| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0022862804122925676, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.620934707641892e-05, | |
| "eval_loss": 1.807066559791565, | |
| "eval_runtime": 568.4022, | |
| "eval_samples_per_second": 9.72, | |
| "eval_steps_per_second": 4.861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022862804122925678, | |
| "grad_norm": 4.993569850921631, | |
| "learning_rate": 3e-05, | |
| "loss": 7.1038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00045725608245851356, | |
| "grad_norm": 4.809709548950195, | |
| "learning_rate": 6e-05, | |
| "loss": 7.1558, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006096747766113513, | |
| "eval_loss": 1.6106492280960083, | |
| "eval_runtime": 570.7806, | |
| "eval_samples_per_second": 9.68, | |
| "eval_steps_per_second": 4.841, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006858841236877703, | |
| "grad_norm": 3.1479501724243164, | |
| "learning_rate": 9e-05, | |
| "loss": 6.5638, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009145121649170271, | |
| "grad_norm": 1.8017927408218384, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.3315, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011431402061462838, | |
| "grad_norm": 1.7953505516052246, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.1193, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012193495532227027, | |
| "eval_loss": 1.4005733728408813, | |
| "eval_runtime": 570.8146, | |
| "eval_samples_per_second": 9.679, | |
| "eval_steps_per_second": 4.84, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013717682473755406, | |
| "grad_norm": 1.3931858539581299, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.2299, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016003962886047974, | |
| "grad_norm": 1.3211941719055176, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 5.3209, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018290243298340542, | |
| "grad_norm": 1.1876999139785767, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 5.557, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0018290243298340542, | |
| "eval_loss": 1.3526378870010376, | |
| "eval_runtime": 571.4664, | |
| "eval_samples_per_second": 9.668, | |
| "eval_steps_per_second": 4.835, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002057652371063311, | |
| "grad_norm": 1.2355953454971313, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 5.6448, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0022862804122925676, | |
| "grad_norm": 1.1167676448822021, | |
| "learning_rate": 0.0, | |
| "loss": 5.5633, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5526274525102080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |