End of training
Browse files- README.md +40 -41
- all_results.json +10 -10
- eval_results.json +6 -6
- model.safetensors +1 -1
- runs/Dec01_16-28-33_DESKTOP-SKBE9FB/events.out.tfevents.1733092119.DESKTOP-SKBE9FB.15724.0 +3 -0
- runs/Dec01_16-34-25_DESKTOP-SKBE9FB/events.out.tfevents.1733092466.DESKTOP-SKBE9FB.3856.0 +3 -0
- runs/Dec01_16-34-25_DESKTOP-SKBE9FB/events.out.tfevents.1733093058.DESKTOP-SKBE9FB.3856.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +308 -341
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -17,12 +17,12 @@ model-index:
|
|
| 17 |
name: imagefolder
|
| 18 |
type: imagefolder
|
| 19 |
config: default
|
| 20 |
-
split:
|
| 21 |
args: default
|
| 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 |
|
|
@@ -67,43 +67,42 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| No log | 0.
|
| 71 |
-
|
|
| 72 |
-
| 1.
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
| 1.
|
| 76 |
-
| 1.
|
| 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 |
-
| 0.2623 | 36.36 | 200 | 0.3893 | 0.8710 |
|
| 107 |
|
| 108 |
|
| 109 |
### Framework versions
|
|
|
|
| 17 |
name: imagefolder
|
| 18 |
type: imagefolder
|
| 19 |
config: default
|
| 20 |
+
split: validation
|
| 21 |
args: default
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8709677419354839
|
| 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: 0.4334
|
| 36 |
+
- Accuracy: 0.8710
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 0.89 | 4 | 1.3799 | 0.5 |
|
| 71 |
+
| No log | 2.0 | 9 | 1.3424 | 0.4516 |
|
| 72 |
+
| 1.3727 | 2.89 | 13 | 1.2846 | 0.4516 |
|
| 73 |
+
| 1.3727 | 4.0 | 18 | 1.1867 | 0.4516 |
|
| 74 |
+
| 1.262 | 4.89 | 22 | 1.1083 | 0.4516 |
|
| 75 |
+
| 1.262 | 6.0 | 27 | 1.0096 | 0.7419 |
|
| 76 |
+
| 1.0651 | 6.89 | 31 | 0.9655 | 0.6290 |
|
| 77 |
+
| 1.0651 | 8.0 | 36 | 0.7953 | 0.8065 |
|
| 78 |
+
| 0.8729 | 8.89 | 40 | 0.8145 | 0.7742 |
|
| 79 |
+
| 0.8729 | 10.0 | 45 | 0.6767 | 0.7903 |
|
| 80 |
+
| 0.8729 | 10.89 | 49 | 0.6978 | 0.7419 |
|
| 81 |
+
| 0.7206 | 12.0 | 54 | 0.7585 | 0.6935 |
|
| 82 |
+
| 0.7206 | 12.89 | 58 | 0.5204 | 0.8387 |
|
| 83 |
+
| 0.5783 | 14.0 | 63 | 0.6260 | 0.7903 |
|
| 84 |
+
| 0.5783 | 14.89 | 67 | 0.4707 | 0.8387 |
|
| 85 |
+
| 0.4827 | 16.0 | 72 | 0.6392 | 0.8065 |
|
| 86 |
+
| 0.4827 | 16.89 | 76 | 0.4334 | 0.8710 |
|
| 87 |
+
| 0.4465 | 18.0 | 81 | 0.5769 | 0.7903 |
|
| 88 |
+
| 0.4465 | 18.89 | 85 | 0.5047 | 0.8226 |
|
| 89 |
+
| 0.4166 | 20.0 | 90 | 0.5191 | 0.8710 |
|
| 90 |
+
| 0.4166 | 20.89 | 94 | 0.5115 | 0.8226 |
|
| 91 |
+
| 0.4166 | 22.0 | 99 | 0.6454 | 0.7419 |
|
| 92 |
+
| 0.4209 | 22.89 | 103 | 0.5939 | 0.7742 |
|
| 93 |
+
| 0.4209 | 24.0 | 108 | 0.4799 | 0.8710 |
|
| 94 |
+
| 0.3429 | 24.89 | 112 | 0.5511 | 0.8065 |
|
| 95 |
+
| 0.3429 | 26.0 | 117 | 0.4977 | 0.8065 |
|
| 96 |
+
| 0.3344 | 26.89 | 121 | 0.4180 | 0.8710 |
|
| 97 |
+
| 0.3344 | 28.0 | 126 | 0.5254 | 0.8226 |
|
| 98 |
+
| 0.3301 | 28.89 | 130 | 0.5396 | 0.8226 |
|
| 99 |
+
| 0.3301 | 30.0 | 135 | 0.5654 | 0.7903 |
|
| 100 |
+
| 0.3301 | 30.89 | 139 | 0.5932 | 0.8065 |
|
| 101 |
+
| 0.3262 | 32.0 | 144 | 0.5630 | 0.8065 |
|
| 102 |
+
| 0.3262 | 32.89 | 148 | 0.5434 | 0.8065 |
|
| 103 |
+
| 0.2997 | 34.0 | 153 | 0.5314 | 0.8065 |
|
| 104 |
+
| 0.2997 | 34.89 | 157 | 0.5195 | 0.8065 |
|
| 105 |
+
| 0.2891 | 35.56 | 160 | 0.5155 | 0.8065 |
|
|
|
|
| 106 |
|
| 107 |
|
| 108 |
### 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": 1.
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second": 19.
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 35.56,
|
| 3 |
+
"eval_accuracy": 0.8709677419354839,
|
| 4 |
+
"eval_loss": 0.43338534235954285,
|
| 5 |
+
"eval_runtime": 2.5246,
|
| 6 |
+
"eval_samples_per_second": 24.559,
|
| 7 |
+
"eval_steps_per_second": 1.584,
|
| 8 |
+
"train_loss": 0.5975452944636345,
|
| 9 |
+
"train_runtime": 588.8758,
|
| 10 |
+
"train_samples_per_second": 19.563,
|
| 11 |
+
"train_steps_per_second": 0.272
|
| 12 |
}
|
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": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 35.56,
|
| 3 |
+
"eval_accuracy": 0.8709677419354839,
|
| 4 |
+
"eval_loss": 0.43338534235954285,
|
| 5 |
+
"eval_runtime": 2.5246,
|
| 6 |
+
"eval_samples_per_second": 24.559,
|
| 7 |
+
"eval_steps_per_second": 1.584
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343086480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9461d3c4b7148ad7928d9f22de8764e8b5e4a05aca1aba6bff0b3200b36d426b
|
| 3 |
size 343086480
|
runs/Dec01_16-28-33_DESKTOP-SKBE9FB/events.out.tfevents.1733092119.DESKTOP-SKBE9FB.15724.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7da310f272f8d7cfdbe1551cdd4e61cf82d3cac652bc2312b7a5f0187aa8c6d
|
| 3 |
+
size 12259
|
runs/Dec01_16-34-25_DESKTOP-SKBE9FB/events.out.tfevents.1733092466.DESKTOP-SKBE9FB.3856.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abf62d50b1797eb837982840b548d62200aa0b17339f5eb8037fb4ecf791eb92
|
| 3 |
+
size 19611
|
runs/Dec01_16-34-25_DESKTOP-SKBE9FB/events.out.tfevents.1733093058.DESKTOP-SKBE9FB.3856.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36f22657f56ca9309c07907391173190b955b6ecfda37e8abdc5725d85f950c4
|
| 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": 19.
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 35.56,
|
| 3 |
+
"train_loss": 0.5975452944636345,
|
| 4 |
+
"train_runtime": 588.8758,
|
| 5 |
+
"train_samples_per_second": 19.563,
|
| 6 |
+
"train_steps_per_second": 0.272
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,482 +1,449 @@
|
|
| 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": 1.
|
| 15 |
-
"eval_runtime": 2.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second": 1.
|
| 18 |
-
"step":
|
| 19 |
},
|
| 20 |
{
|
| 21 |
-
"epoch":
|
| 22 |
-
"
|
| 23 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 2.
|
| 28 |
"eval_accuracy": 0.45161290322580644,
|
| 29 |
-
"eval_loss": 1.
|
| 30 |
-
"eval_runtime": 2.
|
| 31 |
-
"eval_samples_per_second": 27.
|
| 32 |
-
"eval_steps_per_second": 1.
|
| 33 |
-
"step":
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch":
|
| 37 |
"eval_accuracy": 0.45161290322580644,
|
| 38 |
-
"eval_loss": 1.
|
| 39 |
-
"eval_runtime": 2.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second": 1.
|
| 42 |
-
"step":
|
| 43 |
},
|
| 44 |
{
|
| 45 |
-
"epoch":
|
| 46 |
-
"learning_rate":
|
| 47 |
-
"loss": 1.
|
| 48 |
"step": 20
|
| 49 |
},
|
| 50 |
{
|
| 51 |
-
"epoch": 4.
|
| 52 |
-
"eval_accuracy": 0.
|
| 53 |
-
"eval_loss": 1.
|
| 54 |
-
"eval_runtime": 2.
|
| 55 |
-
"eval_samples_per_second": 27.
|
| 56 |
-
"eval_steps_per_second": 1.
|
| 57 |
"step": 22
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch":
|
| 61 |
"eval_accuracy": 0.7419354838709677,
|
| 62 |
-
"eval_loss": 1.
|
| 63 |
-
"eval_runtime": 2.
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second": 1.
|
| 66 |
"step": 27
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"learning_rate": 4.
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 30
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 6.
|
| 76 |
-
"eval_accuracy": 0.
|
| 77 |
-
"eval_loss": 0.
|
| 78 |
-
"eval_runtime": 2.
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second": 1.
|
| 81 |
-
"step":
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 6.91,
|
| 85 |
-
"eval_accuracy": 0.8387096774193549,
|
| 86 |
-
"eval_loss": 0.7693949937820435,
|
| 87 |
-
"eval_runtime": 2.2431,
|
| 88 |
-
"eval_samples_per_second": 27.641,
|
| 89 |
-
"eval_steps_per_second": 1.783,
|
| 90 |
-
"step": 38
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 7.27,
|
| 94 |
-
"learning_rate": 4.4444444444444447e-05,
|
| 95 |
-
"loss": 0.917,
|
| 96 |
-
"step": 40
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 8.0,
|
| 100 |
"eval_accuracy": 0.8064516129032258,
|
| 101 |
-
"eval_loss": 0.
|
| 102 |
-
"eval_runtime": 2.
|
| 103 |
-
"eval_samples_per_second": 27.
|
| 104 |
-
"eval_steps_per_second": 1.
|
| 105 |
-
"step":
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 8.
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"
|
| 112 |
-
"eval_samples_per_second": 26.729,
|
| 113 |
-
"eval_steps_per_second": 1.724,
|
| 114 |
-
"step": 49
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
|
|
|
|
|
|
|
|
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 10.0,
|
| 124 |
"eval_accuracy": 0.7903225806451613,
|
| 125 |
-
"eval_loss": 0.
|
| 126 |
-
"eval_runtime": 2.
|
| 127 |
-
"eval_samples_per_second":
|
| 128 |
-
"eval_steps_per_second": 1.
|
| 129 |
-
"step":
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 10.
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
"
|
|
|
|
|
|
|
|
|
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"eval_samples_per_second": 26.502,
|
| 143 |
-
"eval_steps_per_second": 1.71,
|
| 144 |
-
"step": 60
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 12.0,
|
| 148 |
-
"eval_accuracy": 0.
|
| 149 |
-
"eval_loss": 0.
|
| 150 |
-
"eval_runtime": 2.
|
| 151 |
-
"eval_samples_per_second":
|
| 152 |
-
"eval_steps_per_second": 1.
|
| 153 |
-
"step":
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 12.
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
|
|
|
|
|
|
|
|
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"eval_samples_per_second": 26.54,
|
| 167 |
-
"eval_steps_per_second": 1.712,
|
| 168 |
-
"step": 71
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 14.0,
|
| 172 |
-
"eval_accuracy": 0.
|
| 173 |
-
"eval_loss": 0.
|
| 174 |
-
"eval_runtime": 2.
|
| 175 |
-
"eval_samples_per_second":
|
| 176 |
-
"eval_steps_per_second": 1.
|
| 177 |
-
"step":
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 14.
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
|
|
|
|
|
|
|
|
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"eval_samples_per_second": 27.403,
|
| 191 |
-
"eval_steps_per_second": 1.768,
|
| 192 |
-
"step": 82
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 16.0,
|
| 196 |
-
"eval_accuracy": 0.
|
| 197 |
-
"eval_loss": 0.
|
| 198 |
-
"eval_runtime": 2.
|
| 199 |
-
"eval_samples_per_second":
|
| 200 |
-
"eval_steps_per_second": 1.
|
| 201 |
-
"step":
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 16.36,
|
| 205 |
-
"learning_rate": 3.055555555555556e-05,
|
| 206 |
-
"loss": 0.47,
|
| 207 |
-
"step": 90
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 16.91,
|
| 211 |
-
"eval_accuracy": 0.8709677419354839,
|
| 212 |
-
"eval_loss": 0.4357836842536926,
|
| 213 |
-
"eval_runtime": 2.5957,
|
| 214 |
-
"eval_samples_per_second": 23.886,
|
| 215 |
-
"eval_steps_per_second": 1.541,
|
| 216 |
-
"step": 93
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"epoch":
|
| 220 |
"eval_accuracy": 0.8709677419354839,
|
| 221 |
-
"eval_loss": 0.
|
| 222 |
-
"eval_runtime": 2.
|
| 223 |
-
"eval_samples_per_second":
|
| 224 |
-
"eval_steps_per_second": 1.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
"learning_rate": 2.777777777777778e-05,
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"step":
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 18.
|
| 235 |
-
"eval_accuracy": 0.
|
| 236 |
-
"eval_loss": 0.
|
| 237 |
-
"eval_runtime": 2.
|
| 238 |
-
"eval_samples_per_second":
|
| 239 |
-
"eval_steps_per_second": 1.
|
| 240 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 20.0,
|
| 244 |
-
"learning_rate": 2.
|
| 245 |
-
"loss": 0.
|
| 246 |
-
"step":
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 20.0,
|
| 250 |
-
"eval_accuracy": 0.
|
| 251 |
-
"eval_loss": 0.
|
| 252 |
-
"eval_runtime": 2.
|
| 253 |
-
"eval_samples_per_second":
|
| 254 |
-
"eval_steps_per_second": 1.
|
| 255 |
-
"step":
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 20.91,
|
| 259 |
-
"eval_accuracy": 0.9193548387096774,
|
| 260 |
-
"eval_loss": 0.3676328957080841,
|
| 261 |
-
"eval_runtime": 2.4661,
|
| 262 |
-
"eval_samples_per_second": 25.141,
|
| 263 |
-
"eval_steps_per_second": 1.622,
|
| 264 |
-
"step": 115
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"epoch":
|
| 268 |
-
"
|
| 269 |
-
"
|
| 270 |
-
"
|
|
|
|
|
|
|
|
|
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 22.0,
|
| 274 |
-
"eval_accuracy": 0.
|
| 275 |
-
"eval_loss": 0.
|
| 276 |
-
"eval_runtime": 2.
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second": 1.
|
| 279 |
-
"step":
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch": 22.
|
| 283 |
-
"
|
| 284 |
-
"
|
| 285 |
-
"
|
| 286 |
-
"eval_samples_per_second": 27.809,
|
| 287 |
-
"eval_steps_per_second": 1.794,
|
| 288 |
-
"step": 126
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch":
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
|
|
|
|
|
|
|
|
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 24.0,
|
| 298 |
-
"eval_accuracy": 0.
|
| 299 |
-
"eval_loss": 0.
|
| 300 |
-
"eval_runtime": 2.
|
| 301 |
-
"eval_samples_per_second":
|
| 302 |
-
"eval_steps_per_second": 1.
|
| 303 |
-
"step":
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 24.
|
| 307 |
-
"
|
| 308 |
-
"
|
| 309 |
-
"
|
| 310 |
-
"eval_samples_per_second": 27.282,
|
| 311 |
-
"eval_steps_per_second": 1.76,
|
| 312 |
-
"step": 137
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"epoch":
|
| 316 |
-
"
|
| 317 |
-
"
|
| 318 |
-
"
|
|
|
|
|
|
|
|
|
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 26.0,
|
| 322 |
-
"eval_accuracy": 0.
|
| 323 |
-
"eval_loss": 0.
|
| 324 |
-
"eval_runtime": 2.
|
| 325 |
-
"eval_samples_per_second":
|
| 326 |
-
"eval_steps_per_second": 1.
|
| 327 |
-
"step":
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 26.91,
|
| 331 |
-
"eval_accuracy": 0.8548387096774194,
|
| 332 |
-
"eval_loss": 0.405973881483078,
|
| 333 |
-
"eval_runtime": 2.3056,
|
| 334 |
-
"eval_samples_per_second": 26.892,
|
| 335 |
-
"eval_steps_per_second": 1.735,
|
| 336 |
-
"step": 148
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch":
|
| 340 |
"learning_rate": 1.388888888888889e-05,
|
| 341 |
-
"loss": 0.
|
| 342 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 28.0,
|
| 346 |
-
"eval_accuracy": 0.
|
| 347 |
-
"eval_loss": 0.
|
| 348 |
-
"eval_runtime": 2.
|
| 349 |
-
"eval_samples_per_second":
|
| 350 |
-
"eval_steps_per_second": 1.
|
| 351 |
-
"step":
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch": 28.
|
| 355 |
-
"
|
| 356 |
-
"
|
| 357 |
-
"
|
| 358 |
-
"eval_samples_per_second": 25.864,
|
| 359 |
-
"eval_steps_per_second": 1.669,
|
| 360 |
-
"step": 159
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch":
|
| 364 |
-
"
|
| 365 |
-
"
|
| 366 |
-
"
|
|
|
|
|
|
|
|
|
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 30.0,
|
| 370 |
-
"eval_accuracy": 0.
|
| 371 |
-
"eval_loss": 0.
|
| 372 |
-
"eval_runtime": 2.
|
| 373 |
-
"eval_samples_per_second":
|
| 374 |
-
"eval_steps_per_second": 1.
|
| 375 |
-
"step":
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch": 30.
|
| 379 |
-
"
|
| 380 |
-
"
|
| 381 |
-
"
|
|
|
|
|
|
|
|
|
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch":
|
| 385 |
-
"
|
| 386 |
-
"
|
| 387 |
-
"
|
| 388 |
-
"eval_samples_per_second": 27.666,
|
| 389 |
-
"eval_steps_per_second": 1.785,
|
| 390 |
-
"step": 170
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 32.0,
|
| 394 |
-
"eval_accuracy": 0.
|
| 395 |
-
"eval_loss": 0.
|
| 396 |
-
"eval_runtime": 2.
|
| 397 |
-
"eval_samples_per_second":
|
| 398 |
-
"eval_steps_per_second": 1.
|
| 399 |
-
"step":
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch": 32.
|
| 403 |
-
"
|
| 404 |
-
"
|
| 405 |
-
"
|
|
|
|
|
|
|
|
|
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch":
|
| 409 |
-
"
|
| 410 |
-
"
|
| 411 |
-
"
|
| 412 |
-
"eval_samples_per_second": 27.312,
|
| 413 |
-
"eval_steps_per_second": 1.762,
|
| 414 |
-
"step": 181
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 34.0,
|
| 418 |
-
"eval_accuracy": 0.
|
| 419 |
-
"eval_loss": 0.
|
| 420 |
-
"eval_runtime": 2.
|
| 421 |
-
"eval_samples_per_second":
|
| 422 |
-
"eval_steps_per_second": 1.
|
| 423 |
-
"step":
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 34.55,
|
| 427 |
-
"learning_rate": 2.777777777777778e-06,
|
| 428 |
-
"loss": 0.2906,
|
| 429 |
-
"step": 190
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 34.
|
| 433 |
-
"eval_accuracy": 0.
|
| 434 |
-
"eval_loss": 0.
|
| 435 |
-
"eval_runtime": 2.
|
| 436 |
-
"eval_samples_per_second": 28.
|
| 437 |
-
"eval_steps_per_second": 1.
|
| 438 |
-
"step":
|
| 439 |
},
|
| 440 |
{
|
| 441 |
-
"epoch":
|
| 442 |
-
"
|
| 443 |
-
"
|
| 444 |
-
"
|
| 445 |
-
"eval_samples_per_second": 28.703,
|
| 446 |
-
"eval_steps_per_second": 1.852,
|
| 447 |
-
"step": 198
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch":
|
| 451 |
-
"
|
| 452 |
-
"
|
| 453 |
-
"
|
|
|
|
|
|
|
|
|
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch":
|
| 457 |
-
"
|
| 458 |
-
"
|
| 459 |
-
"
|
| 460 |
-
"
|
| 461 |
-
"
|
| 462 |
-
"
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 36.36,
|
| 466 |
-
"step": 200,
|
| 467 |
-
"total_flos": 9.859141601338982e+17,
|
| 468 |
-
"train_loss": 0.5621715986728668,
|
| 469 |
-
"train_runtime": 710.3552,
|
| 470 |
-
"train_samples_per_second": 19.708,
|
| 471 |
-
"train_steps_per_second": 0.282
|
| 472 |
}
|
| 473 |
],
|
| 474 |
"logging_steps": 10,
|
| 475 |
-
"max_steps":
|
| 476 |
"num_input_tokens_seen": 0,
|
| 477 |
"num_train_epochs": 40,
|
| 478 |
"save_steps": 500,
|
| 479 |
-
"total_flos":
|
| 480 |
"train_batch_size": 16,
|
| 481 |
"trial_name": null,
|
| 482 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8709677419354839,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-OT\\checkpoint-76",
|
| 4 |
+
"epoch": 35.55555555555556,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 160,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.89,
|
| 13 |
+
"eval_accuracy": 0.5,
|
| 14 |
+
"eval_loss": 1.379904866218567,
|
| 15 |
+
"eval_runtime": 2.315,
|
| 16 |
+
"eval_samples_per_second": 26.782,
|
| 17 |
+
"eval_steps_per_second": 1.728,
|
| 18 |
+
"step": 4
|
| 19 |
},
|
| 20 |
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.45161290322580644,
|
| 23 |
+
"eval_loss": 1.3424019813537598,
|
| 24 |
+
"eval_runtime": 2.1675,
|
| 25 |
+
"eval_samples_per_second": 28.604,
|
| 26 |
+
"eval_steps_per_second": 1.845,
|
| 27 |
+
"step": 9
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.22,
|
| 31 |
+
"learning_rate": 3.125e-05,
|
| 32 |
+
"loss": 1.3727,
|
| 33 |
"step": 10
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 2.89,
|
| 37 |
"eval_accuracy": 0.45161290322580644,
|
| 38 |
+
"eval_loss": 1.2845711708068848,
|
| 39 |
+
"eval_runtime": 2.2255,
|
| 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": 0.45161290322580644,
|
| 47 |
+
"eval_loss": 1.186702847480774,
|
| 48 |
+
"eval_runtime": 2.174,
|
| 49 |
+
"eval_samples_per_second": 28.519,
|
| 50 |
+
"eval_steps_per_second": 1.84,
|
| 51 |
+
"step": 18
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 4.44,
|
| 55 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 56 |
+
"loss": 1.262,
|
| 57 |
"step": 20
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 4.89,
|
| 61 |
+
"eval_accuracy": 0.45161290322580644,
|
| 62 |
+
"eval_loss": 1.1083455085754395,
|
| 63 |
+
"eval_runtime": 2.2285,
|
| 64 |
+
"eval_samples_per_second": 27.821,
|
| 65 |
+
"eval_steps_per_second": 1.795,
|
| 66 |
"step": 22
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 6.0,
|
| 70 |
"eval_accuracy": 0.7419354838709677,
|
| 71 |
+
"eval_loss": 1.0096312761306763,
|
| 72 |
+
"eval_runtime": 2.3886,
|
| 73 |
+
"eval_samples_per_second": 25.957,
|
| 74 |
+
"eval_steps_per_second": 1.675,
|
| 75 |
"step": 27
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 6.67,
|
| 79 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 80 |
+
"loss": 1.0651,
|
| 81 |
"step": 30
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 6.89,
|
| 85 |
+
"eval_accuracy": 0.6290322580645161,
|
| 86 |
+
"eval_loss": 0.965541660785675,
|
| 87 |
+
"eval_runtime": 2.1775,
|
| 88 |
+
"eval_samples_per_second": 28.473,
|
| 89 |
+
"eval_steps_per_second": 1.837,
|
| 90 |
+
"step": 31
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 8.0,
|
| 94 |
"eval_accuracy": 0.8064516129032258,
|
| 95 |
+
"eval_loss": 0.7952606678009033,
|
| 96 |
+
"eval_runtime": 2.2276,
|
| 97 |
+
"eval_samples_per_second": 27.833,
|
| 98 |
+
"eval_steps_per_second": 1.796,
|
| 99 |
+
"step": 36
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 8.89,
|
| 103 |
+
"learning_rate": 4.166666666666667e-05,
|
| 104 |
+
"loss": 0.8729,
|
| 105 |
+
"step": 40
|
|
|
|
|
|
|
|
|
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 8.89,
|
| 109 |
+
"eval_accuracy": 0.7741935483870968,
|
| 110 |
+
"eval_loss": 0.8145327568054199,
|
| 111 |
+
"eval_runtime": 2.2085,
|
| 112 |
+
"eval_samples_per_second": 28.073,
|
| 113 |
+
"eval_steps_per_second": 1.811,
|
| 114 |
+
"step": 40
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 10.0,
|
| 118 |
"eval_accuracy": 0.7903225806451613,
|
| 119 |
+
"eval_loss": 0.6766544580459595,
|
| 120 |
+
"eval_runtime": 2.6727,
|
| 121 |
+
"eval_samples_per_second": 23.198,
|
| 122 |
+
"eval_steps_per_second": 1.497,
|
| 123 |
+
"step": 45
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 10.89,
|
| 127 |
+
"eval_accuracy": 0.7419354838709677,
|
| 128 |
+
"eval_loss": 0.6978453993797302,
|
| 129 |
+
"eval_runtime": 2.1745,
|
| 130 |
+
"eval_samples_per_second": 28.512,
|
| 131 |
+
"eval_steps_per_second": 1.839,
|
| 132 |
+
"step": 49
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 11.11,
|
| 136 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 137 |
+
"loss": 0.7206,
|
| 138 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 12.0,
|
| 142 |
+
"eval_accuracy": 0.6935483870967742,
|
| 143 |
+
"eval_loss": 0.7585192918777466,
|
| 144 |
+
"eval_runtime": 2.1875,
|
| 145 |
+
"eval_samples_per_second": 28.342,
|
| 146 |
+
"eval_steps_per_second": 1.829,
|
| 147 |
+
"step": 54
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 12.89,
|
| 151 |
+
"eval_accuracy": 0.8387096774193549,
|
| 152 |
+
"eval_loss": 0.5204325318336487,
|
| 153 |
+
"eval_runtime": 2.2877,
|
| 154 |
+
"eval_samples_per_second": 27.101,
|
| 155 |
+
"eval_steps_per_second": 1.748,
|
| 156 |
+
"step": 58
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 13.33,
|
| 160 |
+
"learning_rate": 3.472222222222222e-05,
|
| 161 |
+
"loss": 0.5783,
|
| 162 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 14.0,
|
| 166 |
+
"eval_accuracy": 0.7903225806451613,
|
| 167 |
+
"eval_loss": 0.6260057687759399,
|
| 168 |
+
"eval_runtime": 2.148,
|
| 169 |
+
"eval_samples_per_second": 28.864,
|
| 170 |
+
"eval_steps_per_second": 1.862,
|
| 171 |
+
"step": 63
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 14.89,
|
| 175 |
+
"eval_accuracy": 0.8387096774193549,
|
| 176 |
+
"eval_loss": 0.47068876028060913,
|
| 177 |
+
"eval_runtime": 2.2305,
|
| 178 |
+
"eval_samples_per_second": 27.796,
|
| 179 |
+
"eval_steps_per_second": 1.793,
|
| 180 |
+
"step": 67
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"epoch": 15.56,
|
| 184 |
+
"learning_rate": 3.125e-05,
|
| 185 |
+
"loss": 0.4827,
|
| 186 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 16.0,
|
| 190 |
+
"eval_accuracy": 0.8064516129032258,
|
| 191 |
+
"eval_loss": 0.6392358541488647,
|
| 192 |
+
"eval_runtime": 2.274,
|
| 193 |
+
"eval_samples_per_second": 27.264,
|
| 194 |
+
"eval_steps_per_second": 1.759,
|
| 195 |
+
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 16.89,
|
| 199 |
"eval_accuracy": 0.8709677419354839,
|
| 200 |
+
"eval_loss": 0.43338534235954285,
|
| 201 |
+
"eval_runtime": 2.2445,
|
| 202 |
+
"eval_samples_per_second": 27.623,
|
| 203 |
+
"eval_steps_per_second": 1.782,
|
| 204 |
+
"step": 76
|
| 205 |
},
|
| 206 |
{
|
| 207 |
+
"epoch": 17.78,
|
| 208 |
"learning_rate": 2.777777777777778e-05,
|
| 209 |
+
"loss": 0.4465,
|
| 210 |
+
"step": 80
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"epoch": 18.0,
|
| 214 |
+
"eval_accuracy": 0.7903225806451613,
|
| 215 |
+
"eval_loss": 0.5768514275550842,
|
| 216 |
+
"eval_runtime": 2.222,
|
| 217 |
+
"eval_samples_per_second": 27.902,
|
| 218 |
+
"eval_steps_per_second": 1.8,
|
| 219 |
+
"step": 81
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 18.89,
|
| 223 |
+
"eval_accuracy": 0.8225806451612904,
|
| 224 |
+
"eval_loss": 0.5046879053115845,
|
| 225 |
+
"eval_runtime": 2.2336,
|
| 226 |
+
"eval_samples_per_second": 27.758,
|
| 227 |
+
"eval_steps_per_second": 1.791,
|
| 228 |
+
"step": 85
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 20.0,
|
| 232 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 233 |
+
"loss": 0.4166,
|
| 234 |
+
"step": 90
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 20.0,
|
| 238 |
+
"eval_accuracy": 0.8709677419354839,
|
| 239 |
+
"eval_loss": 0.5190597772598267,
|
| 240 |
+
"eval_runtime": 2.2074,
|
| 241 |
+
"eval_samples_per_second": 28.087,
|
| 242 |
+
"eval_steps_per_second": 1.812,
|
| 243 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 20.89,
|
| 247 |
+
"eval_accuracy": 0.8225806451612904,
|
| 248 |
+
"eval_loss": 0.5115006566047668,
|
| 249 |
+
"eval_runtime": 2.1835,
|
| 250 |
+
"eval_samples_per_second": 28.395,
|
| 251 |
+
"eval_steps_per_second": 1.832,
|
| 252 |
+
"step": 94
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 22.0,
|
| 256 |
+
"eval_accuracy": 0.7419354838709677,
|
| 257 |
+
"eval_loss": 0.6454288959503174,
|
| 258 |
+
"eval_runtime": 2.19,
|
| 259 |
+
"eval_samples_per_second": 28.31,
|
| 260 |
+
"eval_steps_per_second": 1.826,
|
| 261 |
+
"step": 99
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 22.22,
|
| 265 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 266 |
+
"loss": 0.4209,
|
| 267 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 22.89,
|
| 271 |
+
"eval_accuracy": 0.7741935483870968,
|
| 272 |
+
"eval_loss": 0.5938693881034851,
|
| 273 |
+
"eval_runtime": 2.135,
|
| 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": 0.8709677419354839,
|
| 281 |
+
"eval_loss": 0.4799472391605377,
|
| 282 |
+
"eval_runtime": 2.2005,
|
| 283 |
+
"eval_samples_per_second": 28.175,
|
| 284 |
+
"eval_steps_per_second": 1.818,
|
| 285 |
+
"step": 108
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 24.44,
|
| 289 |
+
"learning_rate": 1.736111111111111e-05,
|
| 290 |
+
"loss": 0.3429,
|
| 291 |
+
"step": 110
|
|
|
|
|
|
|
|
|
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 24.89,
|
| 295 |
+
"eval_accuracy": 0.8064516129032258,
|
| 296 |
+
"eval_loss": 0.5510820150375366,
|
| 297 |
+
"eval_runtime": 2.216,
|
| 298 |
+
"eval_samples_per_second": 27.978,
|
| 299 |
+
"eval_steps_per_second": 1.805,
|
| 300 |
+
"step": 112
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 26.0,
|
| 304 |
+
"eval_accuracy": 0.8064516129032258,
|
| 305 |
+
"eval_loss": 0.4977356493473053,
|
| 306 |
+
"eval_runtime": 2.1565,
|
| 307 |
+
"eval_samples_per_second": 28.75,
|
| 308 |
+
"eval_steps_per_second": 1.855,
|
| 309 |
+
"step": 117
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 26.67,
|
| 313 |
"learning_rate": 1.388888888888889e-05,
|
| 314 |
+
"loss": 0.3344,
|
| 315 |
+
"step": 120
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 26.89,
|
| 319 |
+
"eval_accuracy": 0.8709677419354839,
|
| 320 |
+
"eval_loss": 0.41801995038986206,
|
| 321 |
+
"eval_runtime": 2.357,
|
| 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": 0.8225806451612904,
|
| 329 |
+
"eval_loss": 0.5254219770431519,
|
| 330 |
+
"eval_runtime": 2.3326,
|
| 331 |
+
"eval_samples_per_second": 26.58,
|
| 332 |
+
"eval_steps_per_second": 1.715,
|
| 333 |
+
"step": 126
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 28.89,
|
| 337 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 338 |
+
"loss": 0.3301,
|
| 339 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 28.89,
|
| 343 |
+
"eval_accuracy": 0.8225806451612904,
|
| 344 |
+
"eval_loss": 0.5396197438240051,
|
| 345 |
+
"eval_runtime": 2.0979,
|
| 346 |
+
"eval_samples_per_second": 29.553,
|
| 347 |
+
"eval_steps_per_second": 1.907,
|
| 348 |
+
"step": 130
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 30.0,
|
| 352 |
+
"eval_accuracy": 0.7903225806451613,
|
| 353 |
+
"eval_loss": 0.5654030442237854,
|
| 354 |
+
"eval_runtime": 2.3721,
|
| 355 |
+
"eval_samples_per_second": 26.138,
|
| 356 |
+
"eval_steps_per_second": 1.686,
|
| 357 |
+
"step": 135
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 30.89,
|
| 361 |
+
"eval_accuracy": 0.8064516129032258,
|
| 362 |
+
"eval_loss": 0.5931597948074341,
|
| 363 |
+
"eval_runtime": 2.252,
|
| 364 |
+
"eval_samples_per_second": 27.531,
|
| 365 |
+
"eval_steps_per_second": 1.776,
|
| 366 |
+
"step": 139
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 31.11,
|
| 370 |
+
"learning_rate": 6.944444444444445e-06,
|
| 371 |
+
"loss": 0.3262,
|
| 372 |
+
"step": 140
|
|
|
|
|
|
|
|
|
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 32.0,
|
| 376 |
+
"eval_accuracy": 0.8064516129032258,
|
| 377 |
+
"eval_loss": 0.5630321502685547,
|
| 378 |
+
"eval_runtime": 2.111,
|
| 379 |
+
"eval_samples_per_second": 29.37,
|
| 380 |
+
"eval_steps_per_second": 1.895,
|
| 381 |
+
"step": 144
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 32.89,
|
| 385 |
+
"eval_accuracy": 0.8064516129032258,
|
| 386 |
+
"eval_loss": 0.5433912873268127,
|
| 387 |
+
"eval_runtime": 2.2255,
|
| 388 |
+
"eval_samples_per_second": 27.858,
|
| 389 |
+
"eval_steps_per_second": 1.797,
|
| 390 |
+
"step": 148
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"epoch": 33.33,
|
| 394 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 395 |
+
"loss": 0.2997,
|
| 396 |
+
"step": 150
|
|
|
|
|
|
|
|
|
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 34.0,
|
| 400 |
+
"eval_accuracy": 0.8064516129032258,
|
| 401 |
+
"eval_loss": 0.5314125418663025,
|
| 402 |
+
"eval_runtime": 2.275,
|
| 403 |
+
"eval_samples_per_second": 27.252,
|
| 404 |
+
"eval_steps_per_second": 1.758,
|
| 405 |
+
"step": 153
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 406 |
},
|
| 407 |
{
|
| 408 |
+
"epoch": 34.89,
|
| 409 |
+
"eval_accuracy": 0.8064516129032258,
|
| 410 |
+
"eval_loss": 0.5194743275642395,
|
| 411 |
+
"eval_runtime": 2.1655,
|
| 412 |
+
"eval_samples_per_second": 28.631,
|
| 413 |
+
"eval_steps_per_second": 1.847,
|
| 414 |
+
"step": 157
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 35.56,
|
| 418 |
+
"learning_rate": 0.0,
|
| 419 |
+
"loss": 0.2891,
|
| 420 |
+
"step": 160
|
|
|
|
|
|
|
|
|
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"epoch": 35.56,
|
| 424 |
+
"eval_accuracy": 0.8064516129032258,
|
| 425 |
+
"eval_loss": 0.5155302286148071,
|
| 426 |
+
"eval_runtime": 2.3866,
|
| 427 |
+
"eval_samples_per_second": 25.979,
|
| 428 |
+
"eval_steps_per_second": 1.676,
|
| 429 |
+
"step": 160
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 35.56,
|
| 433 |
+
"step": 160,
|
| 434 |
+
"total_flos": 7.931930389512192e+17,
|
| 435 |
+
"train_loss": 0.5975452944636345,
|
| 436 |
+
"train_runtime": 588.8758,
|
| 437 |
+
"train_samples_per_second": 19.563,
|
| 438 |
+
"train_steps_per_second": 0.272
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 439 |
}
|
| 440 |
],
|
| 441 |
"logging_steps": 10,
|
| 442 |
+
"max_steps": 160,
|
| 443 |
"num_input_tokens_seen": 0,
|
| 444 |
"num_train_epochs": 40,
|
| 445 |
"save_steps": 500,
|
| 446 |
+
"total_flos": 7.931930389512192e+17,
|
| 447 |
"train_batch_size": 16,
|
| 448 |
"trial_name": null,
|
| 449 |
"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 sha256:492f9fd8b047d1211e7f0f6292ed08cde5c5098394b987a9a0ea2f84aaed7e54
|
| 3 |
size 4728
|