| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005047672462142457, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005608524957936063, | |
| "grad_norm": 0.01492331176996231, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9315, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005608524957936063, | |
| "eval_loss": 11.931306838989258, | |
| "eval_runtime": 3.0288, | |
| "eval_samples_per_second": 247.95, | |
| "eval_steps_per_second": 124.14, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011217049915872126, | |
| "grad_norm": 0.008967285975813866, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016825574873808188, | |
| "grad_norm": 0.016075991094112396, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016825574873808188, | |
| "eval_loss": 11.931303977966309, | |
| "eval_runtime": 3.0838, | |
| "eval_samples_per_second": 243.535, | |
| "eval_steps_per_second": 121.929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002243409983174425, | |
| "grad_norm": 0.016678154468536377, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9328, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028042624789680315, | |
| "grad_norm": 0.018861737102270126, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9248, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033651149747616375, | |
| "grad_norm": 0.009495808742940426, | |
| "learning_rate": 0.00012, | |
| "loss": 11.926, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033651149747616375, | |
| "eval_loss": 11.93128776550293, | |
| "eval_runtime": 3.1316, | |
| "eval_samples_per_second": 239.81, | |
| "eval_steps_per_second": 120.065, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003925967470555244, | |
| "grad_norm": 0.012134317308664322, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00448681996634885, | |
| "grad_norm": 0.007003261707723141, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9349, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005047672462142457, | |
| "grad_norm": 0.013818953186273575, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005047672462142457, | |
| "eval_loss": 11.93126392364502, | |
| "eval_runtime": 3.0619, | |
| "eval_samples_per_second": 245.272, | |
| "eval_steps_per_second": 122.799, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1092993024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |