Training in progress, epoch 0
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +57 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.4,
|
| 3 |
+
"total_flos": 3.668743974312346e+16,
|
| 4 |
+
"train_loss": 0.7068924109141032,
|
| 5 |
+
"train_runtime": 122.4557,
|
| 6 |
+
"train_samples_per_second": 14.944,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.4,
|
| 3 |
+
"total_flos": 3.668743974312346e+16,
|
| 4 |
+
"train_loss": 0.7068924109141032,
|
| 5 |
+
"train_runtime": 122.4557,
|
| 6 |
+
"train_samples_per_second": 14.944,
|
| 7 |
+
"train_steps_per_second": 0.024
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6493506493506493,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-3",
|
| 4 |
+
"epoch": 2.4,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3,
|
| 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 |
+
"eval_accuracy": 0.43506493506493504,
|
| 14 |
+
"eval_loss": 0.749769389629364,
|
| 15 |
+
"eval_runtime": 15.883,
|
| 16 |
+
"eval_samples_per_second": 9.696,
|
| 17 |
+
"eval_steps_per_second": 0.126,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.6,
|
| 22 |
+
"eval_accuracy": 0.6168831168831169,
|
| 23 |
+
"eval_loss": 0.6566048860549927,
|
| 24 |
+
"eval_runtime": 15.2755,
|
| 25 |
+
"eval_samples_per_second": 10.081,
|
| 26 |
+
"eval_steps_per_second": 0.131,
|
| 27 |
+
"step": 2
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.4,
|
| 31 |
+
"eval_accuracy": 0.6493506493506493,
|
| 32 |
+
"eval_loss": 0.6294699311256409,
|
| 33 |
+
"eval_runtime": 15.3989,
|
| 34 |
+
"eval_samples_per_second": 10.001,
|
| 35 |
+
"eval_steps_per_second": 0.13,
|
| 36 |
+
"step": 3
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.4,
|
| 40 |
+
"step": 3,
|
| 41 |
+
"total_flos": 3.668743974312346e+16,
|
| 42 |
+
"train_loss": 0.7068924109141032,
|
| 43 |
+
"train_runtime": 122.4557,
|
| 44 |
+
"train_samples_per_second": 14.944,
|
| 45 |
+
"train_steps_per_second": 0.024
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
+
"logging_steps": 10,
|
| 49 |
+
"max_steps": 3,
|
| 50 |
+
"num_input_tokens_seen": 0,
|
| 51 |
+
"num_train_epochs": 3,
|
| 52 |
+
"save_steps": 500,
|
| 53 |
+
"total_flos": 3.668743974312346e+16,
|
| 54 |
+
"train_batch_size": 128,
|
| 55 |
+
"trial_name": null,
|
| 56 |
+
"trial_params": null
|
| 57 |
+
}
|