| { |
| "best_metric": 1.695717692375183, |
| "best_model_checkpoint": "output/the-grateful-dead/checkpoint-289", |
| "epoch": 1.0, |
| "global_step": 289, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.00013709869490949843, |
| "loss": 3.4767, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.00013679507884269807, |
| "loss": 3.3233, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00013629004853001075, |
| "loss": 3.034, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00013558509557906132, |
| "loss": 3.0326, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00013468230206922286, |
| "loss": 3.0633, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00013358433440219266, |
| "loss": 2.6577, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00013229443542677182, |
| "loss": 2.9416, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00013081641486110732, |
| "loss": 2.8888, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00012915463804068515, |
| "loss": 2.6352, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00012731401302530662, |
| "loss": 2.9574, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00012529997610312806, |
| "loss": 2.7793, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00012311847573457732, |
| "loss": 2.5208, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00012077595498356889, |
| "loss": 2.5793, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00011827933248790689, |
| "loss": 2.5326, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00011563598202508025, |
| "loss": 2.5729, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00011285371073380224, |
| "loss": 2.6515, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.000109940736055617, |
| "loss": 2.59, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00010690566146467614, |
| "loss": 2.62, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00010375745105736788, |
| "loss": 2.5348, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00010050540307684762, |
| "loss": 2.3504, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 9.715912245066583e-05, |
| "loss": 2.4245, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 9.372849242260327e-05, |
| "loss": 2.3522, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 9.022364536249872e-05, |
| "loss": 2.2091, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 8.665493284028274e-05, |
| "loss": 2.2353, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 8.303289505260362e-05, |
| "loss": 2.2043, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 7.936822969234422e-05, |
| "loss": 2.25, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 7.56717603529733e-05, |
| "loss": 2.2438, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 7.195440456104955e-05, |
| "loss": 2.2188, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 6.822714153129379e-05, |
| "loss": 2.1493, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 6.450097973946566e-05, |
| "loss": 2.3241, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 6.0786924408817136e-05, |
| "loss": 2.1267, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 5.709594500615288e-05, |
| "loss": 2.0304, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 5.343894284349703e-05, |
| "loss": 1.9702, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.982671888105512e-05, |
| "loss": 2.0854, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 4.62699418265656e-05, |
| "loss": 2.0528, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 4.277911662525875e-05, |
| "loss": 1.9738, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3.936455343348859e-05, |
| "loss": 2.1449, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.6036337167674e-05, |
| "loss": 1.9034, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 3.280429771848598e-05, |
| "loss": 1.9098, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 2.9677980918254152e-05, |
| "loss": 1.9427, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 2.6666620347339532e-05, |
| "loss": 2.243, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 2.377911006274416e-05, |
| "loss": 1.9729, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 2.1023978329503206e-05, |
| "loss": 2.0628, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 1.8409362432444018e-05, |
| "loss": 1.8724, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 1.594298464270594e-05, |
| "loss": 2.0964, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 1.3632129410003275e-05, |
| "loss": 1.9228, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.1483621847994469e-05, |
| "loss": 1.797, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 9.503807576300871e-06, |
| "loss": 2.0553, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 7.698533978711721e-06, |
| "loss": 1.8949, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 6.073132932929161e-06, |
| "loss": 1.8748, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 4.6324050628611986e-06, |
| "loss": 1.9711, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3.3806055599732885e-06, |
| "loss": 1.9954, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 2.3214316155753564e-06, |
| "loss": 1.8547, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 1.4580115011628363e-06, |
| "loss": 1.8839, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 7.928953290631928e-07, |
| "loss": 1.9188, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 3.280475206760945e-07, |
| "loss": 1.8588, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 6.484100455249007e-08, |
| "loss": 1.8212, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.695717692375183, |
| "eval_runtime": 5.4445, |
| "eval_samples_per_second": 76.959, |
| "eval_steps_per_second": 9.735, |
| "step": 289 |
| } |
| ], |
| "max_steps": 289, |
| "num_train_epochs": 1, |
| "total_flos": 302053588992000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
