End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +61 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.9,
|
| 3 |
+
"eval_accuracy": 0.6353790613718412,
|
| 4 |
+
"eval_loss": 0.764682948589325,
|
| 5 |
+
"eval_runtime": 0.9007,
|
| 6 |
+
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 307.546,
|
| 8 |
+
"eval_steps_per_second": 9.992,
|
| 9 |
+
"train_loss": 0.5004565590306332,
|
| 10 |
+
"train_runtime": 76.0596,
|
| 11 |
+
"train_samples": 2490,
|
| 12 |
+
"train_samples_per_second": 130.95,
|
| 13 |
+
"train_steps_per_second": 0.999
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.9,
|
| 3 |
+
"eval_accuracy": 0.6353790613718412,
|
| 4 |
+
"eval_loss": 0.764682948589325,
|
| 5 |
+
"eval_runtime": 0.9007,
|
| 6 |
+
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 307.546,
|
| 8 |
+
"eval_steps_per_second": 9.992
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.9,
|
| 3 |
+
"train_loss": 0.5004565590306332,
|
| 4 |
+
"train_runtime": 76.0596,
|
| 5 |
+
"train_samples": 2490,
|
| 6 |
+
"train_samples_per_second": 130.95,
|
| 7 |
+
"train_steps_per_second": 0.999
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.8974358974358974,
|
| 5 |
+
"global_step": 76,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.97,
|
| 12 |
+
"eval_accuracy": 0.6462093862815884,
|
| 13 |
+
"eval_loss": 0.6622310280799866,
|
| 14 |
+
"eval_runtime": 0.8176,
|
| 15 |
+
"eval_samples_per_second": 338.782,
|
| 16 |
+
"eval_steps_per_second": 11.007,
|
| 17 |
+
"step": 19
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_accuracy": 0.6389891696750902,
|
| 22 |
+
"eval_loss": 0.6256995797157288,
|
| 23 |
+
"eval_runtime": 0.8184,
|
| 24 |
+
"eval_samples_per_second": 338.47,
|
| 25 |
+
"eval_steps_per_second": 10.997,
|
| 26 |
+
"step": 39
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.97,
|
| 30 |
+
"eval_accuracy": 0.6353790613718412,
|
| 31 |
+
"eval_loss": 0.7572575807571411,
|
| 32 |
+
"eval_runtime": 0.8328,
|
| 33 |
+
"eval_samples_per_second": 332.625,
|
| 34 |
+
"eval_steps_per_second": 10.807,
|
| 35 |
+
"step": 58
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.9,
|
| 39 |
+
"eval_accuracy": 0.6353790613718412,
|
| 40 |
+
"eval_loss": 0.764682948589325,
|
| 41 |
+
"eval_runtime": 0.817,
|
| 42 |
+
"eval_samples_per_second": 339.032,
|
| 43 |
+
"eval_steps_per_second": 11.015,
|
| 44 |
+
"step": 76
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.9,
|
| 48 |
+
"step": 76,
|
| 49 |
+
"total_flos": 2537191448248320.0,
|
| 50 |
+
"train_loss": 0.5004565590306332,
|
| 51 |
+
"train_runtime": 76.0596,
|
| 52 |
+
"train_samples_per_second": 130.95,
|
| 53 |
+
"train_steps_per_second": 0.999
|
| 54 |
+
}
|
| 55 |
+
],
|
| 56 |
+
"max_steps": 76,
|
| 57 |
+
"num_train_epochs": 4,
|
| 58 |
+
"total_flos": 2537191448248320.0,
|
| 59 |
+
"trial_name": null,
|
| 60 |
+
"trial_params": null
|
| 61 |
+
}
|