| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031095735997201383, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.47774845361709595, | |
| "learning_rate": 4.999970160815579e-05, | |
| "loss": 2.0765, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.6051416397094727, | |
| "learning_rate": 4.999880643974619e-05, | |
| "loss": 2.2297, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.6161717772483826, | |
| "learning_rate": 4.9997314516140056e-05, | |
| "loss": 2.1103, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.4686434268951416, | |
| "learning_rate": 4.999522587295162e-05, | |
| "loss": 2.0057, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8412289023399353, | |
| "learning_rate": 4.999254056003963e-05, | |
| "loss": 2.1778, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.5333625078201294, | |
| "learning_rate": 4.99892586415061e-05, | |
| "loss": 2.2399, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.821148157119751, | |
| "learning_rate": 4.9985380195694856e-05, | |
| "loss": 2.3215, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8403909206390381, | |
| "learning_rate": 4.998090531518962e-05, | |
| "loss": 1.8295, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6633398532867432, | |
| "learning_rate": 4.9975834106811834e-05, | |
| "loss": 2.0195, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6386868357658386, | |
| "learning_rate": 4.997016669161806e-05, | |
| "loss": 2.1257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7762248516082764, | |
| "learning_rate": 4.996390320489715e-05, | |
| "loss": 2.057, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.3192856311798096, | |
| "learning_rate": 4.9957043796166966e-05, | |
| "loss": 2.0753, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.9797518849372864, | |
| "learning_rate": 4.994958862917083e-05, | |
| "loss": 1.9736, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.000693440437317, | |
| "learning_rate": 4.994153788187363e-05, | |
| "loss": 2.1572, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6852813959121704, | |
| "learning_rate": 4.993289174645757e-05, | |
| "loss": 2.1491, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.0075691938400269, | |
| "learning_rate": 4.992365042931752e-05, | |
| "loss": 1.945, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.1973133087158203, | |
| "learning_rate": 4.991381415105619e-05, | |
| "loss": 2.0811, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.9927239418029785, | |
| "learning_rate": 4.990338314647881e-05, | |
| "loss": 1.961, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.9499759674072266, | |
| "learning_rate": 4.98923576645875e-05, | |
| "loss": 2.0653, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.7233040928840637, | |
| "learning_rate": 4.9880737968575365e-05, | |
| "loss": 1.9999, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3215, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1342876749004800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |