| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.148720999405116, | |
| "eval_steps": 500, | |
| "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": 9.285714285714285e-05, | |
| "loss": 2.4427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001857142857142857, | |
| "loss": 2.3973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00027857142857142854, | |
| "loss": 2.341, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003714285714285714, | |
| "loss": 2.1281, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0004642857142857143, | |
| "loss": 1.4346, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005571428571428571, | |
| "loss": 1.1715, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00065, | |
| "loss": 1.086, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0006499851830773117, | |
| "loss": 0.9921, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00064994073366027, | |
| "loss": 0.9231, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006498666558018197, | |
| "loss": 0.9343, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006497629562564588, | |
| "loss": 0.9191, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006496296444796219, | |
| "loss": 0.8791, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006494667326268186, | |
| "loss": 0.8632, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006492742355525248, | |
| "loss": 0.9267, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006490521708088281, | |
| "loss": 0.8644, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000648800558643828, | |
| "loss": 0.8353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006485194219997891, | |
| "loss": 0.8482, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006482087865110493, | |
| "loss": 0.8587, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006478686805016826, | |
| "loss": 0.9134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006474991349829163, | |
| "loss": 0.8238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006471001836503035, | |
| "loss": 0.8329, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006466718628806508, | |
| "loss": 0.7995, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006462142117287011, | |
| "loss": 0.8363, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006457272719235728, | |
| "loss": 0.7942, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006452110878649547, | |
| "loss": 0.858, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006446657066190579, | |
| "loss": 0.8474, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000644091177914324, | |
| "loss": 0.8175, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006434875541368907, | |
| "loss": 0.7821, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006428548903258156, | |
| "loss": 0.8583, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006421932441680574, | |
| "loss": 0.8071, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006415026759932158, | |
| "loss": 0.805, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006407832487680309, | |
| "loss": 0.881, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006400350280906415, | |
| "loss": 0.8302, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006392580821846041, | |
| "loss": 0.8456, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006384524818926723, | |
| "loss": 0.8067, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006376183006703367, | |
| "loss": 0.8307, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006367556145791275, | |
| "loss": 0.8347, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006358645022796795, | |
| "loss": 0.8086, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006349450450245589, | |
| "loss": 0.8726, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006339973266508556, | |
| "loss": 0.78, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006330214335725379, | |
| "loss": 0.7902, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006320174547725736, | |
| "loss": 0.7823, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006309854817948169, | |
| "loss": 0.8211, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006299256087356603, | |
| "loss": 0.8656, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000628837932235456, | |
| "loss": 0.7767, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006277225514697028, | |
| "loss": 0.7542, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006265795681400046, | |
| "loss": 0.8254, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006254090864647957, | |
| "loss": 0.8099, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006242112131698394, | |
| "loss": 0.7786, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006229860574784954, | |
| "loss": 0.7895, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 336, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 6.338982512767795e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |