Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +84 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6741573033707865,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11235955056179775,
|
| 13 |
+
"grad_norm": 2.1474151611328125,
|
| 14 |
+
"learning_rate": 0.00019264940672148018,
|
| 15 |
+
"loss": 0.6606,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2247191011235955,
|
| 20 |
+
"grad_norm": 32.052978515625,
|
| 21 |
+
"learning_rate": 0.00015922352526649803,
|
| 22 |
+
"loss": 0.3779,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.33707865168539325,
|
| 27 |
+
"grad_norm": 94.88410186767578,
|
| 28 |
+
"learning_rate": 0.00010825793454723325,
|
| 29 |
+
"loss": 0.3968,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.449438202247191,
|
| 34 |
+
"grad_norm": 99.2090072631836,
|
| 35 |
+
"learning_rate": 5.484666416891109e-05,
|
| 36 |
+
"loss": 0.3301,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5617977528089888,
|
| 41 |
+
"grad_norm": 106.09911346435547,
|
| 42 |
+
"learning_rate": 1.4808059116167305e-05,
|
| 43 |
+
"loss": 0.3134,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6741573033707865,
|
| 48 |
+
"grad_norm": 217.75341796875,
|
| 49 |
+
"learning_rate": 0.0,
|
| 50 |
+
"loss": 0.3172,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6741573033707865,
|
| 55 |
+
"step": 60,
|
| 56 |
+
"total_flos": 8512833379000320.0,
|
| 57 |
+
"train_loss": 0.3993192434310913,
|
| 58 |
+
"train_runtime": 93.2679,
|
| 59 |
+
"train_samples_per_second": 41.172,
|
| 60 |
+
"train_steps_per_second": 0.643
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"logging_steps": 10,
|
| 64 |
+
"max_steps": 60,
|
| 65 |
+
"num_input_tokens_seen": 0,
|
| 66 |
+
"num_train_epochs": 1,
|
| 67 |
+
"save_steps": 10000,
|
| 68 |
+
"stateful_callbacks": {
|
| 69 |
+
"TrainerControl": {
|
| 70 |
+
"args": {
|
| 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": 8512833379000320.0,
|
| 81 |
+
"train_batch_size": 64,
|
| 82 |
+
"trial_name": null,
|
| 83 |
+
"trial_params": null
|
| 84 |
+
}
|