| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 79, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.563, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.3043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2638, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.999145758387301e-05, | |
| "loss": 1.3178, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.99658449300667e-05, | |
| "loss": 0.9881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.992320579737045e-05, | |
| "loss": 0.9734, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9863613034027224e-05, | |
| "loss": 1.0088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9787168453273546e-05, | |
| "loss": 0.996, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9694002659393306e-05, | |
| "loss": 0.8973, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.958427482458253e-05, | |
| "loss": 0.9568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9458172417006347e-05, | |
| "loss": 0.9458, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9315910880512792e-05, | |
| "loss": 0.9379, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9157733266550577e-05, | |
| "loss": 0.9296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.898390981891979e-05, | |
| "loss": 0.8659, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.879473751206489e-05, | |
| "loss": 0.876, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8590539543698852e-05, | |
| "loss": 0.8748, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.8371664782625287e-05, | |
| "loss": 0.9528, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.813848717270195e-05, | |
| "loss": 0.9572, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.789140509396394e-05, | |
| "loss": 0.903, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.7630840681998068e-05, | |
| "loss": 0.8989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.735723910673132e-05, | |
| "loss": 0.8918, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.8911, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.6772815716257414e-05, | |
| "loss": 0.9015, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.646299237860941e-05, | |
| "loss": 0.8788, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.6142127126896682e-05, | |
| "loss": 0.8929, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.5810768154019386e-05, | |
| "loss": 0.9049, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.5469481581224274e-05, | |
| "loss": 0.8985, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.5118850490896012e-05, | |
| "loss": 0.9353, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.4759473930370738e-05, | |
| "loss": 0.8249, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.4391965888473705e-05, | |
| "loss": 0.8426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.4016954246529697e-05, | |
| "loss": 0.8492, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.3635079705638298e-05, | |
| "loss": 0.8952, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.3246994692046837e-05, | |
| "loss": 0.8821, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.2853362242491054e-05, | |
| "loss": 0.8758, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.2454854871407993e-05, | |
| "loss": 0.8224, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.2052153421956343e-05, | |
| "loss": 0.8758, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.164594590280734e-05, | |
| "loss": 0.8689, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.123692631269348e-05, | |
| "loss": 0.7884, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0825793454723325e-05, | |
| "loss": 0.8356, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0413249742488132e-05, | |
| "loss": 0.8492, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9018, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.586750257511868e-06, | |
| "loss": 0.8776, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.174206545276678e-06, | |
| "loss": 0.8249, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.763073687306523e-06, | |
| "loss": 0.9175, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.35405409719266e-06, | |
| "loss": 0.8375, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.947846578043658e-06, | |
| "loss": 0.9021, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.545145128592009e-06, | |
| "loss": 0.8291, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.14663775750895e-06, | |
| "loss": 0.8727, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.7530053079531664e-06, | |
| "loss": 0.8673, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.364920294361701e-06, | |
| "loss": 0.8716, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.983045753470308e-06, | |
| "loss": 0.8658, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.608034111526298e-06, | |
| "loss": 0.8199, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.240526069629265e-06, | |
| "loss": 0.9193, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.881149509103993e-06, | |
| "loss": 0.7906, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.530518418775734e-06, | |
| "loss": 0.8785, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.189231845980618e-06, | |
| "loss": 0.8281, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.857872873103322e-06, | |
| "loss": 0.8772, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.5370076213905904e-06, | |
| "loss": 0.8723, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.2271842837425917e-06, | |
| "loss": 0.8242, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 0.8723, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.642760893268684e-06, | |
| "loss": 0.8294, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.369159318001937e-06, | |
| "loss": 0.8132, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.1085949060360654e-06, | |
| "loss": 0.9158, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.861512827298051e-06, | |
| "loss": 0.8152, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.6283352173747148e-06, | |
| "loss": 0.8172, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.409460456301147e-06, | |
| "loss": 0.8718, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.2052624879351105e-06, | |
| "loss": 0.8251, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.0160901810802114e-06, | |
| "loss": 0.8401, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.42266733449425e-07, | |
| "loss": 0.8318, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.840891194872112e-07, | |
| "loss": 0.8563, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.418275829936537e-07, | |
| "loss": 0.87, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.1572517541747294e-07, | |
| "loss": 0.8736, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.059973406066963e-07, | |
| "loss": 0.837, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.1283154672645522e-07, | |
| "loss": 0.8477, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3638696597277678e-07, | |
| "loss": 0.8302, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.679420262954984e-08, | |
| "loss": 0.8606, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.4155069933301535e-08, | |
| "loss": 0.904, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 8.542416126989805e-09, | |
| "loss": 0.8027, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.8881, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 79, | |
| "total_flos": 2.0832241753627034e+17, | |
| "train_loss": 0.9012186353719687, | |
| "train_runtime": 1256.0083, | |
| "train_samples_per_second": 3.981, | |
| "train_steps_per_second": 0.063 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 79, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 2.0832241753627034e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |