| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.3601, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2e-05, | |
| "loss": 1.182, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.9991677993445832e-05, | |
| "loss": 1.1059, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.9966725824941933e-05, | |
| "loss": 1.1749, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.992518502491028e-05, | |
| "loss": 1.0747, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.986712473391289e-05, | |
| "loss": 0.9747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9792641587574212e-05, | |
| "loss": 0.9993, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.9701859555740647e-05, | |
| "loss": 0.9763, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9594929736144978e-05, | |
| "loss": 0.9384, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9472030102919102e-05, | |
| "loss": 0.92, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.9333365210373668e-05, | |
| "loss": 0.8887, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9179165852537596e-05, | |
| "loss": 0.8901, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.8899, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.8825215767863215e-05, | |
| "loss": 0.8582, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8626054156009807e-05, | |
| "loss": 0.825, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.8412535328311813e-05, | |
| "loss": 0.7255, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.8185014665785936e-05, | |
| "loss": 0.657, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.7943870854121126e-05, | |
| "loss": 0.6711, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.768950525339362e-05, | |
| "loss": 0.6601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.74223412300427e-05, | |
| "loss": 0.624, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.7142823452219036e-05, | |
| "loss": 0.6565, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.6851417149678442e-05, | |
| "loss": 0.6261, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.6548607339452853e-05, | |
| "loss": 0.6236, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.6117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.5910811325286768e-05, | |
| "loss": 0.6045, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.5576886669868297e-05, | |
| "loss": 0.6028, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.5233679836966122e-05, | |
| "loss": 0.572, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.4881762060482814e-05, | |
| "loss": 0.5704, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.4521719072826858e-05, | |
| "loss": 0.5803, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.4154150130018867e-05, | |
| "loss": 0.5498, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3779667014289067e-05, | |
| "loss": 0.5326, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.3398893015826166e-05, | |
| "loss": 0.4371, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.3012461895372343e-05, | |
| "loss": 0.4313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.2621016829391022e-05, | |
| "loss": 0.4185, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.395, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.182569820839362e-05, | |
| "loss": 0.39, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1423148382732854e-05, | |
| "loss": 0.3944, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.1018229867038358e-05, | |
| "loss": 0.3712, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.0611616608218429e-05, | |
| "loss": 0.3747, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.0203985373914056e-05, | |
| "loss": 0.3914, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 9.79601462608595e-06, | |
| "loss": 0.3527, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 9.388383391781576e-06, | |
| "loss": 0.3686, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.981770132961649e-06, | |
| "loss": 0.3851, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 8.576851617267151e-06, | |
| "loss": 0.3588, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.174301791606384e-06, | |
| "loss": 0.3676, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 0.3536, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.378983170608982e-06, | |
| "loss": 0.352, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 6.9875381046276605e-06, | |
| "loss": 0.2721, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 6.601106984173835e-06, | |
| "loss": 0.2634, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 6.220332985710936e-06, | |
| "loss": 0.2643, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 5.845849869981137e-06, | |
| "loss": 0.2545, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 5.478280927173145e-06, | |
| "loss": 0.2531, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 5.11823793951719e-06, | |
| "loss": 0.2466, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 4.766320163033882e-06, | |
| "loss": 0.2431, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 4.423113330131708e-06, | |
| "loss": 0.2456, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 4.0891886747132356e-06, | |
| "loss": 0.2329, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 0.2382, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.4513926605471504e-06, | |
| "loss": 0.2501, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.1485828503215588e-06, | |
| "loss": 0.2364, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 2.8571765477809645e-06, | |
| "loss": 0.2425, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 2.5776587699573007e-06, | |
| "loss": 0.2406, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 2.3104947466063785e-06, | |
| "loss": 0.233, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.0561291458788736e-06, | |
| "loss": 0.224, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.8149853342140644e-06, | |
| "loss": 0.1944, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.587464671688187e-06, | |
| "loss": 0.2007, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.373945843990192e-06, | |
| "loss": 0.2071, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1.1747842321367886e-06, | |
| "loss": 0.1901, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 0.1873, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 8.208341474624071e-07, | |
| "loss": 0.1869, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 6.666347896263326e-07, | |
| "loss": 0.2017, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 5.279698970809011e-07, | |
| "loss": 0.1854, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.0507026385502747e-07, | |
| "loss": 0.1934, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.9814044425935605e-07, | |
| "loss": 0.1985, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.0735841242578992e-07, | |
| "loss": 0.194, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.3287526608711132e-07, | |
| "loss": 0.1906, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 7.481497508972313e-08, | |
| "loss": 0.1911, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 3.327417505806785e-08, | |
| "loss": 0.1998, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 8.322006554171147e-09, | |
| "loss": 0.1917, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1933, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 80, | |
| "total_flos": 47113191161856.0, | |
| "train_loss": 0.4929528107866645, | |
| "train_runtime": 370.5772, | |
| "train_samples_per_second": 27.444, | |
| "train_steps_per_second": 0.216 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50000, | |
| "total_flos": 47113191161856.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |