End of training
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +55 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.4,
|
| 3 |
+
"eval_accuracy": 0.5056179775280899,
|
| 4 |
+
"eval_loss": 1.9271498918533325,
|
| 5 |
+
"eval_runtime": 7.7361,
|
| 6 |
+
"eval_samples_per_second": 11.505,
|
| 7 |
+
"eval_steps_per_second": 0.259,
|
| 8 |
+
"total_flos": 1.1577925830662554e+17,
|
| 9 |
+
"train_loss": 2.0264652570088706,
|
| 10 |
+
"train_runtime": 486.3273,
|
| 11 |
+
"train_samples_per_second": 3.818,
|
| 12 |
+
"train_steps_per_second": 0.012
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.4,
|
| 3 |
+
"eval_accuracy": 0.5056179775280899,
|
| 4 |
+
"eval_loss": 1.9271498918533325,
|
| 5 |
+
"eval_runtime": 7.7361,
|
| 6 |
+
"eval_samples_per_second": 11.505,
|
| 7 |
+
"eval_steps_per_second": 0.259
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.4,
|
| 3 |
+
"total_flos": 1.1577925830662554e+17,
|
| 4 |
+
"train_loss": 2.0264652570088706,
|
| 5 |
+
"train_runtime": 486.3273,
|
| 6 |
+
"train_samples_per_second": 3.818,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5056179775280899,
|
| 3 |
+
"best_model_checkpoint": "VitTea/checkpoint-6",
|
| 4 |
+
"epoch": 2.4,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6,
|
| 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": 0.24719101123595505,
|
| 14 |
+
"eval_loss": 2.0342581272125244,
|
| 15 |
+
"eval_runtime": 7.6205,
|
| 16 |
+
"eval_samples_per_second": 11.679,
|
| 17 |
+
"eval_steps_per_second": 0.262,
|
| 18 |
+
"step": 2
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.48314606741573035,
|
| 23 |
+
"eval_loss": 1.937175989151001,
|
| 24 |
+
"eval_runtime": 7.7661,
|
| 25 |
+
"eval_samples_per_second": 11.46,
|
| 26 |
+
"eval_steps_per_second": 0.258,
|
| 27 |
+
"step": 5
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.4,
|
| 31 |
+
"eval_accuracy": 0.5056179775280899,
|
| 32 |
+
"eval_loss": 1.9271498918533325,
|
| 33 |
+
"eval_runtime": 7.771,
|
| 34 |
+
"eval_samples_per_second": 11.453,
|
| 35 |
+
"eval_steps_per_second": 0.257,
|
| 36 |
+
"step": 6
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.4,
|
| 40 |
+
"step": 6,
|
| 41 |
+
"total_flos": 1.1577925830662554e+17,
|
| 42 |
+
"train_loss": 2.0264652570088706,
|
| 43 |
+
"train_runtime": 486.3273,
|
| 44 |
+
"train_samples_per_second": 3.818,
|
| 45 |
+
"train_steps_per_second": 0.012
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
+
"logging_steps": 10,
|
| 49 |
+
"max_steps": 6,
|
| 50 |
+
"num_train_epochs": 3,
|
| 51 |
+
"save_steps": 500,
|
| 52 |
+
"total_flos": 1.1577925830662554e+17,
|
| 53 |
+
"trial_name": null,
|
| 54 |
+
"trial_params": null
|
| 55 |
+
}
|