| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.536, | |
| "eval_steps": 500, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.047607421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3836, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.04541015625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2449, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.056396484375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1513, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.03857421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0705, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.0286865234375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0488, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.03173828125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0391, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.054931640625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0278, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1414, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.015625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0371, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.0257568359375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.02197265625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0101, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.020751953125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0098, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.0164794921875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0088, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.0120849609375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0086, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.05078125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0572, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.031982421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0092, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.0196533203125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0077, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.0238037109375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0054, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.0108642578125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.0091552734375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.01336669921875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.033203125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0122, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.0169677734375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0173, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.00909423828125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0031, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.01171875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.00946044921875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.014892578125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.01239013671875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.006, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.00982666015625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 0.01031494140625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.024, | |
| "grad_norm": 0.006927490234375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 0.0084228515625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.088, | |
| "grad_norm": 0.005584716796875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.006683349609375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 0.004486083984375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.184, | |
| "grad_norm": 0.0087890625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.216, | |
| "grad_norm": 0.0062255859375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 0.0128173828125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.006683349609375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.312, | |
| "grad_norm": 0.00787353515625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 0.0096435546875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.376, | |
| "grad_norm": 0.0096435546875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.408, | |
| "grad_norm": 0.005859375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.00848388671875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.472, | |
| "grad_norm": 0.015625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.504, | |
| "grad_norm": 0.03857421875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0067, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 0.00811767578125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0062, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "step": 240, | |
| "total_flos": 9.355246833433805e+17, | |
| "train_loss": 0.029236048091358196, | |
| "train_runtime": 30800.5629, | |
| "train_samples_per_second": 0.499, | |
| "train_steps_per_second": 0.008 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 90, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.355246833433805e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |