| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008789277081960008, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017578554163920018, | |
| "eval_loss": 1.3559997081756592, | |
| "eval_runtime": 149.1273, | |
| "eval_samples_per_second": 16.067, | |
| "eval_steps_per_second": 8.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008789277081960009, | |
| "grad_norm": 26.121601104736328, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3463, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017578554163920018, | |
| "grad_norm": 18.39797019958496, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017578554163920018, | |
| "eval_loss": 0.3040425181388855, | |
| "eval_runtime": 150.4577, | |
| "eval_samples_per_second": 15.925, | |
| "eval_steps_per_second": 7.962, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0026367831245880024, | |
| "grad_norm": 11.072988510131836, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6892, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0035157108327840037, | |
| "grad_norm": 34.34139633178711, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035157108327840037, | |
| "eval_loss": 0.05951165780425072, | |
| "eval_runtime": 150.4359, | |
| "eval_samples_per_second": 15.927, | |
| "eval_steps_per_second": 7.964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004394638540980004, | |
| "grad_norm": 21.095478057861328, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4683, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005273566249176005, | |
| "grad_norm": 16.064796447753906, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2612, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005273566249176005, | |
| "eval_loss": 0.05736084654927254, | |
| "eval_runtime": 150.4867, | |
| "eval_samples_per_second": 15.922, | |
| "eval_steps_per_second": 7.961, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0061524939573720065, | |
| "grad_norm": 1.8894904851913452, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007031421665568007, | |
| "grad_norm": 7.167157173156738, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0972, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007031421665568007, | |
| "eval_loss": 0.046873368322849274, | |
| "eval_runtime": 150.4406, | |
| "eval_samples_per_second": 15.927, | |
| "eval_steps_per_second": 7.963, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007910349373764008, | |
| "grad_norm": 13.457677841186523, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0963, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008789277081960008, | |
| "grad_norm": 15.055408477783203, | |
| "learning_rate": 0.0, | |
| "loss": 0.1247, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008789277081960008, | |
| "eval_loss": 0.043586064130067825, | |
| "eval_runtime": 150.7829, | |
| "eval_samples_per_second": 15.89, | |
| "eval_steps_per_second": 7.945, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |