| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0025760470557928856, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.58682351930962e-05, | |
| "eval_loss": 2.5068418979644775, | |
| "eval_runtime": 286.8019, | |
| "eval_samples_per_second": 17.099, | |
| "eval_steps_per_second": 8.549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002576047055792886, | |
| "grad_norm": 2.3656258583068848, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005152094111585772, | |
| "grad_norm": 2.195690631866455, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3511, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006869458815447696, | |
| "eval_loss": 2.145287275314331, | |
| "eval_runtime": 284.4035, | |
| "eval_samples_per_second": 17.243, | |
| "eval_steps_per_second": 8.622, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007728141167378657, | |
| "grad_norm": 1.7706506252288818, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2156, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010304188223171544, | |
| "grad_norm": 2.0543875694274902, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.9913, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012880235278964428, | |
| "grad_norm": 1.5944548845291138, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.8435, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013738917630895392, | |
| "eval_loss": 1.8917441368103027, | |
| "eval_runtime": 285.4858, | |
| "eval_samples_per_second": 17.178, | |
| "eval_steps_per_second": 8.589, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015456282334757314, | |
| "grad_norm": 2.3291523456573486, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8668, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00180323293905502, | |
| "grad_norm": 1.8036468029022217, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.844, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002060837644634309, | |
| "grad_norm": 1.6711976528167725, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.8548, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002060837644634309, | |
| "eval_loss": 1.8616937398910522, | |
| "eval_runtime": 285.8477, | |
| "eval_samples_per_second": 17.156, | |
| "eval_steps_per_second": 8.578, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0023184423502135973, | |
| "grad_norm": 1.5501047372817993, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.8738, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0025760470557928856, | |
| "grad_norm": 1.5348728895187378, | |
| "learning_rate": 0.0, | |
| "loss": 1.6399, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |