| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015601841017240034, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.800920508620017e-05, | |
| "eval_loss": 2.6932764053344727, | |
| "eval_runtime": 161.6543, | |
| "eval_samples_per_second": 33.392, | |
| "eval_steps_per_second": 16.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007800920508620017, | |
| "grad_norm": 1.6918610334396362, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015601841017240034, | |
| "grad_norm": 0.8769293427467346, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9108, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002340276152586005, | |
| "grad_norm": 0.8490325808525085, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8986, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003120368203448007, | |
| "grad_norm": 0.7544106841087341, | |
| "learning_rate": 0.0002, | |
| "loss": 0.837, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0039004602543100085, | |
| "grad_norm": 0.8223780989646912, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9035, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0039004602543100085, | |
| "eval_loss": 0.8136085271835327, | |
| "eval_runtime": 160.6948, | |
| "eval_samples_per_second": 33.592, | |
| "eval_steps_per_second": 16.796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00468055230517201, | |
| "grad_norm": 1.2069497108459473, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7518, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005460644356034012, | |
| "grad_norm": 0.8096679449081421, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8775, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006240736406896014, | |
| "grad_norm": 0.6722874045372009, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8393, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007020828457758015, | |
| "grad_norm": 0.7288264036178589, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8743, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.007800920508620017, | |
| "grad_norm": 0.756664514541626, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8471, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007800920508620017, | |
| "eval_loss": 0.787709653377533, | |
| "eval_runtime": 160.5519, | |
| "eval_samples_per_second": 33.622, | |
| "eval_steps_per_second": 16.811, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.008581012559482019, | |
| "grad_norm": 0.6181501746177673, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8125, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.00936110461034402, | |
| "grad_norm": 0.9252316355705261, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8039, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.010141196661206022, | |
| "grad_norm": 0.8269910216331482, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8983, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.010921288712068024, | |
| "grad_norm": 0.7751689553260803, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7934, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.011701380762930026, | |
| "grad_norm": 0.7328248620033264, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7806, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.011701380762930026, | |
| "eval_loss": 0.7735591530799866, | |
| "eval_runtime": 160.5021, | |
| "eval_samples_per_second": 33.632, | |
| "eval_steps_per_second": 16.816, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.012481472813792027, | |
| "grad_norm": 0.7903790473937988, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9333, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.013261564864654029, | |
| "grad_norm": 0.736691951751709, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7328, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01404165691551603, | |
| "grad_norm": 0.7038111090660095, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7207, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.014821748966378032, | |
| "grad_norm": 0.7238824367523193, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7662, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.015601841017240034, | |
| "grad_norm": 0.7471156120300293, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7058, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.015601841017240034, | |
| "eval_loss": 0.7626497149467468, | |
| "eval_runtime": 160.42, | |
| "eval_samples_per_second": 33.649, | |
| "eval_steps_per_second": 16.825, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.328602305200128e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |