beit-mass-secondstep
Browse files- README.md +46 -53
- all_results.json +6 -6
- config.json +4 -4
- model.safetensors +1 -1
- train_results.json +6 -6
- trainer_state.json +442 -568
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
-
- Accuracy: 0.
|
| 24 |
-
- Precision: 0.
|
| 25 |
-
- Recall: 0.
|
| 26 |
-
- F1 Score: 0.
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -43,11 +43,11 @@ More information needed
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 5e-05
|
| 46 |
-
- train_batch_size:
|
| 47 |
-
- eval_batch_size:
|
| 48 |
- seed: 42
|
| 49 |
- gradient_accumulation_steps: 4
|
| 50 |
-
- total_train_batch_size:
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_ratio: 0.1
|
|
@@ -55,51 +55,44 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
### Training results
|
| 57 |
|
| 58 |
-
| Training Loss | Epoch
|
| 59 |
-
|
| 60 |
-
| No log | 0.
|
| 61 |
-
| No log |
|
| 62 |
-
| No log | 2.
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.0013 | 36.9412 | 157 | 0.6365 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 97 |
-
| 0.0013 | 37.8824 | 161 | 0.6695 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 98 |
-
| 0.0001 | 38.8235 | 165 | 0.6846 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 99 |
-
| 0.0001 | 40.0 | 170 | 0.6930 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 100 |
-
| 0.0001 | 40.9412 | 174 | 0.6958 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 101 |
-
| 0.0001 | 41.8824 | 178 | 0.6967 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 102 |
-
| 0.0044 | 42.3529 | 180 | 0.6952 | 0.9153 | 0.9120 | 0.9153 | 0.9132 |
|
| 103 |
|
| 104 |
|
| 105 |
### Framework versions
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.8528
|
| 23 |
+
- Accuracy: 0.8268
|
| 24 |
+
- Precision: 0.8303
|
| 25 |
+
- Recall: 0.8268
|
| 26 |
+
- F1 Score: 0.8283
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 5e-05
|
| 46 |
+
- train_batch_size: 48
|
| 47 |
+
- eval_batch_size: 48
|
| 48 |
- seed: 42
|
| 49 |
- gradient_accumulation_steps: 4
|
| 50 |
+
- total_train_batch_size: 192
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
|
| 55 |
|
| 56 |
### Training results
|
| 57 |
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
|
| 60 |
+
| No log | 0.8 | 2 | 0.6993 | 0.5882 | 0.5390 | 0.5882 | 0.5541 |
|
| 61 |
+
| No log | 2.0 | 5 | 0.5971 | 0.6863 | 0.6806 | 0.6863 | 0.6033 |
|
| 62 |
+
| No log | 2.8 | 7 | 0.5306 | 0.8039 | 0.8000 | 0.8039 | 0.8006 |
|
| 63 |
+
| No log | 4.0 | 10 | 0.4828 | 0.7255 | 0.7229 | 0.7255 | 0.6859 |
|
| 64 |
+
| No log | 4.8 | 12 | 0.3812 | 0.7843 | 0.7786 | 0.7843 | 0.7784 |
|
| 65 |
+
| 0.5413 | 6.0 | 15 | 0.5268 | 0.7451 | 0.7461 | 0.7451 | 0.7141 |
|
| 66 |
+
| 0.5413 | 6.8 | 17 | 0.5349 | 0.7451 | 0.8556 | 0.7451 | 0.7502 |
|
| 67 |
+
| 0.5413 | 8.0 | 20 | 0.4120 | 0.8039 | 0.8485 | 0.8039 | 0.7756 |
|
| 68 |
+
| 0.5413 | 8.8 | 22 | 0.3156 | 0.8039 | 0.8003 | 0.8039 | 0.7963 |
|
| 69 |
+
| 0.5413 | 10.0 | 25 | 0.3217 | 0.8039 | 0.8061 | 0.8039 | 0.7909 |
|
| 70 |
+
| 0.5413 | 10.8 | 27 | 0.5161 | 0.7843 | 0.7870 | 0.7843 | 0.7664 |
|
| 71 |
+
| 0.0919 | 12.0 | 30 | 0.3677 | 0.8431 | 0.8498 | 0.8431 | 0.8451 |
|
| 72 |
+
| 0.0919 | 12.8 | 32 | 0.4631 | 0.8431 | 0.8407 | 0.8431 | 0.8405 |
|
| 73 |
+
| 0.0919 | 14.0 | 35 | 0.5001 | 0.8235 | 0.8214 | 0.8235 | 0.8221 |
|
| 74 |
+
| 0.0919 | 14.8 | 37 | 0.4489 | 0.8431 | 0.8431 | 0.8431 | 0.8431 |
|
| 75 |
+
| 0.0919 | 16.0 | 40 | 0.5892 | 0.7843 | 0.7799 | 0.7843 | 0.7731 |
|
| 76 |
+
| 0.0919 | 16.8 | 42 | 0.6579 | 0.7843 | 0.7799 | 0.7843 | 0.7731 |
|
| 77 |
+
| 0.006 | 18.0 | 45 | 0.7038 | 0.7843 | 0.7799 | 0.7843 | 0.7731 |
|
| 78 |
+
| 0.006 | 18.8 | 47 | 0.5864 | 0.8627 | 0.8737 | 0.8627 | 0.8651 |
|
| 79 |
+
| 0.006 | 20.0 | 50 | 0.5488 | 0.8627 | 0.8737 | 0.8627 | 0.8651 |
|
| 80 |
+
| 0.006 | 20.8 | 52 | 0.6651 | 0.8039 | 0.8003 | 0.8039 | 0.7963 |
|
| 81 |
+
| 0.006 | 22.0 | 55 | 0.6265 | 0.8039 | 0.8000 | 0.8039 | 0.8006 |
|
| 82 |
+
| 0.006 | 22.8 | 57 | 0.5229 | 0.8627 | 0.8653 | 0.8627 | 0.8637 |
|
| 83 |
+
| 0.0048 | 24.0 | 60 | 0.5421 | 0.8627 | 0.8653 | 0.8627 | 0.8637 |
|
| 84 |
+
| 0.0048 | 24.8 | 62 | 0.6335 | 0.8235 | 0.8205 | 0.8235 | 0.8187 |
|
| 85 |
+
| 0.0048 | 26.0 | 65 | 1.0379 | 0.8039 | 0.8201 | 0.8039 | 0.7841 |
|
| 86 |
+
| 0.0048 | 26.8 | 67 | 0.9758 | 0.8235 | 0.8366 | 0.8235 | 0.8089 |
|
| 87 |
+
| 0.0048 | 28.0 | 70 | 0.6117 | 0.8235 | 0.8205 | 0.8235 | 0.8187 |
|
| 88 |
+
| 0.0048 | 28.8 | 72 | 0.5403 | 0.8627 | 0.8613 | 0.8627 | 0.8617 |
|
| 89 |
+
| 0.0063 | 30.0 | 75 | 0.6469 | 0.8431 | 0.8407 | 0.8431 | 0.8405 |
|
| 90 |
+
| 0.0063 | 30.8 | 77 | 0.7014 | 0.8235 | 0.8205 | 0.8235 | 0.8187 |
|
| 91 |
+
| 0.0063 | 32.0 | 80 | 0.7514 | 0.8235 | 0.8205 | 0.8235 | 0.8187 |
|
| 92 |
+
| 0.0063 | 32.8 | 82 | 0.7771 | 0.8235 | 0.8248 | 0.8235 | 0.8144 |
|
| 93 |
+
| 0.0063 | 34.0 | 85 | 0.7599 | 0.8039 | 0.8003 | 0.8039 | 0.7963 |
|
| 94 |
+
| 0.0063 | 34.8 | 87 | 0.7554 | 0.8039 | 0.8003 | 0.8039 | 0.7963 |
|
| 95 |
+
| 0.0045 | 36.0 | 90 | 0.7308 | 0.8039 | 0.8003 | 0.8039 | 0.7963 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
|
| 97 |
|
| 98 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 36.0,
|
| 3 |
+
"total_flos": 1.2659877490145034e+18,
|
| 4 |
+
"train_loss": 0.10912525819407569,
|
| 5 |
+
"train_runtime": 949.2365,
|
| 6 |
+
"train_samples_per_second": 21.523,
|
| 7 |
+
"train_steps_per_second": 0.095
|
| 8 |
}
|
config.json
CHANGED
|
@@ -14,15 +14,15 @@
|
|
| 14 |
"hidden_dropout_prob": 0.0,
|
| 15 |
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
-
"0": "
|
| 18 |
-
"1": "
|
| 19 |
},
|
| 20 |
"image_size": 224,
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
| 23 |
"label2id": {
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
},
|
| 27 |
"layer_norm_eps": 1e-12,
|
| 28 |
"layer_scale_init_value": 0.1,
|
|
|
|
| 14 |
"hidden_dropout_prob": 0.0,
|
| 15 |
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
+
"0": "Benign",
|
| 18 |
+
"1": "Malignant"
|
| 19 |
},
|
| 20 |
"image_size": 224,
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
| 23 |
"label2id": {
|
| 24 |
+
"Benign": 0,
|
| 25 |
+
"Malignant": 1
|
| 26 |
},
|
| 27 |
"layer_norm_eps": 1e-12,
|
| 28 |
"layer_scale_init_value": 0.1,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343080328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:070c5b244ea67c14e33049ce84f0a492470a5f8f7b7bcefcb07dc7846bf3c7d3
|
| 3 |
size 343080328
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 36.0,
|
| 3 |
+
"total_flos": 1.2659877490145034e+18,
|
| 4 |
+
"train_loss": 0.10912525819407569,
|
| 5 |
+
"train_runtime": 949.2365,
|
| 6 |
+
"train_samples_per_second": 21.523,
|
| 7 |
+
"train_steps_per_second": 0.095
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,642 +1,516 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "beit-base-patch16-224/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_f1_score": 0.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_precision": 0.
|
| 17 |
-
"eval_recall": 0.
|
| 18 |
-
"eval_runtime": 0.
|
| 19 |
-
"eval_samples_per_second":
|
| 20 |
-
"eval_steps_per_second": 2.
|
| 21 |
-
"step":
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch":
|
| 25 |
-
"eval_accuracy": 0.
|
| 26 |
-
"eval_f1_score": 0.
|
| 27 |
-
"eval_loss": 0.
|
| 28 |
-
"eval_precision": 0.
|
| 29 |
-
"eval_recall": 0.
|
| 30 |
-
"eval_runtime":
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second":
|
| 33 |
-
"step":
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 2.
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_f1_score": 0.
|
| 39 |
-
"eval_loss": 0.
|
| 40 |
-
"eval_precision": 0.
|
| 41 |
-
"eval_recall": 0.
|
| 42 |
-
"eval_runtime":
|
| 43 |
-
"eval_samples_per_second":
|
| 44 |
-
"eval_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate": 4.
|
| 51 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"step": 15
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch":
|
| 56 |
-
"eval_accuracy": 0.
|
| 57 |
-
"eval_f1_score": 0.
|
| 58 |
-
"eval_loss": 0.
|
| 59 |
-
"eval_precision": 0.
|
| 60 |
-
"eval_recall": 0.
|
| 61 |
-
"eval_runtime":
|
| 62 |
-
"eval_samples_per_second":
|
| 63 |
-
"eval_steps_per_second":
|
| 64 |
"step": 17
|
| 65 |
},
|
| 66 |
{
|
| 67 |
-
"epoch":
|
| 68 |
-
"eval_accuracy": 0.
|
| 69 |
-
"eval_f1_score": 0.
|
| 70 |
-
"eval_loss": 0.
|
| 71 |
-
"eval_precision": 0.
|
| 72 |
-
"eval_recall": 0.
|
| 73 |
-
"eval_runtime":
|
| 74 |
-
"eval_samples_per_second":
|
| 75 |
-
"eval_steps_per_second":
|
| 76 |
-
"step":
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch":
|
| 80 |
-
"eval_accuracy": 0.
|
| 81 |
-
"eval_f1_score": 0.
|
| 82 |
-
"eval_loss": 0.
|
| 83 |
-
"eval_precision": 0.
|
| 84 |
-
"eval_recall": 0.
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
"step": 25
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"epoch":
|
| 92 |
-
"eval_accuracy": 0.
|
| 93 |
-
"eval_f1_score": 0.
|
| 94 |
-
"eval_loss": 0.
|
| 95 |
-
"eval_precision": 0.
|
| 96 |
-
"eval_recall": 0.
|
| 97 |
-
"eval_runtime":
|
| 98 |
-
"eval_samples_per_second":
|
| 99 |
-
"eval_steps_per_second":
|
| 100 |
-
"step":
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch":
|
| 104 |
-
"grad_norm": 3.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 30
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"eval_accuracy": 0.
|
| 112 |
-
"eval_f1_score": 0.
|
| 113 |
-
"eval_loss": 0.
|
| 114 |
-
"eval_precision": 0.
|
| 115 |
-
"eval_recall": 0.
|
| 116 |
-
"eval_runtime":
|
| 117 |
-
"eval_samples_per_second":
|
| 118 |
-
"eval_steps_per_second":
|
| 119 |
-
"step":
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 8
|
| 123 |
-
"eval_accuracy": 0.
|
| 124 |
-
"eval_f1_score": 0.
|
| 125 |
-
"eval_loss": 0.
|
| 126 |
-
"eval_precision": 0.
|
| 127 |
-
"eval_recall": 0.
|
| 128 |
-
"eval_runtime":
|
| 129 |
-
"eval_samples_per_second":
|
| 130 |
-
"eval_steps_per_second":
|
| 131 |
-
"step":
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch":
|
| 135 |
-
"eval_accuracy": 0.
|
| 136 |
-
"eval_f1_score": 0.
|
| 137 |
-
"eval_loss": 0.
|
| 138 |
-
"eval_precision": 0.
|
| 139 |
-
"eval_recall": 0.
|
| 140 |
-
"eval_runtime":
|
| 141 |
-
"eval_samples_per_second": 53.
|
| 142 |
-
"eval_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 143 |
"step": 42
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"grad_norm":
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 45
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch":
|
| 154 |
-
"eval_accuracy": 0.
|
| 155 |
-
"eval_f1_score": 0.
|
| 156 |
-
"eval_loss": 0.
|
| 157 |
-
"eval_precision": 0.
|
| 158 |
-
"eval_recall": 0.
|
| 159 |
-
"eval_runtime": 1.
|
| 160 |
-
"eval_samples_per_second":
|
| 161 |
-
"eval_steps_per_second": 1.
|
| 162 |
-
"step":
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch":
|
| 166 |
-
"eval_accuracy": 0.
|
| 167 |
-
"eval_f1_score": 0.
|
| 168 |
-
"eval_loss": 0.
|
| 169 |
-
"eval_precision": 0.
|
| 170 |
-
"eval_recall": 0.
|
| 171 |
-
"eval_runtime":
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second":
|
| 174 |
-
"step":
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch":
|
| 178 |
-
"eval_accuracy": 0.
|
| 179 |
-
"eval_f1_score": 0.
|
| 180 |
-
"eval_loss": 0.
|
| 181 |
-
"eval_precision": 0.
|
| 182 |
-
"eval_recall": 0.
|
| 183 |
-
"eval_runtime":
|
| 184 |
-
"eval_samples_per_second":
|
| 185 |
-
"eval_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 186 |
"step": 55
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch":
|
| 190 |
-
"eval_accuracy": 0.
|
| 191 |
-
"eval_f1_score": 0.
|
| 192 |
-
"eval_loss": 0.
|
| 193 |
-
"eval_precision": 0.
|
| 194 |
-
"eval_recall": 0.
|
| 195 |
-
"eval_runtime":
|
| 196 |
-
"eval_samples_per_second":
|
| 197 |
-
"eval_steps_per_second":
|
| 198 |
-
"step":
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"grad_norm":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
"step": 60
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"eval_accuracy": 0.
|
| 210 |
-
"eval_f1_score": 0.
|
| 211 |
-
"eval_loss": 0.
|
| 212 |
-
"eval_precision": 0.
|
| 213 |
-
"eval_recall": 0.
|
| 214 |
-
"eval_runtime":
|
| 215 |
-
"eval_samples_per_second":
|
| 216 |
-
"eval_steps_per_second":
|
| 217 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 218 |
},
|
| 219 |
{
|
| 220 |
-
"epoch":
|
| 221 |
-
"eval_accuracy": 0.
|
| 222 |
-
"eval_f1_score": 0.
|
| 223 |
-
"eval_loss": 0.
|
| 224 |
-
"eval_precision": 0.
|
| 225 |
-
"eval_recall": 0.
|
| 226 |
-
"eval_runtime":
|
| 227 |
-
"eval_samples_per_second":
|
| 228 |
-
"eval_steps_per_second":
|
| 229 |
-
"step":
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch":
|
| 233 |
-
"eval_accuracy": 0.
|
| 234 |
-
"eval_f1_score": 0.
|
| 235 |
-
"eval_loss": 0.
|
| 236 |
-
"eval_precision": 0.
|
| 237 |
-
"eval_recall": 0.
|
| 238 |
-
"eval_runtime":
|
| 239 |
-
"eval_samples_per_second":
|
| 240 |
-
"eval_steps_per_second":
|
| 241 |
"step": 72
|
| 242 |
},
|
| 243 |
{
|
| 244 |
-
"epoch":
|
| 245 |
-
"grad_norm":
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 75
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch":
|
| 252 |
-
"eval_accuracy": 0.
|
| 253 |
-
"eval_f1_score": 0.
|
| 254 |
-
"eval_loss": 0.
|
| 255 |
-
"eval_precision": 0.
|
| 256 |
-
"eval_recall": 0.
|
| 257 |
-
"eval_runtime":
|
| 258 |
-
"eval_samples_per_second":
|
| 259 |
-
"eval_steps_per_second":
|
| 260 |
-
"step":
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 18.823529411764707,
|
| 264 |
-
"eval_accuracy": 0.9322033898305084,
|
| 265 |
-
"eval_f1_score": 0.9322033898305084,
|
| 266 |
-
"eval_loss": 0.44370484352111816,
|
| 267 |
-
"eval_precision": 0.9322033898305084,
|
| 268 |
-
"eval_recall": 0.9322033898305084,
|
| 269 |
-
"eval_runtime": 1.1079,
|
| 270 |
-
"eval_samples_per_second": 53.253,
|
| 271 |
-
"eval_steps_per_second": 1.805,
|
| 272 |
-
"step": 80
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 20.0,
|
| 276 |
-
"eval_accuracy": 0.9322033898305084,
|
| 277 |
-
"eval_f1_score": 0.9322033898305084,
|
| 278 |
-
"eval_loss": 0.4818989932537079,
|
| 279 |
-
"eval_precision": 0.9322033898305084,
|
| 280 |
-
"eval_recall": 0.9322033898305084,
|
| 281 |
-
"eval_runtime": 1.3186,
|
| 282 |
-
"eval_samples_per_second": 44.744,
|
| 283 |
-
"eval_steps_per_second": 1.517,
|
| 284 |
-
"step": 85
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"eval_accuracy": 0.
|
| 289 |
-
"eval_f1_score": 0.
|
| 290 |
-
"eval_loss": 0.
|
| 291 |
-
"eval_precision": 0.
|
| 292 |
-
"eval_recall": 0.
|
| 293 |
-
"eval_runtime": 1.
|
| 294 |
-
"eval_samples_per_second":
|
| 295 |
-
"eval_steps_per_second": 1.
|
| 296 |
-
"step":
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"
|
| 301 |
-
"
|
| 302 |
-
"
|
| 303 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"eval_accuracy": 0.
|
| 308 |
-
"eval_f1_score": 0.
|
| 309 |
-
"eval_loss": 0.
|
| 310 |
-
"eval_precision": 0.
|
| 311 |
-
"eval_recall": 0.
|
| 312 |
-
"eval_runtime":
|
| 313 |
-
"eval_samples_per_second":
|
| 314 |
-
"eval_steps_per_second":
|
| 315 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch":
|
| 319 |
-
"eval_accuracy": 0.
|
| 320 |
-
"eval_f1_score": 0.
|
| 321 |
-
"eval_loss": 0.
|
| 322 |
-
"eval_precision": 0.
|
| 323 |
-
"eval_recall": 0.
|
| 324 |
-
"eval_runtime":
|
| 325 |
-
"eval_samples_per_second":
|
| 326 |
-
"eval_steps_per_second":
|
| 327 |
-
"step":
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch":
|
| 331 |
-
"
|
| 332 |
-
"
|
| 333 |
-
"
|
| 334 |
-
"
|
| 335 |
-
"eval_recall": 0.8983050847457628,
|
| 336 |
-
"eval_runtime": 1.1092,
|
| 337 |
-
"eval_samples_per_second": 53.192,
|
| 338 |
-
"eval_steps_per_second": 1.803,
|
| 339 |
-
"step": 102
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 24.705882352941178,
|
| 343 |
-
"grad_norm": 0.018473587930202484,
|
| 344 |
-
"learning_rate": 2.314814814814815e-05,
|
| 345 |
-
"loss": 0.0028,
|
| 346 |
-
"step": 105
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 24.941176470588236,
|
| 350 |
-
"eval_accuracy": 0.9491525423728814,
|
| 351 |
-
"eval_f1_score": 0.947908749000523,
|
| 352 |
-
"eval_loss": 0.3955690562725067,
|
| 353 |
-
"eval_precision": 0.9476985709538053,
|
| 354 |
-
"eval_recall": 0.9491525423728814,
|
| 355 |
-
"eval_runtime": 1.2914,
|
| 356 |
-
"eval_samples_per_second": 45.688,
|
| 357 |
-
"eval_steps_per_second": 1.549,
|
| 358 |
-
"step": 106
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 25.88235294117647,
|
| 362 |
-
"eval_accuracy": 0.9322033898305084,
|
| 363 |
-
"eval_f1_score": 0.9286307743436357,
|
| 364 |
-
"eval_loss": 0.4670986831188202,
|
| 365 |
-
"eval_precision": 0.9293164462655988,
|
| 366 |
-
"eval_recall": 0.9322033898305084,
|
| 367 |
-
"eval_runtime": 1.1219,
|
| 368 |
-
"eval_samples_per_second": 52.592,
|
| 369 |
-
"eval_steps_per_second": 1.783,
|
| 370 |
-
"step": 110
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 26.823529411764707,
|
| 374 |
-
"eval_accuracy": 0.9322033898305084,
|
| 375 |
-
"eval_f1_score": 0.9322033898305084,
|
| 376 |
-
"eval_loss": 0.3811493515968323,
|
| 377 |
-
"eval_precision": 0.9322033898305084,
|
| 378 |
-
"eval_recall": 0.9322033898305084,
|
| 379 |
-
"eval_runtime": 1.2582,
|
| 380 |
-
"eval_samples_per_second": 46.893,
|
| 381 |
-
"eval_steps_per_second": 1.59,
|
| 382 |
-
"step": 114
|
| 383 |
},
|
| 384 |
{
|
| 385 |
-
"epoch":
|
| 386 |
-
"eval_accuracy": 0.
|
| 387 |
-
"eval_f1_score": 0.
|
| 388 |
-
"eval_loss": 0.
|
| 389 |
-
"eval_precision": 0.
|
| 390 |
-
"eval_recall": 0.
|
| 391 |
-
"eval_runtime":
|
| 392 |
-
"eval_samples_per_second":
|
| 393 |
-
"eval_steps_per_second":
|
| 394 |
-
"step":
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 28.235294117647058,
|
| 398 |
-
"grad_norm": 0.08375111222267151,
|
| 399 |
-
"learning_rate": 1.8518518518518518e-05,
|
| 400 |
-
"loss": 0.0006,
|
| 401 |
-
"step": 120
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 28.941176470588236,
|
| 405 |
-
"eval_accuracy": 0.9322033898305084,
|
| 406 |
-
"eval_f1_score": 0.9322033898305084,
|
| 407 |
-
"eval_loss": 0.40281012654304504,
|
| 408 |
-
"eval_precision": 0.9322033898305084,
|
| 409 |
-
"eval_recall": 0.9322033898305084,
|
| 410 |
-
"eval_runtime": 1.1715,
|
| 411 |
-
"eval_samples_per_second": 50.362,
|
| 412 |
-
"eval_steps_per_second": 1.707,
|
| 413 |
-
"step": 123
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 29.88235294117647,
|
| 417 |
-
"eval_accuracy": 0.9152542372881356,
|
| 418 |
-
"eval_f1_score": 0.9080138226098403,
|
| 419 |
-
"eval_loss": 0.6924118995666504,
|
| 420 |
-
"eval_precision": 0.9106172049888072,
|
| 421 |
-
"eval_recall": 0.9152542372881356,
|
| 422 |
-
"eval_runtime": 1.1072,
|
| 423 |
-
"eval_samples_per_second": 53.287,
|
| 424 |
-
"eval_steps_per_second": 1.806,
|
| 425 |
-
"step": 127
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 30.823529411764707,
|
| 429 |
-
"eval_accuracy": 0.9152542372881356,
|
| 430 |
-
"eval_f1_score": 0.9080138226098403,
|
| 431 |
-
"eval_loss": 0.6948609948158264,
|
| 432 |
-
"eval_precision": 0.9106172049888072,
|
| 433 |
-
"eval_recall": 0.9152542372881356,
|
| 434 |
-
"eval_runtime": 1.1092,
|
| 435 |
-
"eval_samples_per_second": 53.191,
|
| 436 |
-
"eval_steps_per_second": 1.803,
|
| 437 |
-
"step": 131
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 31.764705882352942,
|
| 441 |
-
"grad_norm": 0.0031740041449666023,
|
| 442 |
-
"learning_rate": 1.388888888888889e-05,
|
| 443 |
-
"loss": 0.0033,
|
| 444 |
-
"step": 135
|
| 445 |
},
|
| 446 |
{
|
| 447 |
-
"epoch":
|
| 448 |
-
"
|
| 449 |
-
"
|
| 450 |
-
"
|
| 451 |
-
"
|
| 452 |
-
"
|
| 453 |
-
"
|
| 454 |
-
"eval_samples_per_second": 52.896,
|
| 455 |
-
"eval_steps_per_second": 1.793,
|
| 456 |
-
"step": 136
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 32.94117647058823,
|
| 460 |
-
"eval_accuracy": 0.9322033898305084,
|
| 461 |
-
"eval_f1_score": 0.9322033898305084,
|
| 462 |
-
"eval_loss": 0.5128433108329773,
|
| 463 |
-
"eval_precision": 0.9322033898305084,
|
| 464 |
-
"eval_recall": 0.9322033898305084,
|
| 465 |
-
"eval_runtime": 1.0996,
|
| 466 |
-
"eval_samples_per_second": 53.657,
|
| 467 |
-
"eval_steps_per_second": 1.819,
|
| 468 |
-
"step": 140
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 33.88235294117647,
|
| 472 |
-
"eval_accuracy": 0.9491525423728814,
|
| 473 |
-
"eval_f1_score": 0.9502338280215176,
|
| 474 |
-
"eval_loss": 0.44105064868927,
|
| 475 |
-
"eval_precision": 0.9521964718090626,
|
| 476 |
-
"eval_recall": 0.9491525423728814,
|
| 477 |
-
"eval_runtime": 1.3012,
|
| 478 |
-
"eval_samples_per_second": 45.342,
|
| 479 |
-
"eval_steps_per_second": 1.537,
|
| 480 |
-
"step": 144
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 34.8235294117647,
|
| 484 |
-
"eval_accuracy": 0.9491525423728814,
|
| 485 |
-
"eval_f1_score": 0.9502338280215176,
|
| 486 |
-
"eval_loss": 0.4420201778411865,
|
| 487 |
-
"eval_precision": 0.9521964718090626,
|
| 488 |
-
"eval_recall": 0.9491525423728814,
|
| 489 |
-
"eval_runtime": 1.1093,
|
| 490 |
-
"eval_samples_per_second": 53.188,
|
| 491 |
-
"eval_steps_per_second": 1.803,
|
| 492 |
-
"step": 148
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 35.294117647058826,
|
| 496 |
-
"grad_norm": 0.0013447869569063187,
|
| 497 |
-
"learning_rate": 9.259259259259259e-06,
|
| 498 |
-
"loss": 0.0013,
|
| 499 |
-
"step": 150
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 36.0,
|
| 503 |
-
"eval_accuracy": 0.
|
| 504 |
-
"eval_f1_score": 0.
|
| 505 |
-
"eval_loss": 0.
|
| 506 |
-
"eval_precision": 0.
|
| 507 |
-
"eval_recall": 0.
|
| 508 |
-
"eval_runtime":
|
| 509 |
-
"eval_samples_per_second":
|
| 510 |
-
"eval_steps_per_second": 1.
|
| 511 |
-
"step":
|
| 512 |
-
},
|
| 513 |
-
{
|
| 514 |
-
"epoch": 36.94117647058823,
|
| 515 |
-
"eval_accuracy": 0.9152542372881356,
|
| 516 |
-
"eval_f1_score": 0.9131812483342053,
|
| 517 |
-
"eval_loss": 0.6365456581115723,
|
| 518 |
-
"eval_precision": 0.912013958125623,
|
| 519 |
-
"eval_recall": 0.9152542372881356,
|
| 520 |
-
"eval_runtime": 1.0934,
|
| 521 |
-
"eval_samples_per_second": 53.961,
|
| 522 |
-
"eval_steps_per_second": 1.829,
|
| 523 |
-
"step": 157
|
| 524 |
-
},
|
| 525 |
-
{
|
| 526 |
-
"epoch": 37.88235294117647,
|
| 527 |
-
"eval_accuracy": 0.9152542372881356,
|
| 528 |
-
"eval_f1_score": 0.9131812483342053,
|
| 529 |
-
"eval_loss": 0.6694910526275635,
|
| 530 |
-
"eval_precision": 0.912013958125623,
|
| 531 |
-
"eval_recall": 0.9152542372881356,
|
| 532 |
-
"eval_runtime": 1.0997,
|
| 533 |
-
"eval_samples_per_second": 53.65,
|
| 534 |
-
"eval_steps_per_second": 1.819,
|
| 535 |
-
"step": 161
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 38.8235294117647,
|
| 539 |
-
"grad_norm": 0.0024713820312172174,
|
| 540 |
-
"learning_rate": 4.6296296296296296e-06,
|
| 541 |
-
"loss": 0.0001,
|
| 542 |
-
"step": 165
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 38.8235294117647,
|
| 546 |
-
"eval_accuracy": 0.9152542372881356,
|
| 547 |
-
"eval_f1_score": 0.9131812483342053,
|
| 548 |
-
"eval_loss": 0.6845612525939941,
|
| 549 |
-
"eval_precision": 0.912013958125623,
|
| 550 |
-
"eval_recall": 0.9152542372881356,
|
| 551 |
-
"eval_runtime": 1.1919,
|
| 552 |
-
"eval_samples_per_second": 49.501,
|
| 553 |
-
"eval_steps_per_second": 1.678,
|
| 554 |
-
"step": 165
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 40.0,
|
| 558 |
-
"eval_accuracy": 0.9152542372881356,
|
| 559 |
-
"eval_f1_score": 0.9131812483342053,
|
| 560 |
-
"eval_loss": 0.6930243968963623,
|
| 561 |
-
"eval_precision": 0.912013958125623,
|
| 562 |
-
"eval_recall": 0.9152542372881356,
|
| 563 |
-
"eval_runtime": 1.1022,
|
| 564 |
-
"eval_samples_per_second": 53.53,
|
| 565 |
-
"eval_steps_per_second": 1.815,
|
| 566 |
-
"step": 170
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 40.94117647058823,
|
| 570 |
-
"eval_accuracy": 0.9152542372881356,
|
| 571 |
-
"eval_f1_score": 0.9131812483342053,
|
| 572 |
-
"eval_loss": 0.6957547068595886,
|
| 573 |
-
"eval_precision": 0.912013958125623,
|
| 574 |
-
"eval_recall": 0.9152542372881356,
|
| 575 |
-
"eval_runtime": 1.1025,
|
| 576 |
-
"eval_samples_per_second": 53.515,
|
| 577 |
-
"eval_steps_per_second": 1.814,
|
| 578 |
-
"step": 174
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 41.88235294117647,
|
| 582 |
-
"eval_accuracy": 0.9152542372881356,
|
| 583 |
-
"eval_f1_score": 0.9131812483342053,
|
| 584 |
-
"eval_loss": 0.6966932415962219,
|
| 585 |
-
"eval_precision": 0.912013958125623,
|
| 586 |
-
"eval_recall": 0.9152542372881356,
|
| 587 |
-
"eval_runtime": 1.0997,
|
| 588 |
-
"eval_samples_per_second": 53.649,
|
| 589 |
-
"eval_steps_per_second": 1.819,
|
| 590 |
-
"step": 178
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 42.35294117647059,
|
| 594 |
-
"grad_norm": 0.0012529775267466903,
|
| 595 |
-
"learning_rate": 0.0,
|
| 596 |
-
"loss": 0.0044,
|
| 597 |
-
"step": 180
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 42.35294117647059,
|
| 601 |
-
"eval_accuracy": 0.9152542372881356,
|
| 602 |
-
"eval_f1_score": 0.9131812483342053,
|
| 603 |
-
"eval_loss": 0.6952070593833923,
|
| 604 |
-
"eval_precision": 0.912013958125623,
|
| 605 |
-
"eval_recall": 0.9152542372881356,
|
| 606 |
-
"eval_runtime": 1.142,
|
| 607 |
-
"eval_samples_per_second": 51.664,
|
| 608 |
-
"eval_steps_per_second": 1.751,
|
| 609 |
-
"step": 180
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 42.35294117647059,
|
| 613 |
-
"step": 180,
|
| 614 |
-
"total_flos": 1.7260934287224177e+18,
|
| 615 |
-
"train_loss": 0.030212831471969064,
|
| 616 |
-
"train_runtime": 1290.1323,
|
| 617 |
-
"train_samples_per_second": 18.347,
|
| 618 |
-
"train_steps_per_second": 0.14
|
| 619 |
-
},
|
| 620 |
-
{
|
| 621 |
-
"epoch": 42.35294117647059,
|
| 622 |
-
"eval_accuracy": 0.9387755102040817,
|
| 623 |
-
"eval_f1_score": 0.9412065766745571,
|
| 624 |
-
"eval_loss": 0.3751787841320038,
|
| 625 |
-
"eval_precision": 0.9451036228444866,
|
| 626 |
-
"eval_recall": 0.9387755102040817,
|
| 627 |
-
"eval_runtime": 3.0643,
|
| 628 |
-
"eval_samples_per_second": 47.972,
|
| 629 |
-
"eval_steps_per_second": 1.632,
|
| 630 |
-
"step": 180
|
| 631 |
}
|
| 632 |
],
|
| 633 |
"logging_steps": 15,
|
| 634 |
-
"max_steps":
|
| 635 |
"num_input_tokens_seen": 0,
|
| 636 |
"num_train_epochs": 45,
|
| 637 |
"save_steps": 500,
|
| 638 |
-
"total_flos": 1.
|
| 639 |
-
"train_batch_size":
|
| 640 |
"trial_name": null,
|
| 641 |
"trial_params": null
|
| 642 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8627450980392157,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224/checkpoint-47",
|
| 4 |
+
"epoch": 36.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 90,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.8,
|
| 13 |
+
"eval_accuracy": 0.5882352941176471,
|
| 14 |
+
"eval_f1_score": 0.554074074074074,
|
| 15 |
+
"eval_loss": 0.6992508172988892,
|
| 16 |
+
"eval_precision": 0.5390243902439025,
|
| 17 |
+
"eval_recall": 0.5882352941176471,
|
| 18 |
+
"eval_runtime": 0.8655,
|
| 19 |
+
"eval_samples_per_second": 58.922,
|
| 20 |
+
"eval_steps_per_second": 2.311,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_accuracy": 0.6862745098039216,
|
| 26 |
+
"eval_f1_score": 0.6032520325203252,
|
| 27 |
+
"eval_loss": 0.5970537662506104,
|
| 28 |
+
"eval_precision": 0.6805555555555555,
|
| 29 |
+
"eval_recall": 0.6862745098039216,
|
| 30 |
+
"eval_runtime": 0.8959,
|
| 31 |
+
"eval_samples_per_second": 56.925,
|
| 32 |
+
"eval_steps_per_second": 2.232,
|
| 33 |
+
"step": 5
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.8,
|
| 37 |
+
"eval_accuracy": 0.803921568627451,
|
| 38 |
+
"eval_f1_score": 0.800595238095238,
|
| 39 |
+
"eval_loss": 0.5305531024932861,
|
| 40 |
+
"eval_precision": 0.7999999999999999,
|
| 41 |
+
"eval_recall": 0.803921568627451,
|
| 42 |
+
"eval_runtime": 0.9046,
|
| 43 |
+
"eval_samples_per_second": 56.379,
|
| 44 |
+
"eval_steps_per_second": 2.211,
|
| 45 |
+
"step": 7
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.0,
|
| 49 |
+
"eval_accuracy": 0.7254901960784313,
|
| 50 |
+
"eval_f1_score": 0.6858974358974359,
|
| 51 |
+
"eval_loss": 0.48283636569976807,
|
| 52 |
+
"eval_precision": 0.722943722943723,
|
| 53 |
+
"eval_recall": 0.7254901960784313,
|
| 54 |
+
"eval_runtime": 0.9029,
|
| 55 |
+
"eval_samples_per_second": 56.482,
|
| 56 |
+
"eval_steps_per_second": 2.215,
|
| 57 |
+
"step": 10
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.8,
|
| 61 |
+
"eval_accuracy": 0.7843137254901961,
|
| 62 |
+
"eval_f1_score": 0.7784340451310011,
|
| 63 |
+
"eval_loss": 0.3811856508255005,
|
| 64 |
+
"eval_precision": 0.7786357786357786,
|
| 65 |
+
"eval_recall": 0.7843137254901961,
|
| 66 |
+
"eval_runtime": 0.92,
|
| 67 |
+
"eval_samples_per_second": 55.436,
|
| 68 |
+
"eval_steps_per_second": 2.174,
|
| 69 |
"step": 12
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 6.0,
|
| 73 |
+
"grad_norm": 4.578022480010986,
|
| 74 |
+
"learning_rate": 4.62962962962963e-05,
|
| 75 |
+
"loss": 0.5413,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 6.0,
|
| 80 |
+
"eval_accuracy": 0.7450980392156863,
|
| 81 |
+
"eval_f1_score": 0.7141125541125543,
|
| 82 |
+
"eval_loss": 0.5268120765686035,
|
| 83 |
+
"eval_precision": 0.7461240310077519,
|
| 84 |
+
"eval_recall": 0.7450980392156863,
|
| 85 |
+
"eval_runtime": 0.9096,
|
| 86 |
+
"eval_samples_per_second": 56.066,
|
| 87 |
+
"eval_steps_per_second": 2.199,
|
| 88 |
"step": 15
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"epoch": 6.8,
|
| 92 |
+
"eval_accuracy": 0.7450980392156863,
|
| 93 |
+
"eval_f1_score": 0.7502256608639587,
|
| 94 |
+
"eval_loss": 0.5349109768867493,
|
| 95 |
+
"eval_precision": 0.8555555555555555,
|
| 96 |
+
"eval_recall": 0.7450980392156863,
|
| 97 |
+
"eval_runtime": 0.9137,
|
| 98 |
+
"eval_samples_per_second": 55.818,
|
| 99 |
+
"eval_steps_per_second": 2.189,
|
| 100 |
"step": 17
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_accuracy": 0.803921568627451,
|
| 105 |
+
"eval_f1_score": 0.7756410256410257,
|
| 106 |
+
"eval_loss": 0.4119790494441986,
|
| 107 |
+
"eval_precision": 0.8484848484848485,
|
| 108 |
+
"eval_recall": 0.803921568627451,
|
| 109 |
+
"eval_runtime": 0.9237,
|
| 110 |
+
"eval_samples_per_second": 55.215,
|
| 111 |
+
"eval_steps_per_second": 2.165,
|
| 112 |
+
"step": 20
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.8,
|
| 116 |
+
"eval_accuracy": 0.803921568627451,
|
| 117 |
+
"eval_f1_score": 0.7962962962962962,
|
| 118 |
+
"eval_loss": 0.3156317472457886,
|
| 119 |
+
"eval_precision": 0.8002699055330634,
|
| 120 |
+
"eval_recall": 0.803921568627451,
|
| 121 |
+
"eval_runtime": 0.9335,
|
| 122 |
+
"eval_samples_per_second": 54.63,
|
| 123 |
+
"eval_steps_per_second": 2.142,
|
| 124 |
+
"step": 22
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 10.0,
|
| 128 |
+
"eval_accuracy": 0.803921568627451,
|
| 129 |
+
"eval_f1_score": 0.7908622908622909,
|
| 130 |
+
"eval_loss": 0.3216821253299713,
|
| 131 |
+
"eval_precision": 0.806060606060606,
|
| 132 |
+
"eval_recall": 0.803921568627451,
|
| 133 |
+
"eval_runtime": 0.9256,
|
| 134 |
+
"eval_samples_per_second": 55.1,
|
| 135 |
+
"eval_steps_per_second": 2.161,
|
| 136 |
"step": 25
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 10.8,
|
| 140 |
+
"eval_accuracy": 0.7843137254901961,
|
| 141 |
+
"eval_f1_score": 0.7664197530864199,
|
| 142 |
+
"eval_loss": 0.5160595774650574,
|
| 143 |
+
"eval_precision": 0.7869918699186993,
|
| 144 |
+
"eval_recall": 0.7843137254901961,
|
| 145 |
+
"eval_runtime": 0.9267,
|
| 146 |
+
"eval_samples_per_second": 55.031,
|
| 147 |
+
"eval_steps_per_second": 2.158,
|
| 148 |
+
"step": 27
|
| 149 |
},
|
| 150 |
{
|
| 151 |
+
"epoch": 12.0,
|
| 152 |
+
"grad_norm": 3.5482540130615234,
|
| 153 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 154 |
+
"loss": 0.0919,
|
| 155 |
"step": 30
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 12.0,
|
| 159 |
+
"eval_accuracy": 0.8431372549019608,
|
| 160 |
+
"eval_f1_score": 0.845117845117845,
|
| 161 |
+
"eval_loss": 0.36771491169929504,
|
| 162 |
+
"eval_precision": 0.849780701754386,
|
| 163 |
+
"eval_recall": 0.8431372549019608,
|
| 164 |
+
"eval_runtime": 0.942,
|
| 165 |
+
"eval_samples_per_second": 54.142,
|
| 166 |
+
"eval_steps_per_second": 2.123,
|
| 167 |
+
"step": 30
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 12.8,
|
| 171 |
+
"eval_accuracy": 0.8431372549019608,
|
| 172 |
+
"eval_f1_score": 0.8404761904761906,
|
| 173 |
+
"eval_loss": 0.46310773491859436,
|
| 174 |
+
"eval_precision": 0.8407407407407408,
|
| 175 |
+
"eval_recall": 0.8431372549019608,
|
| 176 |
+
"eval_runtime": 0.9403,
|
| 177 |
+
"eval_samples_per_second": 54.24,
|
| 178 |
+
"eval_steps_per_second": 2.127,
|
| 179 |
+
"step": 32
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 14.0,
|
| 183 |
+
"eval_accuracy": 0.8235294117647058,
|
| 184 |
+
"eval_f1_score": 0.8221343873517787,
|
| 185 |
+
"eval_loss": 0.5000560879707336,
|
| 186 |
+
"eval_precision": 0.8214285714285714,
|
| 187 |
+
"eval_recall": 0.8235294117647058,
|
| 188 |
+
"eval_runtime": 0.9615,
|
| 189 |
+
"eval_samples_per_second": 53.039,
|
| 190 |
+
"eval_steps_per_second": 2.08,
|
| 191 |
+
"step": 35
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.8,
|
| 195 |
+
"eval_accuracy": 0.8431372549019608,
|
| 196 |
+
"eval_f1_score": 0.8431372549019608,
|
| 197 |
+
"eval_loss": 0.4489041268825531,
|
| 198 |
+
"eval_precision": 0.8431372549019608,
|
| 199 |
+
"eval_recall": 0.8431372549019608,
|
| 200 |
+
"eval_runtime": 0.9337,
|
| 201 |
+
"eval_samples_per_second": 54.621,
|
| 202 |
+
"eval_steps_per_second": 2.142,
|
| 203 |
+
"step": 37
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 16.0,
|
| 207 |
+
"eval_accuracy": 0.7843137254901961,
|
| 208 |
+
"eval_f1_score": 0.7731065973862385,
|
| 209 |
+
"eval_loss": 0.5892294049263,
|
| 210 |
+
"eval_precision": 0.7799145299145298,
|
| 211 |
+
"eval_recall": 0.7843137254901961,
|
| 212 |
+
"eval_runtime": 1.0872,
|
| 213 |
+
"eval_samples_per_second": 46.909,
|
| 214 |
+
"eval_steps_per_second": 1.84,
|
| 215 |
+
"step": 40
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 16.8,
|
| 219 |
+
"eval_accuracy": 0.7843137254901961,
|
| 220 |
+
"eval_f1_score": 0.7731065973862385,
|
| 221 |
+
"eval_loss": 0.6578794717788696,
|
| 222 |
+
"eval_precision": 0.7799145299145298,
|
| 223 |
+
"eval_recall": 0.7843137254901961,
|
| 224 |
+
"eval_runtime": 0.9215,
|
| 225 |
+
"eval_samples_per_second": 55.345,
|
| 226 |
+
"eval_steps_per_second": 2.17,
|
| 227 |
"step": 42
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 18.0,
|
| 231 |
+
"grad_norm": 3.25277042388916,
|
| 232 |
+
"learning_rate": 2.777777777777778e-05,
|
| 233 |
+
"loss": 0.006,
|
| 234 |
"step": 45
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 18.0,
|
| 238 |
+
"eval_accuracy": 0.7843137254901961,
|
| 239 |
+
"eval_f1_score": 0.7731065973862385,
|
| 240 |
+
"eval_loss": 0.703818678855896,
|
| 241 |
+
"eval_precision": 0.7799145299145298,
|
| 242 |
+
"eval_recall": 0.7843137254901961,
|
| 243 |
+
"eval_runtime": 1.0077,
|
| 244 |
+
"eval_samples_per_second": 50.61,
|
| 245 |
+
"eval_steps_per_second": 1.985,
|
| 246 |
+
"step": 45
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 18.8,
|
| 250 |
+
"eval_accuracy": 0.8627450980392157,
|
| 251 |
+
"eval_f1_score": 0.865142065142065,
|
| 252 |
+
"eval_loss": 0.5864243507385254,
|
| 253 |
+
"eval_precision": 0.8736559139784946,
|
| 254 |
+
"eval_recall": 0.8627450980392157,
|
| 255 |
+
"eval_runtime": 0.9259,
|
| 256 |
+
"eval_samples_per_second": 55.08,
|
| 257 |
+
"eval_steps_per_second": 2.16,
|
| 258 |
+
"step": 47
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 20.0,
|
| 262 |
+
"eval_accuracy": 0.8627450980392157,
|
| 263 |
+
"eval_f1_score": 0.865142065142065,
|
| 264 |
+
"eval_loss": 0.5488199591636658,
|
| 265 |
+
"eval_precision": 0.8736559139784946,
|
| 266 |
+
"eval_recall": 0.8627450980392157,
|
| 267 |
+
"eval_runtime": 0.9318,
|
| 268 |
+
"eval_samples_per_second": 54.735,
|
| 269 |
+
"eval_steps_per_second": 2.146,
|
| 270 |
+
"step": 50
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 20.8,
|
| 274 |
+
"eval_accuracy": 0.803921568627451,
|
| 275 |
+
"eval_f1_score": 0.7962962962962962,
|
| 276 |
+
"eval_loss": 0.6650967597961426,
|
| 277 |
+
"eval_precision": 0.8002699055330634,
|
| 278 |
+
"eval_recall": 0.803921568627451,
|
| 279 |
+
"eval_runtime": 0.9328,
|
| 280 |
+
"eval_samples_per_second": 54.677,
|
| 281 |
+
"eval_steps_per_second": 2.144,
|
| 282 |
+
"step": 52
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 22.0,
|
| 286 |
+
"eval_accuracy": 0.803921568627451,
|
| 287 |
+
"eval_f1_score": 0.800595238095238,
|
| 288 |
+
"eval_loss": 0.6264931559562683,
|
| 289 |
+
"eval_precision": 0.7999999999999999,
|
| 290 |
+
"eval_recall": 0.803921568627451,
|
| 291 |
+
"eval_runtime": 0.9317,
|
| 292 |
+
"eval_samples_per_second": 54.741,
|
| 293 |
+
"eval_steps_per_second": 2.147,
|
| 294 |
"step": 55
|
| 295 |
},
|
| 296 |
{
|
| 297 |
+
"epoch": 22.8,
|
| 298 |
+
"eval_accuracy": 0.8627450980392157,
|
| 299 |
+
"eval_f1_score": 0.8636815920398009,
|
| 300 |
+
"eval_loss": 0.5228903889656067,
|
| 301 |
+
"eval_precision": 0.8653198653198653,
|
| 302 |
+
"eval_recall": 0.8627450980392157,
|
| 303 |
+
"eval_runtime": 0.9295,
|
| 304 |
+
"eval_samples_per_second": 54.868,
|
| 305 |
+
"eval_steps_per_second": 2.152,
|
| 306 |
+
"step": 57
|
| 307 |
},
|
| 308 |
{
|
| 309 |
+
"epoch": 24.0,
|
| 310 |
+
"grad_norm": 0.0452270582318306,
|
| 311 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 312 |
+
"loss": 0.0048,
|
| 313 |
+
"step": 60
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 24.0,
|
| 317 |
+
"eval_accuracy": 0.8627450980392157,
|
| 318 |
+
"eval_f1_score": 0.8636815920398009,
|
| 319 |
+
"eval_loss": 0.542142927646637,
|
| 320 |
+
"eval_precision": 0.8653198653198653,
|
| 321 |
+
"eval_recall": 0.8627450980392157,
|
| 322 |
+
"eval_runtime": 0.9409,
|
| 323 |
+
"eval_samples_per_second": 54.206,
|
| 324 |
+
"eval_steps_per_second": 2.126,
|
| 325 |
"step": 60
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 24.8,
|
| 329 |
+
"eval_accuracy": 0.8235294117647058,
|
| 330 |
+
"eval_f1_score": 0.8187187641980918,
|
| 331 |
+
"eval_loss": 0.6334545016288757,
|
| 332 |
+
"eval_precision": 0.8204633204633205,
|
| 333 |
+
"eval_recall": 0.8235294117647058,
|
| 334 |
+
"eval_runtime": 0.9368,
|
| 335 |
+
"eval_samples_per_second": 54.438,
|
| 336 |
+
"eval_steps_per_second": 2.135,
|
| 337 |
+
"step": 62
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 26.0,
|
| 341 |
+
"eval_accuracy": 0.803921568627451,
|
| 342 |
+
"eval_f1_score": 0.7840755735492576,
|
| 343 |
+
"eval_loss": 1.0379055738449097,
|
| 344 |
+
"eval_precision": 0.82010582010582,
|
| 345 |
+
"eval_recall": 0.803921568627451,
|
| 346 |
+
"eval_runtime": 0.927,
|
| 347 |
+
"eval_samples_per_second": 55.015,
|
| 348 |
+
"eval_steps_per_second": 2.157,
|
| 349 |
+
"step": 65
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 26.8,
|
| 353 |
+
"eval_accuracy": 0.8235294117647058,
|
| 354 |
+
"eval_f1_score": 0.808888888888889,
|
| 355 |
+
"eval_loss": 0.9758451581001282,
|
| 356 |
+
"eval_precision": 0.8365853658536586,
|
| 357 |
+
"eval_recall": 0.8235294117647058,
|
| 358 |
+
"eval_runtime": 0.927,
|
| 359 |
+
"eval_samples_per_second": 55.017,
|
| 360 |
+
"eval_steps_per_second": 2.158,
|
| 361 |
+
"step": 67
|
| 362 |
},
|
| 363 |
{
|
| 364 |
+
"epoch": 28.0,
|
| 365 |
+
"eval_accuracy": 0.8235294117647058,
|
| 366 |
+
"eval_f1_score": 0.8187187641980918,
|
| 367 |
+
"eval_loss": 0.6116669774055481,
|
| 368 |
+
"eval_precision": 0.8204633204633205,
|
| 369 |
+
"eval_recall": 0.8235294117647058,
|
| 370 |
+
"eval_runtime": 0.9261,
|
| 371 |
+
"eval_samples_per_second": 55.07,
|
| 372 |
+
"eval_steps_per_second": 2.16,
|
| 373 |
+
"step": 70
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 28.8,
|
| 377 |
+
"eval_accuracy": 0.8627450980392157,
|
| 378 |
+
"eval_f1_score": 0.8616600790513834,
|
| 379 |
+
"eval_loss": 0.540273904800415,
|
| 380 |
+
"eval_precision": 0.8613095238095237,
|
| 381 |
+
"eval_recall": 0.8627450980392157,
|
| 382 |
+
"eval_runtime": 0.9247,
|
| 383 |
+
"eval_samples_per_second": 55.15,
|
| 384 |
+
"eval_steps_per_second": 2.163,
|
| 385 |
"step": 72
|
| 386 |
},
|
| 387 |
{
|
| 388 |
+
"epoch": 30.0,
|
| 389 |
+
"grad_norm": 0.026938632130622864,
|
| 390 |
+
"learning_rate": 9.259259259259259e-06,
|
| 391 |
+
"loss": 0.0063,
|
| 392 |
"step": 75
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 30.0,
|
| 396 |
+
"eval_accuracy": 0.8431372549019608,
|
| 397 |
+
"eval_f1_score": 0.8404761904761906,
|
| 398 |
+
"eval_loss": 0.6468568444252014,
|
| 399 |
+
"eval_precision": 0.8407407407407408,
|
| 400 |
+
"eval_recall": 0.8431372549019608,
|
| 401 |
+
"eval_runtime": 0.9235,
|
| 402 |
+
"eval_samples_per_second": 55.223,
|
| 403 |
+
"eval_steps_per_second": 2.166,
|
| 404 |
+
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 30.8,
|
| 408 |
+
"eval_accuracy": 0.8235294117647058,
|
| 409 |
+
"eval_f1_score": 0.8187187641980918,
|
| 410 |
+
"eval_loss": 0.7013790607452393,
|
| 411 |
+
"eval_precision": 0.8204633204633205,
|
| 412 |
+
"eval_recall": 0.8235294117647058,
|
| 413 |
+
"eval_runtime": 1.1388,
|
| 414 |
+
"eval_samples_per_second": 44.785,
|
| 415 |
+
"eval_steps_per_second": 1.756,
|
| 416 |
+
"step": 77
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 32.0,
|
| 420 |
+
"eval_accuracy": 0.8235294117647058,
|
| 421 |
+
"eval_f1_score": 0.8187187641980918,
|
| 422 |
+
"eval_loss": 0.7514360547065735,
|
| 423 |
+
"eval_precision": 0.8204633204633205,
|
| 424 |
+
"eval_recall": 0.8235294117647058,
|
| 425 |
+
"eval_runtime": 0.9424,
|
| 426 |
+
"eval_samples_per_second": 54.118,
|
| 427 |
+
"eval_steps_per_second": 2.122,
|
| 428 |
+
"step": 80
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 32.8,
|
| 432 |
+
"eval_accuracy": 0.8235294117647058,
|
| 433 |
+
"eval_f1_score": 0.8143599433160132,
|
| 434 |
+
"eval_loss": 0.7771488428115845,
|
| 435 |
+
"eval_precision": 0.8247863247863249,
|
| 436 |
+
"eval_recall": 0.8235294117647058,
|
| 437 |
+
"eval_runtime": 0.9338,
|
| 438 |
+
"eval_samples_per_second": 54.616,
|
| 439 |
+
"eval_steps_per_second": 2.142,
|
| 440 |
+
"step": 82
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 34.0,
|
| 444 |
+
"eval_accuracy": 0.803921568627451,
|
| 445 |
+
"eval_f1_score": 0.7962962962962962,
|
| 446 |
+
"eval_loss": 0.7598747611045837,
|
| 447 |
+
"eval_precision": 0.8002699055330634,
|
| 448 |
+
"eval_recall": 0.803921568627451,
|
| 449 |
+
"eval_runtime": 0.9331,
|
| 450 |
+
"eval_samples_per_second": 54.655,
|
| 451 |
+
"eval_steps_per_second": 2.143,
|
| 452 |
+
"step": 85
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 34.8,
|
| 456 |
+
"eval_accuracy": 0.803921568627451,
|
| 457 |
+
"eval_f1_score": 0.7962962962962962,
|
| 458 |
+
"eval_loss": 0.7554459571838379,
|
| 459 |
+
"eval_precision": 0.8002699055330634,
|
| 460 |
+
"eval_recall": 0.803921568627451,
|
| 461 |
+
"eval_runtime": 0.9307,
|
| 462 |
+
"eval_samples_per_second": 54.796,
|
| 463 |
+
"eval_steps_per_second": 2.149,
|
| 464 |
+
"step": 87
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 36.0,
|
| 468 |
+
"grad_norm": 0.014645076356828213,
|
| 469 |
+
"learning_rate": 0.0,
|
| 470 |
+
"loss": 0.0045,
|
| 471 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 36.0,
|
| 475 |
+
"eval_accuracy": 0.803921568627451,
|
| 476 |
+
"eval_f1_score": 0.7962962962962962,
|
| 477 |
+
"eval_loss": 0.7308478951454163,
|
| 478 |
+
"eval_precision": 0.8002699055330634,
|
| 479 |
+
"eval_recall": 0.803921568627451,
|
| 480 |
+
"eval_runtime": 0.9231,
|
| 481 |
+
"eval_samples_per_second": 55.246,
|
| 482 |
+
"eval_steps_per_second": 2.167,
|
| 483 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 36.0,
|
| 487 |
+
"step": 90,
|
| 488 |
+
"total_flos": 1.2659877490145034e+18,
|
| 489 |
+
"train_loss": 0.10912525819407569,
|
| 490 |
+
"train_runtime": 949.2365,
|
| 491 |
+
"train_samples_per_second": 21.523,
|
| 492 |
+
"train_steps_per_second": 0.095
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 36.0,
|
| 496 |
+
"eval_accuracy": 0.8267716535433071,
|
| 497 |
+
"eval_f1_score": 0.8283048858023182,
|
| 498 |
+
"eval_loss": 0.8527529239654541,
|
| 499 |
+
"eval_precision": 0.8302904444636728,
|
| 500 |
+
"eval_recall": 0.8267716535433071,
|
| 501 |
+
"eval_runtime": 2.5545,
|
| 502 |
+
"eval_samples_per_second": 49.716,
|
| 503 |
+
"eval_steps_per_second": 1.174,
|
| 504 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 505 |
}
|
| 506 |
],
|
| 507 |
"logging_steps": 15,
|
| 508 |
+
"max_steps": 90,
|
| 509 |
"num_input_tokens_seen": 0,
|
| 510 |
"num_train_epochs": 45,
|
| 511 |
"save_steps": 500,
|
| 512 |
+
"total_flos": 1.2659877490145034e+18,
|
| 513 |
+
"train_batch_size": 48,
|
| 514 |
"trial_name": null,
|
| 515 |
"trial_params": null
|
| 516 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9c4f61894c45d65bf229deb2fd4dc876cbd903f9e7da4c19cfe4a3825e08c68
|
| 3 |
size 4984
|