| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11461318051575932, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002292263610315186, |
| "eval_loss": 0.6850675344467163, |
| "eval_runtime": 32.1049, |
| "eval_samples_per_second": 5.731, |
| "eval_steps_per_second": 2.866, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011461318051575931, |
| "grad_norm": 8.41812801361084, |
| "learning_rate": 5e-05, |
| "loss": 2.6706, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.022922636103151862, |
| "grad_norm": 6.175701141357422, |
| "learning_rate": 0.0001, |
| "loss": 2.3579, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.022922636103151862, |
| "eval_loss": 0.5222229957580566, |
| "eval_runtime": 34.3718, |
| "eval_samples_per_second": 5.353, |
| "eval_steps_per_second": 2.677, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.034383954154727794, |
| "grad_norm": 4.626423358917236, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.0376, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.045845272206303724, |
| "grad_norm": 4.920547008514404, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.7548, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.045845272206303724, |
| "eval_loss": 0.4074614942073822, |
| "eval_runtime": 35.1925, |
| "eval_samples_per_second": 5.228, |
| "eval_steps_per_second": 2.614, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05730659025787966, |
| "grad_norm": 4.158402919769287, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.5327, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.06876790830945559, |
| "grad_norm": 4.287597179412842, |
| "learning_rate": 5e-05, |
| "loss": 1.3894, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.06876790830945559, |
| "eval_loss": 0.37142413854599, |
| "eval_runtime": 35.3436, |
| "eval_samples_per_second": 5.206, |
| "eval_steps_per_second": 2.603, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08022922636103152, |
| "grad_norm": 3.6002652645111084, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.454, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.09169054441260745, |
| "grad_norm": 3.943558931350708, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.4878, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.09169054441260745, |
| "eval_loss": 0.3554995059967041, |
| "eval_runtime": 35.3678, |
| "eval_samples_per_second": 5.202, |
| "eval_steps_per_second": 2.601, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.10315186246418338, |
| "grad_norm": 4.879668712615967, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.4834, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.11461318051575932, |
| "grad_norm": 3.6490864753723145, |
| "learning_rate": 0.0, |
| "loss": 1.5293, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.11461318051575932, |
| "eval_loss": 0.3512641191482544, |
| "eval_runtime": 35.4018, |
| "eval_samples_per_second": 5.197, |
| "eval_steps_per_second": 2.599, |
| "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": 1.75267179921408e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
