| { | |
| "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": 8.112344215556096, | |
| "learning_rate": 5e-07, | |
| "loss": 1.4798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 7.311316913520959, | |
| "learning_rate": 8.742553740855505e-07, | |
| "loss": 1.4207, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.5384521484375, | |
| "eval_runtime": 1.3346, | |
| "eval_samples_per_second": 5.245, | |
| "eval_steps_per_second": 0.749, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 6.371575259126873, | |
| "learning_rate": 3.2269755647873214e-07, | |
| "loss": 1.4041, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.4936072826385498, | |
| "eval_runtime": 1.3789, | |
| "eval_samples_per_second": 5.077, | |
| "eval_steps_per_second": 0.725, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 6.425727499342206, | |
| "learning_rate": 0.0, | |
| "loss": 1.379, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 1.4922218322753906, | |
| "eval_runtime": 1.3795, | |
| "eval_samples_per_second": 5.074, | |
| "eval_steps_per_second": 0.725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "step": 15, | |
| "total_flos": 3088349921280.0, | |
| "train_loss": 1.4052010297775268, | |
| "train_runtime": 248.3278, | |
| "train_samples_per_second": 4.24, | |
| "train_steps_per_second": 0.06 | |
| } | |
| ], | |
| "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 | |
| } | |