| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.7232568264007568, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 1.1006, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.3090097904205322, | |
| "learning_rate": 4.690766700109659e-05, | |
| "loss": 1.049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.6444264650344849, | |
| "learning_rate": 4.3224215685535294e-05, | |
| "loss": 1.0269, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.920586109161377, | |
| "learning_rate": 3.8395669874474915e-05, | |
| "loss": 0.9896, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.7457690238952637, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 1.0179, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.9631178379058838, | |
| "learning_rate": 2.656976298823284e-05, | |
| "loss": 0.9636, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.050771951675415, | |
| "learning_rate": 2.031546713535688e-05, | |
| "loss": 1.0151, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.9484338760375977, | |
| "learning_rate": 1.4355517710873184e-05, | |
| "loss": 1.0039, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.7718967199325562, | |
| "learning_rate": 9.064400256282757e-06, | |
| "loss": 0.9773, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.00250506401062, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.9578, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 2.0536956787109375, | |
| "learning_rate": 1.7555878527937164e-06, | |
| "loss": 0.9773, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 2.105520248413086, | |
| "learning_rate": 1.9713246713805588e-07, | |
| "loss": 1.0422, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 125, | |
| "total_flos": 1.7032957304347034e+17, | |
| "train_loss": 1.0112789268493652, | |
| "train_runtime": 5845.5599, | |
| "train_samples_per_second": 0.342, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 1.7032957304347034e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |