| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11622501162250116, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 2.2776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014444444444444444, | |
| "loss": 2.2089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00021666666666666666, | |
| "loss": 2.2124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002888888888888889, | |
| "loss": 2.0872, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003611111111111111, | |
| "loss": 1.9608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0004333333333333333, | |
| "loss": 1.9254, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005055555555555555, | |
| "loss": 1.8716, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005777777777777778, | |
| "loss": 1.8424, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00065, | |
| "loss": 1.8139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0006499909512851264, | |
| "loss": 1.8298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006499638056443784, | |
| "loss": 1.735, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006499185645893443, | |
| "loss": 1.707, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006498552306392452, | |
| "loss": 1.7144, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006497738073207941, | |
| "loss": 1.6774, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006496742991679994, | |
| "loss": 1.6373, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006495567117219131, | |
| "loss": 1.5874, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006494210515303213, | |
| "loss": 1.5767, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006492673261473803, | |
| "loss": 1.3921, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006490955441331957, | |
| "loss": 1.2696, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006489057150533456, | |
| "loss": 1.065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006486978494783486, | |
| "loss": 0.9967, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006484719589830741, | |
| "loss": 0.8554, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006482280561460987, | |
| "loss": 0.8944, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006479661545490054, | |
| "loss": 0.8563, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000647686268775627, | |
| "loss": 0.9036, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.782578706741333, | |
| "eval_runtime": 47.3187, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 0.528, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006473884144112352, | |
| "loss": 0.8622, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006470726080416708, | |
| "loss": 0.8543, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000646738867252422, | |
| "loss": 0.821, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006463872106276441, | |
| "loss": 0.798, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006460176577491251, | |
| "loss": 0.7795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006456302291951948, | |
| "loss": 0.845, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006452249465395796, | |
| "loss": 0.8199, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006448018323502008, | |
| "loss": 0.8371, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006443609101879176, | |
| "loss": 0.8235, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006439022046052159, | |
| "loss": 0.8063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006434257411448404, | |
| "loss": 0.8153, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006429315463383726, | |
| "loss": 0.8219, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006424196477047534, | |
| "loss": 0.8167, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006418900737487508, | |
| "loss": 0.7766, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006413428539593724, | |
| "loss": 0.8465, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006407780188082232, | |
| "loss": 0.7966, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006401955997478094, | |
| "loss": 0.8225, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006395956292097865, | |
| "loss": 0.7915, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006389781406031534, | |
| "loss": 0.7923, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006383431683123921, | |
| "loss": 0.8051, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006376907476955534, | |
| "loss": 0.8127, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000637020915082287, | |
| "loss": 0.7747, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00063633370777182, | |
| "loss": 0.797, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006356291640308783, | |
| "loss": 0.743, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000634907323091557, | |
| "loss": 0.8201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.7397407293319702, | |
| "eval_runtime": 47.3134, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 0.528, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 430, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 1.2212033932689408e+17, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |