| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00301182139899104, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.02364279798208e-05, | |
| "eval_loss": 5.864229202270508, | |
| "eval_runtime": 643.2876, | |
| "eval_samples_per_second": 10.866, | |
| "eval_steps_per_second": 5.433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030118213989910396, | |
| "grad_norm": 1.7193124294281006, | |
| "learning_rate": 5e-05, | |
| "loss": 5.7912, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "grad_norm": 3.2139346599578857, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "eval_loss": 4.955783843994141, | |
| "eval_runtime": 646.6116, | |
| "eval_samples_per_second": 10.81, | |
| "eval_steps_per_second": 5.405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009035464196973119, | |
| "grad_norm": 4.723598003387451, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1179, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012047285595964158, | |
| "grad_norm": 3.0093629360198975, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.215, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012047285595964158, | |
| "eval_loss": 1.6245232820510864, | |
| "eval_runtime": 646.9745, | |
| "eval_samples_per_second": 10.804, | |
| "eval_steps_per_second": 5.402, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00150591069949552, | |
| "grad_norm": 3.5096235275268555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018070928393946238, | |
| "grad_norm": 5.103176116943359, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018070928393946238, | |
| "eval_loss": 0.8057319521903992, | |
| "eval_runtime": 647.3135, | |
| "eval_samples_per_second": 10.798, | |
| "eval_steps_per_second": 5.399, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002108274979293728, | |
| "grad_norm": 3.2122302055358887, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5477, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0024094571191928317, | |
| "grad_norm": 2.535107135772705, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6273, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0024094571191928317, | |
| "eval_loss": 0.5916562676429749, | |
| "eval_runtime": 647.0882, | |
| "eval_samples_per_second": 10.802, | |
| "eval_steps_per_second": 5.401, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0027106392590919358, | |
| "grad_norm": 3.415269136428833, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5726, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00301182139899104, | |
| "grad_norm": 4.0245561599731445, | |
| "learning_rate": 0.0, | |
| "loss": 0.613, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00301182139899104, | |
| "eval_loss": 0.5487688779830933, | |
| "eval_runtime": 650.0807, | |
| "eval_samples_per_second": 10.753, | |
| "eval_steps_per_second": 5.376, | |
| "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": 1.4254449660788736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |