| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0030670142616163166, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006134028523232633, | |
| "grad_norm": 3.3871912956237793, | |
| "learning_rate": 1e-05, | |
| "loss": 177.375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006134028523232633, | |
| "eval_loss": 11.085943222045898, | |
| "eval_runtime": 11.7544, | |
| "eval_samples_per_second": 233.616, | |
| "eval_steps_per_second": 116.808, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012268057046465265, | |
| "grad_norm": 3.270690441131592, | |
| "learning_rate": 2e-05, | |
| "loss": 177.5625, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012268057046465265, | |
| "eval_loss": 11.085988998413086, | |
| "eval_runtime": 6.6098, | |
| "eval_samples_per_second": 415.444, | |
| "eval_steps_per_second": 207.722, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018402085569697898, | |
| "grad_norm": 2.693251848220825, | |
| "learning_rate": 3e-05, | |
| "loss": 177.4375, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002453611409293053, | |
| "grad_norm": 3.8025851249694824, | |
| "learning_rate": 4e-05, | |
| "loss": 177.1875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002453611409293053, | |
| "eval_loss": 11.08585262298584, | |
| "eval_runtime": 6.9433, | |
| "eval_samples_per_second": 395.488, | |
| "eval_steps_per_second": 197.744, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030670142616163166, | |
| "grad_norm": 3.4057934284210205, | |
| "learning_rate": 5e-05, | |
| "loss": 177.375, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 14942208000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |