End of training
Browse files- README.md +3 -1
- all_results.json +16 -0
- eval_results.json +12 -0
- train_results.json +7 -0
- trainer_state.json +802 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-base-imagenet1k-1-layer
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -19,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# dinov2-base-imagenet1k-1-layer-boulderspot-vN
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: 0.0519
|
| 25 |
- Accuracy: 0.9810
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-base-imagenet1k-1-layer
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 21 |
|
| 22 |
# dinov2-base-imagenet1k-1-layer-boulderspot-vN
|
| 23 |
|
| 24 |
+
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on the pszemraj/boulderspot dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
- Loss: 0.0519
|
| 27 |
- Accuracy: 0.9810
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_accuracy": 0.9809941520467836,
|
| 4 |
+
"eval_f1": 0.9808994233422476,
|
| 5 |
+
"eval_loss": 0.051854074001312256,
|
| 6 |
+
"eval_matthews_correlation": 0.8500768147494288,
|
| 7 |
+
"eval_precision": 0.9808194985441887,
|
| 8 |
+
"eval_recall": 0.9809941520467836,
|
| 9 |
+
"eval_runtime": 4.1858,
|
| 10 |
+
"eval_samples_per_second": 163.41,
|
| 11 |
+
"eval_steps_per_second": 10.273,
|
| 12 |
+
"train_loss": 0.08605182834446724,
|
| 13 |
+
"train_runtime": 583.274,
|
| 14 |
+
"train_samples_per_second": 111.397,
|
| 15 |
+
"train_steps_per_second": 1.74
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_accuracy": 0.9809941520467836,
|
| 4 |
+
"eval_f1": 0.9808994233422476,
|
| 5 |
+
"eval_loss": 0.051854074001312256,
|
| 6 |
+
"eval_matthews_correlation": 0.8500768147494288,
|
| 7 |
+
"eval_precision": 0.9808194985441887,
|
| 8 |
+
"eval_recall": 0.9809941520467836,
|
| 9 |
+
"eval_runtime": 4.1858,
|
| 10 |
+
"eval_samples_per_second": 163.41,
|
| 11 |
+
"eval_steps_per_second": 10.273
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"train_loss": 0.08605182834446724,
|
| 4 |
+
"train_runtime": 583.274,
|
| 5 |
+
"train_samples_per_second": 111.397,
|
| 6 |
+
"train_steps_per_second": 1.74
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,802 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9808994233422476,
|
| 3 |
+
"best_model_checkpoint": "./outputs/dinov2-base-imagenet1k-1-layer-boulderspot-vN/checkpoint-1015",
|
| 4 |
+
"epoch": 4.993849938499385,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1015,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 21.444149017333984,
|
| 14 |
+
"learning_rate": 3.92156862745098e-06,
|
| 15 |
+
"loss": 0.3077,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 20.83109474182129,
|
| 21 |
+
"learning_rate": 7.84313725490196e-06,
|
| 22 |
+
"loss": 0.0953,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 8.993614196777344,
|
| 28 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 29 |
+
"loss": 0.1968,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 32.97685241699219,
|
| 35 |
+
"learning_rate": 1.568627450980392e-05,
|
| 36 |
+
"loss": 0.1265,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 10.921149253845215,
|
| 42 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 43 |
+
"loss": 0.166,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 30.291000366210938,
|
| 49 |
+
"learning_rate": 1.9995698998770955e-05,
|
| 50 |
+
"loss": 0.1484,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.34,
|
| 55 |
+
"grad_norm": 7.144667625427246,
|
| 56 |
+
"learning_rate": 1.998083609002402e-05,
|
| 57 |
+
"loss": 0.1529,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.39,
|
| 62 |
+
"grad_norm": 72.38031005859375,
|
| 63 |
+
"learning_rate": 1.995537395500004e-05,
|
| 64 |
+
"loss": 0.1588,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.44,
|
| 69 |
+
"grad_norm": 9.280795097351074,
|
| 70 |
+
"learning_rate": 1.9919339633410737e-05,
|
| 71 |
+
"loss": 0.1575,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.49,
|
| 76 |
+
"grad_norm": 8.867383003234863,
|
| 77 |
+
"learning_rate": 1.9872771392183334e-05,
|
| 78 |
+
"loss": 0.1345,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.54,
|
| 83 |
+
"grad_norm": 11.048301696777344,
|
| 84 |
+
"learning_rate": 1.981571868482269e-05,
|
| 85 |
+
"loss": 0.1832,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.59,
|
| 90 |
+
"grad_norm": 18.908288955688477,
|
| 91 |
+
"learning_rate": 1.974824209889377e-05,
|
| 92 |
+
"loss": 0.1392,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.64,
|
| 97 |
+
"grad_norm": 6.0579047203063965,
|
| 98 |
+
"learning_rate": 1.9670413291680223e-05,
|
| 99 |
+
"loss": 0.1179,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.69,
|
| 104 |
+
"grad_norm": 6.6037774085998535,
|
| 105 |
+
"learning_rate": 1.9582314914087344e-05,
|
| 106 |
+
"loss": 0.1258,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.74,
|
| 111 |
+
"grad_norm": 17.16813087463379,
|
| 112 |
+
"learning_rate": 1.9484040522870333e-05,
|
| 113 |
+
"loss": 0.1914,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.79,
|
| 118 |
+
"grad_norm": 15.085983276367188,
|
| 119 |
+
"learning_rate": 1.9375694481280965e-05,
|
| 120 |
+
"loss": 0.1747,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.84,
|
| 125 |
+
"grad_norm": 6.54490852355957,
|
| 126 |
+
"learning_rate": 1.9257391848238212e-05,
|
| 127 |
+
"loss": 0.0749,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.89,
|
| 132 |
+
"grad_norm": 0.9332025051116943,
|
| 133 |
+
"learning_rate": 1.9129258256140556e-05,
|
| 134 |
+
"loss": 0.0706,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.93,
|
| 139 |
+
"grad_norm": 26.89777946472168,
|
| 140 |
+
"learning_rate": 1.8991429777449674e-05,
|
| 141 |
+
"loss": 0.0852,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.98,
|
| 146 |
+
"grad_norm": 4.798658847808838,
|
| 147 |
+
"learning_rate": 1.884405278018722e-05,
|
| 148 |
+
"loss": 0.1596,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.9766081871345029,
|
| 154 |
+
"eval_f1": 0.9758655635300373,
|
| 155 |
+
"eval_loss": 0.0732586681842804,
|
| 156 |
+
"eval_matthews_correlation": 0.8078903073020254,
|
| 157 |
+
"eval_precision": 0.9756885037132272,
|
| 158 |
+
"eval_recall": 0.9766081871345029,
|
| 159 |
+
"eval_runtime": 3.9698,
|
| 160 |
+
"eval_samples_per_second": 172.303,
|
| 161 |
+
"eval_steps_per_second": 10.832,
|
| 162 |
+
"step": 203
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.03,
|
| 166 |
+
"grad_norm": 13.787192344665527,
|
| 167 |
+
"learning_rate": 1.8687283772498205e-05,
|
| 168 |
+
"loss": 0.1367,
|
| 169 |
+
"step": 210
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.08,
|
| 173 |
+
"grad_norm": 5.066114902496338,
|
| 174 |
+
"learning_rate": 1.852128923644593e-05,
|
| 175 |
+
"loss": 0.1308,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.13,
|
| 180 |
+
"grad_norm": 2.300729990005493,
|
| 181 |
+
"learning_rate": 1.8346245451215068e-05,
|
| 182 |
+
"loss": 0.1011,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.18,
|
| 187 |
+
"grad_norm": 6.617341995239258,
|
| 188 |
+
"learning_rate": 1.8162338305910636e-05,
|
| 189 |
+
"loss": 0.0879,
|
| 190 |
+
"step": 240
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.23,
|
| 194 |
+
"grad_norm": 5.020946025848389,
|
| 195 |
+
"learning_rate": 1.79697631021516e-05,
|
| 196 |
+
"loss": 0.0969,
|
| 197 |
+
"step": 250
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.28,
|
| 201 |
+
"grad_norm": 7.580730438232422,
|
| 202 |
+
"learning_rate": 1.776872434666882e-05,
|
| 203 |
+
"loss": 0.0942,
|
| 204 |
+
"step": 260
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.33,
|
| 208 |
+
"grad_norm": 1.9427905082702637,
|
| 209 |
+
"learning_rate": 1.7559435534127534e-05,
|
| 210 |
+
"loss": 0.0745,
|
| 211 |
+
"step": 270
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.38,
|
| 215 |
+
"grad_norm": 10.397661209106445,
|
| 216 |
+
"learning_rate": 1.7342118920405035e-05,
|
| 217 |
+
"loss": 0.1028,
|
| 218 |
+
"step": 280
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.43,
|
| 222 |
+
"grad_norm": 8.107540130615234,
|
| 223 |
+
"learning_rate": 1.7117005286564344e-05,
|
| 224 |
+
"loss": 0.0941,
|
| 225 |
+
"step": 290
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.48,
|
| 229 |
+
"grad_norm": 13.503528594970703,
|
| 230 |
+
"learning_rate": 1.688433369377444e-05,
|
| 231 |
+
"loss": 0.1162,
|
| 232 |
+
"step": 300
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.53,
|
| 236 |
+
"grad_norm": 15.07189655303955,
|
| 237 |
+
"learning_rate": 1.6644351229437416e-05,
|
| 238 |
+
"loss": 0.1301,
|
| 239 |
+
"step": 310
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.57,
|
| 243 |
+
"grad_norm": 3.9105443954467773,
|
| 244 |
+
"learning_rate": 1.63973127447921e-05,
|
| 245 |
+
"loss": 0.1441,
|
| 246 |
+
"step": 320
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.62,
|
| 250 |
+
"grad_norm": 7.494752883911133,
|
| 251 |
+
"learning_rate": 1.6143480584272794e-05,
|
| 252 |
+
"loss": 0.1002,
|
| 253 |
+
"step": 330
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.67,
|
| 257 |
+
"grad_norm": 2.2176589965820312,
|
| 258 |
+
"learning_rate": 1.5883124306910563e-05,
|
| 259 |
+
"loss": 0.0731,
|
| 260 |
+
"step": 340
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.72,
|
| 264 |
+
"grad_norm": 5.566643714904785,
|
| 265 |
+
"learning_rate": 1.5616520400072963e-05,
|
| 266 |
+
"loss": 0.093,
|
| 267 |
+
"step": 350
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.77,
|
| 271 |
+
"grad_norm": 4.072403907775879,
|
| 272 |
+
"learning_rate": 1.5343951985846096e-05,
|
| 273 |
+
"loss": 0.0899,
|
| 274 |
+
"step": 360
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.82,
|
| 278 |
+
"grad_norm": 4.870898246765137,
|
| 279 |
+
"learning_rate": 1.5065708520370943e-05,
|
| 280 |
+
"loss": 0.0781,
|
| 281 |
+
"step": 370
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.87,
|
| 285 |
+
"grad_norm": 21.179044723510742,
|
| 286 |
+
"learning_rate": 1.4782085486453155e-05,
|
| 287 |
+
"loss": 0.0807,
|
| 288 |
+
"step": 380
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.92,
|
| 292 |
+
"grad_norm": 4.826471328735352,
|
| 293 |
+
"learning_rate": 1.4493384079772815e-05,
|
| 294 |
+
"loss": 0.0852,
|
| 295 |
+
"step": 390
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.97,
|
| 299 |
+
"grad_norm": 3.290867328643799,
|
| 300 |
+
"learning_rate": 1.4199910889027335e-05,
|
| 301 |
+
"loss": 0.0635,
|
| 302 |
+
"step": 400
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 0.9473684210526315,
|
| 307 |
+
"eval_f1": 0.9522155218554862,
|
| 308 |
+
"eval_loss": 0.12761278450489044,
|
| 309 |
+
"eval_matthews_correlation": 0.6844503635019795,
|
| 310 |
+
"eval_precision": 0.9618507818612543,
|
| 311 |
+
"eval_recall": 0.9473684210526315,
|
| 312 |
+
"eval_runtime": 4.0112,
|
| 313 |
+
"eval_samples_per_second": 170.521,
|
| 314 |
+
"eval_steps_per_second": 10.72,
|
| 315 |
+
"step": 406
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.02,
|
| 319 |
+
"grad_norm": 16.522815704345703,
|
| 320 |
+
"learning_rate": 1.390197757034721e-05,
|
| 321 |
+
"loss": 0.0853,
|
| 322 |
+
"step": 410
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.07,
|
| 326 |
+
"grad_norm": 5.749844074249268,
|
| 327 |
+
"learning_rate": 1.3599900516330382e-05,
|
| 328 |
+
"loss": 0.0685,
|
| 329 |
+
"step": 420
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.12,
|
| 333 |
+
"grad_norm": 4.761476993560791,
|
| 334 |
+
"learning_rate": 1.3294000520046666e-05,
|
| 335 |
+
"loss": 0.086,
|
| 336 |
+
"step": 430
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.16,
|
| 340 |
+
"grad_norm": 5.712699890136719,
|
| 341 |
+
"learning_rate": 1.2984602434369058e-05,
|
| 342 |
+
"loss": 0.0927,
|
| 343 |
+
"step": 440
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.21,
|
| 347 |
+
"grad_norm": 7.019559860229492,
|
| 348 |
+
"learning_rate": 1.2672034826993716e-05,
|
| 349 |
+
"loss": 0.0771,
|
| 350 |
+
"step": 450
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.26,
|
| 354 |
+
"grad_norm": 5.033693313598633,
|
| 355 |
+
"learning_rate": 1.235662963151493e-05,
|
| 356 |
+
"loss": 0.065,
|
| 357 |
+
"step": 460
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.31,
|
| 361 |
+
"grad_norm": 7.356439590454102,
|
| 362 |
+
"learning_rate": 1.2038721794925689e-05,
|
| 363 |
+
"loss": 0.0782,
|
| 364 |
+
"step": 470
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.36,
|
| 368 |
+
"grad_norm": 13.046978950500488,
|
| 369 |
+
"learning_rate": 1.1718648921918112e-05,
|
| 370 |
+
"loss": 0.1074,
|
| 371 |
+
"step": 480
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.41,
|
| 375 |
+
"grad_norm": 2.489901542663574,
|
| 376 |
+
"learning_rate": 1.1396750916361526e-05,
|
| 377 |
+
"loss": 0.0891,
|
| 378 |
+
"step": 490
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.46,
|
| 382 |
+
"grad_norm": 8.636452674865723,
|
| 383 |
+
"learning_rate": 1.1073369620338928e-05,
|
| 384 |
+
"loss": 0.0922,
|
| 385 |
+
"step": 500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.51,
|
| 389 |
+
"grad_norm": 3.626593589782715,
|
| 390 |
+
"learning_rate": 1.074884845112512e-05,
|
| 391 |
+
"loss": 0.0832,
|
| 392 |
+
"step": 510
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.56,
|
| 396 |
+
"grad_norm": 2.680762529373169,
|
| 397 |
+
"learning_rate": 1.0423532036492077e-05,
|
| 398 |
+
"loss": 0.0659,
|
| 399 |
+
"step": 520
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.61,
|
| 403 |
+
"grad_norm": 9.335197448730469,
|
| 404 |
+
"learning_rate": 1.0097765848728825e-05,
|
| 405 |
+
"loss": 0.0718,
|
| 406 |
+
"step": 530
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.66,
|
| 410 |
+
"grad_norm": 2.929506301879883,
|
| 411 |
+
"learning_rate": 9.771895837764438e-06,
|
| 412 |
+
"loss": 0.0975,
|
| 413 |
+
"step": 540
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.71,
|
| 417 |
+
"grad_norm": 1.251734733581543,
|
| 418 |
+
"learning_rate": 9.446268063783853e-06,
|
| 419 |
+
"loss": 0.0343,
|
| 420 |
+
"step": 550
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.76,
|
| 424 |
+
"grad_norm": 11.404159545898438,
|
| 425 |
+
"learning_rate": 9.121228329726563e-06,
|
| 426 |
+
"loss": 0.0488,
|
| 427 |
+
"step": 560
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.8,
|
| 431 |
+
"grad_norm": 3.3042876720428467,
|
| 432 |
+
"learning_rate": 8.797121814058502e-06,
|
| 433 |
+
"loss": 0.0641,
|
| 434 |
+
"step": 570
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.85,
|
| 438 |
+
"grad_norm": 10.385183334350586,
|
| 439 |
+
"learning_rate": 8.474292704207095e-06,
|
| 440 |
+
"loss": 0.0951,
|
| 441 |
+
"step": 580
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.9,
|
| 445 |
+
"grad_norm": 7.184572219848633,
|
| 446 |
+
"learning_rate": 8.153083831048772e-06,
|
| 447 |
+
"loss": 0.0591,
|
| 448 |
+
"step": 590
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.95,
|
| 452 |
+
"grad_norm": 4.226497650146484,
|
| 453 |
+
"learning_rate": 7.833836304837022e-06,
|
| 454 |
+
"loss": 0.1031,
|
| 455 |
+
"step": 600
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.0,
|
| 459 |
+
"eval_accuracy": 0.9751461988304093,
|
| 460 |
+
"eval_f1": 0.9755012041745224,
|
| 461 |
+
"eval_loss": 0.06017656996846199,
|
| 462 |
+
"eval_matthews_correlation": 0.8118305972172924,
|
| 463 |
+
"eval_precision": 0.9759749663327615,
|
| 464 |
+
"eval_recall": 0.9751461988304093,
|
| 465 |
+
"eval_runtime": 4.1933,
|
| 466 |
+
"eval_samples_per_second": 163.119,
|
| 467 |
+
"eval_steps_per_second": 10.255,
|
| 468 |
+
"step": 609
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.0,
|
| 472 |
+
"grad_norm": 4.557692527770996,
|
| 473 |
+
"learning_rate": 7.516889152957744e-06,
|
| 474 |
+
"loss": 0.0533,
|
| 475 |
+
"step": 610
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 3.05,
|
| 479 |
+
"grad_norm": 3.751300096511841,
|
| 480 |
+
"learning_rate": 7.202578959896491e-06,
|
| 481 |
+
"loss": 0.0782,
|
| 482 |
+
"step": 620
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.1,
|
| 486 |
+
"grad_norm": 4.593023777008057,
|
| 487 |
+
"learning_rate": 6.891239509799932e-06,
|
| 488 |
+
"loss": 0.0627,
|
| 489 |
+
"step": 630
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.15,
|
| 493 |
+
"grad_norm": 4.492953777313232,
|
| 494 |
+
"learning_rate": 6.583201432011217e-06,
|
| 495 |
+
"loss": 0.0564,
|
| 496 |
+
"step": 640
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.2,
|
| 500 |
+
"grad_norm": 3.022425889968872,
|
| 501 |
+
"learning_rate": 6.278791849955583e-06,
|
| 502 |
+
"loss": 0.0719,
|
| 503 |
+
"step": 650
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.25,
|
| 507 |
+
"grad_norm": 4.909082889556885,
|
| 508 |
+
"learning_rate": 5.978334033749076e-06,
|
| 509 |
+
"loss": 0.0531,
|
| 510 |
+
"step": 660
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.3,
|
| 514 |
+
"grad_norm": 2.2064766883850098,
|
| 515 |
+
"learning_rate": 5.682147056899361e-06,
|
| 516 |
+
"loss": 0.0628,
|
| 517 |
+
"step": 670
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 3.35,
|
| 521 |
+
"grad_norm": 5.478167533874512,
|
| 522 |
+
"learning_rate": 5.390545457463134e-06,
|
| 523 |
+
"loss": 0.0705,
|
| 524 |
+
"step": 680
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.39,
|
| 528 |
+
"grad_norm": 5.376189708709717,
|
| 529 |
+
"learning_rate": 5.103838904019993e-06,
|
| 530 |
+
"loss": 0.0888,
|
| 531 |
+
"step": 690
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.44,
|
| 535 |
+
"grad_norm": 3.5109596252441406,
|
| 536 |
+
"learning_rate": 4.822331866817478e-06,
|
| 537 |
+
"loss": 0.0577,
|
| 538 |
+
"step": 700
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.49,
|
| 542 |
+
"grad_norm": 0.5529822707176208,
|
| 543 |
+
"learning_rate": 4.546323294436556e-06,
|
| 544 |
+
"loss": 0.0421,
|
| 545 |
+
"step": 710
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.54,
|
| 549 |
+
"grad_norm": 10.782859802246094,
|
| 550 |
+
"learning_rate": 4.276106296320828e-06,
|
| 551 |
+
"loss": 0.0579,
|
| 552 |
+
"step": 720
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 3.59,
|
| 556 |
+
"grad_norm": 0.36797773838043213,
|
| 557 |
+
"learning_rate": 4.0119678315067025e-06,
|
| 558 |
+
"loss": 0.0381,
|
| 559 |
+
"step": 730
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 3.64,
|
| 563 |
+
"grad_norm": 3.724026679992676,
|
| 564 |
+
"learning_rate": 3.754188403885013e-06,
|
| 565 |
+
"loss": 0.057,
|
| 566 |
+
"step": 740
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.69,
|
| 570 |
+
"grad_norm": 6.234977722167969,
|
| 571 |
+
"learning_rate": 3.5030417643177416e-06,
|
| 572 |
+
"loss": 0.0556,
|
| 573 |
+
"step": 750
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.74,
|
| 577 |
+
"grad_norm": 6.538670063018799,
|
| 578 |
+
"learning_rate": 3.258794619926159e-06,
|
| 579 |
+
"loss": 0.0624,
|
| 580 |
+
"step": 760
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 3.79,
|
| 584 |
+
"grad_norm": 1.8592917919158936,
|
| 585 |
+
"learning_rate": 3.021706350859147e-06,
|
| 586 |
+
"loss": 0.0544,
|
| 587 |
+
"step": 770
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.84,
|
| 591 |
+
"grad_norm": 1.5543180704116821,
|
| 592 |
+
"learning_rate": 2.792028734842418e-06,
|
| 593 |
+
"loss": 0.0321,
|
| 594 |
+
"step": 780
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.89,
|
| 598 |
+
"grad_norm": 6.113970756530762,
|
| 599 |
+
"learning_rate": 2.5700056798012164e-06,
|
| 600 |
+
"loss": 0.052,
|
| 601 |
+
"step": 790
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.94,
|
| 605 |
+
"grad_norm": 6.493689060211182,
|
| 606 |
+
"learning_rate": 2.3558729648404065e-06,
|
| 607 |
+
"loss": 0.046,
|
| 608 |
+
"step": 800
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.99,
|
| 612 |
+
"grad_norm": 3.7167036533355713,
|
| 613 |
+
"learning_rate": 2.1498579898570228e-06,
|
| 614 |
+
"loss": 0.0587,
|
| 615 |
+
"step": 810
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.0,
|
| 619 |
+
"eval_accuracy": 0.9736842105263158,
|
| 620 |
+
"eval_f1": 0.9734187929958467,
|
| 621 |
+
"eval_loss": 0.05119941756129265,
|
| 622 |
+
"eval_matthews_correlation": 0.7904630921052955,
|
| 623 |
+
"eval_precision": 0.9732101510950039,
|
| 624 |
+
"eval_recall": 0.9736842105263158,
|
| 625 |
+
"eval_runtime": 4.2261,
|
| 626 |
+
"eval_samples_per_second": 161.853,
|
| 627 |
+
"eval_steps_per_second": 10.175,
|
| 628 |
+
"step": 813
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.03,
|
| 632 |
+
"grad_norm": 6.378363132476807,
|
| 633 |
+
"learning_rate": 1.952179534051183e-06,
|
| 634 |
+
"loss": 0.0389,
|
| 635 |
+
"step": 820
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.08,
|
| 639 |
+
"grad_norm": 5.403367042541504,
|
| 640 |
+
"learning_rate": 1.763047523591831e-06,
|
| 641 |
+
"loss": 0.0727,
|
| 642 |
+
"step": 830
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.13,
|
| 646 |
+
"grad_norm": 5.556785583496094,
|
| 647 |
+
"learning_rate": 1.5826628086839968e-06,
|
| 648 |
+
"loss": 0.0365,
|
| 649 |
+
"step": 840
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.18,
|
| 653 |
+
"grad_norm": 10.821802139282227,
|
| 654 |
+
"learning_rate": 1.41121695027438e-06,
|
| 655 |
+
"loss": 0.0419,
|
| 656 |
+
"step": 850
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.23,
|
| 660 |
+
"grad_norm": 2.722320795059204,
|
| 661 |
+
"learning_rate": 1.2488920166217034e-06,
|
| 662 |
+
"loss": 0.0404,
|
| 663 |
+
"step": 860
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 4.28,
|
| 667 |
+
"grad_norm": 11.169462203979492,
|
| 668 |
+
"learning_rate": 1.095860389947928e-06,
|
| 669 |
+
"loss": 0.0522,
|
| 670 |
+
"step": 870
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 4.33,
|
| 674 |
+
"grad_norm": 4.065892696380615,
|
| 675 |
+
"learning_rate": 9.522845833756001e-07,
|
| 676 |
+
"loss": 0.0497,
|
| 677 |
+
"step": 880
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 4.38,
|
| 681 |
+
"grad_norm": 11.717745780944824,
|
| 682 |
+
"learning_rate": 8.183170683457986e-07,
|
| 683 |
+
"loss": 0.0543,
|
| 684 |
+
"step": 890
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.43,
|
| 688 |
+
"grad_norm": 3.715181589126587,
|
| 689 |
+
"learning_rate": 6.941001126998892e-07,
|
| 690 |
+
"loss": 0.065,
|
| 691 |
+
"step": 900
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 4.48,
|
| 695 |
+
"grad_norm": 8.879691123962402,
|
| 696 |
+
"learning_rate": 5.797656295970955e-07,
|
| 697 |
+
"loss": 0.0546,
|
| 698 |
+
"step": 910
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.53,
|
| 702 |
+
"grad_norm": 6.542267799377441,
|
| 703 |
+
"learning_rate": 4.754350374283001e-07,
|
| 704 |
+
"loss": 0.0491,
|
| 705 |
+
"step": 920
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.58,
|
| 709 |
+
"grad_norm": 5.4677557945251465,
|
| 710 |
+
"learning_rate": 3.8121913087483033e-07,
|
| 711 |
+
"loss": 0.0434,
|
| 712 |
+
"step": 930
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.62,
|
| 716 |
+
"grad_norm": 5.965972900390625,
|
| 717 |
+
"learning_rate": 2.972179632491989e-07,
|
| 718 |
+
"loss": 0.0594,
|
| 719 |
+
"step": 940
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 4.67,
|
| 723 |
+
"grad_norm": 5.097690105438232,
|
| 724 |
+
"learning_rate": 2.23520740242712e-07,
|
| 725 |
+
"loss": 0.0632,
|
| 726 |
+
"step": 950
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.72,
|
| 730 |
+
"grad_norm": 5.078763961791992,
|
| 731 |
+
"learning_rate": 1.602057251927891e-07,
|
| 732 |
+
"loss": 0.0448,
|
| 733 |
+
"step": 960
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.77,
|
| 737 |
+
"grad_norm": 4.476650714874268,
|
| 738 |
+
"learning_rate": 1.0734015597060222e-07,
|
| 739 |
+
"loss": 0.0481,
|
| 740 |
+
"step": 970
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.82,
|
| 744 |
+
"grad_norm": 3.210946798324585,
|
| 745 |
+
"learning_rate": 6.498017357731035e-08,
|
| 746 |
+
"loss": 0.0604,
|
| 747 |
+
"step": 980
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.87,
|
| 751 |
+
"grad_norm": 6.374156951904297,
|
| 752 |
+
"learning_rate": 3.317076252467133e-08,
|
| 753 |
+
"loss": 0.0406,
|
| 754 |
+
"step": 990
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.92,
|
| 758 |
+
"grad_norm": 2.580352306365967,
|
| 759 |
+
"learning_rate": 1.1945703063402925e-08,
|
| 760 |
+
"loss": 0.0343,
|
| 761 |
+
"step": 1000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.97,
|
| 765 |
+
"grad_norm": 1.094759464263916,
|
| 766 |
+
"learning_rate": 1.327535309979533e-09,
|
| 767 |
+
"loss": 0.038,
|
| 768 |
+
"step": 1010
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.99,
|
| 772 |
+
"eval_accuracy": 0.9809941520467836,
|
| 773 |
+
"eval_f1": 0.9808994233422476,
|
| 774 |
+
"eval_loss": 0.051854074001312256,
|
| 775 |
+
"eval_matthews_correlation": 0.8500768147494288,
|
| 776 |
+
"eval_precision": 0.9808194985441887,
|
| 777 |
+
"eval_recall": 0.9809941520467836,
|
| 778 |
+
"eval_runtime": 4.1997,
|
| 779 |
+
"eval_samples_per_second": 162.87,
|
| 780 |
+
"eval_steps_per_second": 10.239,
|
| 781 |
+
"step": 1015
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 4.99,
|
| 785 |
+
"step": 1015,
|
| 786 |
+
"total_flos": 6.629580853384053e+18,
|
| 787 |
+
"train_loss": 0.08605182834446724,
|
| 788 |
+
"train_runtime": 583.274,
|
| 789 |
+
"train_samples_per_second": 111.397,
|
| 790 |
+
"train_steps_per_second": 1.74
|
| 791 |
+
}
|
| 792 |
+
],
|
| 793 |
+
"logging_steps": 10,
|
| 794 |
+
"max_steps": 1015,
|
| 795 |
+
"num_input_tokens_seen": 0,
|
| 796 |
+
"num_train_epochs": 5,
|
| 797 |
+
"save_steps": 500,
|
| 798 |
+
"total_flos": 6.629580853384053e+18,
|
| 799 |
+
"train_batch_size": 16,
|
| 800 |
+
"trial_name": null,
|
| 801 |
+
"trial_params": null
|
| 802 |
+
}
|