File size: 1,643 Bytes
488f5f0 |
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 71 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.03377110694183865,
"eval_steps": 9,
"global_step": 9,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00375234521575985,
"eval_loss": 10.385416984558105,
"eval_runtime": 16.6568,
"eval_samples_per_second": 13.508,
"eval_steps_per_second": 3.422,
"step": 1
},
{
"epoch": 0.01125703564727955,
"grad_norm": 9.703173637390137,
"learning_rate": 3e-05,
"loss": 10.4586,
"step": 3
},
{
"epoch": 0.0225140712945591,
"grad_norm": 8.736605644226074,
"learning_rate": 6e-05,
"loss": 9.0406,
"step": 6
},
{
"epoch": 0.03377110694183865,
"grad_norm": 9.648565292358398,
"learning_rate": 9e-05,
"loss": 5.2104,
"step": 9
},
{
"epoch": 0.03377110694183865,
"eval_loss": 1.994680404663086,
"eval_runtime": 16.3241,
"eval_samples_per_second": 13.783,
"eval_steps_per_second": 3.492,
"step": 9
}
],
"logging_steps": 3,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 9,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6398499084042240.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|