| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 1.7578125, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 2.3492, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 2.0, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.3615, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 1.7265625, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 2.3282, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.984375, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 2.3701, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 2.3456, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 1.5078125, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 2.312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 4.340277777777778e-05, | |
| "loss": 2.3212, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.3098, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 1.5, | |
| "learning_rate": 3.993055555555556e-05, | |
| "loss": 2.3412, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 1.4140625, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 2.2825, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34375, | |
| "grad_norm": 1.40625, | |
| "learning_rate": 3.6458333333333336e-05, | |
| "loss": 2.2644, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 1.40625, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 2.2336, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "grad_norm": 1.3125, | |
| "learning_rate": 3.2986111111111115e-05, | |
| "loss": 2.3171, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 1.359375, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.2456, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 1.3671875, | |
| "learning_rate": 2.951388888888889e-05, | |
| "loss": 2.2368, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.3984375, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 2.2996, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.53125, | |
| "grad_norm": 1.375, | |
| "learning_rate": 2.604166666666667e-05, | |
| "loss": 2.2731, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 1.359375, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 2.2269, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.59375, | |
| "grad_norm": 1.3046875, | |
| "learning_rate": 2.2569444444444447e-05, | |
| "loss": 2.2403, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 1.3515625, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 2.2705, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 1.265625, | |
| "learning_rate": 1.9097222222222222e-05, | |
| "loss": 2.3167, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 1.296875, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 2.2239, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71875, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 2.2531, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 2.2595, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 1.234375, | |
| "learning_rate": 1.2152777777777779e-05, | |
| "loss": 2.2648, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 2.1887, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 8.680555555555556e-06, | |
| "loss": 2.233, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 2.2527, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.90625, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 5.208333333333334e-06, | |
| "loss": 2.2889, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 1.1640625, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 2.2687, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96875, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.7361111111111112e-06, | |
| "loss": 2.2693, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.328125, | |
| "learning_rate": 0.0, | |
| "loss": 2.2365, | |
| "step": 160 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.295937563905229e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |