| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.96, | |
| "eval_steps": 1, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 226.19036865234375, | |
| "learning_rate": 1e-05, | |
| "loss": 98.1875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 6.354166507720947, | |
| "eval_runtime": 4.9848, | |
| "eval_samples_per_second": 1.204, | |
| "eval_steps_per_second": 0.602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 223.04212951660156, | |
| "learning_rate": 2e-05, | |
| "loss": 100.5312, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 6.291666507720947, | |
| "eval_runtime": 0.0939, | |
| "eval_samples_per_second": 63.882, | |
| "eval_steps_per_second": 31.941, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 220.1862030029297, | |
| "learning_rate": 3e-05, | |
| "loss": 102.5, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 6.21875, | |
| "eval_runtime": 0.0931, | |
| "eval_samples_per_second": 64.457, | |
| "eval_steps_per_second": 32.229, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 25475413966848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |