
"grad_norm": 6.443134307861328,
|
| 524 |
+
"learning_rate": 3.143309580364212e-05,
|
| 525 |
+
"loss": 0.2865,
|
| 526 |
+
"step": 610
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 10.021367521367521,
|
| 530 |
+
"grad_norm": 5.271445274353027,
|
| 531 |
+
"learning_rate": 3.1037212984956455e-05,
|
| 532 |
+
"loss": 0.2709,
|
| 533 |
+
"step": 620
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 10.028490028490028,
|
| 537 |
+
"grad_norm": 5.430334568023682,
|
| 538 |
+
"learning_rate": 3.064133016627079e-05,
|
| 539 |
+
"loss": 0.3552,
|
| 540 |
+
"step": 630
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 10.035612535612536,
|
| 544 |
+
"grad_norm": 8.00438117980957,
|
| 545 |
+
"learning_rate": 3.0245447347585115e-05,
|
| 546 |
+
"loss": 0.2236,
|
| 547 |
+
"step": 640
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 10.042022792022792,
|
| 551 |
+
"eval_accuracy": 0.6553398058252428,
|
| 552 |
+
"eval_loss": 1.3206462860107422,
|
| 553 |
+
"eval_runtime": 18.1657,
|
| 554 |
+
"eval_samples_per_second": 11.34,
|
| 555 |
+
"eval_steps_per_second": 0.716,
|
| 556 |
+
"step": 649
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 11.000712250712251,
|
| 560 |
+
"grad_norm": 8.367637634277344,
|
| 561 |
+
"learning_rate": 2.984956452889945e-05,
|
| 562 |
+
"loss": 0.2997,
|
| 563 |
+
"step": 650
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 11.007834757834758,
|
| 567 |
+
"grad_norm": 4.96151065826416,
|
| 568 |
+
"learning_rate": 2.9453681710213776e-05,
|
| 569 |
+
"loss": 0.2366,
|
| 570 |
+
"step": 660
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 11.014957264957266,
|
| 574 |
+
"grad_norm": 4.967086315155029,
|
| 575 |
+
"learning_rate": 2.905779889152811e-05,
|
| 576 |
+
"loss": 0.2191,
|
| 577 |
+
"step": 670
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 11.022079772079772,
|
| 581 |
+
"grad_norm": 5.6478095054626465,
|
| 582 |
+
"learning_rate": 2.8661916072842436e-05,
|
| 583 |
+
"loss": 0.2042,
|
| 584 |
+
"step": 680
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 11.029202279202279,
|
| 588 |
+
"grad_norm": 15.652437210083008,
|
| 589 |
+
"learning_rate": 2.826603325415677e-05,
|
| 590 |
+
"loss": 0.2747,
|
| 591 |
+
"step": 690
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 11.036324786324787,
|
| 595 |
+
"grad_norm": 4.030658721923828,
|
| 596 |
+
"learning_rate": 2.7870150435471103e-05,
|
| 597 |
+
"loss": 0.1756,
|
| 598 |
+
"step": 700
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 11.042022792022792,
|
| 602 |
+
"eval_accuracy": 0.6601941747572816,
|
| 603 |
+
"eval_loss": 1.5112863779067993,
|
| 604 |
+
"eval_runtime": 18.776,
|
| 605 |
+
"eval_samples_per_second": 10.971,
|
| 606 |
+
"eval_steps_per_second": 0.692,
|
| 607 |
+
"step": 708
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 12.001424501424502,
|
| 611 |
+
"grad_norm": 3.84013295173645,
|
| 612 |
+
"learning_rate": 2.7474267616785433e-05,
|
| 613 |
+
"loss": 0.1714,
|
| 614 |
+
"step": 710
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 12.008547008547009,
|
| 618 |
+
"grad_norm": 5.428359508514404,
|
| 619 |
+
"learning_rate": 2.7078384798099763e-05,
|
| 620 |
+
"loss": 0.2056,
|
| 621 |
+
"step": 720
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.015669515669515,
|
| 625 |
+
"grad_norm": 5.529027938842773,
|
| 626 |
+
"learning_rate": 2.6682501979414094e-05,
|
| 627 |
+
"loss": 0.1018,
|
| 628 |
+
"step": 730
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 12.022792022792023,
|
| 632 |
+
"grad_norm": 5.976778984069824,
|
| 633 |
+
"learning_rate": 2.6286619160728427e-05,
|
| 634 |
+
"loss": 0.0961,
|
| 635 |
+
"step": 740
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 12.02991452991453,
|
| 639 |
+
"grad_norm": 6.043054580688477,
|
| 640 |
+
"learning_rate": 2.5890736342042754e-05,
|
| 641 |
+
"loss": 0.2393,
|
| 642 |
+
"step": 750
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 12.037037037037036,
|
| 646 |
+
"grad_norm": 4.8577656745910645,
|
| 647 |
+
"learning_rate": 2.5494853523357088e-05,
|
| 648 |
+
"loss": 0.1341,
|
| 649 |
+
"step": 760
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 12.042022792022792,
|
| 653 |
+
"eval_accuracy": 0.6407766990291263,
|
| 654 |
+
"eval_loss": 1.6544133424758911,
|
| 655 |
+
"eval_runtime": 18.7553,
|
| 656 |
+
"eval_samples_per_second": 10.984,
|
| 657 |
+
"eval_steps_per_second": 0.693,
|
| 658 |
+
"step": 767
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 13.002136752136753,
|
| 662 |
+
"grad_norm": 3.0963165760040283,
|
| 663 |
+
"learning_rate": 2.509897070467142e-05,
|
| 664 |
+
"loss": 0.1632,
|
| 665 |
+
"step": 770
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 13.00925925925926,
|
| 669 |
+
"grad_norm": 1.0908960103988647,
|
| 670 |
+
"learning_rate": 2.4703087885985748e-05,
|
| 671 |
+
"loss": 0.1377,
|
| 672 |
+
"step": 780
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 13.016381766381766,
|
| 676 |
+
"grad_norm": 13.51460075378418,
|
| 677 |
+
"learning_rate": 2.4307205067300078e-05,
|
| 678 |
+
"loss": 0.1605,
|
| 679 |
+
"step": 790
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 13.023504273504274,
|
| 683 |
+
"grad_norm": 3.4943864345550537,
|
| 684 |
+
"learning_rate": 2.3911322248614412e-05,
|
| 685 |
+
"loss": 0.1576,
|
| 686 |
+
"step": 800
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 13.03062678062678,
|
| 690 |
+
"grad_norm": 3.6334426403045654,
|
| 691 |
+
"learning_rate": 2.3515439429928742e-05,
|
| 692 |
+
"loss": 0.1366,
|
| 693 |
+
"step": 810
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 13.037749287749287,
|
| 697 |
+
"grad_norm": 1.571234107017517,
|
| 698 |
+
"learning_rate": 2.3119556611243072e-05,
|
| 699 |
+
"loss": 0.0823,
|
| 700 |
+
"step": 820
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 13.042022792022792,
|
| 704 |
+
"eval_accuracy": 0.6553398058252428,
|
| 705 |
+
"eval_loss": 1.61236572265625,
|
| 706 |
+
"eval_runtime": 18.782,
|
| 707 |
+
"eval_samples_per_second": 10.968,
|
| 708 |
+
"eval_steps_per_second": 0.692,
|
| 709 |
+
"step": 826
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 14.002849002849002,
|
| 713 |
+
"grad_norm": 6.992094039916992,
|
| 714 |
+
"learning_rate": 2.2723673792557402e-05,
|
| 715 |
+
"loss": 0.0825,
|
| 716 |
+
"step": 830
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 14.00997150997151,
|
| 720 |
+
"grad_norm": 0.7775176763534546,
|
| 721 |
+
"learning_rate": 2.2327790973871736e-05,
|
| 722 |
+
"loss": 0.0993,
|
| 723 |
+
"step": 840
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 14.017094017094017,
|
| 727 |
+
"grad_norm": 5.0337700843811035,
|
| 728 |
+
"learning_rate": 2.1931908155186066e-05,
|
| 729 |
+
"loss": 0.0713,
|
| 730 |
+
"step": 850
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 14.024216524216524,
|
| 734 |
+
"grad_norm": 0.6653324365615845,
|
| 735 |
+
"learning_rate": 2.1536025336500396e-05,
|
| 736 |
+
"loss": 0.1065,
|
| 737 |
+
"step": 860
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 14.031339031339032,
|
| 741 |
+
"grad_norm": 11.971256256103516,
|
| 742 |
+
"learning_rate": 2.114014251781473e-05,
|
| 743 |
+
"loss": 0.144,
|
| 744 |
+
"step": 870
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 14.038461538461538,
|
| 748 |
+
"grad_norm": 10.947636604309082,
|
| 749 |
+
"learning_rate": 2.074425969912906e-05,
|
| 750 |
+
"loss": 0.0691,
|
| 751 |
+
"step": 880
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 14.042022792022792,
|
| 755 |
+
"eval_accuracy": 0.6456310679611651,
|
| 756 |
+
"eval_loss": 1.8230090141296387,
|
| 757 |
+
"eval_runtime": 17.8025,
|
| 758 |
+
"eval_samples_per_second": 11.571,
|
| 759 |
+
"eval_steps_per_second": 0.73,
|
| 760 |
+
"step": 885
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 14.042022792022792,
|
| 764 |
+
"step": 885,
|
| 765 |
+
"total_flos": 6.204645759270519e+19,
|
| 766 |
+
"train_loss": 0.8409665932847281,
|
| 767 |
+
"train_runtime": 3290.4789,
|
| 768 |
+
"train_samples_per_second": 6.827,
|
| 769 |
+
"train_steps_per_second": 0.427
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 14.042022792022792,
|
| 773 |
+
"eval_accuracy": 0.6146341463414634,
|
| 774 |
+
"eval_loss": 1.5203598737716675,
|
| 775 |
+
"eval_runtime": 24.6199,
|
| 776 |
+
"eval_samples_per_second": 8.327,
|
| 777 |
+
"eval_steps_per_second": 0.528,
|
| 778 |
+
"step": 885
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 14.042022792022792,
|
| 782 |
+
"eval_accuracy": 0.6146341463414634,
|
| 783 |
+
"eval_loss": 1.5239903926849365,
|
| 784 |
+
"eval_runtime": 17.6083,
|
| 785 |
+
"eval_samples_per_second": 11.642,
|
| 786 |
+
"eval_steps_per_second": 0.738,
|
| 787 |
+
"step": 885
|
| 788 |
+
}
|
| 789 |
+
],
|
| 790 |
+
"logging_steps": 10,
|
| 791 |
+
"max_steps": 1404,
|
| 792 |
+
"num_input_tokens_seen": 0,
|
| 793 |
+
"num_train_epochs": 9223372036854775807,
|
| 794 |
+
"save_steps": 500,
|
| 795 |
+
"stateful_callbacks": {
|
| 796 |
+
"EarlyStoppingCallback": {
|
| 797 |
+
"args": {
|
| 798 |
+
"early_stopping_patience": 3,
|
| 799 |
+
"early_stopping_threshold": 0.0
|
| 800 |
+
},
|
| 801 |
+
"attributes": {
|
| 802 |
+
"early_stopping_patience_counter": 0
|
| 803 |
+
}
|
| 804 |
+
},
|
| 805 |
+
"TrainerControl": {
|
| 806 |
+
"args": {
|
| 807 |
+
"should_epoch_stop": false,
|
| 808 |
+
"should_evaluate": false,
|
| 809 |
+
"should_log": false,
|
| 810 |
+
"should_save": true,
|
| 811 |
+
"should_training_stop": true
|
| 812 |
+
},
|
| 813 |
+
"attributes": {}
|
| 814 |
+
}
|
| 815 |
+
},
|
| 816 |
+
"total_flos": 6.204645759270519e+19,
|
| 817 |
+
"train_batch_size": 16,
|
| 818 |
+
"trial_name": null,
|
| 819 |
+
"trial_params": null
|
| 820 |
+
}
|