End of training
Browse files- README.md +3 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +373 -32
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9675324675324676
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.1073
|
| 36 |
+
- Accuracy: 0.9675
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 5.
|
| 6 |
-
"eval_samples_per_second": 26.
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"total_flos": 4.548645984411648e+
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.9675324675324676,
|
| 4 |
+
"eval_loss": 0.10734522342681885,
|
| 5 |
+
"eval_runtime": 5.7441,
|
| 6 |
+
"eval_samples_per_second": 26.81,
|
| 7 |
+
"eval_steps_per_second": 0.87,
|
| 8 |
+
"total_flos": 4.548645984411648e+17,
|
| 9 |
+
"train_loss": 0.11414109120766322,
|
| 10 |
+
"train_runtime": 869.5797,
|
| 11 |
+
"train_samples_per_second": 21.045,
|
| 12 |
+
"train_steps_per_second": 0.172
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 5.
|
| 6 |
-
"eval_samples_per_second": 26.
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.9675324675324676,
|
| 4 |
+
"eval_loss": 0.10734522342681885,
|
| 5 |
+
"eval_runtime": 5.7441,
|
| 6 |
+
"eval_samples_per_second": 26.81,
|
| 7 |
+
"eval_steps_per_second": 0.87
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 4.548645984411648e+
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"total_flos": 4.548645984411648e+17,
|
| 4 |
+
"train_loss": 0.11414109120766322,
|
| 5 |
+
"train_runtime": 869.5797,
|
| 6 |
+
"train_samples_per_second": 21.045,
|
| 7 |
+
"train_steps_per_second": 0.172
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,63 +1,404 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/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": 1.0,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_runtime": 5.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second": 0.
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
-
"grad_norm":
|
| 23 |
-
"learning_rate":
|
| 24 |
-
"loss": 0.
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"epoch": 2.0,
|
| 29 |
-
"eval_accuracy": 0.
|
| 30 |
-
"eval_loss": 0.
|
| 31 |
-
"eval_runtime": 5.
|
| 32 |
-
"eval_samples_per_second": 27.
|
| 33 |
-
"eval_steps_per_second": 0.
|
| 34 |
"step": 10
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 3.0,
|
| 38 |
-
"eval_accuracy": 0.
|
| 39 |
-
"eval_loss": 0.
|
| 40 |
-
"eval_runtime": 5.
|
| 41 |
-
"eval_samples_per_second":
|
| 42 |
-
"eval_steps_per_second": 0.
|
| 43 |
"step": 15
|
| 44 |
},
|
| 45 |
{
|
| 46 |
-
"epoch":
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
}
|
| 54 |
],
|
| 55 |
"logging_steps": 10,
|
| 56 |
-
"max_steps":
|
| 57 |
"num_input_tokens_seen": 0,
|
| 58 |
-
"num_train_epochs":
|
| 59 |
"save_steps": 500,
|
| 60 |
-
"total_flos": 4.548645984411648e+
|
| 61 |
"train_batch_size": 32,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9675324675324676,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-70",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 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": 0.6298701298701299,
|
| 14 |
+
"eval_loss": 0.6615892648696899,
|
| 15 |
+
"eval_runtime": 5.9895,
|
| 16 |
+
"eval_samples_per_second": 25.712,
|
| 17 |
+
"eval_steps_per_second": 0.835,
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
+
"grad_norm": 6.212774753570557,
|
| 23 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 24 |
+
"loss": 0.6583,
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"epoch": 2.0,
|
| 29 |
+
"eval_accuracy": 0.7597402597402597,
|
| 30 |
+
"eval_loss": 0.5232259631156921,
|
| 31 |
+
"eval_runtime": 5.5139,
|
| 32 |
+
"eval_samples_per_second": 27.929,
|
| 33 |
+
"eval_steps_per_second": 0.907,
|
| 34 |
"step": 10
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 3.0,
|
| 38 |
+
"eval_accuracy": 0.7857142857142857,
|
| 39 |
+
"eval_loss": 0.5042803287506104,
|
| 40 |
+
"eval_runtime": 5.8851,
|
| 41 |
+
"eval_samples_per_second": 26.168,
|
| 42 |
+
"eval_steps_per_second": 0.85,
|
| 43 |
"step": 15
|
| 44 |
},
|
| 45 |
{
|
| 46 |
+
"epoch": 4.0,
|
| 47 |
+
"grad_norm": 3.873718738555908,
|
| 48 |
+
"learning_rate": 4.814814814814815e-05,
|
| 49 |
+
"loss": 0.3346,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_accuracy": 0.8766233766233766,
|
| 55 |
+
"eval_loss": 0.287881076335907,
|
| 56 |
+
"eval_runtime": 5.8126,
|
| 57 |
+
"eval_samples_per_second": 26.494,
|
| 58 |
+
"eval_steps_per_second": 0.86,
|
| 59 |
+
"step": 20
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 5.0,
|
| 63 |
+
"eval_accuracy": 0.9090909090909091,
|
| 64 |
+
"eval_loss": 0.24241776764392853,
|
| 65 |
+
"eval_runtime": 5.8885,
|
| 66 |
+
"eval_samples_per_second": 26.152,
|
| 67 |
+
"eval_steps_per_second": 0.849,
|
| 68 |
+
"step": 25
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.0,
|
| 72 |
+
"grad_norm": 4.3201093673706055,
|
| 73 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 74 |
+
"loss": 0.1544,
|
| 75 |
+
"step": 30
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.0,
|
| 79 |
+
"eval_accuracy": 0.8896103896103896,
|
| 80 |
+
"eval_loss": 0.22171010076999664,
|
| 81 |
+
"eval_runtime": 5.7903,
|
| 82 |
+
"eval_samples_per_second": 26.596,
|
| 83 |
+
"eval_steps_per_second": 0.864,
|
| 84 |
+
"step": 30
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 7.0,
|
| 88 |
+
"eval_accuracy": 0.922077922077922,
|
| 89 |
+
"eval_loss": 0.14658886194229126,
|
| 90 |
+
"eval_runtime": 5.8797,
|
| 91 |
+
"eval_samples_per_second": 26.192,
|
| 92 |
+
"eval_steps_per_second": 0.85,
|
| 93 |
+
"step": 35
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.0,
|
| 97 |
+
"grad_norm": 4.792673587799072,
|
| 98 |
+
"learning_rate": 4.074074074074074e-05,
|
| 99 |
+
"loss": 0.088,
|
| 100 |
+
"step": 40
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_accuracy": 0.948051948051948,
|
| 105 |
+
"eval_loss": 0.12608817219734192,
|
| 106 |
+
"eval_runtime": 5.723,
|
| 107 |
+
"eval_samples_per_second": 26.909,
|
| 108 |
+
"eval_steps_per_second": 0.874,
|
| 109 |
+
"step": 40
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 9.0,
|
| 113 |
+
"eval_accuracy": 0.922077922077922,
|
| 114 |
+
"eval_loss": 0.16798314452171326,
|
| 115 |
+
"eval_runtime": 5.7613,
|
| 116 |
+
"eval_samples_per_second": 26.73,
|
| 117 |
+
"eval_steps_per_second": 0.868,
|
| 118 |
+
"step": 45
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 10.0,
|
| 122 |
+
"grad_norm": 6.038075923919678,
|
| 123 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 124 |
+
"loss": 0.0977,
|
| 125 |
+
"step": 50
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 10.0,
|
| 129 |
+
"eval_accuracy": 0.935064935064935,
|
| 130 |
+
"eval_loss": 0.14464019238948822,
|
| 131 |
+
"eval_runtime": 5.8083,
|
| 132 |
+
"eval_samples_per_second": 26.514,
|
| 133 |
+
"eval_steps_per_second": 0.861,
|
| 134 |
+
"step": 50
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 11.0,
|
| 138 |
+
"eval_accuracy": 0.922077922077922,
|
| 139 |
+
"eval_loss": 0.18122775852680206,
|
| 140 |
+
"eval_runtime": 6.1597,
|
| 141 |
+
"eval_samples_per_second": 25.001,
|
| 142 |
+
"eval_steps_per_second": 0.812,
|
| 143 |
+
"step": 55
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 12.0,
|
| 147 |
+
"grad_norm": 4.068108558654785,
|
| 148 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 149 |
+
"loss": 0.0719,
|
| 150 |
+
"step": 60
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 12.0,
|
| 154 |
+
"eval_accuracy": 0.9285714285714286,
|
| 155 |
+
"eval_loss": 0.17976221442222595,
|
| 156 |
+
"eval_runtime": 6.0227,
|
| 157 |
+
"eval_samples_per_second": 25.57,
|
| 158 |
+
"eval_steps_per_second": 0.83,
|
| 159 |
+
"step": 60
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 13.0,
|
| 163 |
+
"eval_accuracy": 0.961038961038961,
|
| 164 |
+
"eval_loss": 0.105579674243927,
|
| 165 |
+
"eval_runtime": 5.8224,
|
| 166 |
+
"eval_samples_per_second": 26.449,
|
| 167 |
+
"eval_steps_per_second": 0.859,
|
| 168 |
+
"step": 65
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 14.0,
|
| 172 |
+
"grad_norm": 3.0755834579467773,
|
| 173 |
+
"learning_rate": 2.962962962962963e-05,
|
| 174 |
+
"loss": 0.0629,
|
| 175 |
+
"step": 70
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 14.0,
|
| 179 |
+
"eval_accuracy": 0.9675324675324676,
|
| 180 |
+
"eval_loss": 0.10734522342681885,
|
| 181 |
+
"eval_runtime": 5.9253,
|
| 182 |
+
"eval_samples_per_second": 25.99,
|
| 183 |
+
"eval_steps_per_second": 0.844,
|
| 184 |
+
"step": 70
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 15.0,
|
| 188 |
+
"eval_accuracy": 0.9545454545454546,
|
| 189 |
+
"eval_loss": 0.11058878153562546,
|
| 190 |
+
"eval_runtime": 5.9322,
|
| 191 |
+
"eval_samples_per_second": 25.96,
|
| 192 |
+
"eval_steps_per_second": 0.843,
|
| 193 |
+
"step": 75
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 16.0,
|
| 197 |
+
"grad_norm": 1.3675538301467896,
|
| 198 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 199 |
+
"loss": 0.0414,
|
| 200 |
+
"step": 80
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 16.0,
|
| 204 |
+
"eval_accuracy": 0.9415584415584416,
|
| 205 |
+
"eval_loss": 0.12863656878471375,
|
| 206 |
+
"eval_runtime": 5.8097,
|
| 207 |
+
"eval_samples_per_second": 26.508,
|
| 208 |
+
"eval_steps_per_second": 0.861,
|
| 209 |
+
"step": 80
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 17.0,
|
| 213 |
+
"eval_accuracy": 0.961038961038961,
|
| 214 |
+
"eval_loss": 0.07608745247125626,
|
| 215 |
+
"eval_runtime": 5.9871,
|
| 216 |
+
"eval_samples_per_second": 25.722,
|
| 217 |
+
"eval_steps_per_second": 0.835,
|
| 218 |
+
"step": 85
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 18.0,
|
| 222 |
+
"grad_norm": 3.8409650325775146,
|
| 223 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 224 |
+
"loss": 0.0397,
|
| 225 |
+
"step": 90
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 18.0,
|
| 229 |
+
"eval_accuracy": 0.9675324675324676,
|
| 230 |
+
"eval_loss": 0.07851818948984146,
|
| 231 |
+
"eval_runtime": 5.9494,
|
| 232 |
+
"eval_samples_per_second": 25.885,
|
| 233 |
+
"eval_steps_per_second": 0.84,
|
| 234 |
+
"step": 90
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 19.0,
|
| 238 |
+
"eval_accuracy": 0.9675324675324676,
|
| 239 |
+
"eval_loss": 0.07459615916013718,
|
| 240 |
+
"eval_runtime": 5.5847,
|
| 241 |
+
"eval_samples_per_second": 27.575,
|
| 242 |
+
"eval_steps_per_second": 0.895,
|
| 243 |
+
"step": 95
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 20.0,
|
| 247 |
+
"grad_norm": 40.9788932800293,
|
| 248 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 249 |
+
"loss": 0.0487,
|
| 250 |
+
"step": 100
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 20.0,
|
| 254 |
+
"eval_accuracy": 0.9675324675324676,
|
| 255 |
+
"eval_loss": 0.06842251867055893,
|
| 256 |
+
"eval_runtime": 5.7506,
|
| 257 |
+
"eval_samples_per_second": 26.78,
|
| 258 |
+
"eval_steps_per_second": 0.869,
|
| 259 |
+
"step": 100
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 21.0,
|
| 263 |
+
"eval_accuracy": 0.961038961038961,
|
| 264 |
+
"eval_loss": 0.06015988811850548,
|
| 265 |
+
"eval_runtime": 5.6354,
|
| 266 |
+
"eval_samples_per_second": 27.327,
|
| 267 |
+
"eval_steps_per_second": 0.887,
|
| 268 |
+
"step": 105
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 22.0,
|
| 272 |
+
"grad_norm": 0.32140201330184937,
|
| 273 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 274 |
+
"loss": 0.0244,
|
| 275 |
+
"step": 110
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 22.0,
|
| 279 |
+
"eval_accuracy": 0.9675324675324676,
|
| 280 |
+
"eval_loss": 0.055138688534498215,
|
| 281 |
+
"eval_runtime": 5.6318,
|
| 282 |
+
"eval_samples_per_second": 27.344,
|
| 283 |
+
"eval_steps_per_second": 0.888,
|
| 284 |
+
"step": 110
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 23.0,
|
| 288 |
+
"eval_accuracy": 0.9675324675324676,
|
| 289 |
+
"eval_loss": 0.06390709429979324,
|
| 290 |
+
"eval_runtime": 5.9133,
|
| 291 |
+
"eval_samples_per_second": 26.043,
|
| 292 |
+
"eval_steps_per_second": 0.846,
|
| 293 |
+
"step": 115
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 24.0,
|
| 297 |
+
"grad_norm": 0.17090357840061188,
|
| 298 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 299 |
+
"loss": 0.0214,
|
| 300 |
+
"step": 120
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 24.0,
|
| 304 |
+
"eval_accuracy": 0.9675324675324676,
|
| 305 |
+
"eval_loss": 0.05834332853555679,
|
| 306 |
+
"eval_runtime": 5.6237,
|
| 307 |
+
"eval_samples_per_second": 27.384,
|
| 308 |
+
"eval_steps_per_second": 0.889,
|
| 309 |
+
"step": 120
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 25.0,
|
| 313 |
+
"eval_accuracy": 0.9675324675324676,
|
| 314 |
+
"eval_loss": 0.06634216755628586,
|
| 315 |
+
"eval_runtime": 5.782,
|
| 316 |
+
"eval_samples_per_second": 26.634,
|
| 317 |
+
"eval_steps_per_second": 0.865,
|
| 318 |
+
"step": 125
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 26.0,
|
| 322 |
+
"grad_norm": 15.199660301208496,
|
| 323 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 324 |
+
"loss": 0.0261,
|
| 325 |
+
"step": 130
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 26.0,
|
| 329 |
+
"eval_accuracy": 0.961038961038961,
|
| 330 |
+
"eval_loss": 0.10064199566841125,
|
| 331 |
+
"eval_runtime": 5.8966,
|
| 332 |
+
"eval_samples_per_second": 26.117,
|
| 333 |
+
"eval_steps_per_second": 0.848,
|
| 334 |
+
"step": 130
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 27.0,
|
| 338 |
+
"eval_accuracy": 0.9675324675324676,
|
| 339 |
+
"eval_loss": 0.07111012190580368,
|
| 340 |
+
"eval_runtime": 5.7198,
|
| 341 |
+
"eval_samples_per_second": 26.924,
|
| 342 |
+
"eval_steps_per_second": 0.874,
|
| 343 |
+
"step": 135
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 28.0,
|
| 347 |
+
"grad_norm": 0.7294249534606934,
|
| 348 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 349 |
+
"loss": 0.019,
|
| 350 |
+
"step": 140
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 28.0,
|
| 354 |
+
"eval_accuracy": 0.9675324675324676,
|
| 355 |
+
"eval_loss": 0.06293747574090958,
|
| 356 |
+
"eval_runtime": 6.017,
|
| 357 |
+
"eval_samples_per_second": 25.594,
|
| 358 |
+
"eval_steps_per_second": 0.831,
|
| 359 |
+
"step": 140
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 29.0,
|
| 363 |
+
"eval_accuracy": 0.961038961038961,
|
| 364 |
+
"eval_loss": 0.07278253883123398,
|
| 365 |
+
"eval_runtime": 5.5819,
|
| 366 |
+
"eval_samples_per_second": 27.589,
|
| 367 |
+
"eval_steps_per_second": 0.896,
|
| 368 |
+
"step": 145
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 30.0,
|
| 372 |
+
"grad_norm": 0.9749196171760559,
|
| 373 |
+
"learning_rate": 0.0,
|
| 374 |
+
"loss": 0.0237,
|
| 375 |
+
"step": 150
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 30.0,
|
| 379 |
+
"eval_accuracy": 0.961038961038961,
|
| 380 |
+
"eval_loss": 0.07468711584806442,
|
| 381 |
+
"eval_runtime": 5.8121,
|
| 382 |
+
"eval_samples_per_second": 26.496,
|
| 383 |
+
"eval_steps_per_second": 0.86,
|
| 384 |
+
"step": 150
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.0,
|
| 388 |
+
"step": 150,
|
| 389 |
+
"total_flos": 4.548645984411648e+17,
|
| 390 |
+
"train_loss": 0.11414109120766322,
|
| 391 |
+
"train_runtime": 869.5797,
|
| 392 |
+
"train_samples_per_second": 21.045,
|
| 393 |
+
"train_steps_per_second": 0.172
|
| 394 |
}
|
| 395 |
],
|
| 396 |
"logging_steps": 10,
|
| 397 |
+
"max_steps": 150,
|
| 398 |
"num_input_tokens_seen": 0,
|
| 399 |
+
"num_train_epochs": 30,
|
| 400 |
"save_steps": 500,
|
| 401 |
+
"total_flos": 4.548645984411648e+17,
|
| 402 |
"train_batch_size": 32,
|
| 403 |
"trial_name": null,
|
| 404 |
"trial_params": null
|