End of training
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +69 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.18110236220472442,
|
| 4 |
+
"eval_loss": NaN,
|
| 5 |
+
"eval_runtime": 5.4272,
|
| 6 |
+
"eval_samples_per_second": 23.401,
|
| 7 |
+
"eval_steps_per_second": 0.737,
|
| 8 |
+
"train_loss": 0.0,
|
| 9 |
+
"train_runtime": 613.4844,
|
| 10 |
+
"train_samples_per_second": 5.584,
|
| 11 |
+
"train_steps_per_second": 0.044
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.18110236220472442,
|
| 4 |
+
"eval_loss": NaN,
|
| 5 |
+
"eval_runtime": 5.4272,
|
| 6 |
+
"eval_samples_per_second": 23.401,
|
| 7 |
+
"eval_steps_per_second": 0.737
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 613.4844,
|
| 5 |
+
"train_samples_per_second": 5.584,
|
| 6 |
+
"train_steps_per_second": 0.044
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18110236220472442,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-mgasior/checkpoint-9",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 27,
|
| 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": 0.18110236220472442,
|
| 14 |
+
"eval_loss": NaN,
|
| 15 |
+
"eval_runtime": 10.8067,
|
| 16 |
+
"eval_samples_per_second": 11.752,
|
| 17 |
+
"eval_steps_per_second": 0.37,
|
| 18 |
+
"step": 9
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.11,
|
| 22 |
+
"learning_rate": 3.541666666666667e-05,
|
| 23 |
+
"loss": 0.0,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.18110236220472442,
|
| 29 |
+
"eval_loss": NaN,
|
| 30 |
+
"eval_runtime": 10.5345,
|
| 31 |
+
"eval_samples_per_second": 12.056,
|
| 32 |
+
"eval_steps_per_second": 0.38,
|
| 33 |
+
"step": 18
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.22,
|
| 37 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 38 |
+
"loss": 0.0,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.18110236220472442,
|
| 44 |
+
"eval_loss": NaN,
|
| 45 |
+
"eval_runtime": 5.5972,
|
| 46 |
+
"eval_samples_per_second": 22.69,
|
| 47 |
+
"eval_steps_per_second": 0.715,
|
| 48 |
+
"step": 27
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"step": 27,
|
| 53 |
+
"total_flos": 8.516613618951782e+16,
|
| 54 |
+
"train_loss": 0.0,
|
| 55 |
+
"train_runtime": 613.4844,
|
| 56 |
+
"train_samples_per_second": 5.584,
|
| 57 |
+
"train_steps_per_second": 0.044
|
| 58 |
+
}
|
| 59 |
+
],
|
| 60 |
+
"logging_steps": 10,
|
| 61 |
+
"max_steps": 27,
|
| 62 |
+
"num_input_tokens_seen": 0,
|
| 63 |
+
"num_train_epochs": 3,
|
| 64 |
+
"save_steps": 500,
|
| 65 |
+
"total_flos": 8.516613618951782e+16,
|
| 66 |
+
"train_batch_size": 32,
|
| 67 |
+
"trial_name": null,
|
| 68 |
+
"trial_params": null
|
| 69 |
+
}
|