| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 13.34932259597944, | |
| "learning_rate": 1e-06, | |
| "loss": 2.0888, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.624112844467163, | |
| "eval_runtime": 26.5506, | |
| "eval_samples_per_second": 12.052, | |
| "eval_steps_per_second": 0.753, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 1.5936492681503296, | |
| "eval_runtime": 26.4217, | |
| "eval_samples_per_second": 12.111, | |
| "eval_steps_per_second": 0.757, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 7.661205315438782, | |
| "learning_rate": 9.549150281252632e-08, | |
| "loss": 2.0408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.5909881591796875, | |
| "eval_runtime": 26.3591, | |
| "eval_samples_per_second": 12.14, | |
| "eval_steps_per_second": 0.759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "step": 6, | |
| "total_flos": 1203933020160.0, | |
| "train_loss": 2.0323738853136697, | |
| "train_runtime": 186.0339, | |
| "train_samples_per_second": 2.096, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1203933020160.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |