File size: 1,488 Bytes
b9bb5c9 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9047619047619047,
"eval_steps": 500,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.19047619047619047,
"grad_norm": 0.551876045004038,
"learning_rate": 4.8776412907378845e-06,
"loss": 0.1469,
"step": 1
},
{
"epoch": 0.9523809523809523,
"grad_norm": 1.2404944004069458,
"learning_rate": 2.5e-06,
"loss": 0.1594,
"step": 5
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.6081967191317266,
"learning_rate": 0.0,
"loss": 0.13,
"step": 10
},
{
"epoch": 1.9047619047619047,
"step": 10,
"total_flos": 6047617712128.0,
"train_loss": 0.14342659264802932,
"train_runtime": 271.853,
"train_samples_per_second": 4.929,
"train_steps_per_second": 0.037
}
],
"logging_steps": 5,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6047617712128.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|