End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jun11_21-49-36_DESKTOP-SKBE9FB/events.out.tfevents.1718164650.DESKTOP-SKBE9FB.4240.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +750 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8043478260869565
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7230
|
| 36 |
+
- Accuracy: 0.8043
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 55.38,
|
| 3 |
+
"eval_accuracy": 0.8043478260869565,
|
| 4 |
+
"eval_loss": 0.7230114340782166,
|
| 5 |
+
"eval_runtime": 0.9035,
|
| 6 |
+
"eval_samples_per_second": 50.913,
|
| 7 |
+
"eval_steps_per_second": 2.214,
|
| 8 |
+
"train_loss": 0.4256666488117642,
|
| 9 |
+
"train_runtime": 439.4382,
|
| 10 |
+
"train_samples_per_second": 111.825,
|
| 11 |
+
"train_steps_per_second": 0.819
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 55.38,
|
| 3 |
+
"eval_accuracy": 0.8043478260869565,
|
| 4 |
+
"eval_loss": 0.7230114340782166,
|
| 5 |
+
"eval_runtime": 0.9035,
|
| 6 |
+
"eval_samples_per_second": 50.913,
|
| 7 |
+
"eval_steps_per_second": 2.214
|
| 8 |
+
}
|
runs/Jun11_21-49-36_DESKTOP-SKBE9FB/events.out.tfevents.1718164650.DESKTOP-SKBE9FB.4240.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5092c876a232a3852f8374900b544c3a1cbfb54a8264d66176218f005aec129a
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 55.38,
|
| 3 |
+
"train_loss": 0.4256666488117642,
|
| 4 |
+
"train_runtime": 439.4382,
|
| 5 |
+
"train_samples_per_second": 111.825,
|
| 6 |
+
"train_steps_per_second": 0.819
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,750 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8043478260869565,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-ve-U11-b-60\\checkpoint-156",
|
| 4 |
+
"epoch": 55.38461538461539,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 360,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.92,
|
| 13 |
+
"eval_accuracy": 0.13043478260869565,
|
| 14 |
+
"eval_loss": 1.3858968019485474,
|
| 15 |
+
"eval_runtime": 0.5992,
|
| 16 |
+
"eval_samples_per_second": 76.77,
|
| 17 |
+
"eval_steps_per_second": 3.338,
|
| 18 |
+
"step": 6
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.54,
|
| 22 |
+
"learning_rate": 1.388888888888889e-05,
|
| 23 |
+
"loss": 1.3858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.2608695652173913,
|
| 29 |
+
"eval_loss": 1.3818036317825317,
|
| 30 |
+
"eval_runtime": 0.6188,
|
| 31 |
+
"eval_samples_per_second": 74.341,
|
| 32 |
+
"eval_steps_per_second": 3.232,
|
| 33 |
+
"step": 13
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.92,
|
| 37 |
+
"eval_accuracy": 0.2608695652173913,
|
| 38 |
+
"eval_loss": 1.3722529411315918,
|
| 39 |
+
"eval_runtime": 0.5891,
|
| 40 |
+
"eval_samples_per_second": 78.08,
|
| 41 |
+
"eval_steps_per_second": 3.395,
|
| 42 |
+
"step": 19
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.08,
|
| 46 |
+
"learning_rate": 2.777777777777778e-05,
|
| 47 |
+
"loss": 1.3747,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.21739130434782608,
|
| 53 |
+
"eval_loss": 1.3355135917663574,
|
| 54 |
+
"eval_runtime": 0.6036,
|
| 55 |
+
"eval_samples_per_second": 76.214,
|
| 56 |
+
"eval_steps_per_second": 3.314,
|
| 57 |
+
"step": 26
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.62,
|
| 61 |
+
"learning_rate": 4.166666666666667e-05,
|
| 62 |
+
"loss": 1.3001,
|
| 63 |
+
"step": 30
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.92,
|
| 67 |
+
"eval_accuracy": 0.3695652173913043,
|
| 68 |
+
"eval_loss": 1.2625232934951782,
|
| 69 |
+
"eval_runtime": 0.6139,
|
| 70 |
+
"eval_samples_per_second": 74.935,
|
| 71 |
+
"eval_steps_per_second": 3.258,
|
| 72 |
+
"step": 32
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.45652173913043476,
|
| 77 |
+
"eval_loss": 1.1305873394012451,
|
| 78 |
+
"eval_runtime": 0.6404,
|
| 79 |
+
"eval_samples_per_second": 71.832,
|
| 80 |
+
"eval_steps_per_second": 3.123,
|
| 81 |
+
"step": 39
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.15,
|
| 85 |
+
"learning_rate": 4.938271604938271e-05,
|
| 86 |
+
"loss": 1.141,
|
| 87 |
+
"step": 40
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.92,
|
| 91 |
+
"eval_accuracy": 0.4782608695652174,
|
| 92 |
+
"eval_loss": 1.0509722232818604,
|
| 93 |
+
"eval_runtime": 0.5953,
|
| 94 |
+
"eval_samples_per_second": 77.271,
|
| 95 |
+
"eval_steps_per_second": 3.36,
|
| 96 |
+
"step": 45
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.69,
|
| 100 |
+
"learning_rate": 4.783950617283951e-05,
|
| 101 |
+
"loss": 0.9784,
|
| 102 |
+
"step": 50
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.0,
|
| 106 |
+
"eval_accuracy": 0.5434782608695652,
|
| 107 |
+
"eval_loss": 0.9585281014442444,
|
| 108 |
+
"eval_runtime": 0.619,
|
| 109 |
+
"eval_samples_per_second": 74.311,
|
| 110 |
+
"eval_steps_per_second": 3.231,
|
| 111 |
+
"step": 52
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.92,
|
| 115 |
+
"eval_accuracy": 0.4782608695652174,
|
| 116 |
+
"eval_loss": 0.9895150661468506,
|
| 117 |
+
"eval_runtime": 0.6106,
|
| 118 |
+
"eval_samples_per_second": 75.334,
|
| 119 |
+
"eval_steps_per_second": 3.275,
|
| 120 |
+
"step": 58
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.23,
|
| 124 |
+
"learning_rate": 4.62962962962963e-05,
|
| 125 |
+
"loss": 0.8533,
|
| 126 |
+
"step": 60
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"eval_accuracy": 0.5,
|
| 131 |
+
"eval_loss": 0.951244592666626,
|
| 132 |
+
"eval_runtime": 0.5862,
|
| 133 |
+
"eval_samples_per_second": 78.472,
|
| 134 |
+
"eval_steps_per_second": 3.412,
|
| 135 |
+
"step": 65
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.77,
|
| 139 |
+
"learning_rate": 4.4753086419753084e-05,
|
| 140 |
+
"loss": 0.7564,
|
| 141 |
+
"step": 70
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.92,
|
| 145 |
+
"eval_accuracy": 0.5217391304347826,
|
| 146 |
+
"eval_loss": 0.9521799683570862,
|
| 147 |
+
"eval_runtime": 0.6175,
|
| 148 |
+
"eval_samples_per_second": 74.496,
|
| 149 |
+
"eval_steps_per_second": 3.239,
|
| 150 |
+
"step": 71
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 12.0,
|
| 154 |
+
"eval_accuracy": 0.5,
|
| 155 |
+
"eval_loss": 0.9143680930137634,
|
| 156 |
+
"eval_runtime": 0.6232,
|
| 157 |
+
"eval_samples_per_second": 73.814,
|
| 158 |
+
"eval_steps_per_second": 3.209,
|
| 159 |
+
"step": 78
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.31,
|
| 163 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 164 |
+
"loss": 0.6735,
|
| 165 |
+
"step": 80
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.92,
|
| 169 |
+
"eval_accuracy": 0.6086956521739131,
|
| 170 |
+
"eval_loss": 0.907021701335907,
|
| 171 |
+
"eval_runtime": 0.6191,
|
| 172 |
+
"eval_samples_per_second": 74.297,
|
| 173 |
+
"eval_steps_per_second": 3.23,
|
| 174 |
+
"step": 84
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 13.85,
|
| 178 |
+
"learning_rate": 4.166666666666667e-05,
|
| 179 |
+
"loss": 0.5919,
|
| 180 |
+
"step": 90
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 14.0,
|
| 184 |
+
"eval_accuracy": 0.6521739130434783,
|
| 185 |
+
"eval_loss": 0.7915353178977966,
|
| 186 |
+
"eval_runtime": 0.6,
|
| 187 |
+
"eval_samples_per_second": 76.662,
|
| 188 |
+
"eval_steps_per_second": 3.333,
|
| 189 |
+
"step": 91
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.92,
|
| 193 |
+
"eval_accuracy": 0.6521739130434783,
|
| 194 |
+
"eval_loss": 0.7988886833190918,
|
| 195 |
+
"eval_runtime": 0.6334,
|
| 196 |
+
"eval_samples_per_second": 72.622,
|
| 197 |
+
"eval_steps_per_second": 3.157,
|
| 198 |
+
"step": 97
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 15.38,
|
| 202 |
+
"learning_rate": 4.012345679012346e-05,
|
| 203 |
+
"loss": 0.504,
|
| 204 |
+
"step": 100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 16.0,
|
| 208 |
+
"eval_accuracy": 0.6521739130434783,
|
| 209 |
+
"eval_loss": 0.9510163068771362,
|
| 210 |
+
"eval_runtime": 0.6024,
|
| 211 |
+
"eval_samples_per_second": 76.367,
|
| 212 |
+
"eval_steps_per_second": 3.32,
|
| 213 |
+
"step": 104
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.92,
|
| 217 |
+
"learning_rate": 3.8580246913580246e-05,
|
| 218 |
+
"loss": 0.4422,
|
| 219 |
+
"step": 110
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.92,
|
| 223 |
+
"eval_accuracy": 0.6739130434782609,
|
| 224 |
+
"eval_loss": 0.8195834159851074,
|
| 225 |
+
"eval_runtime": 0.603,
|
| 226 |
+
"eval_samples_per_second": 76.291,
|
| 227 |
+
"eval_steps_per_second": 3.317,
|
| 228 |
+
"step": 110
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 18.0,
|
| 232 |
+
"eval_accuracy": 0.7608695652173914,
|
| 233 |
+
"eval_loss": 0.6628637909889221,
|
| 234 |
+
"eval_runtime": 0.6198,
|
| 235 |
+
"eval_samples_per_second": 74.213,
|
| 236 |
+
"eval_steps_per_second": 3.227,
|
| 237 |
+
"step": 117
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.46,
|
| 241 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 242 |
+
"loss": 0.4031,
|
| 243 |
+
"step": 120
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.92,
|
| 247 |
+
"eval_accuracy": 0.6521739130434783,
|
| 248 |
+
"eval_loss": 0.8767060041427612,
|
| 249 |
+
"eval_runtime": 0.6311,
|
| 250 |
+
"eval_samples_per_second": 72.889,
|
| 251 |
+
"eval_steps_per_second": 3.169,
|
| 252 |
+
"step": 123
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.0,
|
| 256 |
+
"learning_rate": 3.5493827160493834e-05,
|
| 257 |
+
"loss": 0.3752,
|
| 258 |
+
"step": 130
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 20.0,
|
| 262 |
+
"eval_accuracy": 0.6739130434782609,
|
| 263 |
+
"eval_loss": 0.8252948522567749,
|
| 264 |
+
"eval_runtime": 0.5775,
|
| 265 |
+
"eval_samples_per_second": 79.655,
|
| 266 |
+
"eval_steps_per_second": 3.463,
|
| 267 |
+
"step": 130
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.92,
|
| 271 |
+
"eval_accuracy": 0.7391304347826086,
|
| 272 |
+
"eval_loss": 0.7182953953742981,
|
| 273 |
+
"eval_runtime": 0.653,
|
| 274 |
+
"eval_samples_per_second": 70.442,
|
| 275 |
+
"eval_steps_per_second": 3.063,
|
| 276 |
+
"step": 136
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 21.54,
|
| 280 |
+
"learning_rate": 3.395061728395062e-05,
|
| 281 |
+
"loss": 0.3424,
|
| 282 |
+
"step": 140
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 22.0,
|
| 286 |
+
"eval_accuracy": 0.6739130434782609,
|
| 287 |
+
"eval_loss": 0.88515305519104,
|
| 288 |
+
"eval_runtime": 0.6458,
|
| 289 |
+
"eval_samples_per_second": 71.225,
|
| 290 |
+
"eval_steps_per_second": 3.097,
|
| 291 |
+
"step": 143
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 22.92,
|
| 295 |
+
"eval_accuracy": 0.7391304347826086,
|
| 296 |
+
"eval_loss": 0.7359628081321716,
|
| 297 |
+
"eval_runtime": 0.6099,
|
| 298 |
+
"eval_samples_per_second": 75.427,
|
| 299 |
+
"eval_steps_per_second": 3.279,
|
| 300 |
+
"step": 149
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 23.08,
|
| 304 |
+
"learning_rate": 3.240740740740741e-05,
|
| 305 |
+
"loss": 0.3293,
|
| 306 |
+
"step": 150
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 24.0,
|
| 310 |
+
"eval_accuracy": 0.8043478260869565,
|
| 311 |
+
"eval_loss": 0.7230114340782166,
|
| 312 |
+
"eval_runtime": 0.5934,
|
| 313 |
+
"eval_samples_per_second": 77.518,
|
| 314 |
+
"eval_steps_per_second": 3.37,
|
| 315 |
+
"step": 156
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 24.62,
|
| 319 |
+
"learning_rate": 3.08641975308642e-05,
|
| 320 |
+
"loss": 0.2822,
|
| 321 |
+
"step": 160
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 24.92,
|
| 325 |
+
"eval_accuracy": 0.6956521739130435,
|
| 326 |
+
"eval_loss": 0.8270708918571472,
|
| 327 |
+
"eval_runtime": 0.6168,
|
| 328 |
+
"eval_samples_per_second": 74.575,
|
| 329 |
+
"eval_steps_per_second": 3.242,
|
| 330 |
+
"step": 162
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 26.0,
|
| 334 |
+
"eval_accuracy": 0.8043478260869565,
|
| 335 |
+
"eval_loss": 0.7442592978477478,
|
| 336 |
+
"eval_runtime": 0.5915,
|
| 337 |
+
"eval_samples_per_second": 77.771,
|
| 338 |
+
"eval_steps_per_second": 3.381,
|
| 339 |
+
"step": 169
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 26.15,
|
| 343 |
+
"learning_rate": 2.9320987654320992e-05,
|
| 344 |
+
"loss": 0.2623,
|
| 345 |
+
"step": 170
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 26.92,
|
| 349 |
+
"eval_accuracy": 0.6739130434782609,
|
| 350 |
+
"eval_loss": 0.9371039271354675,
|
| 351 |
+
"eval_runtime": 0.5932,
|
| 352 |
+
"eval_samples_per_second": 77.541,
|
| 353 |
+
"eval_steps_per_second": 3.371,
|
| 354 |
+
"step": 175
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 27.69,
|
| 358 |
+
"learning_rate": 2.777777777777778e-05,
|
| 359 |
+
"loss": 0.2807,
|
| 360 |
+
"step": 180
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 28.0,
|
| 364 |
+
"eval_accuracy": 0.7391304347826086,
|
| 365 |
+
"eval_loss": 0.7391819357872009,
|
| 366 |
+
"eval_runtime": 0.5861,
|
| 367 |
+
"eval_samples_per_second": 78.483,
|
| 368 |
+
"eval_steps_per_second": 3.412,
|
| 369 |
+
"step": 182
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 28.92,
|
| 373 |
+
"eval_accuracy": 0.6739130434782609,
|
| 374 |
+
"eval_loss": 0.8753820657730103,
|
| 375 |
+
"eval_runtime": 0.5828,
|
| 376 |
+
"eval_samples_per_second": 78.931,
|
| 377 |
+
"eval_steps_per_second": 3.432,
|
| 378 |
+
"step": 188
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 29.23,
|
| 382 |
+
"learning_rate": 2.623456790123457e-05,
|
| 383 |
+
"loss": 0.223,
|
| 384 |
+
"step": 190
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.0,
|
| 388 |
+
"eval_accuracy": 0.782608695652174,
|
| 389 |
+
"eval_loss": 0.7145875096321106,
|
| 390 |
+
"eval_runtime": 0.5811,
|
| 391 |
+
"eval_samples_per_second": 79.16,
|
| 392 |
+
"eval_steps_per_second": 3.442,
|
| 393 |
+
"step": 195
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 30.77,
|
| 397 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 398 |
+
"loss": 0.2185,
|
| 399 |
+
"step": 200
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 30.92,
|
| 403 |
+
"eval_accuracy": 0.7391304347826086,
|
| 404 |
+
"eval_loss": 0.7702176570892334,
|
| 405 |
+
"eval_runtime": 0.5879,
|
| 406 |
+
"eval_samples_per_second": 78.249,
|
| 407 |
+
"eval_steps_per_second": 3.402,
|
| 408 |
+
"step": 201
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 32.0,
|
| 412 |
+
"eval_accuracy": 0.717391304347826,
|
| 413 |
+
"eval_loss": 0.7329592704772949,
|
| 414 |
+
"eval_runtime": 0.6173,
|
| 415 |
+
"eval_samples_per_second": 74.523,
|
| 416 |
+
"eval_steps_per_second": 3.24,
|
| 417 |
+
"step": 208
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 32.31,
|
| 421 |
+
"learning_rate": 2.314814814814815e-05,
|
| 422 |
+
"loss": 0.2157,
|
| 423 |
+
"step": 210
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 32.92,
|
| 427 |
+
"eval_accuracy": 0.6956521739130435,
|
| 428 |
+
"eval_loss": 0.8817254900932312,
|
| 429 |
+
"eval_runtime": 0.5926,
|
| 430 |
+
"eval_samples_per_second": 77.63,
|
| 431 |
+
"eval_steps_per_second": 3.375,
|
| 432 |
+
"step": 214
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 33.85,
|
| 436 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 437 |
+
"loss": 0.2011,
|
| 438 |
+
"step": 220
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 34.0,
|
| 442 |
+
"eval_accuracy": 0.717391304347826,
|
| 443 |
+
"eval_loss": 0.7459983229637146,
|
| 444 |
+
"eval_runtime": 0.5797,
|
| 445 |
+
"eval_samples_per_second": 79.357,
|
| 446 |
+
"eval_steps_per_second": 3.45,
|
| 447 |
+
"step": 221
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 34.92,
|
| 451 |
+
"eval_accuracy": 0.6739130434782609,
|
| 452 |
+
"eval_loss": 0.9663064479827881,
|
| 453 |
+
"eval_runtime": 0.6007,
|
| 454 |
+
"eval_samples_per_second": 76.581,
|
| 455 |
+
"eval_steps_per_second": 3.33,
|
| 456 |
+
"step": 227
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 35.38,
|
| 460 |
+
"learning_rate": 2.006172839506173e-05,
|
| 461 |
+
"loss": 0.2204,
|
| 462 |
+
"step": 230
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 36.0,
|
| 466 |
+
"eval_accuracy": 0.717391304347826,
|
| 467 |
+
"eval_loss": 0.8055830597877502,
|
| 468 |
+
"eval_runtime": 0.6033,
|
| 469 |
+
"eval_samples_per_second": 76.247,
|
| 470 |
+
"eval_steps_per_second": 3.315,
|
| 471 |
+
"step": 234
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 36.92,
|
| 475 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 476 |
+
"loss": 0.1856,
|
| 477 |
+
"step": 240
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 36.92,
|
| 481 |
+
"eval_accuracy": 0.717391304347826,
|
| 482 |
+
"eval_loss": 0.7798697352409363,
|
| 483 |
+
"eval_runtime": 0.6168,
|
| 484 |
+
"eval_samples_per_second": 74.584,
|
| 485 |
+
"eval_steps_per_second": 3.243,
|
| 486 |
+
"step": 240
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 38.0,
|
| 490 |
+
"eval_accuracy": 0.6956521739130435,
|
| 491 |
+
"eval_loss": 0.8410213589668274,
|
| 492 |
+
"eval_runtime": 0.6255,
|
| 493 |
+
"eval_samples_per_second": 73.539,
|
| 494 |
+
"eval_steps_per_second": 3.197,
|
| 495 |
+
"step": 247
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 38.46,
|
| 499 |
+
"learning_rate": 1.697530864197531e-05,
|
| 500 |
+
"loss": 0.1678,
|
| 501 |
+
"step": 250
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 38.92,
|
| 505 |
+
"eval_accuracy": 0.7391304347826086,
|
| 506 |
+
"eval_loss": 0.7334251999855042,
|
| 507 |
+
"eval_runtime": 0.6096,
|
| 508 |
+
"eval_samples_per_second": 75.455,
|
| 509 |
+
"eval_steps_per_second": 3.281,
|
| 510 |
+
"step": 253
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 40.0,
|
| 514 |
+
"learning_rate": 1.54320987654321e-05,
|
| 515 |
+
"loss": 0.1682,
|
| 516 |
+
"step": 260
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 40.0,
|
| 520 |
+
"eval_accuracy": 0.6956521739130435,
|
| 521 |
+
"eval_loss": 0.8507670760154724,
|
| 522 |
+
"eval_runtime": 0.5939,
|
| 523 |
+
"eval_samples_per_second": 77.45,
|
| 524 |
+
"eval_steps_per_second": 3.367,
|
| 525 |
+
"step": 260
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 40.92,
|
| 529 |
+
"eval_accuracy": 0.6956521739130435,
|
| 530 |
+
"eval_loss": 0.8106131553649902,
|
| 531 |
+
"eval_runtime": 0.5922,
|
| 532 |
+
"eval_samples_per_second": 77.674,
|
| 533 |
+
"eval_steps_per_second": 3.377,
|
| 534 |
+
"step": 266
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 41.54,
|
| 538 |
+
"learning_rate": 1.388888888888889e-05,
|
| 539 |
+
"loss": 0.1638,
|
| 540 |
+
"step": 270
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 42.0,
|
| 544 |
+
"eval_accuracy": 0.717391304347826,
|
| 545 |
+
"eval_loss": 0.8402844071388245,
|
| 546 |
+
"eval_runtime": 0.6501,
|
| 547 |
+
"eval_samples_per_second": 70.759,
|
| 548 |
+
"eval_steps_per_second": 3.076,
|
| 549 |
+
"step": 273
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 42.92,
|
| 553 |
+
"eval_accuracy": 0.6956521739130435,
|
| 554 |
+
"eval_loss": 0.9157429337501526,
|
| 555 |
+
"eval_runtime": 0.6015,
|
| 556 |
+
"eval_samples_per_second": 76.475,
|
| 557 |
+
"eval_steps_per_second": 3.325,
|
| 558 |
+
"step": 279
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 43.08,
|
| 562 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 563 |
+
"loss": 0.1573,
|
| 564 |
+
"step": 280
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 44.0,
|
| 568 |
+
"eval_accuracy": 0.7391304347826086,
|
| 569 |
+
"eval_loss": 0.9271051287651062,
|
| 570 |
+
"eval_runtime": 0.617,
|
| 571 |
+
"eval_samples_per_second": 74.552,
|
| 572 |
+
"eval_steps_per_second": 3.241,
|
| 573 |
+
"step": 286
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 44.62,
|
| 577 |
+
"learning_rate": 1.0802469135802469e-05,
|
| 578 |
+
"loss": 0.1476,
|
| 579 |
+
"step": 290
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 44.92,
|
| 583 |
+
"eval_accuracy": 0.717391304347826,
|
| 584 |
+
"eval_loss": 0.9167048335075378,
|
| 585 |
+
"eval_runtime": 0.5836,
|
| 586 |
+
"eval_samples_per_second": 78.822,
|
| 587 |
+
"eval_steps_per_second": 3.427,
|
| 588 |
+
"step": 292
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 46.0,
|
| 592 |
+
"eval_accuracy": 0.717391304347826,
|
| 593 |
+
"eval_loss": 0.9309194684028625,
|
| 594 |
+
"eval_runtime": 0.62,
|
| 595 |
+
"eval_samples_per_second": 74.197,
|
| 596 |
+
"eval_steps_per_second": 3.226,
|
| 597 |
+
"step": 299
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 46.15,
|
| 601 |
+
"learning_rate": 9.259259259259259e-06,
|
| 602 |
+
"loss": 0.1466,
|
| 603 |
+
"step": 300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 46.92,
|
| 607 |
+
"eval_accuracy": 0.782608695652174,
|
| 608 |
+
"eval_loss": 0.8235711455345154,
|
| 609 |
+
"eval_runtime": 0.6116,
|
| 610 |
+
"eval_samples_per_second": 75.219,
|
| 611 |
+
"eval_steps_per_second": 3.27,
|
| 612 |
+
"step": 305
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 47.69,
|
| 616 |
+
"learning_rate": 7.71604938271605e-06,
|
| 617 |
+
"loss": 0.1457,
|
| 618 |
+
"step": 310
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 48.0,
|
| 622 |
+
"eval_accuracy": 0.782608695652174,
|
| 623 |
+
"eval_loss": 0.8834730386734009,
|
| 624 |
+
"eval_runtime": 0.6232,
|
| 625 |
+
"eval_samples_per_second": 73.809,
|
| 626 |
+
"eval_steps_per_second": 3.209,
|
| 627 |
+
"step": 312
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 48.92,
|
| 631 |
+
"eval_accuracy": 0.7391304347826086,
|
| 632 |
+
"eval_loss": 0.9161576628684998,
|
| 633 |
+
"eval_runtime": 0.6019,
|
| 634 |
+
"eval_samples_per_second": 76.426,
|
| 635 |
+
"eval_steps_per_second": 3.323,
|
| 636 |
+
"step": 318
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 49.23,
|
| 640 |
+
"learning_rate": 6.172839506172839e-06,
|
| 641 |
+
"loss": 0.1625,
|
| 642 |
+
"step": 320
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 50.0,
|
| 646 |
+
"eval_accuracy": 0.7391304347826086,
|
| 647 |
+
"eval_loss": 0.8969017267227173,
|
| 648 |
+
"eval_runtime": 0.6023,
|
| 649 |
+
"eval_samples_per_second": 76.373,
|
| 650 |
+
"eval_steps_per_second": 3.321,
|
| 651 |
+
"step": 325
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 50.77,
|
| 655 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 656 |
+
"loss": 0.1163,
|
| 657 |
+
"step": 330
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 50.92,
|
| 661 |
+
"eval_accuracy": 0.7391304347826086,
|
| 662 |
+
"eval_loss": 0.9183077812194824,
|
| 663 |
+
"eval_runtime": 0.6149,
|
| 664 |
+
"eval_samples_per_second": 74.806,
|
| 665 |
+
"eval_steps_per_second": 3.252,
|
| 666 |
+
"step": 331
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 52.0,
|
| 670 |
+
"eval_accuracy": 0.7391304347826086,
|
| 671 |
+
"eval_loss": 0.9172530770301819,
|
| 672 |
+
"eval_runtime": 0.7065,
|
| 673 |
+
"eval_samples_per_second": 65.107,
|
| 674 |
+
"eval_steps_per_second": 2.831,
|
| 675 |
+
"step": 338
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 52.31,
|
| 679 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 680 |
+
"loss": 0.1375,
|
| 681 |
+
"step": 340
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 52.92,
|
| 685 |
+
"eval_accuracy": 0.7608695652173914,
|
| 686 |
+
"eval_loss": 0.8886280655860901,
|
| 687 |
+
"eval_runtime": 0.5667,
|
| 688 |
+
"eval_samples_per_second": 81.175,
|
| 689 |
+
"eval_steps_per_second": 3.529,
|
| 690 |
+
"step": 344
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 53.85,
|
| 694 |
+
"learning_rate": 1.5432098765432098e-06,
|
| 695 |
+
"loss": 0.1379,
|
| 696 |
+
"step": 350
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 54.0,
|
| 700 |
+
"eval_accuracy": 0.7391304347826086,
|
| 701 |
+
"eval_loss": 0.877066969871521,
|
| 702 |
+
"eval_runtime": 0.6245,
|
| 703 |
+
"eval_samples_per_second": 73.66,
|
| 704 |
+
"eval_steps_per_second": 3.203,
|
| 705 |
+
"step": 351
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 54.92,
|
| 709 |
+
"eval_accuracy": 0.7391304347826086,
|
| 710 |
+
"eval_loss": 0.885678231716156,
|
| 711 |
+
"eval_runtime": 0.6368,
|
| 712 |
+
"eval_samples_per_second": 72.233,
|
| 713 |
+
"eval_steps_per_second": 3.141,
|
| 714 |
+
"step": 357
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 55.38,
|
| 718 |
+
"learning_rate": 0.0,
|
| 719 |
+
"loss": 0.1321,
|
| 720 |
+
"step": 360
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 55.38,
|
| 724 |
+
"eval_accuracy": 0.7391304347826086,
|
| 725 |
+
"eval_loss": 0.8883605003356934,
|
| 726 |
+
"eval_runtime": 0.618,
|
| 727 |
+
"eval_samples_per_second": 74.43,
|
| 728 |
+
"eval_steps_per_second": 3.236,
|
| 729 |
+
"step": 360
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 55.38,
|
| 733 |
+
"step": 360,
|
| 734 |
+
"total_flos": 1.1276549556120576e+18,
|
| 735 |
+
"train_loss": 0.4256666488117642,
|
| 736 |
+
"train_runtime": 439.4382,
|
| 737 |
+
"train_samples_per_second": 111.825,
|
| 738 |
+
"train_steps_per_second": 0.819
|
| 739 |
+
}
|
| 740 |
+
],
|
| 741 |
+
"logging_steps": 10,
|
| 742 |
+
"max_steps": 360,
|
| 743 |
+
"num_input_tokens_seen": 0,
|
| 744 |
+
"num_train_epochs": 60,
|
| 745 |
+
"save_steps": 500,
|
| 746 |
+
"total_flos": 1.1276549556120576e+18,
|
| 747 |
+
"train_batch_size": 32,
|
| 748 |
+
"trial_name": null,
|
| 749 |
+
"trial_params": null
|
| 750 |
+
}
|