| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20587427944002196, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01372495196266813, | |
| "grad_norm": 23.43617820739746, | |
| "learning_rate": 6.378600823045268e-07, | |
| "loss": 3.6307, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02744990392533626, | |
| "grad_norm": 27.224123001098633, | |
| "learning_rate": 1.3237311385459534e-06, | |
| "loss": 0.8845, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04117485588800439, | |
| "grad_norm": 22.287761688232422, | |
| "learning_rate": 2.00960219478738e-06, | |
| "loss": 0.5517, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05489980785067252, | |
| "grad_norm": 14.750782012939453, | |
| "learning_rate": 2.6954732510288067e-06, | |
| "loss": 0.3488, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06862475981334065, | |
| "grad_norm": 51.949310302734375, | |
| "learning_rate": 3.3813443072702336e-06, | |
| "loss": 0.3129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08234971177600878, | |
| "grad_norm": 10.03300666809082, | |
| "learning_rate": 4.06721536351166e-06, | |
| "loss": 0.2679, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09607466373867692, | |
| "grad_norm": 26.423612594604492, | |
| "learning_rate": 4.753086419753087e-06, | |
| "loss": 0.2911, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.10979961570134504, | |
| "grad_norm": 3.058533191680908, | |
| "learning_rate": 5.438957475994513e-06, | |
| "loss": 0.2801, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12352456766401318, | |
| "grad_norm": 18.2351016998291, | |
| "learning_rate": 6.12482853223594e-06, | |
| "loss": 0.2771, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1372495196266813, | |
| "grad_norm": 7.775646686553955, | |
| "learning_rate": 6.810699588477366e-06, | |
| "loss": 0.2446, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15097447158934943, | |
| "grad_norm": 10.91329574584961, | |
| "learning_rate": 7.496570644718793e-06, | |
| "loss": 0.2736, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.16469942355201755, | |
| "grad_norm": 32.206260681152344, | |
| "learning_rate": 8.18244170096022e-06, | |
| "loss": 0.2983, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1784243755146857, | |
| "grad_norm": 30.968856811523438, | |
| "learning_rate": 8.868312757201646e-06, | |
| "loss": 0.2933, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.19214932747735383, | |
| "grad_norm": 31.030960083007812, | |
| "learning_rate": 9.554183813443072e-06, | |
| "loss": 0.2826, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.20587427944002196, | |
| "grad_norm": 17.41258430480957, | |
| "learning_rate": 9.97331096538051e-06, | |
| "loss": 0.2527, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 14572, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |