| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02609262883235486, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002609262883235486, | |
| "grad_norm": 0.6899170279502869, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7018, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002609262883235486, | |
| "eval_loss": 2.74656343460083, | |
| "eval_runtime": 3.6737, | |
| "eval_samples_per_second": 44.097, | |
| "eval_steps_per_second": 22.049, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005218525766470972, | |
| "grad_norm": 0.7338986396789551, | |
| "learning_rate": 4e-05, | |
| "loss": 2.849, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007827788649706457, | |
| "grad_norm": 0.5598652958869934, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9166, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007827788649706457, | |
| "eval_loss": 2.746614456176758, | |
| "eval_runtime": 2.964, | |
| "eval_samples_per_second": 54.655, | |
| "eval_steps_per_second": 27.328, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010437051532941943, | |
| "grad_norm": 0.5019466280937195, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8293, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01304631441617743, | |
| "grad_norm": 0.47560611367225647, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6752, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015655577299412915, | |
| "grad_norm": 0.5056817531585693, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8824, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015655577299412915, | |
| "eval_loss": 2.736074209213257, | |
| "eval_runtime": 2.9469, | |
| "eval_samples_per_second": 54.973, | |
| "eval_steps_per_second": 27.486, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0182648401826484, | |
| "grad_norm": 0.5827949643135071, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3452, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020874103065883887, | |
| "grad_norm": 0.5860369205474854, | |
| "learning_rate": 0.00016, | |
| "loss": 2.9203, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "grad_norm": 0.5119990110397339, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "eval_loss": 2.6998348236083984, | |
| "eval_runtime": 2.9584, | |
| "eval_samples_per_second": 54.759, | |
| "eval_steps_per_second": 27.38, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02609262883235486, | |
| "grad_norm": 0.4843307435512543, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2512, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 65156035903488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |