checkpoint: Add trainer_state.json
Browse files- trainer_state.json +61 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2211,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2261420171867933,
|
| 13 |
+
"grad_norm": 0.06914567202329636,
|
| 14 |
+
"learning_rate": 3.869289914066034e-05,
|
| 15 |
+
"loss": 0.5695,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4522840343735866,
|
| 20 |
+
"grad_norm": 0.08596434444189072,
|
| 21 |
+
"learning_rate": 2.7385798281320668e-05,
|
| 22 |
+
"loss": 0.4016,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6784260515603799,
|
| 27 |
+
"grad_norm": 0.0946701392531395,
|
| 28 |
+
"learning_rate": 1.6078697421981004e-05,
|
| 29 |
+
"loss": 0.3921,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9045680687471732,
|
| 34 |
+
"grad_norm": 0.09613804519176483,
|
| 35 |
+
"learning_rate": 4.771596562641339e-06,
|
| 36 |
+
"loss": 0.39,
|
| 37 |
+
"step": 2000
|
| 38 |
+
}
|
| 39 |
+
],
|
| 40 |
+
"logging_steps": 500,
|
| 41 |
+
"max_steps": 2211,
|
| 42 |
+
"num_input_tokens_seen": 0,
|
| 43 |
+
"num_train_epochs": 1,
|
| 44 |
+
"save_steps": 5000,
|
| 45 |
+
"stateful_callbacks": {
|
| 46 |
+
"TrainerControl": {
|
| 47 |
+
"args": {
|
| 48 |
+
"should_epoch_stop": false,
|
| 49 |
+
"should_evaluate": false,
|
| 50 |
+
"should_log": false,
|
| 51 |
+
"should_save": true,
|
| 52 |
+
"should_training_stop": true
|
| 53 |
+
},
|
| 54 |
+
"attributes": {}
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"total_flos": 5.1529691352589664e+19,
|
| 58 |
+
"train_batch_size": 128,
|
| 59 |
+
"trial_name": null,
|
| 60 |
+
"trial_params": null
|
| 61 |
+
}
|