End of training
Browse files- trainer_state.json +55 -13
trainer_state.json
CHANGED
|
@@ -1,25 +1,67 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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,
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 2,
|
| 22 |
-
"max_steps":
|
| 23 |
"num_input_tokens_seen": 0,
|
| 24 |
"num_train_epochs": 2,
|
| 25 |
"save_steps": 500,
|
|
@@ -29,13 +71,13 @@
|
|
| 29 |
"should_epoch_stop": false,
|
| 30 |
"should_evaluate": false,
|
| 31 |
"should_log": false,
|
| 32 |
-
"should_save":
|
| 33 |
-
"should_training_stop":
|
| 34 |
},
|
| 35 |
"attributes": {}
|
| 36 |
}
|
| 37 |
},
|
| 38 |
-
"total_flos":
|
| 39 |
"train_batch_size": 2,
|
| 40 |
"trial_name": null,
|
| 41 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 12,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.32,
|
| 13 |
+
"grad_norm": 0.17948530614376068,
|
| 14 |
+
"learning_rate": 0.0001666666666666667,
|
| 15 |
+
"loss": 8.9023,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.64,
|
| 20 |
+
"grad_norm": 0.33971741795539856,
|
| 21 |
+
"learning_rate": 0.00013333333333333334,
|
| 22 |
+
"loss": 8.7931,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.96,
|
| 27 |
+
"grad_norm": 0.4960370361804962,
|
| 28 |
+
"learning_rate": 0.0001,
|
| 29 |
+
"loss": 8.6895,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.16,
|
| 34 |
+
"grad_norm": 0.5553238391876221,
|
| 35 |
+
"learning_rate": 6.666666666666667e-05,
|
| 36 |
+
"loss": 5.3485,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.48,
|
| 41 |
+
"grad_norm": 0.7772231698036194,
|
| 42 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 43 |
+
"loss": 8.4708,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.8,
|
| 48 |
+
"grad_norm": 0.7240044474601746,
|
| 49 |
+
"learning_rate": 0.0,
|
| 50 |
+
"loss": 8.4396,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.8,
|
| 55 |
+
"step": 12,
|
| 56 |
+
"total_flos": 33316935156720.0,
|
| 57 |
+
"train_loss": 8.10729185740153,
|
| 58 |
+
"train_runtime": 84.0152,
|
| 59 |
+
"train_samples_per_second": 2.381,
|
| 60 |
+
"train_steps_per_second": 0.143
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 2,
|
| 64 |
+
"max_steps": 12,
|
| 65 |
"num_input_tokens_seen": 0,
|
| 66 |
"num_train_epochs": 2,
|
| 67 |
"save_steps": 500,
|
|
|
|
| 71 |
"should_epoch_stop": false,
|
| 72 |
"should_evaluate": false,
|
| 73 |
"should_log": false,
|
| 74 |
+
"should_save": true,
|
| 75 |
+
"should_training_stop": true
|
| 76 |
},
|
| 77 |
"attributes": {}
|
| 78 |
}
|
| 79 |
},
|
| 80 |
+
"total_flos": 33316935156720.0,
|
| 81 |
"train_batch_size": 2,
|
| 82 |
"trial_name": null,
|
| 83 |
"trial_params": null
|