| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021260763261401083, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004252152652280217, | |
| "eval_loss": 1.7155253887176514, | |
| "eval_runtime": 67.8791, | |
| "eval_samples_per_second": 14.599, | |
| "eval_steps_per_second": 7.307, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021260763261401086, | |
| "grad_norm": 21.15373420715332, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0144, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004252152652280217, | |
| "grad_norm": 11.718650817871094, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004252152652280217, | |
| "eval_loss": 1.278249979019165, | |
| "eval_runtime": 68.4631, | |
| "eval_samples_per_second": 14.475, | |
| "eval_steps_per_second": 7.245, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006378228978420325, | |
| "grad_norm": 8.320859909057617, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8707, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008504305304560434, | |
| "grad_norm": 9.103741645812988, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.5468, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008504305304560434, | |
| "eval_loss": 1.1138205528259277, | |
| "eval_runtime": 68.3518, | |
| "eval_samples_per_second": 14.499, | |
| "eval_steps_per_second": 7.257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010630381630700542, | |
| "grad_norm": 9.408296585083008, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.5072, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01275645795684065, | |
| "grad_norm": 9.910293579101562, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9498, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01275645795684065, | |
| "eval_loss": 1.0580389499664307, | |
| "eval_runtime": 68.675, | |
| "eval_samples_per_second": 14.43, | |
| "eval_steps_per_second": 7.222, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01488253428298076, | |
| "grad_norm": 7.2373433113098145, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.2421, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01700861060912087, | |
| "grad_norm": 6.351443767547607, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.2157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01700861060912087, | |
| "eval_loss": 1.0389580726623535, | |
| "eval_runtime": 68.6435, | |
| "eval_samples_per_second": 14.437, | |
| "eval_steps_per_second": 7.226, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019134686935260974, | |
| "grad_norm": 5.888601779937744, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6582, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021260763261401083, | |
| "grad_norm": 10.042596817016602, | |
| "learning_rate": 0.0, | |
| "loss": 4.3925, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021260763261401083, | |
| "eval_loss": 1.0340659618377686, | |
| "eval_runtime": 68.5819, | |
| "eval_samples_per_second": 14.45, | |
| "eval_steps_per_second": 7.232, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9552050333417472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |