| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0114370675358838, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022874135071767598, | |
| "eval_loss": 4.032942295074463, | |
| "eval_runtime": 218.0184, | |
| "eval_samples_per_second": 8.444, | |
| "eval_steps_per_second": 4.224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00114370675358838, | |
| "grad_norm": 3.1650936603546143, | |
| "learning_rate": 5e-05, | |
| "loss": 15.8386, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00228741350717676, | |
| "grad_norm": 4.878422737121582, | |
| "learning_rate": 0.0001, | |
| "loss": 16.1186, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00228741350717676, | |
| "eval_loss": 3.8768084049224854, | |
| "eval_runtime": 218.599, | |
| "eval_samples_per_second": 8.422, | |
| "eval_steps_per_second": 4.213, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0034311202607651397, | |
| "grad_norm": 9.079002380371094, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 15.8643, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00457482701435352, | |
| "grad_norm": 6.7085957527160645, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00457482701435352, | |
| "eval_loss": 2.3919756412506104, | |
| "eval_runtime": 219.3206, | |
| "eval_samples_per_second": 8.394, | |
| "eval_steps_per_second": 4.199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0057185337679419, | |
| "grad_norm": 10.618727684020996, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 8.336, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006862240521530279, | |
| "grad_norm": 7.3490777015686035, | |
| "learning_rate": 5e-05, | |
| "loss": 7.0602, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006862240521530279, | |
| "eval_loss": 1.865958333015442, | |
| "eval_runtime": 219.3454, | |
| "eval_samples_per_second": 8.393, | |
| "eval_steps_per_second": 4.199, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00800594727511866, | |
| "grad_norm": 7.472850799560547, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.0896, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00914965402870704, | |
| "grad_norm": 8.473782539367676, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00914965402870704, | |
| "eval_loss": 1.759209394454956, | |
| "eval_runtime": 219.2241, | |
| "eval_samples_per_second": 8.398, | |
| "eval_steps_per_second": 4.201, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010293360782295419, | |
| "grad_norm": 9.23664665222168, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.9458, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0114370675358838, | |
| "grad_norm": 7.948398590087891, | |
| "learning_rate": 0.0, | |
| "loss": 7.2517, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0114370675358838, | |
| "eval_loss": 1.743358850479126, | |
| "eval_runtime": 219.1872, | |
| "eval_samples_per_second": 8.399, | |
| "eval_steps_per_second": 4.202, | |
| "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": 1.698683682816e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |