End of training
Browse files- README.md +2 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan18_08-35-09_850581c2dd71/events.out.tfevents.1737189952.850581c2dd71.12583.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +723 -0
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2067
|
| 22 |
+
- Accuracy: 0.9589
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.585365853658537,
|
| 3 |
+
"eval_accuracy": 0.958904109589041,
|
| 4 |
+
"eval_loss": 0.20672719180583954,
|
| 5 |
+
"eval_runtime": 0.711,
|
| 6 |
+
"eval_samples_per_second": 102.672,
|
| 7 |
+
"eval_steps_per_second": 7.032,
|
| 8 |
+
"total_flos": 6.102198151010058e+17,
|
| 9 |
+
"train_loss": 0.7502146526177724,
|
| 10 |
+
"train_runtime": 483.2384,
|
| 11 |
+
"train_samples_per_second": 40.725,
|
| 12 |
+
"train_steps_per_second": 1.242
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.585365853658537,
|
| 3 |
+
"eval_accuracy": 0.958904109589041,
|
| 4 |
+
"eval_loss": 0.20672719180583954,
|
| 5 |
+
"eval_runtime": 0.711,
|
| 6 |
+
"eval_samples_per_second": 102.672,
|
| 7 |
+
"eval_steps_per_second": 7.032
|
| 8 |
+
}
|
runs/Jan18_08-35-09_850581c2dd71/events.out.tfevents.1737189952.850581c2dd71.12583.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1251f051479cc656c850dd2a01cd47db369a7ab203eebf5de1e4899ffaa00b52
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 28.585365853658537,
|
| 3 |
+
"total_flos": 6.102198151010058e+17,
|
| 4 |
+
"train_loss": 0.7502146526177724,
|
| 5 |
+
"train_runtime": 483.2384,
|
| 6 |
+
"train_samples_per_second": 40.725,
|
| 7 |
+
"train_steps_per_second": 1.242
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.958904109589041,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-humeda-DAV3/checkpoint-525",
|
| 4 |
+
"epoch": 28.585365853658537,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.4878048780487805,
|
| 13 |
+
"grad_norm": 12.429728507995605,
|
| 14 |
+
"learning_rate": 9.999999999999999e-06,
|
| 15 |
+
"loss": 4.7086,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.975609756097561,
|
| 20 |
+
"grad_norm": 15.98269271850586,
|
| 21 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 22 |
+
"loss": 3.9845,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.3424657534246575,
|
| 28 |
+
"eval_loss": 1.6832486391067505,
|
| 29 |
+
"eval_runtime": 0.6873,
|
| 30 |
+
"eval_samples_per_second": 106.209,
|
| 31 |
+
"eval_steps_per_second": 7.275,
|
| 32 |
+
"step": 21
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.4390243902439024,
|
| 36 |
+
"grad_norm": 19.85782814025879,
|
| 37 |
+
"learning_rate": 3e-05,
|
| 38 |
+
"loss": 2.9173,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.9268292682926829,
|
| 43 |
+
"grad_norm": 23.9186954498291,
|
| 44 |
+
"learning_rate": 2.9473684210526314e-05,
|
| 45 |
+
"loss": 2.4369,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0,
|
| 50 |
+
"eval_accuracy": 0.4383561643835616,
|
| 51 |
+
"eval_loss": 1.1981052160263062,
|
| 52 |
+
"eval_runtime": 0.7433,
|
| 53 |
+
"eval_samples_per_second": 98.212,
|
| 54 |
+
"eval_steps_per_second": 6.727,
|
| 55 |
+
"step": 42
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.3902439024390243,
|
| 59 |
+
"grad_norm": 39.31980895996094,
|
| 60 |
+
"learning_rate": 2.8947368421052634e-05,
|
| 61 |
+
"loss": 1.9976,
|
| 62 |
+
"step": 50
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.8780487804878048,
|
| 66 |
+
"grad_norm": 34.83562469482422,
|
| 67 |
+
"learning_rate": 2.8421052631578946e-05,
|
| 68 |
+
"loss": 1.7752,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.0,
|
| 73 |
+
"eval_accuracy": 0.6301369863013698,
|
| 74 |
+
"eval_loss": 0.8411616086959839,
|
| 75 |
+
"eval_runtime": 0.7016,
|
| 76 |
+
"eval_samples_per_second": 104.055,
|
| 77 |
+
"eval_steps_per_second": 7.127,
|
| 78 |
+
"step": 63
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.341463414634146,
|
| 82 |
+
"grad_norm": 24.540483474731445,
|
| 83 |
+
"learning_rate": 2.7894736842105263e-05,
|
| 84 |
+
"loss": 1.5326,
|
| 85 |
+
"step": 70
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.8292682926829267,
|
| 89 |
+
"grad_norm": 33.162715911865234,
|
| 90 |
+
"learning_rate": 2.736842105263158e-05,
|
| 91 |
+
"loss": 1.3772,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.0,
|
| 96 |
+
"eval_accuracy": 0.7123287671232876,
|
| 97 |
+
"eval_loss": 0.7895165681838989,
|
| 98 |
+
"eval_runtime": 0.6266,
|
| 99 |
+
"eval_samples_per_second": 116.511,
|
| 100 |
+
"eval_steps_per_second": 7.98,
|
| 101 |
+
"step": 84
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.2926829268292686,
|
| 105 |
+
"grad_norm": 21.98711585998535,
|
| 106 |
+
"learning_rate": 2.6842105263157896e-05,
|
| 107 |
+
"loss": 1.414,
|
| 108 |
+
"step": 90
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.780487804878049,
|
| 112 |
+
"grad_norm": 27.87204360961914,
|
| 113 |
+
"learning_rate": 2.631578947368421e-05,
|
| 114 |
+
"loss": 1.1556,
|
| 115 |
+
"step": 100
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.0,
|
| 119 |
+
"eval_accuracy": 0.7808219178082192,
|
| 120 |
+
"eval_loss": 0.7384896874427795,
|
| 121 |
+
"eval_runtime": 0.6327,
|
| 122 |
+
"eval_samples_per_second": 115.385,
|
| 123 |
+
"eval_steps_per_second": 7.903,
|
| 124 |
+
"step": 105
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 5.2439024390243905,
|
| 128 |
+
"grad_norm": 24.45848274230957,
|
| 129 |
+
"learning_rate": 2.578947368421053e-05,
|
| 130 |
+
"loss": 1.0818,
|
| 131 |
+
"step": 110
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 5.7317073170731705,
|
| 135 |
+
"grad_norm": 16.963436126708984,
|
| 136 |
+
"learning_rate": 2.526315789473684e-05,
|
| 137 |
+
"loss": 1.0059,
|
| 138 |
+
"step": 120
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 6.0,
|
| 142 |
+
"eval_accuracy": 0.8082191780821918,
|
| 143 |
+
"eval_loss": 0.6626368165016174,
|
| 144 |
+
"eval_runtime": 0.6356,
|
| 145 |
+
"eval_samples_per_second": 114.844,
|
| 146 |
+
"eval_steps_per_second": 7.866,
|
| 147 |
+
"step": 126
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.195121951219512,
|
| 151 |
+
"grad_norm": 45.89384460449219,
|
| 152 |
+
"learning_rate": 2.4736842105263158e-05,
|
| 153 |
+
"loss": 0.9054,
|
| 154 |
+
"step": 130
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.682926829268292,
|
| 158 |
+
"grad_norm": 27.633718490600586,
|
| 159 |
+
"learning_rate": 2.4210526315789474e-05,
|
| 160 |
+
"loss": 0.8598,
|
| 161 |
+
"step": 140
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 7.0,
|
| 165 |
+
"eval_accuracy": 0.7808219178082192,
|
| 166 |
+
"eval_loss": 0.5402742624282837,
|
| 167 |
+
"eval_runtime": 0.6334,
|
| 168 |
+
"eval_samples_per_second": 115.247,
|
| 169 |
+
"eval_steps_per_second": 7.894,
|
| 170 |
+
"step": 147
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.146341463414634,
|
| 174 |
+
"grad_norm": 25.943758010864258,
|
| 175 |
+
"learning_rate": 2.368421052631579e-05,
|
| 176 |
+
"loss": 0.8268,
|
| 177 |
+
"step": 150
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.634146341463414,
|
| 181 |
+
"grad_norm": 37.037078857421875,
|
| 182 |
+
"learning_rate": 2.3157894736842103e-05,
|
| 183 |
+
"loss": 0.8724,
|
| 184 |
+
"step": 160
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 8.0,
|
| 188 |
+
"eval_accuracy": 0.821917808219178,
|
| 189 |
+
"eval_loss": 0.5519894361495972,
|
| 190 |
+
"eval_runtime": 0.6379,
|
| 191 |
+
"eval_samples_per_second": 114.432,
|
| 192 |
+
"eval_steps_per_second": 7.838,
|
| 193 |
+
"step": 168
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 8.097560975609756,
|
| 197 |
+
"grad_norm": 22.22051429748535,
|
| 198 |
+
"learning_rate": 2.2631578947368423e-05,
|
| 199 |
+
"loss": 0.7427,
|
| 200 |
+
"step": 170
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.585365853658537,
|
| 204 |
+
"grad_norm": 33.7209587097168,
|
| 205 |
+
"learning_rate": 2.2105263157894736e-05,
|
| 206 |
+
"loss": 0.7096,
|
| 207 |
+
"step": 180
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.0,
|
| 211 |
+
"eval_accuracy": 0.8356164383561644,
|
| 212 |
+
"eval_loss": 0.5182141661643982,
|
| 213 |
+
"eval_runtime": 0.7436,
|
| 214 |
+
"eval_samples_per_second": 98.169,
|
| 215 |
+
"eval_steps_per_second": 6.724,
|
| 216 |
+
"step": 189
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.048780487804878,
|
| 220 |
+
"grad_norm": 17.677778244018555,
|
| 221 |
+
"learning_rate": 2.1578947368421053e-05,
|
| 222 |
+
"loss": 0.5608,
|
| 223 |
+
"step": 190
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 9.536585365853659,
|
| 227 |
+
"grad_norm": 34.34571075439453,
|
| 228 |
+
"learning_rate": 2.105263157894737e-05,
|
| 229 |
+
"loss": 0.5748,
|
| 230 |
+
"step": 200
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 10.0,
|
| 234 |
+
"grad_norm": 9.038191795349121,
|
| 235 |
+
"learning_rate": 2.0526315789473685e-05,
|
| 236 |
+
"loss": 0.5038,
|
| 237 |
+
"step": 210
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 10.0,
|
| 241 |
+
"eval_accuracy": 0.8493150684931506,
|
| 242 |
+
"eval_loss": 0.4132954180240631,
|
| 243 |
+
"eval_runtime": 0.6251,
|
| 244 |
+
"eval_samples_per_second": 116.788,
|
| 245 |
+
"eval_steps_per_second": 7.999,
|
| 246 |
+
"step": 210
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 10.487804878048781,
|
| 250 |
+
"grad_norm": 31.543596267700195,
|
| 251 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 252 |
+
"loss": 0.5488,
|
| 253 |
+
"step": 220
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 10.975609756097562,
|
| 257 |
+
"grad_norm": 23.798019409179688,
|
| 258 |
+
"learning_rate": 1.9473684210526318e-05,
|
| 259 |
+
"loss": 0.4951,
|
| 260 |
+
"step": 230
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 11.0,
|
| 264 |
+
"eval_accuracy": 0.8767123287671232,
|
| 265 |
+
"eval_loss": 0.3548040986061096,
|
| 266 |
+
"eval_runtime": 0.6389,
|
| 267 |
+
"eval_samples_per_second": 114.257,
|
| 268 |
+
"eval_steps_per_second": 7.826,
|
| 269 |
+
"step": 231
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 11.439024390243903,
|
| 273 |
+
"grad_norm": 16.509632110595703,
|
| 274 |
+
"learning_rate": 1.894736842105263e-05,
|
| 275 |
+
"loss": 0.5018,
|
| 276 |
+
"step": 240
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 11.926829268292684,
|
| 280 |
+
"grad_norm": 17.9029598236084,
|
| 281 |
+
"learning_rate": 1.8421052631578947e-05,
|
| 282 |
+
"loss": 0.4692,
|
| 283 |
+
"step": 250
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 12.0,
|
| 287 |
+
"eval_accuracy": 0.8493150684931506,
|
| 288 |
+
"eval_loss": 0.38450247049331665,
|
| 289 |
+
"eval_runtime": 0.6355,
|
| 290 |
+
"eval_samples_per_second": 114.878,
|
| 291 |
+
"eval_steps_per_second": 7.868,
|
| 292 |
+
"step": 252
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 12.390243902439025,
|
| 296 |
+
"grad_norm": 29.795612335205078,
|
| 297 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 298 |
+
"loss": 0.5316,
|
| 299 |
+
"step": 260
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 12.878048780487806,
|
| 303 |
+
"grad_norm": 14.258842468261719,
|
| 304 |
+
"learning_rate": 1.736842105263158e-05,
|
| 305 |
+
"loss": 0.5339,
|
| 306 |
+
"step": 270
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 13.0,
|
| 310 |
+
"eval_accuracy": 0.8904109589041096,
|
| 311 |
+
"eval_loss": 0.3178386390209198,
|
| 312 |
+
"eval_runtime": 0.6456,
|
| 313 |
+
"eval_samples_per_second": 113.071,
|
| 314 |
+
"eval_steps_per_second": 7.745,
|
| 315 |
+
"step": 273
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 13.341463414634147,
|
| 319 |
+
"grad_norm": 28.944801330566406,
|
| 320 |
+
"learning_rate": 1.6842105263157893e-05,
|
| 321 |
+
"loss": 0.5021,
|
| 322 |
+
"step": 280
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 13.829268292682928,
|
| 326 |
+
"grad_norm": 19.169776916503906,
|
| 327 |
+
"learning_rate": 1.6315789473684213e-05,
|
| 328 |
+
"loss": 0.4536,
|
| 329 |
+
"step": 290
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 14.0,
|
| 333 |
+
"eval_accuracy": 0.8904109589041096,
|
| 334 |
+
"eval_loss": 0.3252336084842682,
|
| 335 |
+
"eval_runtime": 0.6543,
|
| 336 |
+
"eval_samples_per_second": 111.574,
|
| 337 |
+
"eval_steps_per_second": 7.642,
|
| 338 |
+
"step": 294
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 14.292682926829269,
|
| 342 |
+
"grad_norm": 19.354726791381836,
|
| 343 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 344 |
+
"loss": 0.3055,
|
| 345 |
+
"step": 300
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 14.78048780487805,
|
| 349 |
+
"grad_norm": 18.675071716308594,
|
| 350 |
+
"learning_rate": 1.5263157894736842e-05,
|
| 351 |
+
"loss": 0.4369,
|
| 352 |
+
"step": 310
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 15.0,
|
| 356 |
+
"eval_accuracy": 0.8904109589041096,
|
| 357 |
+
"eval_loss": 0.27849265933036804,
|
| 358 |
+
"eval_runtime": 0.6484,
|
| 359 |
+
"eval_samples_per_second": 112.585,
|
| 360 |
+
"eval_steps_per_second": 7.711,
|
| 361 |
+
"step": 315
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 15.24390243902439,
|
| 365 |
+
"grad_norm": 29.19399642944336,
|
| 366 |
+
"learning_rate": 1.4736842105263157e-05,
|
| 367 |
+
"loss": 0.447,
|
| 368 |
+
"step": 320
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 15.731707317073171,
|
| 372 |
+
"grad_norm": 5.669158935546875,
|
| 373 |
+
"learning_rate": 1.4210526315789473e-05,
|
| 374 |
+
"loss": 0.3941,
|
| 375 |
+
"step": 330
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 16.0,
|
| 379 |
+
"eval_accuracy": 0.9041095890410958,
|
| 380 |
+
"eval_loss": 0.28995245695114136,
|
| 381 |
+
"eval_runtime": 0.6348,
|
| 382 |
+
"eval_samples_per_second": 114.996,
|
| 383 |
+
"eval_steps_per_second": 7.876,
|
| 384 |
+
"step": 336
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 16.195121951219512,
|
| 388 |
+
"grad_norm": 21.81118392944336,
|
| 389 |
+
"learning_rate": 1.368421052631579e-05,
|
| 390 |
+
"loss": 0.3228,
|
| 391 |
+
"step": 340
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 16.682926829268293,
|
| 395 |
+
"grad_norm": 34.80079650878906,
|
| 396 |
+
"learning_rate": 1.3157894736842104e-05,
|
| 397 |
+
"loss": 0.4363,
|
| 398 |
+
"step": 350
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 17.0,
|
| 402 |
+
"eval_accuracy": 0.863013698630137,
|
| 403 |
+
"eval_loss": 0.3426441252231598,
|
| 404 |
+
"eval_runtime": 0.6573,
|
| 405 |
+
"eval_samples_per_second": 111.053,
|
| 406 |
+
"eval_steps_per_second": 7.606,
|
| 407 |
+
"step": 357
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 17.146341463414632,
|
| 411 |
+
"grad_norm": 25.49156379699707,
|
| 412 |
+
"learning_rate": 1.263157894736842e-05,
|
| 413 |
+
"loss": 0.3729,
|
| 414 |
+
"step": 360
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 17.634146341463413,
|
| 418 |
+
"grad_norm": 25.156068801879883,
|
| 419 |
+
"learning_rate": 1.2105263157894737e-05,
|
| 420 |
+
"loss": 0.2819,
|
| 421 |
+
"step": 370
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 18.0,
|
| 425 |
+
"eval_accuracy": 0.9041095890410958,
|
| 426 |
+
"eval_loss": 0.283920019865036,
|
| 427 |
+
"eval_runtime": 0.7572,
|
| 428 |
+
"eval_samples_per_second": 96.41,
|
| 429 |
+
"eval_steps_per_second": 6.603,
|
| 430 |
+
"step": 378
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 18.097560975609756,
|
| 434 |
+
"grad_norm": 36.39301300048828,
|
| 435 |
+
"learning_rate": 1.1578947368421052e-05,
|
| 436 |
+
"loss": 0.3253,
|
| 437 |
+
"step": 380
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 18.585365853658537,
|
| 441 |
+
"grad_norm": 24.839868545532227,
|
| 442 |
+
"learning_rate": 1.1052631578947368e-05,
|
| 443 |
+
"loss": 0.361,
|
| 444 |
+
"step": 390
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 19.0,
|
| 448 |
+
"eval_accuracy": 0.9041095890410958,
|
| 449 |
+
"eval_loss": 0.22234712541103363,
|
| 450 |
+
"eval_runtime": 0.7512,
|
| 451 |
+
"eval_samples_per_second": 97.175,
|
| 452 |
+
"eval_steps_per_second": 6.656,
|
| 453 |
+
"step": 399
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 19.048780487804876,
|
| 457 |
+
"grad_norm": 22.352935791015625,
|
| 458 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 459 |
+
"loss": 0.3204,
|
| 460 |
+
"step": 400
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 19.536585365853657,
|
| 464 |
+
"grad_norm": 12.527485847473145,
|
| 465 |
+
"learning_rate": 9.999999999999999e-06,
|
| 466 |
+
"loss": 0.2965,
|
| 467 |
+
"step": 410
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 20.0,
|
| 471 |
+
"grad_norm": 16.140165328979492,
|
| 472 |
+
"learning_rate": 9.473684210526315e-06,
|
| 473 |
+
"loss": 0.1857,
|
| 474 |
+
"step": 420
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 20.0,
|
| 478 |
+
"eval_accuracy": 0.9178082191780822,
|
| 479 |
+
"eval_loss": 0.25217577815055847,
|
| 480 |
+
"eval_runtime": 0.6292,
|
| 481 |
+
"eval_samples_per_second": 116.026,
|
| 482 |
+
"eval_steps_per_second": 7.947,
|
| 483 |
+
"step": 420
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 20.48780487804878,
|
| 487 |
+
"grad_norm": 12.794975280761719,
|
| 488 |
+
"learning_rate": 8.947368421052632e-06,
|
| 489 |
+
"loss": 0.1904,
|
| 490 |
+
"step": 430
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 20.975609756097562,
|
| 494 |
+
"grad_norm": 32.452125549316406,
|
| 495 |
+
"learning_rate": 8.421052631578947e-06,
|
| 496 |
+
"loss": 0.3161,
|
| 497 |
+
"step": 440
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 21.0,
|
| 501 |
+
"eval_accuracy": 0.9178082191780822,
|
| 502 |
+
"eval_loss": 0.21637919545173645,
|
| 503 |
+
"eval_runtime": 0.6487,
|
| 504 |
+
"eval_samples_per_second": 112.528,
|
| 505 |
+
"eval_steps_per_second": 7.707,
|
| 506 |
+
"step": 441
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 21.4390243902439,
|
| 510 |
+
"grad_norm": 17.289514541625977,
|
| 511 |
+
"learning_rate": 7.894736842105263e-06,
|
| 512 |
+
"loss": 0.2523,
|
| 513 |
+
"step": 450
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 21.926829268292682,
|
| 517 |
+
"grad_norm": 42.501861572265625,
|
| 518 |
+
"learning_rate": 7.3684210526315784e-06,
|
| 519 |
+
"loss": 0.3273,
|
| 520 |
+
"step": 460
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 22.0,
|
| 524 |
+
"eval_accuracy": 0.9315068493150684,
|
| 525 |
+
"eval_loss": 0.22238127887248993,
|
| 526 |
+
"eval_runtime": 0.6384,
|
| 527 |
+
"eval_samples_per_second": 114.34,
|
| 528 |
+
"eval_steps_per_second": 7.831,
|
| 529 |
+
"step": 462
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 22.390243902439025,
|
| 533 |
+
"grad_norm": 32.69398498535156,
|
| 534 |
+
"learning_rate": 6.842105263157895e-06,
|
| 535 |
+
"loss": 0.1996,
|
| 536 |
+
"step": 470
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 22.878048780487806,
|
| 540 |
+
"grad_norm": 21.498504638671875,
|
| 541 |
+
"learning_rate": 6.31578947368421e-06,
|
| 542 |
+
"loss": 0.3458,
|
| 543 |
+
"step": 480
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 23.0,
|
| 547 |
+
"eval_accuracy": 0.9452054794520548,
|
| 548 |
+
"eval_loss": 0.21988777816295624,
|
| 549 |
+
"eval_runtime": 0.7497,
|
| 550 |
+
"eval_samples_per_second": 97.368,
|
| 551 |
+
"eval_steps_per_second": 6.669,
|
| 552 |
+
"step": 483
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 23.341463414634145,
|
| 556 |
+
"grad_norm": 8.661595344543457,
|
| 557 |
+
"learning_rate": 5.789473684210526e-06,
|
| 558 |
+
"loss": 0.2248,
|
| 559 |
+
"step": 490
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 23.829268292682926,
|
| 563 |
+
"grad_norm": 23.505203247070312,
|
| 564 |
+
"learning_rate": 5.263157894736842e-06,
|
| 565 |
+
"loss": 0.337,
|
| 566 |
+
"step": 500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 24.0,
|
| 570 |
+
"eval_accuracy": 0.9315068493150684,
|
| 571 |
+
"eval_loss": 0.23766528069972992,
|
| 572 |
+
"eval_runtime": 0.768,
|
| 573 |
+
"eval_samples_per_second": 95.058,
|
| 574 |
+
"eval_steps_per_second": 6.511,
|
| 575 |
+
"step": 504
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 24.29268292682927,
|
| 579 |
+
"grad_norm": 13.873770713806152,
|
| 580 |
+
"learning_rate": 4.736842105263158e-06,
|
| 581 |
+
"loss": 0.201,
|
| 582 |
+
"step": 510
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 24.78048780487805,
|
| 586 |
+
"grad_norm": 16.176956176757812,
|
| 587 |
+
"learning_rate": 4.210526315789473e-06,
|
| 588 |
+
"loss": 0.1801,
|
| 589 |
+
"step": 520
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 25.0,
|
| 593 |
+
"eval_accuracy": 0.958904109589041,
|
| 594 |
+
"eval_loss": 0.20672719180583954,
|
| 595 |
+
"eval_runtime": 0.6363,
|
| 596 |
+
"eval_samples_per_second": 114.732,
|
| 597 |
+
"eval_steps_per_second": 7.858,
|
| 598 |
+
"step": 525
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 25.24390243902439,
|
| 602 |
+
"grad_norm": 39.25809097290039,
|
| 603 |
+
"learning_rate": 3.6842105263157892e-06,
|
| 604 |
+
"loss": 0.2077,
|
| 605 |
+
"step": 530
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 25.73170731707317,
|
| 609 |
+
"grad_norm": 46.6181755065918,
|
| 610 |
+
"learning_rate": 3.157894736842105e-06,
|
| 611 |
+
"loss": 0.3283,
|
| 612 |
+
"step": 540
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 26.0,
|
| 616 |
+
"eval_accuracy": 0.9315068493150684,
|
| 617 |
+
"eval_loss": 0.24006159603595734,
|
| 618 |
+
"eval_runtime": 0.6339,
|
| 619 |
+
"eval_samples_per_second": 115.158,
|
| 620 |
+
"eval_steps_per_second": 7.888,
|
| 621 |
+
"step": 546
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 26.195121951219512,
|
| 625 |
+
"grad_norm": 10.685463905334473,
|
| 626 |
+
"learning_rate": 2.631578947368421e-06,
|
| 627 |
+
"loss": 0.3054,
|
| 628 |
+
"step": 550
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 26.682926829268293,
|
| 632 |
+
"grad_norm": 28.955364227294922,
|
| 633 |
+
"learning_rate": 2.1052631578947366e-06,
|
| 634 |
+
"loss": 0.2211,
|
| 635 |
+
"step": 560
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 27.0,
|
| 639 |
+
"eval_accuracy": 0.9315068493150684,
|
| 640 |
+
"eval_loss": 0.21667610108852386,
|
| 641 |
+
"eval_runtime": 0.6327,
|
| 642 |
+
"eval_samples_per_second": 115.37,
|
| 643 |
+
"eval_steps_per_second": 7.902,
|
| 644 |
+
"step": 567
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 27.146341463414632,
|
| 648 |
+
"grad_norm": 20.726945877075195,
|
| 649 |
+
"learning_rate": 1.5789473684210526e-06,
|
| 650 |
+
"loss": 0.2556,
|
| 651 |
+
"step": 570
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 27.634146341463413,
|
| 655 |
+
"grad_norm": 6.582526206970215,
|
| 656 |
+
"learning_rate": 1.0526315789473683e-06,
|
| 657 |
+
"loss": 0.1783,
|
| 658 |
+
"step": 580
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 28.0,
|
| 662 |
+
"eval_accuracy": 0.9315068493150684,
|
| 663 |
+
"eval_loss": 0.21801576018333435,
|
| 664 |
+
"eval_runtime": 0.6499,
|
| 665 |
+
"eval_samples_per_second": 112.334,
|
| 666 |
+
"eval_steps_per_second": 7.694,
|
| 667 |
+
"step": 588
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 28.097560975609756,
|
| 671 |
+
"grad_norm": 16.22028923034668,
|
| 672 |
+
"learning_rate": 5.263157894736842e-07,
|
| 673 |
+
"loss": 0.1982,
|
| 674 |
+
"step": 590
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 28.585365853658537,
|
| 678 |
+
"grad_norm": 15.770591735839844,
|
| 679 |
+
"learning_rate": 0.0,
|
| 680 |
+
"loss": 0.2783,
|
| 681 |
+
"step": 600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 28.585365853658537,
|
| 685 |
+
"eval_accuracy": 0.9315068493150684,
|
| 686 |
+
"eval_loss": 0.22231744229793549,
|
| 687 |
+
"eval_runtime": 0.8149,
|
| 688 |
+
"eval_samples_per_second": 89.581,
|
| 689 |
+
"eval_steps_per_second": 6.136,
|
| 690 |
+
"step": 600
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 28.585365853658537,
|
| 694 |
+
"step": 600,
|
| 695 |
+
"total_flos": 6.102198151010058e+17,
|
| 696 |
+
"train_loss": 0.7502146526177724,
|
| 697 |
+
"train_runtime": 483.2384,
|
| 698 |
+
"train_samples_per_second": 40.725,
|
| 699 |
+
"train_steps_per_second": 1.242
|
| 700 |
+
}
|
| 701 |
+
],
|
| 702 |
+
"logging_steps": 10,
|
| 703 |
+
"max_steps": 600,
|
| 704 |
+
"num_input_tokens_seen": 0,
|
| 705 |
+
"num_train_epochs": 30,
|
| 706 |
+
"save_steps": 500,
|
| 707 |
+
"stateful_callbacks": {
|
| 708 |
+
"TrainerControl": {
|
| 709 |
+
"args": {
|
| 710 |
+
"should_epoch_stop": false,
|
| 711 |
+
"should_evaluate": false,
|
| 712 |
+
"should_log": false,
|
| 713 |
+
"should_save": true,
|
| 714 |
+
"should_training_stop": true
|
| 715 |
+
},
|
| 716 |
+
"attributes": {}
|
| 717 |
+
}
|
| 718 |
+
},
|
| 719 |
+
"total_flos": 6.102198151010058e+17,
|
| 720 |
+
"train_batch_size": 16,
|
| 721 |
+
"trial_name": null,
|
| 722 |
+
"trial_params": null
|
| 723 |
+
}
|