| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.7272727272727275, | |
| "eval_steps": 500, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 7.793628580537048, | |
| "learning_rate": 5e-07, | |
| "loss": 1.4406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 7.623422031496145, | |
| "learning_rate": 8.742553740855505e-07, | |
| "loss": 1.438, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.428216576576233, | |
| "eval_runtime": 1.3237, | |
| "eval_samples_per_second": 10.577, | |
| "eval_steps_per_second": 0.755, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 6.428473039745435, | |
| "learning_rate": 3.2269755647873214e-07, | |
| "loss": 1.3992, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.383201241493225, | |
| "eval_runtime": 1.3846, | |
| "eval_samples_per_second": 10.111, | |
| "eval_steps_per_second": 0.722, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 6.111637983949403, | |
| "learning_rate": 0.0, | |
| "loss": 1.3839, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 1.3816066980361938, | |
| "eval_runtime": 1.3794, | |
| "eval_samples_per_second": 10.149, | |
| "eval_steps_per_second": 0.725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "step": 15, | |
| "total_flos": 3088349921280.0, | |
| "train_loss": 1.4071982065836588, | |
| "train_runtime": 254.5495, | |
| "train_samples_per_second": 4.054, | |
| "train_steps_per_second": 0.059 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3088349921280.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |