| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.948453608247423, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0, | |
| "loss": 2.1604, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0003, | |
| "loss": 1.8622, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0003, | |
| "loss": 1.9463, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4473, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003, | |
| "loss": 1.668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003, | |
| "loss": 1.5916, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003, | |
| "loss": 1.5706, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003, | |
| "loss": 1.7616, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003, | |
| "loss": 1.6622, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003, | |
| "loss": 1.7693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4949, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4915, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1377, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2455, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4614, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0003, | |
| "loss": 1.3197, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1472, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4865, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0797, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1111, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0739, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0003, | |
| "loss": 1.055, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1461, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8745, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7532, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7711, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0003, | |
| "loss": 0.601, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7436, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9629, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7265, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6751, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6175, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5347, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6743, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5514, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0003, | |
| "loss": 0.451, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6012, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.309, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.391, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.0003, | |
| "loss": 0.414, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3751, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2296, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3704, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4085, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4152, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4042, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2674, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1529, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2256, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2363, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2326, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3368, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1513, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1721, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1693, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5106, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1793, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1768, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "step": 60, | |
| "total_flos": 9032879937945600.0, | |
| "train_loss": 0.8441792408625285, | |
| "train_runtime": 6463.9545, | |
| "train_samples_per_second": 0.15, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "total_flos": 9032879937945600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |