| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23391812865497075, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 2.5154502391815186, | |
| "eval_runtime": 6.0947, | |
| "eval_samples_per_second": 14.767, | |
| "eval_steps_per_second": 7.383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 7.17006254196167, | |
| "learning_rate": 5e-05, | |
| "loss": 9.3033, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 6.0110344886779785, | |
| "learning_rate": 0.0001, | |
| "loss": 8.4186, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": 2.278883457183838, | |
| "eval_runtime": 6.1015, | |
| "eval_samples_per_second": 14.75, | |
| "eval_steps_per_second": 7.375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 10.051191329956055, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.6795, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 8.716605186462402, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.7438, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "eval_loss": 1.0906450748443604, | |
| "eval_runtime": 6.0499, | |
| "eval_samples_per_second": 14.876, | |
| "eval_steps_per_second": 7.438, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 12.805469512939453, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.4344, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 11.407937049865723, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "eval_loss": 0.367561012506485, | |
| "eval_runtime": 6.041, | |
| "eval_samples_per_second": 14.898, | |
| "eval_steps_per_second": 7.449, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16374269005847952, | |
| "grad_norm": 9.037041664123535, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2853, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 7.488927364349365, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9677, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "eval_loss": 0.1949077844619751, | |
| "eval_runtime": 6.2337, | |
| "eval_samples_per_second": 14.438, | |
| "eval_steps_per_second": 7.219, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 6.888825416564941, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7785, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "grad_norm": 8.694323539733887, | |
| "learning_rate": 0.0, | |
| "loss": 0.8306, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "eval_loss": 0.17766140401363373, | |
| "eval_runtime": 6.0202, | |
| "eval_samples_per_second": 14.95, | |
| "eval_steps_per_second": 7.475, | |
| "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": 8143665679564800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |