| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004660538059118925, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.660538059118925e-05, | |
| "grad_norm": 0.013180263340473175, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3787, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.660538059118925e-05, | |
| "eval_loss": 10.381084442138672, | |
| "eval_runtime": 24.2148, | |
| "eval_samples_per_second": 373.119, | |
| "eval_steps_per_second": 186.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.32107611823785e-05, | |
| "grad_norm": 0.014053184539079666, | |
| "learning_rate": 4e-05, | |
| "loss": 10.383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013981614177356776, | |
| "grad_norm": 0.017326638102531433, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3827, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013981614177356776, | |
| "eval_loss": 10.381073951721191, | |
| "eval_runtime": 24.3154, | |
| "eval_samples_per_second": 371.575, | |
| "eval_steps_per_second": 185.808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000186421522364757, | |
| "grad_norm": 0.020090481266379356, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3799, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023302690295594626, | |
| "grad_norm": 0.02198541909456253, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3782, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002796322835471355, | |
| "grad_norm": 0.016029352322220802, | |
| "learning_rate": 0.00012, | |
| "loss": 10.38, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002796322835471355, | |
| "eval_loss": 10.381016731262207, | |
| "eval_runtime": 24.1312, | |
| "eval_samples_per_second": 374.412, | |
| "eval_steps_per_second": 187.227, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003262376641383248, | |
| "grad_norm": 0.02153741382062435, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3821, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000372843044729514, | |
| "grad_norm": 0.02051008678972721, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3784, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004194484253207033, | |
| "grad_norm": 0.0244196318089962, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3814, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004194484253207033, | |
| "eval_loss": 10.380924224853516, | |
| "eval_runtime": 25.1971, | |
| "eval_samples_per_second": 358.572, | |
| "eval_steps_per_second": 179.306, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004660538059118925, | |
| "grad_norm": 0.029234416782855988, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3874, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 161636352000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |