| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02615832325147958, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001307916162573979, | |
| "eval_loss": 3.9479501247406006, | |
| "eval_runtime": 37.5868, | |
| "eval_samples_per_second": 85.668, | |
| "eval_steps_per_second": 42.834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001307916162573979, | |
| "grad_norm": 6.595814228057861, | |
| "learning_rate": 0.0002, | |
| "loss": 15.3333, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002615832325147958, | |
| "grad_norm": 6.2806596755981445, | |
| "learning_rate": 0.0002, | |
| "loss": 14.378, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003923748487721937, | |
| "grad_norm": 7.519875526428223, | |
| "learning_rate": 0.0002, | |
| "loss": 13.7137, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005231664650295916, | |
| "grad_norm": 7.988043785095215, | |
| "learning_rate": 0.0002, | |
| "loss": 13.6446, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006539580812869895, | |
| "grad_norm": 7.619246959686279, | |
| "learning_rate": 0.0002, | |
| "loss": 12.593, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006539580812869895, | |
| "eval_loss": 3.214905023574829, | |
| "eval_runtime": 37.5958, | |
| "eval_samples_per_second": 85.648, | |
| "eval_steps_per_second": 42.824, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007847496975443874, | |
| "grad_norm": 18.687952041625977, | |
| "learning_rate": 0.0002, | |
| "loss": 12.9873, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009155413138017853, | |
| "grad_norm": 8.790769577026367, | |
| "learning_rate": 0.0002, | |
| "loss": 12.423, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010463329300591831, | |
| "grad_norm": 8.85031509399414, | |
| "learning_rate": 0.0002, | |
| "loss": 12.0676, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.011771245463165811, | |
| "grad_norm": 12.773844718933105, | |
| "learning_rate": 0.0002, | |
| "loss": 12.8019, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01307916162573979, | |
| "grad_norm": 11.019274711608887, | |
| "learning_rate": 0.0002, | |
| "loss": 12.2702, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01307916162573979, | |
| "eval_loss": 3.001326560974121, | |
| "eval_runtime": 37.3516, | |
| "eval_samples_per_second": 86.208, | |
| "eval_steps_per_second": 43.104, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.014387077788313768, | |
| "grad_norm": 12.210068702697754, | |
| "learning_rate": 0.0002, | |
| "loss": 12.0112, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.015694993950887748, | |
| "grad_norm": 11.919943809509277, | |
| "learning_rate": 0.0002, | |
| "loss": 11.319, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.017002910113461726, | |
| "grad_norm": 10.63607120513916, | |
| "learning_rate": 0.0002, | |
| "loss": 11.7438, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.018310826276035707, | |
| "grad_norm": 11.607667922973633, | |
| "learning_rate": 0.0002, | |
| "loss": 11.2511, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.019618742438609685, | |
| "grad_norm": 13.221806526184082, | |
| "learning_rate": 0.0002, | |
| "loss": 11.3896, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.019618742438609685, | |
| "eval_loss": 2.847592353820801, | |
| "eval_runtime": 37.3438, | |
| "eval_samples_per_second": 86.226, | |
| "eval_steps_per_second": 43.113, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.020926658601183663, | |
| "grad_norm": 12.179810523986816, | |
| "learning_rate": 0.0002, | |
| "loss": 11.7368, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.022234574763757644, | |
| "grad_norm": 14.598481178283691, | |
| "learning_rate": 0.0002, | |
| "loss": 11.1283, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.023542490926331622, | |
| "grad_norm": 9.615200996398926, | |
| "learning_rate": 0.0002, | |
| "loss": 11.2235, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0248504070889056, | |
| "grad_norm": 10.755783081054688, | |
| "learning_rate": 0.0002, | |
| "loss": 11.2189, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02615832325147958, | |
| "grad_norm": 12.484338760375977, | |
| "learning_rate": 0.0002, | |
| "loss": 11.5377, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02615832325147958, | |
| "eval_loss": 2.7612085342407227, | |
| "eval_runtime": 37.0673, | |
| "eval_samples_per_second": 86.869, | |
| "eval_steps_per_second": 43.435, | |
| "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": 1546434851635200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |