| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008519701810436636, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001703940362087327, | |
| "eval_loss": 1.4592077732086182, | |
| "eval_runtime": 152.6783, | |
| "eval_samples_per_second": 16.184, | |
| "eval_steps_per_second": 8.095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008519701810436634, | |
| "grad_norm": 12.976332664489746, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017039403620873268, | |
| "grad_norm": 12.687151908874512, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017039403620873268, | |
| "eval_loss": 1.213706135749817, | |
| "eval_runtime": 155.0861, | |
| "eval_samples_per_second": 15.933, | |
| "eval_steps_per_second": 7.97, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025559105431309905, | |
| "grad_norm": 13.283295631408691, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.4468, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034078807241746537, | |
| "grad_norm": 10.58646011352539, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.4071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034078807241746537, | |
| "eval_loss": 1.1461223363876343, | |
| "eval_runtime": 155.1477, | |
| "eval_samples_per_second": 15.927, | |
| "eval_steps_per_second": 7.967, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004259850905218318, | |
| "grad_norm": 10.58533000946045, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005111821086261981, | |
| "grad_norm": 10.329619407653809, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6977, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005111821086261981, | |
| "eval_loss": 1.1235452890396118, | |
| "eval_runtime": 154.4978, | |
| "eval_samples_per_second": 15.994, | |
| "eval_steps_per_second": 8.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005963791267305644, | |
| "grad_norm": 14.518905639648438, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.9486, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006815761448349307, | |
| "grad_norm": 12.32070255279541, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.6641, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006815761448349307, | |
| "eval_loss": 1.11506187915802, | |
| "eval_runtime": 154.188, | |
| "eval_samples_per_second": 16.026, | |
| "eval_steps_per_second": 8.016, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0076677316293929714, | |
| "grad_norm": 12.092145919799805, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.3513, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008519701810436636, | |
| "grad_norm": 9.324203491210938, | |
| "learning_rate": 0.0, | |
| "loss": 4.2082, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008519701810436636, | |
| "eval_loss": 1.1136835813522339, | |
| "eval_runtime": 153.8035, | |
| "eval_samples_per_second": 16.066, | |
| "eval_steps_per_second": 8.036, | |
| "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 | |
| } | |