Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +76 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.22598870056497175,
|
| 6 |
+
"eval_steps": 10,
|
| 7 |
+
"global_step": 20,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 2.375955265760422,
|
| 14 |
+
"epoch": 0.11299435028248588,
|
| 15 |
+
"grad_norm": 3.953125,
|
| 16 |
+
"learning_rate": 0.00019651162790697676,
|
| 17 |
+
"loss": 16.610369873046874,
|
| 18 |
+
"mean_token_accuracy": 0.10732572241686285,
|
| 19 |
+
"num_tokens": 168709.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11299435028248588,
|
| 24 |
+
"eval_entropy": 2.850843206048012,
|
| 25 |
+
"eval_loss": 16.137414932250977,
|
| 26 |
+
"eval_mean_token_accuracy": 0.0946836918592453,
|
| 27 |
+
"eval_num_tokens": 168709.0,
|
| 28 |
+
"eval_runtime": 43.886,
|
| 29 |
+
"eval_samples_per_second": 4.375,
|
| 30 |
+
"eval_steps_per_second": 1.094,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"entropy": 4.185183194279671,
|
| 35 |
+
"epoch": 0.22598870056497175,
|
| 36 |
+
"grad_norm": 14.125,
|
| 37 |
+
"learning_rate": 0.00018488372093023256,
|
| 38 |
+
"loss": 13.943736267089843,
|
| 39 |
+
"mean_token_accuracy": 0.115196983050555,
|
| 40 |
+
"num_tokens": 336118.0,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.22598870056497175,
|
| 45 |
+
"eval_entropy": 6.767949452002843,
|
| 46 |
+
"eval_loss": 11.27951717376709,
|
| 47 |
+
"eval_mean_token_accuracy": 0.09991752542555332,
|
| 48 |
+
"eval_num_tokens": 336118.0,
|
| 49 |
+
"eval_runtime": 43.8324,
|
| 50 |
+
"eval_samples_per_second": 4.38,
|
| 51 |
+
"eval_steps_per_second": 1.095,
|
| 52 |
+
"step": 20
|
| 53 |
+
}
|
| 54 |
+
],
|
| 55 |
+
"logging_steps": 10,
|
| 56 |
+
"max_steps": 178,
|
| 57 |
+
"num_input_tokens_seen": 0,
|
| 58 |
+
"num_train_epochs": 2,
|
| 59 |
+
"save_steps": 20,
|
| 60 |
+
"stateful_callbacks": {
|
| 61 |
+
"TrainerControl": {
|
| 62 |
+
"args": {
|
| 63 |
+
"should_epoch_stop": false,
|
| 64 |
+
"should_evaluate": false,
|
| 65 |
+
"should_log": false,
|
| 66 |
+
"should_save": true,
|
| 67 |
+
"should_training_stop": false
|
| 68 |
+
},
|
| 69 |
+
"attributes": {}
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"total_flos": 2.397293116495872e+16,
|
| 73 |
+
"train_batch_size": 4,
|
| 74 |
+
"trial_name": null,
|
| 75 |
+
"trial_params": null
|
| 76 |
+
}
|