File size: 1,677 Bytes
b18428f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0017359498727114757,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034718997454229514,
"grad_norm": 0.8856930732727051,
"learning_rate": 0.00019999994169931,
"loss": 2.4069,
"step": 100
},
{
"epoch": 0.0006943799490845903,
"grad_norm": 0.8890424966812134,
"learning_rate": 0.0001999997644357777,
"loss": 2.3882,
"step": 200
},
{
"epoch": 0.0010415699236268853,
"grad_norm": 0.8619076013565063,
"learning_rate": 0.00019999946820366553,
"loss": 2.4208,
"step": 300
},
{
"epoch": 0.0013887598981691806,
"grad_norm": 0.8981874585151672,
"learning_rate": 0.00019999905300332595,
"loss": 2.3859,
"step": 400
},
{
"epoch": 0.0017359498727114757,
"grad_norm": 1.1088451147079468,
"learning_rate": 0.0001999985188352529,
"loss": 2.4031,
"step": 500
}
],
"logging_steps": 100,
"max_steps": 288027,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3740660968730624e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|