End of training
Browse files- README.md +2 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Mar10_03-39-18_ab7c5e129afd/events.out.tfevents.1741578838.ab7c5e129afd.2134.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +766 -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: 0.5934
|
| 22 |
+
- Accuracy: 0.8333
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.96296296296296,
|
| 3 |
+
"eval_accuracy": 0.8333333333333334,
|
| 4 |
+
"eval_loss": 0.593357503414154,
|
| 5 |
+
"eval_runtime": 2.7963,
|
| 6 |
+
"eval_samples_per_second": 81.536,
|
| 7 |
+
"eval_steps_per_second": 5.364,
|
| 8 |
+
"total_flos": 1.1031361417201582e+18,
|
| 9 |
+
"train_loss": 0.543996471625108,
|
| 10 |
+
"train_runtime": 850.8149,
|
| 11 |
+
"train_samples_per_second": 40.103,
|
| 12 |
+
"train_steps_per_second": 0.611
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.96296296296296,
|
| 3 |
+
"eval_accuracy": 0.8333333333333334,
|
| 4 |
+
"eval_loss": 0.593357503414154,
|
| 5 |
+
"eval_runtime": 2.7963,
|
| 6 |
+
"eval_samples_per_second": 81.536,
|
| 7 |
+
"eval_steps_per_second": 5.364
|
| 8 |
+
}
|
runs/Mar10_03-39-18_ab7c5e129afd/events.out.tfevents.1741578838.ab7c5e129afd.2134.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:482e829f2573ecca78d1bf0fcd04be9ec6bfbe572d10418d075bce6d7fe9d203
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 39.96296296296296,
|
| 3 |
+
"total_flos": 1.1031361417201582e+18,
|
| 4 |
+
"train_loss": 0.543996471625108,
|
| 5 |
+
"train_runtime": 850.8149,
|
| 6 |
+
"train_samples_per_second": 40.103,
|
| 7 |
+
"train_steps_per_second": 0.611
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,766 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8333333333333334,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-humeda-DAV60/checkpoint-377",
|
| 4 |
+
"epoch": 39.96296296296296,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 520,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7407407407407407,
|
| 13 |
+
"grad_norm": 4.973352909088135,
|
| 14 |
+
"learning_rate": 7.692307692307694e-06,
|
| 15 |
+
"loss": 1.5779,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9629629629629629,
|
| 20 |
+
"eval_accuracy": 0.3508771929824561,
|
| 21 |
+
"eval_loss": 1.5147490501403809,
|
| 22 |
+
"eval_runtime": 3.3598,
|
| 23 |
+
"eval_samples_per_second": 67.86,
|
| 24 |
+
"eval_steps_per_second": 4.465,
|
| 25 |
+
"step": 13
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.5185185185185186,
|
| 29 |
+
"grad_norm": 4.458120822906494,
|
| 30 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 31 |
+
"loss": 1.532,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.9629629629629628,
|
| 36 |
+
"eval_accuracy": 0.5394736842105263,
|
| 37 |
+
"eval_loss": 1.3726485967636108,
|
| 38 |
+
"eval_runtime": 2.7021,
|
| 39 |
+
"eval_samples_per_second": 84.379,
|
| 40 |
+
"eval_steps_per_second": 5.551,
|
| 41 |
+
"step": 26
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.2962962962962963,
|
| 45 |
+
"grad_norm": 4.9333882331848145,
|
| 46 |
+
"learning_rate": 2.3076923076923076e-05,
|
| 47 |
+
"loss": 1.459,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.962962962962963,
|
| 52 |
+
"eval_accuracy": 0.618421052631579,
|
| 53 |
+
"eval_loss": 0.9851850271224976,
|
| 54 |
+
"eval_runtime": 2.7471,
|
| 55 |
+
"eval_samples_per_second": 82.996,
|
| 56 |
+
"eval_steps_per_second": 5.46,
|
| 57 |
+
"step": 39
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.074074074074074,
|
| 61 |
+
"grad_norm": 10.688750267028809,
|
| 62 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 63 |
+
"loss": 1.2696,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.814814814814815,
|
| 68 |
+
"grad_norm": 6.760787010192871,
|
| 69 |
+
"learning_rate": 3.846153846153846e-05,
|
| 70 |
+
"loss": 1.0357,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.962962962962963,
|
| 75 |
+
"eval_accuracy": 0.6140350877192983,
|
| 76 |
+
"eval_loss": 0.8557938933372498,
|
| 77 |
+
"eval_runtime": 3.6391,
|
| 78 |
+
"eval_samples_per_second": 62.653,
|
| 79 |
+
"eval_steps_per_second": 4.122,
|
| 80 |
+
"step": 52
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.592592592592593,
|
| 84 |
+
"grad_norm": 11.264517784118652,
|
| 85 |
+
"learning_rate": 3.931623931623932e-05,
|
| 86 |
+
"loss": 0.9678,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.962962962962963,
|
| 91 |
+
"eval_accuracy": 0.6622807017543859,
|
| 92 |
+
"eval_loss": 0.7997034788131714,
|
| 93 |
+
"eval_runtime": 2.7329,
|
| 94 |
+
"eval_samples_per_second": 83.428,
|
| 95 |
+
"eval_steps_per_second": 5.489,
|
| 96 |
+
"step": 65
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.37037037037037,
|
| 100 |
+
"grad_norm": 15.311161994934082,
|
| 101 |
+
"learning_rate": 3.854700854700855e-05,
|
| 102 |
+
"loss": 0.9602,
|
| 103 |
+
"step": 70
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.962962962962963,
|
| 107 |
+
"eval_accuracy": 0.6710526315789473,
|
| 108 |
+
"eval_loss": 0.7788758277893066,
|
| 109 |
+
"eval_runtime": 2.711,
|
| 110 |
+
"eval_samples_per_second": 84.1,
|
| 111 |
+
"eval_steps_per_second": 5.533,
|
| 112 |
+
"step": 78
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.148148148148148,
|
| 116 |
+
"grad_norm": 11.81164836883545,
|
| 117 |
+
"learning_rate": 3.769230769230769e-05,
|
| 118 |
+
"loss": 0.8906,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.888888888888889,
|
| 123 |
+
"grad_norm": 7.672252178192139,
|
| 124 |
+
"learning_rate": 3.683760683760684e-05,
|
| 125 |
+
"loss": 0.7664,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 6.962962962962963,
|
| 130 |
+
"eval_accuracy": 0.618421052631579,
|
| 131 |
+
"eval_loss": 0.8889743089675903,
|
| 132 |
+
"eval_runtime": 3.499,
|
| 133 |
+
"eval_samples_per_second": 65.161,
|
| 134 |
+
"eval_steps_per_second": 4.287,
|
| 135 |
+
"step": 91
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 7.666666666666667,
|
| 139 |
+
"grad_norm": 11.658954620361328,
|
| 140 |
+
"learning_rate": 3.598290598290599e-05,
|
| 141 |
+
"loss": 0.8537,
|
| 142 |
+
"step": 100
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 7.962962962962963,
|
| 146 |
+
"eval_accuracy": 0.7105263157894737,
|
| 147 |
+
"eval_loss": 0.6859638094902039,
|
| 148 |
+
"eval_runtime": 2.7594,
|
| 149 |
+
"eval_samples_per_second": 82.627,
|
| 150 |
+
"eval_steps_per_second": 5.436,
|
| 151 |
+
"step": 104
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.444444444444445,
|
| 155 |
+
"grad_norm": 10.199373245239258,
|
| 156 |
+
"learning_rate": 3.512820512820513e-05,
|
| 157 |
+
"loss": 0.7566,
|
| 158 |
+
"step": 110
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.962962962962964,
|
| 162 |
+
"eval_accuracy": 0.7587719298245614,
|
| 163 |
+
"eval_loss": 0.6138375401496887,
|
| 164 |
+
"eval_runtime": 2.7859,
|
| 165 |
+
"eval_samples_per_second": 81.842,
|
| 166 |
+
"eval_steps_per_second": 5.384,
|
| 167 |
+
"step": 117
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.222222222222221,
|
| 171 |
+
"grad_norm": 7.8964643478393555,
|
| 172 |
+
"learning_rate": 3.4273504273504276e-05,
|
| 173 |
+
"loss": 0.71,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.962962962962964,
|
| 178 |
+
"grad_norm": 9.411240577697754,
|
| 179 |
+
"learning_rate": 3.341880341880342e-05,
|
| 180 |
+
"loss": 0.7025,
|
| 181 |
+
"step": 130
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 9.962962962962964,
|
| 185 |
+
"eval_accuracy": 0.793859649122807,
|
| 186 |
+
"eval_loss": 0.520746111869812,
|
| 187 |
+
"eval_runtime": 3.1792,
|
| 188 |
+
"eval_samples_per_second": 71.715,
|
| 189 |
+
"eval_steps_per_second": 4.718,
|
| 190 |
+
"step": 130
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 10.74074074074074,
|
| 194 |
+
"grad_norm": 9.329798698425293,
|
| 195 |
+
"learning_rate": 3.2564102564102565e-05,
|
| 196 |
+
"loss": 0.6081,
|
| 197 |
+
"step": 140
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 10.962962962962964,
|
| 201 |
+
"eval_accuracy": 0.7763157894736842,
|
| 202 |
+
"eval_loss": 0.564355731010437,
|
| 203 |
+
"eval_runtime": 2.7404,
|
| 204 |
+
"eval_samples_per_second": 83.199,
|
| 205 |
+
"eval_steps_per_second": 5.474,
|
| 206 |
+
"step": 143
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.518518518518519,
|
| 210 |
+
"grad_norm": 10.05624771118164,
|
| 211 |
+
"learning_rate": 3.170940170940171e-05,
|
| 212 |
+
"loss": 0.631,
|
| 213 |
+
"step": 150
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 11.962962962962964,
|
| 217 |
+
"eval_accuracy": 0.7543859649122807,
|
| 218 |
+
"eval_loss": 0.5858676433563232,
|
| 219 |
+
"eval_runtime": 3.1578,
|
| 220 |
+
"eval_samples_per_second": 72.203,
|
| 221 |
+
"eval_steps_per_second": 4.75,
|
| 222 |
+
"step": 156
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.296296296296296,
|
| 226 |
+
"grad_norm": 11.134556770324707,
|
| 227 |
+
"learning_rate": 3.085470085470086e-05,
|
| 228 |
+
"loss": 0.6163,
|
| 229 |
+
"step": 160
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 12.962962962962964,
|
| 233 |
+
"eval_accuracy": 0.7105263157894737,
|
| 234 |
+
"eval_loss": 0.7182390093803406,
|
| 235 |
+
"eval_runtime": 2.777,
|
| 236 |
+
"eval_samples_per_second": 82.104,
|
| 237 |
+
"eval_steps_per_second": 5.402,
|
| 238 |
+
"step": 169
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 13.074074074074074,
|
| 242 |
+
"grad_norm": 20.01995849609375,
|
| 243 |
+
"learning_rate": 3.0000000000000004e-05,
|
| 244 |
+
"loss": 0.5923,
|
| 245 |
+
"step": 170
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 13.814814814814815,
|
| 249 |
+
"grad_norm": 10.06767463684082,
|
| 250 |
+
"learning_rate": 2.9145299145299145e-05,
|
| 251 |
+
"loss": 0.5743,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 13.962962962962964,
|
| 256 |
+
"eval_accuracy": 0.7763157894736842,
|
| 257 |
+
"eval_loss": 0.5642982125282288,
|
| 258 |
+
"eval_runtime": 2.7113,
|
| 259 |
+
"eval_samples_per_second": 84.092,
|
| 260 |
+
"eval_steps_per_second": 5.532,
|
| 261 |
+
"step": 182
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 14.592592592592592,
|
| 265 |
+
"grad_norm": 9.349576950073242,
|
| 266 |
+
"learning_rate": 2.8290598290598296e-05,
|
| 267 |
+
"loss": 0.5752,
|
| 268 |
+
"step": 190
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 14.962962962962964,
|
| 272 |
+
"eval_accuracy": 0.793859649122807,
|
| 273 |
+
"eval_loss": 0.5027949213981628,
|
| 274 |
+
"eval_runtime": 3.7508,
|
| 275 |
+
"eval_samples_per_second": 60.787,
|
| 276 |
+
"eval_steps_per_second": 3.999,
|
| 277 |
+
"step": 195
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 15.37037037037037,
|
| 281 |
+
"grad_norm": 10.582262992858887,
|
| 282 |
+
"learning_rate": 2.7435897435897437e-05,
|
| 283 |
+
"loss": 0.461,
|
| 284 |
+
"step": 200
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 15.962962962962964,
|
| 288 |
+
"eval_accuracy": 0.7807017543859649,
|
| 289 |
+
"eval_loss": 0.5465320944786072,
|
| 290 |
+
"eval_runtime": 2.755,
|
| 291 |
+
"eval_samples_per_second": 82.76,
|
| 292 |
+
"eval_steps_per_second": 5.445,
|
| 293 |
+
"step": 208
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 16.14814814814815,
|
| 297 |
+
"grad_norm": 9.319547653198242,
|
| 298 |
+
"learning_rate": 2.658119658119658e-05,
|
| 299 |
+
"loss": 0.5056,
|
| 300 |
+
"step": 210
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.88888888888889,
|
| 304 |
+
"grad_norm": 9.023859977722168,
|
| 305 |
+
"learning_rate": 2.5811965811965814e-05,
|
| 306 |
+
"loss": 0.4145,
|
| 307 |
+
"step": 220
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 16.962962962962962,
|
| 311 |
+
"eval_accuracy": 0.7719298245614035,
|
| 312 |
+
"eval_loss": 0.5868436694145203,
|
| 313 |
+
"eval_runtime": 2.6887,
|
| 314 |
+
"eval_samples_per_second": 84.8,
|
| 315 |
+
"eval_steps_per_second": 5.579,
|
| 316 |
+
"step": 221
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 17.666666666666668,
|
| 320 |
+
"grad_norm": 9.497326850891113,
|
| 321 |
+
"learning_rate": 2.495726495726496e-05,
|
| 322 |
+
"loss": 0.4065,
|
| 323 |
+
"step": 230
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 17.962962962962962,
|
| 327 |
+
"eval_accuracy": 0.7807017543859649,
|
| 328 |
+
"eval_loss": 0.5470357537269592,
|
| 329 |
+
"eval_runtime": 3.1034,
|
| 330 |
+
"eval_samples_per_second": 73.467,
|
| 331 |
+
"eval_steps_per_second": 4.833,
|
| 332 |
+
"step": 234
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.444444444444443,
|
| 336 |
+
"grad_norm": 13.887053489685059,
|
| 337 |
+
"learning_rate": 2.4102564102564103e-05,
|
| 338 |
+
"loss": 0.501,
|
| 339 |
+
"step": 240
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.962962962962962,
|
| 343 |
+
"eval_accuracy": 0.793859649122807,
|
| 344 |
+
"eval_loss": 0.5405624508857727,
|
| 345 |
+
"eval_runtime": 2.7248,
|
| 346 |
+
"eval_samples_per_second": 83.677,
|
| 347 |
+
"eval_steps_per_second": 5.505,
|
| 348 |
+
"step": 247
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 19.22222222222222,
|
| 352 |
+
"grad_norm": 9.410223007202148,
|
| 353 |
+
"learning_rate": 2.324786324786325e-05,
|
| 354 |
+
"loss": 0.3938,
|
| 355 |
+
"step": 250
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 19.962962962962962,
|
| 359 |
+
"grad_norm": 12.785265922546387,
|
| 360 |
+
"learning_rate": 2.2393162393162394e-05,
|
| 361 |
+
"loss": 0.4374,
|
| 362 |
+
"step": 260
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 19.962962962962962,
|
| 366 |
+
"eval_accuracy": 0.793859649122807,
|
| 367 |
+
"eval_loss": 0.5533683896064758,
|
| 368 |
+
"eval_runtime": 3.0615,
|
| 369 |
+
"eval_samples_per_second": 74.473,
|
| 370 |
+
"eval_steps_per_second": 4.9,
|
| 371 |
+
"step": 260
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 20.74074074074074,
|
| 375 |
+
"grad_norm": 11.361822128295898,
|
| 376 |
+
"learning_rate": 2.153846153846154e-05,
|
| 377 |
+
"loss": 0.4614,
|
| 378 |
+
"step": 270
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 20.962962962962962,
|
| 382 |
+
"eval_accuracy": 0.8157894736842105,
|
| 383 |
+
"eval_loss": 0.5484946370124817,
|
| 384 |
+
"eval_runtime": 2.7027,
|
| 385 |
+
"eval_samples_per_second": 84.361,
|
| 386 |
+
"eval_steps_per_second": 5.55,
|
| 387 |
+
"step": 273
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 21.51851851851852,
|
| 391 |
+
"grad_norm": 7.663370609283447,
|
| 392 |
+
"learning_rate": 2.0683760683760686e-05,
|
| 393 |
+
"loss": 0.3836,
|
| 394 |
+
"step": 280
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 21.962962962962962,
|
| 398 |
+
"eval_accuracy": 0.7850877192982456,
|
| 399 |
+
"eval_loss": 0.6217398643493652,
|
| 400 |
+
"eval_runtime": 2.7487,
|
| 401 |
+
"eval_samples_per_second": 82.948,
|
| 402 |
+
"eval_steps_per_second": 5.457,
|
| 403 |
+
"step": 286
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 22.296296296296298,
|
| 407 |
+
"grad_norm": 8.853464126586914,
|
| 408 |
+
"learning_rate": 1.982905982905983e-05,
|
| 409 |
+
"loss": 0.4474,
|
| 410 |
+
"step": 290
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 22.962962962962962,
|
| 414 |
+
"eval_accuracy": 0.7763157894736842,
|
| 415 |
+
"eval_loss": 0.6068528294563293,
|
| 416 |
+
"eval_runtime": 3.6122,
|
| 417 |
+
"eval_samples_per_second": 63.12,
|
| 418 |
+
"eval_steps_per_second": 4.153,
|
| 419 |
+
"step": 299
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 23.074074074074073,
|
| 423 |
+
"grad_norm": 15.08626937866211,
|
| 424 |
+
"learning_rate": 1.8974358974358975e-05,
|
| 425 |
+
"loss": 0.3285,
|
| 426 |
+
"step": 300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 23.814814814814813,
|
| 430 |
+
"grad_norm": 14.73444938659668,
|
| 431 |
+
"learning_rate": 1.8119658119658122e-05,
|
| 432 |
+
"loss": 0.3893,
|
| 433 |
+
"step": 310
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 23.962962962962962,
|
| 437 |
+
"eval_accuracy": 0.793859649122807,
|
| 438 |
+
"eval_loss": 0.5980626344680786,
|
| 439 |
+
"eval_runtime": 2.783,
|
| 440 |
+
"eval_samples_per_second": 81.926,
|
| 441 |
+
"eval_steps_per_second": 5.39,
|
| 442 |
+
"step": 312
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 24.59259259259259,
|
| 446 |
+
"grad_norm": 12.244878768920898,
|
| 447 |
+
"learning_rate": 1.7264957264957267e-05,
|
| 448 |
+
"loss": 0.3548,
|
| 449 |
+
"step": 320
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 24.962962962962962,
|
| 453 |
+
"eval_accuracy": 0.7894736842105263,
|
| 454 |
+
"eval_loss": 0.6003035306930542,
|
| 455 |
+
"eval_runtime": 2.7487,
|
| 456 |
+
"eval_samples_per_second": 82.948,
|
| 457 |
+
"eval_steps_per_second": 5.457,
|
| 458 |
+
"step": 325
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 25.37037037037037,
|
| 462 |
+
"grad_norm": 12.140262603759766,
|
| 463 |
+
"learning_rate": 1.641025641025641e-05,
|
| 464 |
+
"loss": 0.3454,
|
| 465 |
+
"step": 330
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 25.962962962962962,
|
| 469 |
+
"eval_accuracy": 0.8114035087719298,
|
| 470 |
+
"eval_loss": 0.5897476077079773,
|
| 471 |
+
"eval_runtime": 3.3163,
|
| 472 |
+
"eval_samples_per_second": 68.75,
|
| 473 |
+
"eval_steps_per_second": 4.523,
|
| 474 |
+
"step": 338
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 26.14814814814815,
|
| 478 |
+
"grad_norm": 11.911709785461426,
|
| 479 |
+
"learning_rate": 1.555555555555556e-05,
|
| 480 |
+
"loss": 0.3024,
|
| 481 |
+
"step": 340
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 26.88888888888889,
|
| 485 |
+
"grad_norm": 9.537832260131836,
|
| 486 |
+
"learning_rate": 1.4700854700854703e-05,
|
| 487 |
+
"loss": 0.2857,
|
| 488 |
+
"step": 350
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 26.962962962962962,
|
| 492 |
+
"eval_accuracy": 0.8157894736842105,
|
| 493 |
+
"eval_loss": 0.6031244993209839,
|
| 494 |
+
"eval_runtime": 2.7739,
|
| 495 |
+
"eval_samples_per_second": 82.194,
|
| 496 |
+
"eval_steps_per_second": 5.408,
|
| 497 |
+
"step": 351
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 27.666666666666668,
|
| 501 |
+
"grad_norm": 8.15013599395752,
|
| 502 |
+
"learning_rate": 1.3846153846153847e-05,
|
| 503 |
+
"loss": 0.3282,
|
| 504 |
+
"step": 360
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 27.962962962962962,
|
| 508 |
+
"eval_accuracy": 0.7763157894736842,
|
| 509 |
+
"eval_loss": 0.6139560341835022,
|
| 510 |
+
"eval_runtime": 2.7394,
|
| 511 |
+
"eval_samples_per_second": 83.231,
|
| 512 |
+
"eval_steps_per_second": 5.476,
|
| 513 |
+
"step": 364
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 28.444444444444443,
|
| 517 |
+
"grad_norm": 10.504316329956055,
|
| 518 |
+
"learning_rate": 1.2991452991452993e-05,
|
| 519 |
+
"loss": 0.3088,
|
| 520 |
+
"step": 370
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 28.962962962962962,
|
| 524 |
+
"eval_accuracy": 0.8333333333333334,
|
| 525 |
+
"eval_loss": 0.593357503414154,
|
| 526 |
+
"eval_runtime": 3.5071,
|
| 527 |
+
"eval_samples_per_second": 65.01,
|
| 528 |
+
"eval_steps_per_second": 4.277,
|
| 529 |
+
"step": 377
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 29.22222222222222,
|
| 533 |
+
"grad_norm": 9.943313598632812,
|
| 534 |
+
"learning_rate": 1.2136752136752137e-05,
|
| 535 |
+
"loss": 0.2952,
|
| 536 |
+
"step": 380
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 29.962962962962962,
|
| 540 |
+
"grad_norm": 10.9620943069458,
|
| 541 |
+
"learning_rate": 1.1282051282051283e-05,
|
| 542 |
+
"loss": 0.2943,
|
| 543 |
+
"step": 390
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 29.962962962962962,
|
| 547 |
+
"eval_accuracy": 0.7894736842105263,
|
| 548 |
+
"eval_loss": 0.6545236706733704,
|
| 549 |
+
"eval_runtime": 2.7799,
|
| 550 |
+
"eval_samples_per_second": 82.016,
|
| 551 |
+
"eval_steps_per_second": 5.396,
|
| 552 |
+
"step": 390
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 30.74074074074074,
|
| 556 |
+
"grad_norm": 10.951662063598633,
|
| 557 |
+
"learning_rate": 1.0427350427350429e-05,
|
| 558 |
+
"loss": 0.2857,
|
| 559 |
+
"step": 400
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 30.962962962962962,
|
| 563 |
+
"eval_accuracy": 0.7850877192982456,
|
| 564 |
+
"eval_loss": 0.6422854065895081,
|
| 565 |
+
"eval_runtime": 2.7723,
|
| 566 |
+
"eval_samples_per_second": 82.243,
|
| 567 |
+
"eval_steps_per_second": 5.411,
|
| 568 |
+
"step": 403
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 31.51851851851852,
|
| 572 |
+
"grad_norm": 9.850509643554688,
|
| 573 |
+
"learning_rate": 9.572649572649575e-06,
|
| 574 |
+
"loss": 0.2882,
|
| 575 |
+
"step": 410
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 31.962962962962962,
|
| 579 |
+
"eval_accuracy": 0.793859649122807,
|
| 580 |
+
"eval_loss": 0.6610004305839539,
|
| 581 |
+
"eval_runtime": 2.7662,
|
| 582 |
+
"eval_samples_per_second": 82.422,
|
| 583 |
+
"eval_steps_per_second": 5.423,
|
| 584 |
+
"step": 416
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 32.2962962962963,
|
| 588 |
+
"grad_norm": 12.695550918579102,
|
| 589 |
+
"learning_rate": 8.717948717948719e-06,
|
| 590 |
+
"loss": 0.3342,
|
| 591 |
+
"step": 420
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 32.96296296296296,
|
| 595 |
+
"eval_accuracy": 0.7807017543859649,
|
| 596 |
+
"eval_loss": 0.6815162897109985,
|
| 597 |
+
"eval_runtime": 2.6794,
|
| 598 |
+
"eval_samples_per_second": 85.094,
|
| 599 |
+
"eval_steps_per_second": 5.598,
|
| 600 |
+
"step": 429
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 33.074074074074076,
|
| 604 |
+
"grad_norm": 14.900729179382324,
|
| 605 |
+
"learning_rate": 7.863247863247863e-06,
|
| 606 |
+
"loss": 0.2813,
|
| 607 |
+
"step": 430
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 33.81481481481482,
|
| 611 |
+
"grad_norm": 9.834786415100098,
|
| 612 |
+
"learning_rate": 7.008547008547009e-06,
|
| 613 |
+
"loss": 0.2679,
|
| 614 |
+
"step": 440
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 33.96296296296296,
|
| 618 |
+
"eval_accuracy": 0.8114035087719298,
|
| 619 |
+
"eval_loss": 0.6480889320373535,
|
| 620 |
+
"eval_runtime": 3.015,
|
| 621 |
+
"eval_samples_per_second": 75.623,
|
| 622 |
+
"eval_steps_per_second": 4.975,
|
| 623 |
+
"step": 442
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 34.592592592592595,
|
| 627 |
+
"grad_norm": 17.68844985961914,
|
| 628 |
+
"learning_rate": 6.153846153846155e-06,
|
| 629 |
+
"loss": 0.2756,
|
| 630 |
+
"step": 450
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 34.96296296296296,
|
| 634 |
+
"eval_accuracy": 0.8157894736842105,
|
| 635 |
+
"eval_loss": 0.651802659034729,
|
| 636 |
+
"eval_runtime": 2.7547,
|
| 637 |
+
"eval_samples_per_second": 82.768,
|
| 638 |
+
"eval_steps_per_second": 5.445,
|
| 639 |
+
"step": 455
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 35.370370370370374,
|
| 643 |
+
"grad_norm": 13.564445495605469,
|
| 644 |
+
"learning_rate": 5.2991452991453e-06,
|
| 645 |
+
"loss": 0.2733,
|
| 646 |
+
"step": 460
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 35.96296296296296,
|
| 650 |
+
"eval_accuracy": 0.8026315789473685,
|
| 651 |
+
"eval_loss": 0.6514091491699219,
|
| 652 |
+
"eval_runtime": 2.7505,
|
| 653 |
+
"eval_samples_per_second": 82.895,
|
| 654 |
+
"eval_steps_per_second": 5.454,
|
| 655 |
+
"step": 468
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 36.148148148148145,
|
| 659 |
+
"grad_norm": 10.079754829406738,
|
| 660 |
+
"learning_rate": 4.444444444444444e-06,
|
| 661 |
+
"loss": 0.2723,
|
| 662 |
+
"step": 470
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 36.888888888888886,
|
| 666 |
+
"grad_norm": 9.357953071594238,
|
| 667 |
+
"learning_rate": 3.58974358974359e-06,
|
| 668 |
+
"loss": 0.2749,
|
| 669 |
+
"step": 480
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 36.96296296296296,
|
| 673 |
+
"eval_accuracy": 0.8070175438596491,
|
| 674 |
+
"eval_loss": 0.6525157690048218,
|
| 675 |
+
"eval_runtime": 3.7296,
|
| 676 |
+
"eval_samples_per_second": 61.132,
|
| 677 |
+
"eval_steps_per_second": 4.022,
|
| 678 |
+
"step": 481
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 37.666666666666664,
|
| 682 |
+
"grad_norm": 11.598859786987305,
|
| 683 |
+
"learning_rate": 2.7350427350427355e-06,
|
| 684 |
+
"loss": 0.2416,
|
| 685 |
+
"step": 490
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 37.96296296296296,
|
| 689 |
+
"eval_accuracy": 0.8201754385964912,
|
| 690 |
+
"eval_loss": 0.6446716785430908,
|
| 691 |
+
"eval_runtime": 2.8653,
|
| 692 |
+
"eval_samples_per_second": 79.573,
|
| 693 |
+
"eval_steps_per_second": 5.235,
|
| 694 |
+
"step": 494
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 38.44444444444444,
|
| 698 |
+
"grad_norm": 7.851300239562988,
|
| 699 |
+
"learning_rate": 1.8803418803418804e-06,
|
| 700 |
+
"loss": 0.2766,
|
| 701 |
+
"step": 500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 38.96296296296296,
|
| 705 |
+
"eval_accuracy": 0.8201754385964912,
|
| 706 |
+
"eval_loss": 0.635898768901825,
|
| 707 |
+
"eval_runtime": 2.7643,
|
| 708 |
+
"eval_samples_per_second": 82.48,
|
| 709 |
+
"eval_steps_per_second": 5.426,
|
| 710 |
+
"step": 507
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 39.22222222222222,
|
| 714 |
+
"grad_norm": 6.0872416496276855,
|
| 715 |
+
"learning_rate": 1.0256410256410257e-06,
|
| 716 |
+
"loss": 0.2397,
|
| 717 |
+
"step": 510
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 39.96296296296296,
|
| 721 |
+
"grad_norm": 10.594880104064941,
|
| 722 |
+
"learning_rate": 1.7094017094017097e-07,
|
| 723 |
+
"loss": 0.2528,
|
| 724 |
+
"step": 520
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 39.96296296296296,
|
| 728 |
+
"eval_accuracy": 0.8157894736842105,
|
| 729 |
+
"eval_loss": 0.6481040120124817,
|
| 730 |
+
"eval_runtime": 3.9892,
|
| 731 |
+
"eval_samples_per_second": 57.154,
|
| 732 |
+
"eval_steps_per_second": 3.76,
|
| 733 |
+
"step": 520
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 39.96296296296296,
|
| 737 |
+
"step": 520,
|
| 738 |
+
"total_flos": 1.1031361417201582e+18,
|
| 739 |
+
"train_loss": 0.543996471625108,
|
| 740 |
+
"train_runtime": 850.8149,
|
| 741 |
+
"train_samples_per_second": 40.103,
|
| 742 |
+
"train_steps_per_second": 0.611
|
| 743 |
+
}
|
| 744 |
+
],
|
| 745 |
+
"logging_steps": 10,
|
| 746 |
+
"max_steps": 520,
|
| 747 |
+
"num_input_tokens_seen": 0,
|
| 748 |
+
"num_train_epochs": 40,
|
| 749 |
+
"save_steps": 500,
|
| 750 |
+
"stateful_callbacks": {
|
| 751 |
+
"TrainerControl": {
|
| 752 |
+
"args": {
|
| 753 |
+
"should_epoch_stop": false,
|
| 754 |
+
"should_evaluate": false,
|
| 755 |
+
"should_log": false,
|
| 756 |
+
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
+
},
|
| 759 |
+
"attributes": {}
|
| 760 |
+
}
|
| 761 |
+
},
|
| 762 |
+
"total_flos": 1.1031361417201582e+18,
|
| 763 |
+
"train_batch_size": 16,
|
| 764 |
+
"trial_name": null,
|
| 765 |
+
"trial_params": null
|
| 766 |
+
}
|