Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +91 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.4827586206896552,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 72,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3448275862068966,
|
| 13 |
+
"grad_norm": 1.1789525747299194,
|
| 14 |
+
"learning_rate": 0.00019618256431728194,
|
| 15 |
+
"loss": 0.1525,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6896551724137931,
|
| 20 |
+
"grad_norm": 0.7358490824699402,
|
| 21 |
+
"learning_rate": 0.00017390089172206592,
|
| 22 |
+
"loss": 0.0224,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0344827586206897,
|
| 27 |
+
"grad_norm": 0.45523107051849365,
|
| 28 |
+
"learning_rate": 0.00013612416661871533,
|
| 29 |
+
"loss": 0.0108,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.3793103448275863,
|
| 34 |
+
"grad_norm": 0.20521320402622223,
|
| 35 |
+
"learning_rate": 9.077316405366981e-05,
|
| 36 |
+
"loss": 0.0087,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.7241379310344827,
|
| 41 |
+
"grad_norm": 0.22252900898456573,
|
| 42 |
+
"learning_rate": 4.735678371226441e-05,
|
| 43 |
+
"loss": 0.0086,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.0689655172413794,
|
| 48 |
+
"grad_norm": 0.5247920155525208,
|
| 49 |
+
"learning_rate": 1.4978286427038601e-05,
|
| 50 |
+
"loss": 0.0078,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.413793103448276,
|
| 55 |
+
"grad_norm": 0.3118768632411957,
|
| 56 |
+
"learning_rate": 4.2658237049655323e-07,
|
| 57 |
+
"loss": 0.0054,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.4827586206896552,
|
| 62 |
+
"step": 72,
|
| 63 |
+
"total_flos": 1425318441811200.0,
|
| 64 |
+
"train_loss": 0.03014997382544809,
|
| 65 |
+
"train_runtime": 44.0205,
|
| 66 |
+
"train_samples_per_second": 26.17,
|
| 67 |
+
"train_steps_per_second": 1.636
|
| 68 |
+
}
|
| 69 |
+
],
|
| 70 |
+
"logging_steps": 10,
|
| 71 |
+
"max_steps": 72,
|
| 72 |
+
"num_input_tokens_seen": 0,
|
| 73 |
+
"num_train_epochs": 3,
|
| 74 |
+
"save_steps": 500,
|
| 75 |
+
"stateful_callbacks": {
|
| 76 |
+
"TrainerControl": {
|
| 77 |
+
"args": {
|
| 78 |
+
"should_epoch_stop": false,
|
| 79 |
+
"should_evaluate": false,
|
| 80 |
+
"should_log": false,
|
| 81 |
+
"should_save": true,
|
| 82 |
+
"should_training_stop": true
|
| 83 |
+
},
|
| 84 |
+
"attributes": {}
|
| 85 |
+
}
|
| 86 |
+
},
|
| 87 |
+
"total_flos": 1425318441811200.0,
|
| 88 |
+
"train_batch_size": 16,
|
| 89 |
+
"trial_name": null,
|
| 90 |
+
"trial_params": null
|
| 91 |
+
}
|