End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +73 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.88,
|
| 3 |
+
"total_flos": 1.1453639724682445e+17,
|
| 4 |
+
"train_loss": 0.3829680151409573,
|
| 5 |
+
"train_runtime": 90.7696,
|
| 6 |
+
"train_samples_per_second": 52.881,
|
| 7 |
+
"train_steps_per_second": 0.397
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.88,
|
| 3 |
+
"total_flos": 1.1453639724682445e+17,
|
| 4 |
+
"train_loss": 0.3829680151409573,
|
| 5 |
+
"train_runtime": 90.7696,
|
| 6 |
+
"train_samples_per_second": 52.881,
|
| 7 |
+
"train_steps_per_second": 0.397
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.935,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-36",
|
| 4 |
+
"epoch": 2.88,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 36,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8,
|
| 13 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 14 |
+
"loss": 0.6142,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.96,
|
| 19 |
+
"eval_accuracy": 0.835,
|
| 20 |
+
"eval_loss": 0.36099061369895935,
|
| 21 |
+
"eval_runtime": 1.583,
|
| 22 |
+
"eval_samples_per_second": 126.345,
|
| 23 |
+
"eval_steps_per_second": 4.422,
|
| 24 |
+
"step": 12
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.6,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 0.3549,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.9,
|
| 35 |
+
"eval_loss": 0.20535722374916077,
|
| 36 |
+
"eval_runtime": 1.3101,
|
| 37 |
+
"eval_samples_per_second": 152.658,
|
| 38 |
+
"eval_steps_per_second": 5.343,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.4,
|
| 43 |
+
"learning_rate": 9.375000000000001e-06,
|
| 44 |
+
"loss": 0.2612,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.88,
|
| 49 |
+
"eval_accuracy": 0.935,
|
| 50 |
+
"eval_loss": 0.17837801575660706,
|
| 51 |
+
"eval_runtime": 1.3262,
|
| 52 |
+
"eval_samples_per_second": 150.812,
|
| 53 |
+
"eval_steps_per_second": 5.278,
|
| 54 |
+
"step": 36
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.88,
|
| 58 |
+
"step": 36,
|
| 59 |
+
"total_flos": 1.1453639724682445e+17,
|
| 60 |
+
"train_loss": 0.3829680151409573,
|
| 61 |
+
"train_runtime": 90.7696,
|
| 62 |
+
"train_samples_per_second": 52.881,
|
| 63 |
+
"train_steps_per_second": 0.397
|
| 64 |
+
}
|
| 65 |
+
],
|
| 66 |
+
"logging_steps": 10,
|
| 67 |
+
"max_steps": 36,
|
| 68 |
+
"num_train_epochs": 3,
|
| 69 |
+
"save_steps": 500,
|
| 70 |
+
"total_flos": 1.1453639724682445e+17,
|
| 71 |
+
"trial_name": null,
|
| 72 |
+
"trial_params": null
|
| 73 |
+
}
|