End of training
Browse files- README.md +43 -39
- all_results.json +10 -10
- config.json +4 -8
- eval_results.json +6 -6
- model.safetensors +2 -2
- runs/Dec01_16-47-09_DESKTOP-SKBE9FB/events.out.tfevents.1733093230.DESKTOP-SKBE9FB.8952.0 +3 -0
- runs/Dec01_16-47-09_DESKTOP-SKBE9FB/events.out.tfevents.1733093934.DESKTOP-SKBE9FB.8952.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +441 -309
- training_args.bin +1 -1
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/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) 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 |
|
|
@@ -67,42 +67,46 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| No log | 0
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 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.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
|
| 107 |
|
| 108 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8317757009345794
|
| 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/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5393
|
| 36 |
+
- Accuracy: 0.8318
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 8 | 0.6887 | 0.5888 |
|
| 71 |
+
| 0.692 | 2.0 | 16 | 0.6782 | 0.5888 |
|
| 72 |
+
| 0.6801 | 3.0 | 24 | 0.6669 | 0.5888 |
|
| 73 |
+
| 0.6696 | 4.0 | 32 | 0.6644 | 0.5888 |
|
| 74 |
+
| 0.6607 | 5.0 | 40 | 0.6661 | 0.6636 |
|
| 75 |
+
| 0.6607 | 6.0 | 48 | 0.6241 | 0.6542 |
|
| 76 |
+
| 0.6341 | 7.0 | 56 | 0.6235 | 0.6542 |
|
| 77 |
+
| 0.6089 | 8.0 | 64 | 0.6088 | 0.6916 |
|
| 78 |
+
| 0.6095 | 9.0 | 72 | 0.5912 | 0.6916 |
|
| 79 |
+
| 0.5632 | 10.0 | 80 | 0.6607 | 0.6355 |
|
| 80 |
+
| 0.5632 | 11.0 | 88 | 0.5793 | 0.7009 |
|
| 81 |
+
| 0.5418 | 12.0 | 96 | 0.5953 | 0.6822 |
|
| 82 |
+
| 0.5336 | 13.0 | 104 | 0.5793 | 0.7103 |
|
| 83 |
+
| 0.5102 | 14.0 | 112 | 0.5292 | 0.7196 |
|
| 84 |
+
| 0.4762 | 15.0 | 120 | 0.6558 | 0.7009 |
|
| 85 |
+
| 0.4762 | 16.0 | 128 | 0.5371 | 0.7103 |
|
| 86 |
+
| 0.544 | 17.0 | 136 | 0.5401 | 0.7570 |
|
| 87 |
+
| 0.4256 | 18.0 | 144 | 0.4927 | 0.7944 |
|
| 88 |
+
| 0.4082 | 19.0 | 152 | 0.5801 | 0.7383 |
|
| 89 |
+
| 0.4014 | 20.0 | 160 | 0.5823 | 0.7383 |
|
| 90 |
+
| 0.4014 | 21.0 | 168 | 0.5393 | 0.7757 |
|
| 91 |
+
| 0.3483 | 22.0 | 176 | 0.5941 | 0.7103 |
|
| 92 |
+
| 0.3121 | 23.0 | 184 | 0.5569 | 0.7383 |
|
| 93 |
+
| 0.3484 | 24.0 | 192 | 0.5975 | 0.7664 |
|
| 94 |
+
| 0.263 | 25.0 | 200 | 0.6544 | 0.7570 |
|
| 95 |
+
| 0.263 | 26.0 | 208 | 0.5744 | 0.7757 |
|
| 96 |
+
| 0.2633 | 27.0 | 216 | 0.6095 | 0.7664 |
|
| 97 |
+
| 0.2935 | 28.0 | 224 | 0.5286 | 0.7664 |
|
| 98 |
+
| 0.2332 | 29.0 | 232 | 0.6028 | 0.7850 |
|
| 99 |
+
| 0.2314 | 30.0 | 240 | 0.5935 | 0.7944 |
|
| 100 |
+
| 0.2314 | 31.0 | 248 | 0.5393 | 0.8318 |
|
| 101 |
+
| 0.202 | 32.0 | 256 | 0.5556 | 0.8224 |
|
| 102 |
+
| 0.2127 | 33.0 | 264 | 0.5913 | 0.8037 |
|
| 103 |
+
| 0.2035 | 34.0 | 272 | 0.5337 | 0.8037 |
|
| 104 |
+
| 0.2618 | 35.0 | 280 | 0.6221 | 0.8037 |
|
| 105 |
+
| 0.2618 | 36.0 | 288 | 0.5090 | 0.8318 |
|
| 106 |
+
| 0.217 | 37.0 | 296 | 0.5649 | 0.8224 |
|
| 107 |
+
| 0.2111 | 38.0 | 304 | 0.5683 | 0.8131 |
|
| 108 |
+
| 0.2085 | 39.0 | 312 | 0.5398 | 0.8224 |
|
| 109 |
+
| 0.1912 | 40.0 | 320 | 0.5548 | 0.8224 |
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8317757009345794,
|
| 4 |
+
"eval_loss": 0.5392867922782898,
|
| 5 |
+
"eval_runtime": 2.3105,
|
| 6 |
+
"eval_samples_per_second": 46.31,
|
| 7 |
+
"eval_steps_per_second": 3.03,
|
| 8 |
+
"train_loss": 0.4049976162612438,
|
| 9 |
+
"train_runtime": 701.3243,
|
| 10 |
+
"train_samples_per_second": 28.403,
|
| 11 |
+
"train_steps_per_second": 0.456
|
| 12 |
}
|
config.json
CHANGED
|
@@ -14,19 +14,15 @@
|
|
| 14 |
"hidden_dropout_prob": 0.0,
|
| 15 |
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
-
"0": "
|
| 18 |
-
"1": "
|
| 19 |
-
"2": "healthy",
|
| 20 |
-
"3": "inactive"
|
| 21 |
},
|
| 22 |
"image_size": 224,
|
| 23 |
"initializer_range": 0.02,
|
| 24 |
"intermediate_size": 3072,
|
| 25 |
"label2id": {
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"healthy": 2,
|
| 29 |
-
"inactive": 3
|
| 30 |
},
|
| 31 |
"layer_norm_eps": 1e-12,
|
| 32 |
"layer_scale_init_value": 0.1,
|
|
|
|
| 14 |
"hidden_dropout_prob": 0.0,
|
| 15 |
"hidden_size": 768,
|
| 16 |
"id2label": {
|
| 17 |
+
"0": "HR",
|
| 18 |
+
"1": "No HR"
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
"image_size": 224,
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
| 23 |
"label2id": {
|
| 24 |
+
"HR": 0,
|
| 25 |
+
"No HR": 1
|
|
|
|
|
|
|
| 26 |
},
|
| 27 |
"layer_norm_eps": 1e-12,
|
| 28 |
"layer_scale_init_value": 0.1,
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8317757009345794,
|
| 4 |
+
"eval_loss": 0.5392867922782898,
|
| 5 |
+
"eval_runtime": 2.3105,
|
| 6 |
+
"eval_samples_per_second": 46.31,
|
| 7 |
+
"eval_steps_per_second": 3.03
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eeea300ff3a120329583ab7e00d190047c17c87c67ed1e5a5799d0b845cb144
|
| 3 |
+
size 343080328
|
runs/Dec01_16-47-09_DESKTOP-SKBE9FB/events.out.tfevents.1733093230.DESKTOP-SKBE9FB.8952.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb6a8e9bdb89b40f494bf6bdd8f1d6f93f6462b0ae0cbc600c2b435833c9375
|
| 3 |
+
size 23387
|
runs/Dec01_16-47-09_DESKTOP-SKBE9FB/events.out.tfevents.1733093934.DESKTOP-SKBE9FB.8952.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7b161fffc86cb516b20ac597456df212892f3a4f8d5f9685c06b4258273bb69
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"train_loss": 0.4049976162612438,
|
| 4 |
+
"train_runtime": 701.3243,
|
| 5 |
+
"train_samples_per_second": 28.403,
|
| 6 |
+
"train_steps_per_second": 0.456
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,449 +1,581 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "beit-base-patch16-224-OT\\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_loss":
|
| 15 |
-
"eval_runtime": 2.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
-
"eval_accuracy": 0.
|
| 23 |
-
"eval_loss":
|
| 24 |
-
"eval_runtime":
|
| 25 |
-
"eval_samples_per_second":
|
| 26 |
-
"eval_steps_per_second":
|
| 27 |
-
"step":
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 2.
|
| 31 |
"learning_rate": 3.125e-05,
|
| 32 |
-
"loss":
|
| 33 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch":
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"eval_samples_per_second": 27.858,
|
| 41 |
-
"eval_steps_per_second": 1.797,
|
| 42 |
-
"step": 13
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 4.0,
|
| 46 |
-
"eval_accuracy": 0.
|
| 47 |
-
"eval_loss":
|
| 48 |
-
"eval_runtime": 2.
|
| 49 |
-
"eval_samples_per_second":
|
| 50 |
-
"eval_steps_per_second":
|
| 51 |
-
"step":
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
"learning_rate": 4.8611111111111115e-05,
|
| 56 |
-
"loss":
|
| 57 |
-
"step":
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch":
|
| 61 |
-
"eval_accuracy": 0.
|
| 62 |
-
"eval_loss":
|
| 63 |
-
"eval_runtime":
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second":
|
| 66 |
-
"step":
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 6.0,
|
| 70 |
-
"eval_accuracy": 0.
|
| 71 |
-
"eval_loss":
|
| 72 |
-
"eval_runtime": 2.
|
| 73 |
-
"eval_samples_per_second":
|
| 74 |
-
"eval_steps_per_second":
|
| 75 |
-
"step":
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 6.
|
| 79 |
-
"learning_rate": 4.
|
| 80 |
-
"loss":
|
| 81 |
-
"step":
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch":
|
| 85 |
-
"eval_accuracy": 0.
|
| 86 |
-
"eval_loss": 0.
|
| 87 |
-
"eval_runtime":
|
| 88 |
-
"eval_samples_per_second":
|
| 89 |
-
"eval_steps_per_second":
|
| 90 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 8.0,
|
| 94 |
-
"eval_accuracy": 0.
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_runtime": 2.
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second":
|
| 99 |
-
"step":
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 8.
|
| 103 |
-
"learning_rate": 4.
|
| 104 |
-
"loss": 0.
|
| 105 |
-
"step":
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"eval_accuracy": 0.
|
| 110 |
-
"eval_loss": 0.
|
| 111 |
-
"eval_runtime": 2.
|
| 112 |
-
"eval_samples_per_second":
|
| 113 |
-
"eval_steps_per_second":
|
| 114 |
-
"step":
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 10.0,
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"eval_samples_per_second": 23.198,
|
| 122 |
-
"eval_steps_per_second": 1.497,
|
| 123 |
-
"step": 45
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 10.
|
| 127 |
-
"eval_accuracy": 0.
|
| 128 |
-
"eval_loss": 0.
|
| 129 |
-
"eval_runtime": 2.
|
| 130 |
-
"eval_samples_per_second":
|
| 131 |
-
"eval_steps_per_second":
|
| 132 |
-
"step":
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"epoch": 11.
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 12.0,
|
| 142 |
-
"eval_accuracy": 0.
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_runtime": 2.
|
| 145 |
-
"eval_samples_per_second":
|
| 146 |
-
"eval_steps_per_second":
|
| 147 |
-
"step":
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 12.
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"eval_samples_per_second": 27.101,
|
| 155 |
-
"eval_steps_per_second": 1.748,
|
| 156 |
-
"step": 58
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 13.
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 14.0,
|
| 166 |
-
"eval_accuracy": 0.
|
| 167 |
-
"eval_loss": 0.
|
| 168 |
-
"eval_runtime": 2.
|
| 169 |
-
"eval_samples_per_second":
|
| 170 |
-
"eval_steps_per_second":
|
| 171 |
-
"step":
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"eval_samples_per_second": 27.796,
|
| 179 |
-
"eval_steps_per_second": 1.793,
|
| 180 |
-
"step": 67
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch": 15.
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
|
|
|
|
|
|
|
|
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 16.0,
|
| 190 |
-
"eval_accuracy": 0.
|
| 191 |
-
"eval_loss": 0.
|
| 192 |
-
"eval_runtime":
|
| 193 |
-
"eval_samples_per_second":
|
| 194 |
-
"eval_steps_per_second":
|
| 195 |
-
"step":
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 16.
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
"eval_samples_per_second": 27.623,
|
| 203 |
-
"eval_steps_per_second": 1.782,
|
| 204 |
-
"step": 76
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch": 17.
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 18.0,
|
| 214 |
-
"eval_accuracy": 0.
|
| 215 |
-
"eval_loss": 0.
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second":
|
| 219 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"eval_accuracy": 0.
|
| 224 |
-
"eval_loss": 0.
|
| 225 |
-
"eval_runtime":
|
| 226 |
-
"eval_samples_per_second":
|
| 227 |
-
"eval_steps_per_second":
|
| 228 |
-
"step":
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 20.0,
|
| 232 |
-
"learning_rate": 2.
|
| 233 |
-
"loss": 0.
|
| 234 |
-
"step":
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 20.0,
|
| 238 |
-
"eval_accuracy": 0.
|
| 239 |
-
"eval_loss": 0.
|
| 240 |
-
"eval_runtime":
|
| 241 |
-
"eval_samples_per_second":
|
| 242 |
-
"eval_steps_per_second":
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"eval_accuracy": 0.
|
| 248 |
-
"eval_loss": 0.
|
| 249 |
-
"eval_runtime": 2.
|
| 250 |
-
"eval_samples_per_second":
|
| 251 |
-
"eval_steps_per_second":
|
| 252 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 22.0,
|
| 256 |
-
"eval_accuracy": 0.
|
| 257 |
-
"eval_loss": 0.
|
| 258 |
-
"eval_runtime":
|
| 259 |
-
"eval_samples_per_second":
|
| 260 |
-
"eval_steps_per_second":
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 22.
|
| 265 |
-
"learning_rate": 2.
|
| 266 |
-
"loss": 0.
|
| 267 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"
|
| 274 |
-
"eval_samples_per_second": 29.04,
|
| 275 |
-
"eval_steps_per_second": 1.874,
|
| 276 |
-
"step": 103
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 24.0,
|
| 280 |
-
"eval_accuracy": 0.
|
| 281 |
-
"eval_loss": 0.
|
| 282 |
-
"eval_runtime":
|
| 283 |
-
"eval_samples_per_second":
|
| 284 |
-
"eval_steps_per_second":
|
| 285 |
-
"step":
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch":
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss": 0.
|
| 291 |
-
"step":
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch":
|
| 295 |
-
"eval_accuracy": 0.
|
| 296 |
-
"eval_loss": 0.
|
| 297 |
-
"eval_runtime": 2.
|
| 298 |
-
"eval_samples_per_second":
|
| 299 |
-
"eval_steps_per_second":
|
| 300 |
-
"step":
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 26.0,
|
| 304 |
-
"eval_accuracy": 0.
|
| 305 |
-
"eval_loss": 0.
|
| 306 |
-
"eval_runtime": 2.
|
| 307 |
-
"eval_samples_per_second":
|
| 308 |
-
"eval_steps_per_second":
|
| 309 |
-
"step":
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch": 26.
|
| 313 |
-
"learning_rate": 1.
|
| 314 |
-
"loss": 0.
|
| 315 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch":
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"
|
| 322 |
-
"eval_samples_per_second": 26.304,
|
| 323 |
-
"eval_steps_per_second": 1.697,
|
| 324 |
-
"step": 121
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 28.0,
|
| 328 |
-
"eval_accuracy": 0.
|
| 329 |
-
"eval_loss": 0.
|
| 330 |
-
"eval_runtime": 2.
|
| 331 |
-
"eval_samples_per_second":
|
| 332 |
-
"eval_steps_per_second":
|
| 333 |
-
"step":
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch": 28.
|
| 337 |
-
"learning_rate": 1.
|
| 338 |
-
"loss": 0.
|
| 339 |
-
"step":
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch":
|
| 343 |
-
"eval_accuracy": 0.
|
| 344 |
-
"eval_loss": 0.
|
| 345 |
-
"eval_runtime":
|
| 346 |
-
"eval_samples_per_second":
|
| 347 |
-
"eval_steps_per_second":
|
| 348 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 30.0,
|
| 352 |
-
"eval_accuracy": 0.
|
| 353 |
-
"eval_loss": 0.
|
| 354 |
-
"eval_runtime":
|
| 355 |
-
"eval_samples_per_second":
|
| 356 |
-
"eval_steps_per_second":
|
| 357 |
-
"step":
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"eval_accuracy": 0.
|
| 362 |
-
"eval_loss": 0.
|
| 363 |
-
"eval_runtime":
|
| 364 |
-
"eval_samples_per_second":
|
| 365 |
-
"eval_steps_per_second":
|
| 366 |
-
"step":
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch": 31.
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 0.
|
| 372 |
-
"step":
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 32.0,
|
| 376 |
-
"eval_accuracy": 0.
|
| 377 |
-
"eval_loss": 0.
|
| 378 |
-
"eval_runtime": 2.
|
| 379 |
-
"eval_samples_per_second":
|
| 380 |
-
"eval_steps_per_second":
|
| 381 |
-
"step":
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 32.
|
| 385 |
-
"
|
| 386 |
-
"
|
| 387 |
-
"
|
| 388 |
-
"eval_samples_per_second": 27.858,
|
| 389 |
-
"eval_steps_per_second": 1.797,
|
| 390 |
-
"step": 148
|
| 391 |
},
|
| 392 |
{
|
| 393 |
-
"epoch": 33.
|
| 394 |
-
"
|
| 395 |
-
"
|
| 396 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 34.0,
|
| 400 |
-
"eval_accuracy": 0.
|
| 401 |
-
"eval_loss": 0.
|
| 402 |
-
"eval_runtime":
|
| 403 |
-
"eval_samples_per_second":
|
| 404 |
-
"eval_steps_per_second":
|
| 405 |
-
"step":
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch":
|
| 409 |
-
"
|
| 410 |
-
"
|
| 411 |
-
"
|
| 412 |
-
"eval_samples_per_second": 28.631,
|
| 413 |
-
"eval_steps_per_second": 1.847,
|
| 414 |
-
"step": 157
|
| 415 |
},
|
| 416 |
{
|
| 417 |
-
"epoch": 35.
|
| 418 |
-
"
|
| 419 |
-
"
|
| 420 |
-
"
|
|
|
|
|
|
|
|
|
|
| 421 |
},
|
| 422 |
{
|
| 423 |
-
"epoch":
|
| 424 |
-
"eval_accuracy": 0.
|
| 425 |
-
"eval_loss": 0.
|
| 426 |
-
"eval_runtime":
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second":
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"
|
| 434 |
-
"
|
| 435 |
-
"
|
| 436 |
-
|
| 437 |
-
|
| 438 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 439 |
}
|
| 440 |
],
|
| 441 |
"logging_steps": 10,
|
| 442 |
-
"max_steps":
|
| 443 |
"num_input_tokens_seen": 0,
|
| 444 |
"num_train_epochs": 40,
|
| 445 |
"save_steps": 500,
|
| 446 |
-
"total_flos":
|
| 447 |
"train_batch_size": 16,
|
| 448 |
"trial_name": null,
|
| 449 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8317757009345794,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-OT\\checkpoint-248",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 320,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.5887850467289719,
|
| 14 |
+
"eval_loss": 0.6887365579605103,
|
| 15 |
+
"eval_runtime": 2.8498,
|
| 16 |
+
"eval_samples_per_second": 37.546,
|
| 17 |
+
"eval_steps_per_second": 2.456,
|
| 18 |
+
"step": 8
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.25,
|
| 22 |
+
"learning_rate": 1.5625e-05,
|
| 23 |
+
"loss": 0.692,
|
| 24 |
+
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.5887850467289719,
|
| 29 |
+
"eval_loss": 0.678210437297821,
|
| 30 |
+
"eval_runtime": 1.9785,
|
| 31 |
+
"eval_samples_per_second": 54.082,
|
| 32 |
+
"eval_steps_per_second": 3.538,
|
| 33 |
+
"step": 16
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 2.5,
|
| 37 |
"learning_rate": 3.125e-05,
|
| 38 |
+
"loss": 0.6801,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.5887850467289719,
|
| 44 |
+
"eval_loss": 0.6668981313705444,
|
| 45 |
+
"eval_runtime": 2.0656,
|
| 46 |
+
"eval_samples_per_second": 51.802,
|
| 47 |
+
"eval_steps_per_second": 3.389,
|
| 48 |
+
"step": 24
|
| 49 |
},
|
| 50 |
{
|
| 51 |
+
"epoch": 3.75,
|
| 52 |
+
"learning_rate": 4.6875e-05,
|
| 53 |
+
"loss": 0.6696,
|
| 54 |
+
"step": 30
|
|
|
|
|
|
|
|
|
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.5887850467289719,
|
| 59 |
+
"eval_loss": 0.6644209623336792,
|
| 60 |
+
"eval_runtime": 2.1267,
|
| 61 |
+
"eval_samples_per_second": 50.313,
|
| 62 |
+
"eval_steps_per_second": 3.291,
|
| 63 |
+
"step": 32
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
"learning_rate": 4.8611111111111115e-05,
|
| 68 |
+
"loss": 0.6607,
|
| 69 |
+
"step": 40
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"eval_accuracy": 0.6635514018691588,
|
| 74 |
+
"eval_loss": 0.6661449074745178,
|
| 75 |
+
"eval_runtime": 1.995,
|
| 76 |
+
"eval_samples_per_second": 53.635,
|
| 77 |
+
"eval_steps_per_second": 3.509,
|
| 78 |
+
"step": 40
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.6542056074766355,
|
| 83 |
+
"eval_loss": 0.6241438388824463,
|
| 84 |
+
"eval_runtime": 2.0189,
|
| 85 |
+
"eval_samples_per_second": 52.999,
|
| 86 |
+
"eval_steps_per_second": 3.467,
|
| 87 |
+
"step": 48
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 6.25,
|
| 91 |
+
"learning_rate": 4.6875e-05,
|
| 92 |
+
"loss": 0.6341,
|
| 93 |
+
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.6542056074766355,
|
| 98 |
+
"eval_loss": 0.6234968900680542,
|
| 99 |
+
"eval_runtime": 1.9955,
|
| 100 |
+
"eval_samples_per_second": 53.622,
|
| 101 |
+
"eval_steps_per_second": 3.508,
|
| 102 |
+
"step": 56
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.5,
|
| 106 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 107 |
+
"loss": 0.6089,
|
| 108 |
+
"step": 60
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 8.0,
|
| 112 |
+
"eval_accuracy": 0.6915887850467289,
|
| 113 |
+
"eval_loss": 0.6088296175003052,
|
| 114 |
+
"eval_runtime": 2.06,
|
| 115 |
+
"eval_samples_per_second": 51.942,
|
| 116 |
+
"eval_steps_per_second": 3.398,
|
| 117 |
+
"step": 64
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 8.75,
|
| 121 |
+
"learning_rate": 4.340277777777778e-05,
|
| 122 |
+
"loss": 0.6095,
|
| 123 |
+
"step": 70
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 9.0,
|
| 127 |
+
"eval_accuracy": 0.6915887850467289,
|
| 128 |
+
"eval_loss": 0.5911644101142883,
|
| 129 |
+
"eval_runtime": 2.01,
|
| 130 |
+
"eval_samples_per_second": 53.235,
|
| 131 |
+
"eval_steps_per_second": 3.483,
|
| 132 |
+
"step": 72
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 10.0,
|
| 136 |
+
"learning_rate": 4.166666666666667e-05,
|
| 137 |
+
"loss": 0.5632,
|
| 138 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 10.0,
|
| 142 |
+
"eval_accuracy": 0.6355140186915887,
|
| 143 |
+
"eval_loss": 0.660692036151886,
|
| 144 |
+
"eval_runtime": 2.126,
|
| 145 |
+
"eval_samples_per_second": 50.329,
|
| 146 |
+
"eval_steps_per_second": 3.293,
|
| 147 |
+
"step": 80
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 11.0,
|
| 151 |
+
"eval_accuracy": 0.7009345794392523,
|
| 152 |
+
"eval_loss": 0.5792553424835205,
|
| 153 |
+
"eval_runtime": 1.972,
|
| 154 |
+
"eval_samples_per_second": 54.261,
|
| 155 |
+
"eval_steps_per_second": 3.55,
|
| 156 |
+
"step": 88
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.25,
|
| 160 |
+
"learning_rate": 3.993055555555556e-05,
|
| 161 |
+
"loss": 0.5418,
|
| 162 |
+
"step": 90
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 12.0,
|
| 166 |
+
"eval_accuracy": 0.6822429906542056,
|
| 167 |
+
"eval_loss": 0.5953279733657837,
|
| 168 |
+
"eval_runtime": 2.2228,
|
| 169 |
+
"eval_samples_per_second": 48.137,
|
| 170 |
+
"eval_steps_per_second": 3.149,
|
| 171 |
+
"step": 96
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 12.5,
|
| 175 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 176 |
+
"loss": 0.5336,
|
| 177 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"eval_accuracy": 0.7102803738317757,
|
| 182 |
+
"eval_loss": 0.5792534947395325,
|
| 183 |
+
"eval_runtime": 1.991,
|
| 184 |
+
"eval_samples_per_second": 53.742,
|
| 185 |
+
"eval_steps_per_second": 3.516,
|
| 186 |
+
"step": 104
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 13.75,
|
| 190 |
+
"learning_rate": 3.6458333333333336e-05,
|
| 191 |
+
"loss": 0.5102,
|
| 192 |
+
"step": 110
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 14.0,
|
| 196 |
+
"eval_accuracy": 0.719626168224299,
|
| 197 |
+
"eval_loss": 0.5291872024536133,
|
| 198 |
+
"eval_runtime": 2.0585,
|
| 199 |
+
"eval_samples_per_second": 51.98,
|
| 200 |
+
"eval_steps_per_second": 3.401,
|
| 201 |
+
"step": 112
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"learning_rate": 3.472222222222222e-05,
|
| 206 |
+
"loss": 0.4762,
|
| 207 |
+
"step": 120
|
|
|
|
|
|
|
|
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 15.0,
|
| 211 |
+
"eval_accuracy": 0.7009345794392523,
|
| 212 |
+
"eval_loss": 0.6557727456092834,
|
| 213 |
+
"eval_runtime": 1.9985,
|
| 214 |
+
"eval_samples_per_second": 53.541,
|
| 215 |
+
"eval_steps_per_second": 3.503,
|
| 216 |
+
"step": 120
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 16.0,
|
| 220 |
+
"eval_accuracy": 0.7102803738317757,
|
| 221 |
+
"eval_loss": 0.5371208786964417,
|
| 222 |
+
"eval_runtime": 1.971,
|
| 223 |
+
"eval_samples_per_second": 54.288,
|
| 224 |
+
"eval_steps_per_second": 3.552,
|
| 225 |
+
"step": 128
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 16.25,
|
| 229 |
+
"learning_rate": 3.2986111111111115e-05,
|
| 230 |
+
"loss": 0.544,
|
| 231 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 17.0,
|
| 235 |
+
"eval_accuracy": 0.7570093457943925,
|
| 236 |
+
"eval_loss": 0.5400705337524414,
|
| 237 |
+
"eval_runtime": 1.981,
|
| 238 |
+
"eval_samples_per_second": 54.014,
|
| 239 |
+
"eval_steps_per_second": 3.534,
|
| 240 |
+
"step": 136
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 17.5,
|
| 244 |
+
"learning_rate": 3.125e-05,
|
| 245 |
+
"loss": 0.4256,
|
| 246 |
+
"step": 140
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.794392523364486,
|
| 251 |
+
"eval_loss": 0.49267861247062683,
|
| 252 |
+
"eval_runtime": 1.9622,
|
| 253 |
+
"eval_samples_per_second": 54.531,
|
| 254 |
+
"eval_steps_per_second": 3.567,
|
| 255 |
+
"step": 144
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 18.75,
|
| 259 |
+
"learning_rate": 2.951388888888889e-05,
|
| 260 |
+
"loss": 0.4082,
|
| 261 |
+
"step": 150
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"eval_accuracy": 0.7383177570093458,
|
| 266 |
+
"eval_loss": 0.5800967216491699,
|
| 267 |
+
"eval_runtime": 1.9825,
|
| 268 |
+
"eval_samples_per_second": 53.973,
|
| 269 |
+
"eval_steps_per_second": 3.531,
|
| 270 |
+
"step": 152
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 20.0,
|
| 274 |
+
"learning_rate": 2.777777777777778e-05,
|
| 275 |
+
"loss": 0.4014,
|
| 276 |
+
"step": 160
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 20.0,
|
| 280 |
+
"eval_accuracy": 0.7383177570093458,
|
| 281 |
+
"eval_loss": 0.5822688937187195,
|
| 282 |
+
"eval_runtime": 1.985,
|
| 283 |
+
"eval_samples_per_second": 53.905,
|
| 284 |
+
"eval_steps_per_second": 3.526,
|
| 285 |
+
"step": 160
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 21.0,
|
| 289 |
+
"eval_accuracy": 0.7757009345794392,
|
| 290 |
+
"eval_loss": 0.5392723083496094,
|
| 291 |
+
"eval_runtime": 2.117,
|
| 292 |
+
"eval_samples_per_second": 50.542,
|
| 293 |
+
"eval_steps_per_second": 3.306,
|
| 294 |
+
"step": 168
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 21.25,
|
| 298 |
+
"learning_rate": 2.604166666666667e-05,
|
| 299 |
+
"loss": 0.3483,
|
| 300 |
+
"step": 170
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 22.0,
|
| 304 |
+
"eval_accuracy": 0.7102803738317757,
|
| 305 |
+
"eval_loss": 0.5940819382667542,
|
| 306 |
+
"eval_runtime": 1.9765,
|
| 307 |
+
"eval_samples_per_second": 54.137,
|
| 308 |
+
"eval_steps_per_second": 3.542,
|
| 309 |
+
"step": 176
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 22.5,
|
| 313 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 314 |
+
"loss": 0.3121,
|
| 315 |
+
"step": 180
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 23.0,
|
| 319 |
+
"eval_accuracy": 0.7383177570093458,
|
| 320 |
+
"eval_loss": 0.5568514466285706,
|
| 321 |
+
"eval_runtime": 2.1005,
|
| 322 |
+
"eval_samples_per_second": 50.94,
|
| 323 |
+
"eval_steps_per_second": 3.333,
|
| 324 |
+
"step": 184
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 23.75,
|
| 328 |
+
"learning_rate": 2.2569444444444447e-05,
|
| 329 |
+
"loss": 0.3484,
|
| 330 |
+
"step": 190
|
|
|
|
|
|
|
|
|
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 24.0,
|
| 334 |
+
"eval_accuracy": 0.7663551401869159,
|
| 335 |
+
"eval_loss": 0.5975044369697571,
|
| 336 |
+
"eval_runtime": 1.97,
|
| 337 |
+
"eval_samples_per_second": 54.316,
|
| 338 |
+
"eval_steps_per_second": 3.553,
|
| 339 |
+
"step": 192
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 25.0,
|
| 343 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 344 |
+
"loss": 0.263,
|
| 345 |
+
"step": 200
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"eval_accuracy": 0.7570093457943925,
|
| 350 |
+
"eval_loss": 0.6544022560119629,
|
| 351 |
+
"eval_runtime": 2.3716,
|
| 352 |
+
"eval_samples_per_second": 45.118,
|
| 353 |
+
"eval_steps_per_second": 2.952,
|
| 354 |
+
"step": 200
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 26.0,
|
| 358 |
+
"eval_accuracy": 0.7757009345794392,
|
| 359 |
+
"eval_loss": 0.5743973851203918,
|
| 360 |
+
"eval_runtime": 2.0105,
|
| 361 |
+
"eval_samples_per_second": 53.221,
|
| 362 |
+
"eval_steps_per_second": 3.482,
|
| 363 |
+
"step": 208
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 26.25,
|
| 367 |
+
"learning_rate": 1.9097222222222222e-05,
|
| 368 |
+
"loss": 0.2633,
|
| 369 |
+
"step": 210
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 27.0,
|
| 373 |
+
"eval_accuracy": 0.7663551401869159,
|
| 374 |
+
"eval_loss": 0.6095036864280701,
|
| 375 |
+
"eval_runtime": 1.9725,
|
| 376 |
+
"eval_samples_per_second": 54.247,
|
| 377 |
+
"eval_steps_per_second": 3.549,
|
| 378 |
+
"step": 216
|
| 379 |
},
|
| 380 |
{
|
| 381 |
+
"epoch": 27.5,
|
| 382 |
+
"learning_rate": 1.736111111111111e-05,
|
| 383 |
+
"loss": 0.2935,
|
| 384 |
+
"step": 220
|
|
|
|
|
|
|
|
|
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 28.0,
|
| 388 |
+
"eval_accuracy": 0.7663551401869159,
|
| 389 |
+
"eval_loss": 0.528620719909668,
|
| 390 |
+
"eval_runtime": 2.0605,
|
| 391 |
+
"eval_samples_per_second": 51.929,
|
| 392 |
+
"eval_steps_per_second": 3.397,
|
| 393 |
+
"step": 224
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 28.75,
|
| 397 |
+
"learning_rate": 1.5625e-05,
|
| 398 |
+
"loss": 0.2332,
|
| 399 |
+
"step": 230
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 29.0,
|
| 403 |
+
"eval_accuracy": 0.7850467289719626,
|
| 404 |
+
"eval_loss": 0.6027860045433044,
|
| 405 |
+
"eval_runtime": 1.9665,
|
| 406 |
+
"eval_samples_per_second": 54.412,
|
| 407 |
+
"eval_steps_per_second": 3.56,
|
| 408 |
+
"step": 232
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 30.0,
|
| 412 |
+
"learning_rate": 1.388888888888889e-05,
|
| 413 |
+
"loss": 0.2314,
|
| 414 |
+
"step": 240
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 30.0,
|
| 418 |
+
"eval_accuracy": 0.794392523364486,
|
| 419 |
+
"eval_loss": 0.5935384631156921,
|
| 420 |
+
"eval_runtime": 1.962,
|
| 421 |
+
"eval_samples_per_second": 54.537,
|
| 422 |
+
"eval_steps_per_second": 3.568,
|
| 423 |
+
"step": 240
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"epoch": 31.0,
|
| 427 |
+
"eval_accuracy": 0.8317757009345794,
|
| 428 |
+
"eval_loss": 0.5392867922782898,
|
| 429 |
+
"eval_runtime": 1.969,
|
| 430 |
+
"eval_samples_per_second": 54.343,
|
| 431 |
+
"eval_steps_per_second": 3.555,
|
| 432 |
+
"step": 248
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 31.25,
|
| 436 |
+
"learning_rate": 1.2152777777777779e-05,
|
| 437 |
+
"loss": 0.202,
|
| 438 |
+
"step": 250
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 32.0,
|
| 442 |
+
"eval_accuracy": 0.822429906542056,
|
| 443 |
+
"eval_loss": 0.5556337833404541,
|
| 444 |
+
"eval_runtime": 2.012,
|
| 445 |
+
"eval_samples_per_second": 53.182,
|
| 446 |
+
"eval_steps_per_second": 3.479,
|
| 447 |
+
"step": 256
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 32.5,
|
| 451 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 452 |
+
"loss": 0.2127,
|
| 453 |
+
"step": 260
|
|
|
|
|
|
|
|
|
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 33.0,
|
| 457 |
+
"eval_accuracy": 0.8037383177570093,
|
| 458 |
+
"eval_loss": 0.5912833213806152,
|
| 459 |
+
"eval_runtime": 1.98,
|
| 460 |
+
"eval_samples_per_second": 54.041,
|
| 461 |
+
"eval_steps_per_second": 3.535,
|
| 462 |
+
"step": 264
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.75,
|
| 466 |
+
"learning_rate": 8.680555555555556e-06,
|
| 467 |
+
"loss": 0.2035,
|
| 468 |
+
"step": 270
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 34.0,
|
| 472 |
+
"eval_accuracy": 0.8037383177570093,
|
| 473 |
+
"eval_loss": 0.5337203741073608,
|
| 474 |
+
"eval_runtime": 1.9834,
|
| 475 |
+
"eval_samples_per_second": 53.947,
|
| 476 |
+
"eval_steps_per_second": 3.529,
|
| 477 |
+
"step": 272
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 35.0,
|
| 481 |
+
"learning_rate": 6.944444444444445e-06,
|
| 482 |
+
"loss": 0.2618,
|
| 483 |
+
"step": 280
|
|
|
|
|
|
|
|
|
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 35.0,
|
| 487 |
+
"eval_accuracy": 0.8037383177570093,
|
| 488 |
+
"eval_loss": 0.622107982635498,
|
| 489 |
+
"eval_runtime": 2.0025,
|
| 490 |
+
"eval_samples_per_second": 53.434,
|
| 491 |
+
"eval_steps_per_second": 3.496,
|
| 492 |
+
"step": 280
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 36.0,
|
| 496 |
+
"eval_accuracy": 0.8317757009345794,
|
| 497 |
+
"eval_loss": 0.5089600682258606,
|
| 498 |
+
"eval_runtime": 1.9755,
|
| 499 |
+
"eval_samples_per_second": 54.164,
|
| 500 |
+
"eval_steps_per_second": 3.543,
|
| 501 |
+
"step": 288
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 36.25,
|
| 505 |
+
"learning_rate": 5.208333333333334e-06,
|
| 506 |
+
"loss": 0.217,
|
| 507 |
+
"step": 290
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 37.0,
|
| 511 |
+
"eval_accuracy": 0.822429906542056,
|
| 512 |
+
"eval_loss": 0.5649047493934631,
|
| 513 |
+
"eval_runtime": 1.991,
|
| 514 |
+
"eval_samples_per_second": 53.743,
|
| 515 |
+
"eval_steps_per_second": 3.516,
|
| 516 |
+
"step": 296
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 37.5,
|
| 520 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 521 |
+
"loss": 0.2111,
|
| 522 |
+
"step": 300
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 38.0,
|
| 526 |
+
"eval_accuracy": 0.8130841121495327,
|
| 527 |
+
"eval_loss": 0.568317174911499,
|
| 528 |
+
"eval_runtime": 2.0365,
|
| 529 |
+
"eval_samples_per_second": 52.542,
|
| 530 |
+
"eval_steps_per_second": 3.437,
|
| 531 |
+
"step": 304
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 38.75,
|
| 535 |
+
"learning_rate": 1.7361111111111112e-06,
|
| 536 |
+
"loss": 0.2085,
|
| 537 |
+
"step": 310
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 39.0,
|
| 541 |
+
"eval_accuracy": 0.822429906542056,
|
| 542 |
+
"eval_loss": 0.5397838950157166,
|
| 543 |
+
"eval_runtime": 1.9935,
|
| 544 |
+
"eval_samples_per_second": 53.675,
|
| 545 |
+
"eval_steps_per_second": 3.511,
|
| 546 |
+
"step": 312
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 40.0,
|
| 550 |
+
"learning_rate": 0.0,
|
| 551 |
+
"loss": 0.1912,
|
| 552 |
+
"step": 320
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 40.0,
|
| 556 |
+
"eval_accuracy": 0.822429906542056,
|
| 557 |
+
"eval_loss": 0.5548034310340881,
|
| 558 |
+
"eval_runtime": 1.978,
|
| 559 |
+
"eval_samples_per_second": 54.096,
|
| 560 |
+
"eval_steps_per_second": 3.539,
|
| 561 |
+
"step": 320
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"step": 320,
|
| 566 |
+
"total_flos": 1.5429806632629043e+18,
|
| 567 |
+
"train_loss": 0.4049976162612438,
|
| 568 |
+
"train_runtime": 701.3243,
|
| 569 |
+
"train_samples_per_second": 28.403,
|
| 570 |
+
"train_steps_per_second": 0.456
|
| 571 |
}
|
| 572 |
],
|
| 573 |
"logging_steps": 10,
|
| 574 |
+
"max_steps": 320,
|
| 575 |
"num_input_tokens_seen": 0,
|
| 576 |
"num_train_epochs": 40,
|
| 577 |
"save_steps": 500,
|
| 578 |
+
"total_flos": 1.5429806632629043e+18,
|
| 579 |
"train_batch_size": 16,
|
| 580 |
"trial_name": null,
|
| 581 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:289be5ea4287de61c05dc38506ba40eb212d6de2c0bca319801e20a96f6874c0
|
| 3 |
size 4728
|