| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014050699607751304, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.6835665359171006e-05, | |
| "eval_loss": 1.7034660577774048, | |
| "eval_runtime": 1190.3593, | |
| "eval_samples_per_second": 7.552, | |
| "eval_steps_per_second": 3.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014050699607751302, | |
| "grad_norm": 2.799278974533081, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7239, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00028101399215502604, | |
| "grad_norm": 1.3826738595962524, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3739, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00037468532287336805, | |
| "eval_loss": 1.3278619050979614, | |
| "eval_runtime": 1196.3758, | |
| "eval_samples_per_second": 7.514, | |
| "eval_steps_per_second": 3.757, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004215209882325391, | |
| "grad_norm": 1.2530328035354614, | |
| "learning_rate": 9e-05, | |
| "loss": 1.411, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005620279843100521, | |
| "grad_norm": 0.655875027179718, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.9647, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007025349803875652, | |
| "grad_norm": 0.9592669010162354, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007493706457467361, | |
| "eval_loss": 1.0458663702011108, | |
| "eval_runtime": 1196.2164, | |
| "eval_samples_per_second": 7.515, | |
| "eval_steps_per_second": 3.758, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008430419764650782, | |
| "grad_norm": 0.8475580215454102, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.012, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009835489725425913, | |
| "grad_norm": 0.5412721633911133, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.929, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011240559686201042, | |
| "grad_norm": 0.6460533142089844, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.9141, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011240559686201042, | |
| "eval_loss": 0.9949507713317871, | |
| "eval_runtime": 1197.3016, | |
| "eval_samples_per_second": 7.509, | |
| "eval_steps_per_second": 3.754, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012645629646976173, | |
| "grad_norm": 0.49220025539398193, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.9051, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0014050699607751304, | |
| "grad_norm": 0.7920961380004883, | |
| "learning_rate": 0.0, | |
| "loss": 0.937, | |
| "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": 1.1499252895186944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |