| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0707070707070705, | |
| "eval_steps": 25, | |
| "global_step": 19, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 0.09397462755441666, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 11.9178, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "eval_loss": 11.918787956237793, | |
| "eval_runtime": 0.1289, | |
| "eval_samples_per_second": 388.028, | |
| "eval_steps_per_second": 100.887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 0.10107781738042831, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 11.9332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.10633832216262817, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 11.9287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 0.09259266406297684, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 11.9246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 0.10267990082502365, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 11.9268, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.10383405536413193, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 11.9282, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.1313131313131313, | |
| "grad_norm": 0.1870822310447693, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 21.607, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.2929292929292928, | |
| "grad_norm": 0.11836694926023483, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 11.9246, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.11512862890958786, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 11.926, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.6161616161616161, | |
| "grad_norm": 0.10030414909124374, | |
| "learning_rate": 5.128392945374505e-05, | |
| "loss": 11.9236, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.1301475167274475, | |
| "learning_rate": 4.395315307866405e-05, | |
| "loss": 11.9287, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 0.12092076241970062, | |
| "learning_rate": 3.692370589061639e-05, | |
| "loss": 11.9277, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.101010101010101, | |
| "grad_norm": 0.19482478499412537, | |
| "learning_rate": 3.0387332884490805e-05, | |
| "loss": 21.6046, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.2626262626262625, | |
| "grad_norm": 0.12174642831087112, | |
| "learning_rate": 2.4522329276841663e-05, | |
| "loss": 11.9182, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "grad_norm": 0.12407401949167252, | |
| "learning_rate": 1.9488677077162295e-05, | |
| "loss": 11.925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.5858585858585856, | |
| "grad_norm": 0.11212208122015, | |
| "learning_rate": 1.5423681195707997e-05, | |
| "loss": 11.9231, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.7474747474747474, | |
| "grad_norm": 0.12754788994789124, | |
| "learning_rate": 1.2438224123471442e-05, | |
| "loss": 11.9232, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 0.13909247517585754, | |
| "learning_rate": 1.0613741346877497e-05, | |
| "loss": 11.9257, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0707070707070705, | |
| "grad_norm": 0.2264919877052307, | |
| "learning_rate": 1e-05, | |
| "loss": 21.6087, | |
| "step": 19 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 19, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 396147818496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |