| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05489478499542543, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018298261665141812, | |
| "eval_loss": 2.3934693336486816, | |
| "eval_runtime": 33.5003, | |
| "eval_samples_per_second": 6.895, | |
| "eval_steps_per_second": 3.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054894784995425435, | |
| "grad_norm": 1.440449595451355, | |
| "learning_rate": 3e-05, | |
| "loss": 2.42, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "grad_norm": 1.5027227401733398, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3992, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01463860933211345, | |
| "eval_loss": 2.2300760746002197, | |
| "eval_runtime": 32.8212, | |
| "eval_samples_per_second": 7.038, | |
| "eval_steps_per_second": 3.534, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01646843549862763, | |
| "grad_norm": 1.654961109161377, | |
| "learning_rate": 9e-05, | |
| "loss": 2.2091, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "grad_norm": 1.420807957649231, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.0462, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.027447392497712716, | |
| "grad_norm": 1.335792064666748, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.234, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0292772186642269, | |
| "eval_loss": 2.0752601623535156, | |
| "eval_runtime": 32.8407, | |
| "eval_samples_per_second": 7.034, | |
| "eval_steps_per_second": 3.532, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "grad_norm": 0.8707695603370667, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.0026, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0384263494967978, | |
| "grad_norm": 1.0747629404067993, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.0571, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04391582799634035, | |
| "grad_norm": 1.0367234945297241, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.1068, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04391582799634035, | |
| "eval_loss": 2.0426266193389893, | |
| "eval_runtime": 32.8578, | |
| "eval_samples_per_second": 7.03, | |
| "eval_steps_per_second": 3.53, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04940530649588289, | |
| "grad_norm": 1.0442975759506226, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.9313, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05489478499542543, | |
| "grad_norm": 0.9846899509429932, | |
| "learning_rate": 0.0, | |
| "loss": 1.9357, | |
| "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": 1.112831529320448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |