| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0, | |
| "loss": 0.4507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2e-05, | |
| "loss": 0.283, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2844, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4888, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3617, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6094, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3711, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4193, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3409, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4329, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4672, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4515, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4762, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4653, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3432, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2e-05, | |
| "loss": 0.347, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4054, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3938, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3478, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3547, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3563, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3298, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3592, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2e-05, | |
| "loss": 0.348, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3308, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2e-05, | |
| "loss": 0.337, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3458, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2e-05, | |
| "loss": 0.294, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3002, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.252, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.312, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3209, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2459, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3443, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2951, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2993, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2837, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3244, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.295, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3316, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3044, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3092, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3144, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3192, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3349, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3093, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3207, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3169, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.323, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3184, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3076, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2e-05, | |
| "loss": 0.299, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3031, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3322, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 60, | |
| "total_flos": 2862395228160.0, | |
| "train_loss": 0.3803114550809065, | |
| "train_runtime": 774.196, | |
| "train_samples_per_second": 9.817, | |
| "train_steps_per_second": 0.077 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50000, | |
| "total_flos": 2862395228160.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |