| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 29.521047592163086, | |
| "learning_rate": 0.0001928, | |
| "loss": 16.6221, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 10.102843284606934, | |
| "learning_rate": 0.00018480000000000002, | |
| "loss": 4.5141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 26.249595642089844, | |
| "learning_rate": 0.00017680000000000001, | |
| "loss": 3.1669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 10.36505126953125, | |
| "learning_rate": 0.0001688, | |
| "loss": 1.7486, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.466909408569336, | |
| "learning_rate": 0.0001608, | |
| "loss": 0.971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.1537357568740845, | |
| "learning_rate": 0.0001528, | |
| "loss": 0.6793, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.9161125421524048, | |
| "learning_rate": 0.0001448, | |
| "loss": 0.483, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 1.2326666116714478, | |
| "learning_rate": 0.00013680000000000002, | |
| "loss": 0.3513, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 0.9152237176895142, | |
| "learning_rate": 0.00012880000000000001, | |
| "loss": 0.2616, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.1397767066955566, | |
| "learning_rate": 0.0001208, | |
| "loss": 0.2024, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 1.2304277420043945, | |
| "learning_rate": 0.00011279999999999999, | |
| "loss": 0.1512, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.767804741859436, | |
| "learning_rate": 0.00010480000000000001, | |
| "loss": 0.1244, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 0.7617813348770142, | |
| "learning_rate": 9.680000000000001e-05, | |
| "loss": 0.1039, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "grad_norm": 0.7634106874465942, | |
| "learning_rate": 8.88e-05, | |
| "loss": 0.0828, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.7084076404571533, | |
| "learning_rate": 8.080000000000001e-05, | |
| "loss": 0.0803, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 0.7126042246818542, | |
| "learning_rate": 7.280000000000001e-05, | |
| "loss": 0.068, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "grad_norm": 0.8381725549697876, | |
| "learning_rate": 6.48e-05, | |
| "loss": 0.0583, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "grad_norm": 0.6145268678665161, | |
| "learning_rate": 5.68e-05, | |
| "loss": 0.0525, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "grad_norm": 0.6359936594963074, | |
| "learning_rate": 4.88e-05, | |
| "loss": 0.049, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.6751255393028259, | |
| "learning_rate": 4.08e-05, | |
| "loss": 0.0494, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "grad_norm": 2.0084617137908936, | |
| "learning_rate": 3.2800000000000004e-05, | |
| "loss": 0.0431, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "grad_norm": 0.6473382115364075, | |
| "learning_rate": 2.48e-05, | |
| "loss": 0.0413, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "grad_norm": 0.597090482711792, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.0359, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "grad_norm": 0.38703885674476624, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0431, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 0.5048331618309021, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.0401, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 9999999, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 333819209318400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |