| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27787426189649184, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013893713094824591, | |
| "eval_loss": 1.592242956161499, | |
| "eval_runtime": 5.737, | |
| "eval_samples_per_second": 52.815, | |
| "eval_steps_per_second": 26.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013893713094824591, | |
| "grad_norm": 2.1929519176483154, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1021, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027787426189649182, | |
| "grad_norm": 1.7123305797576904, | |
| "learning_rate": 0.0002, | |
| "loss": 0.506, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04168113928447378, | |
| "grad_norm": 1.6912617683410645, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3446, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.055574852379298365, | |
| "grad_norm": 1.588252305984497, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3451, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06946856547412296, | |
| "grad_norm": 0.7013223171234131, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3116, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06946856547412296, | |
| "eval_loss": 0.30412161350250244, | |
| "eval_runtime": 4.894, | |
| "eval_samples_per_second": 61.912, | |
| "eval_steps_per_second": 31.058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08336227856894755, | |
| "grad_norm": 1.06772780418396, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2407, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09725599166377215, | |
| "grad_norm": 4.187992572784424, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2153, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11114970475859673, | |
| "grad_norm": 1.100953221321106, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2603, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12504341785342132, | |
| "grad_norm": 1.9511982202529907, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2081, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13893713094824592, | |
| "grad_norm": 0.6646924614906311, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2752, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13893713094824592, | |
| "eval_loss": 0.27076953649520874, | |
| "eval_runtime": 4.9578, | |
| "eval_samples_per_second": 61.116, | |
| "eval_steps_per_second": 30.659, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1528308440430705, | |
| "grad_norm": 0.974806547164917, | |
| "learning_rate": 0.0002, | |
| "loss": 0.292, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1667245571378951, | |
| "grad_norm": 0.9329864382743835, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2803, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1806182702327197, | |
| "grad_norm": 1.1351346969604492, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2498, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1945119833275443, | |
| "grad_norm": 0.8371953368186951, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2312, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2084056964223689, | |
| "grad_norm": 1.1801189184188843, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2219, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2084056964223689, | |
| "eval_loss": 0.256499707698822, | |
| "eval_runtime": 4.9053, | |
| "eval_samples_per_second": 61.769, | |
| "eval_steps_per_second": 30.987, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22229940951719346, | |
| "grad_norm": 0.9388880729675293, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2882, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.23619312261201805, | |
| "grad_norm": 0.5570294857025146, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2089, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.25008683570684265, | |
| "grad_norm": 0.8899029493331909, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2759, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.26398054880166727, | |
| "grad_norm": 1.1891875267028809, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1959, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.27787426189649184, | |
| "grad_norm": 1.2228397130966187, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2336, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27787426189649184, | |
| "eval_loss": 0.2487281858921051, | |
| "eval_runtime": 4.97, | |
| "eval_samples_per_second": 60.965, | |
| "eval_steps_per_second": 30.583, | |
| "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": 1534476052070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |