| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06946856547412296, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013893713094824591, | |
| "eval_loss": 2.9451565742492676, | |
| "eval_runtime": 34.4539, | |
| "eval_samples_per_second": 8.794, | |
| "eval_steps_per_second": 4.412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069468565474122956, | |
| "grad_norm": 1.3465774059295654, | |
| "learning_rate": 5e-05, | |
| "loss": 2.808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013893713094824591, | |
| "grad_norm": 1.7650309801101685, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013893713094824591, | |
| "eval_loss": 2.687224864959717, | |
| "eval_runtime": 33.832, | |
| "eval_samples_per_second": 8.956, | |
| "eval_steps_per_second": 4.493, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02084056964223689, | |
| "grad_norm": 1.5081523656845093, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2467, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027787426189649182, | |
| "grad_norm": 1.763542652130127, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5649, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027787426189649182, | |
| "eval_loss": 1.5423730611801147, | |
| "eval_runtime": 33.9487, | |
| "eval_samples_per_second": 8.925, | |
| "eval_steps_per_second": 4.477, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03473428273706148, | |
| "grad_norm": 2.000399351119995, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2685, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04168113928447378, | |
| "grad_norm": 1.7187610864639282, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0837, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04168113928447378, | |
| "eval_loss": 1.0210185050964355, | |
| "eval_runtime": 34.0398, | |
| "eval_samples_per_second": 8.901, | |
| "eval_steps_per_second": 4.465, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.048627995831886074, | |
| "grad_norm": 2.0270674228668213, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.055574852379298365, | |
| "grad_norm": 1.9555302858352661, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9449, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.055574852379298365, | |
| "eval_loss": 0.8849262595176697, | |
| "eval_runtime": 34.1213, | |
| "eval_samples_per_second": 8.88, | |
| "eval_steps_per_second": 4.455, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06252170892671066, | |
| "grad_norm": 1.7785624265670776, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7927, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06946856547412296, | |
| "grad_norm": 1.3851503133773804, | |
| "learning_rate": 0.0, | |
| "loss": 0.8639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06946856547412296, | |
| "eval_loss": 0.8625767230987549, | |
| "eval_runtime": 34.1038, | |
| "eval_samples_per_second": 8.885, | |
| "eval_steps_per_second": 4.457, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8713180230451200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |