| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0, | |
| "loss": 1.8695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00012618595071429146, | |
| "loss": 1.3259, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4437, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2393, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1305, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0398, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9901, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8565, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.895, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0172802209854126, | |
| "eval_runtime": 5.2713, | |
| "eval_samples_per_second": 9.485, | |
| "eval_steps_per_second": 0.379, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6846, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5027, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4804, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5402, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4855, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4647, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2764, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2263, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.12456476688385, | |
| "eval_runtime": 5.3567, | |
| "eval_samples_per_second": 9.334, | |
| "eval_steps_per_second": 0.373, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1656, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1102, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.106, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1308, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0876, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0562, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0958, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1003, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0698, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1885429620742798, | |
| "eval_runtime": 5.3252, | |
| "eval_samples_per_second": 9.389, | |
| "eval_steps_per_second": 0.376, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0375, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0344, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0413, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0249, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0317, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0341, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0322, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0402, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0285, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.3966914415359497, | |
| "eval_runtime": 5.2806, | |
| "eval_samples_per_second": 9.469, | |
| "eval_steps_per_second": 0.379, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0119, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.014, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0164, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0101, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0086, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0234, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.009, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0085, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.4822536706924438, | |
| "eval_runtime": 5.2639, | |
| "eval_samples_per_second": 9.499, | |
| "eval_steps_per_second": 0.38, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0026, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0107, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0034, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0065, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0078, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0068, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0055, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0063, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0062, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.4699294567108154, | |
| "eval_runtime": 5.308, | |
| "eval_samples_per_second": 9.42, | |
| "eval_steps_per_second": 0.377, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0022, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0047, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0072, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0044, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0055, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0041, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0028, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0044, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0027, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.497247576713562, | |
| "eval_runtime": 5.3293, | |
| "eval_samples_per_second": 9.382, | |
| "eval_steps_per_second": 0.375, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0028, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.001, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0011, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0057, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0015, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0038, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0024, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0069, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0033, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.5496388673782349, | |
| "eval_runtime": 5.2574, | |
| "eval_samples_per_second": 9.51, | |
| "eval_steps_per_second": 0.38, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0014, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0014, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0008, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.004, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0037, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0194, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0044, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0039, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0016, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.424226999282837, | |
| "eval_runtime": 5.3446, | |
| "eval_samples_per_second": 9.355, | |
| "eval_steps_per_second": 0.374, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0038, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0016, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0058, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0028, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0035, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0044, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.002, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0079, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0037, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.421419620513916, | |
| "eval_runtime": 5.3267, | |
| "eval_samples_per_second": 9.387, | |
| "eval_steps_per_second": 0.375, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 90, | |
| "total_flos": 1.6925537836885606e+17, | |
| "train_loss": 0.18119788986643673, | |
| "train_runtime": 642.8335, | |
| "train_samples_per_second": 4.402, | |
| "train_steps_per_second": 0.14 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 50000, | |
| "total_flos": 1.6925537836885606e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |