| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 12500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.125, | |
| "learning_rate": 9.603841536614646e-05, | |
| "loss": 1.8394, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 9.203681472589036e-05, | |
| "loss": 1.3706, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.8984375, | |
| "learning_rate": 8.803521408563425e-05, | |
| "loss": 1.3084, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.046875, | |
| "learning_rate": 8.403361344537815e-05, | |
| "loss": 1.2739, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.734375, | |
| "learning_rate": 8.003201280512204e-05, | |
| "loss": 1.2551, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 2.671875, | |
| "learning_rate": 7.603041216486595e-05, | |
| "loss": 1.2183, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 1.7421875, | |
| "learning_rate": 7.202881152460985e-05, | |
| "loss": 1.1962, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.8828125, | |
| "learning_rate": 6.802721088435374e-05, | |
| "loss": 1.1709, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 6.402561024409764e-05, | |
| "loss": 1.1534, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 6.002400960384153e-05, | |
| "loss": 1.1418, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 2.765625, | |
| "learning_rate": 5.6022408963585436e-05, | |
| "loss": 1.1375, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 5.202080832332934e-05, | |
| "loss": 1.1271, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 4.801920768307323e-05, | |
| "loss": 1.0945, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.03125, | |
| "learning_rate": 4.4017607042817125e-05, | |
| "loss": 1.106, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 4.001600640256102e-05, | |
| "loss": 1.0835, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 3.6014405762304925e-05, | |
| "loss": 1.0687, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 3.201280512204882e-05, | |
| "loss": 1.0637, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.8984375, | |
| "learning_rate": 2.8011204481792718e-05, | |
| "loss": 1.0477, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 2.4009603841536614e-05, | |
| "loss": 1.0494, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 2.000800320128051e-05, | |
| "loss": 1.0529, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 1.6484375, | |
| "learning_rate": 1.600640256102441e-05, | |
| "loss": 1.0219, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.8359375, | |
| "learning_rate": 1.2004801920768307e-05, | |
| "loss": 1.0338, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 2.125, | |
| "learning_rate": 8.003201280512205e-06, | |
| "loss": 1.0454, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.828125, | |
| "learning_rate": 4.001600640256103e-06, | |
| "loss": 1.0405, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.8359375, | |
| "learning_rate": 0.0, | |
| "loss": 1.0363, | |
| "step": 12500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.596194976892191e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |