Upload trainer_state.json
Browse files- trainer_state.json +76 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8872033047821317,
|
| 3 |
+
"best_model_checkpoint": "./results1/output/checkpoint-831690",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 1108920,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 4.787836344379806e-06,
|
| 13 |
+
"loss": 0.4724,
|
| 14 |
+
"step": 277230
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.8809251522860411,
|
| 19 |
+
"eval_loss": 0.55721116065979,
|
| 20 |
+
"eval_runtime": 500.703,
|
| 21 |
+
"eval_samples_per_second": 85.574,
|
| 22 |
+
"eval_steps_per_second": 21.394,
|
| 23 |
+
"step": 277230
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 3.1926775545288493e-06,
|
| 28 |
+
"loss": 0.3483,
|
| 29 |
+
"step": 554460
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.8858029733703643,
|
| 34 |
+
"eval_loss": 0.5279836058616638,
|
| 35 |
+
"eval_runtime": 500.7272,
|
| 36 |
+
"eval_samples_per_second": 85.57,
|
| 37 |
+
"eval_steps_per_second": 21.393,
|
| 38 |
+
"step": 554460
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 1.5975417888225454e-06,
|
| 43 |
+
"loss": 0.253,
|
| 44 |
+
"step": 831690
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.8872033047821317,
|
| 49 |
+
"eval_loss": 0.624336838722229,
|
| 50 |
+
"eval_runtime": 501.4348,
|
| 51 |
+
"eval_samples_per_second": 85.449,
|
| 52 |
+
"eval_steps_per_second": 21.363,
|
| 53 |
+
"step": 831690
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"learning_rate": 2.3657308630984357e-09,
|
| 58 |
+
"loss": 0.1594,
|
| 59 |
+
"step": 1108920
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.8861297173664434,
|
| 64 |
+
"eval_loss": 0.7563027143478394,
|
| 65 |
+
"eval_runtime": 500.2671,
|
| 66 |
+
"eval_samples_per_second": 85.648,
|
| 67 |
+
"eval_steps_per_second": 21.413,
|
| 68 |
+
"step": 1108920
|
| 69 |
+
}
|
| 70 |
+
],
|
| 71 |
+
"max_steps": 1108920,
|
| 72 |
+
"num_train_epochs": 4,
|
| 73 |
+
"total_flos": 5.3327480440765914e+17,
|
| 74 |
+
"trial_name": null,
|
| 75 |
+
"trial_params": null
|
| 76 |
+
}
|