| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 1100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.090909090909091e-08, | |
| "loss": 2.3833, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.6363636363636366e-07, | |
| "loss": 2.4789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.272727272727273e-07, | |
| "loss": 2.3195, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.090909090909091e-06, | |
| "loss": 2.3366, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4545454545454546e-06, | |
| "loss": 2.3221, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 2.4036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.181818181818182e-06, | |
| "loss": 2.4224, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.5454545454545456e-06, | |
| "loss": 2.6085, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.9090909090909093e-06, | |
| "loss": 2.5477, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.272727272727273e-06, | |
| "loss": 2.4446, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 2.3109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.4149, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.363636363636364e-06, | |
| "loss": 2.5514, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.727272727272728e-06, | |
| "loss": 2.3816, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.090909090909091e-06, | |
| "loss": 2.6293, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 2.2422, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 5.8181818181818185e-06, | |
| "loss": 2.4031, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.181818181818182e-06, | |
| "loss": 2.2303, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.545454545454546e-06, | |
| "loss": 2.2847, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 6.90909090909091e-06, | |
| "loss": 2.1578, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 2.1774, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.636363636363638e-06, | |
| "loss": 2.197, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.2093, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.363636363636365e-06, | |
| "loss": 2.1004, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.727272727272728e-06, | |
| "loss": 2.0526, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 2.0771, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 2.0219, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.81818181818182e-06, | |
| "loss": 1.9439, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.999899300364534e-06, | |
| "loss": 1.9175, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.99909372761763e-06, | |
| "loss": 1.8281, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.997482711915926e-06, | |
| "loss": 1.9423, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 9.99506651282272e-06, | |
| "loss": 1.9385, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.991845519630679e-06, | |
| "loss": 2.0381, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 2.0296, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.982991356370404e-06, | |
| "loss": 1.9167, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 9.977359612865424e-06, | |
| "loss": 1.9132, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 9.970925928158275e-06, | |
| "loss": 1.8455, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 9.963691338830045e-06, | |
| "loss": 1.8692, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 9.955657010501807e-06, | |
| "loss": 1.8812, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 9.946824237646823e-06, | |
| "loss": 1.9785, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.937194443381972e-06, | |
| "loss": 1.9511, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 9.926769179238467e-06, | |
| "loss": 1.8505, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.915550124911866e-06, | |
| "loss": 1.9195, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.903539087991462e-06, | |
| "loss": 1.8527, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 1.7579, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 9.877148934427037e-06, | |
| "loss": 1.9244, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 9.862774069706346e-06, | |
| "loss": 1.8144, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 9.847615725553457e-06, | |
| "loss": 1.8462, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 9.831676344247343e-06, | |
| "loss": 1.7888, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 9.814958493905962e-06, | |
| "loss": 1.9216, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 9.797464868072489e-06, | |
| "loss": 1.7411, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 9.779198285281326e-06, | |
| "loss": 1.7989, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 9.760161688604008e-06, | |
| "loss": 1.8476, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 9.740358145174999e-06, | |
| "loss": 1.7767, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 9.719790845697534e-06, | |
| "loss": 1.7036, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 1.8114, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "gpt4_scores": 0.65, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "std": 0.11335784048754634, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.8505451679229736, | |
| "eval_runtime": 4.9659, | |
| "eval_samples_per_second": 4.632, | |
| "eval_steps_per_second": 1.208, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 9.676378356149733e-06, | |
| "loss": 1.7635, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.653540160603956e-06, | |
| "loss": 1.5819, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 9.629952196931902e-06, | |
| "loss": 1.8023, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 9.60561826557425e-06, | |
| "loss": 1.7447, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 9.580542287160348e-06, | |
| "loss": 1.7547, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 9.554728301876525e-06, | |
| "loss": 1.8657, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 9.528180468815155e-06, | |
| "loss": 1.7641, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 9.50090306530454e-06, | |
| "loss": 1.7088, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 9.47290048621977e-06, | |
| "loss": 1.8404, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 9.444177243274619e-06, | |
| "loss": 1.7781, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 1.804, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 9.384587392471516e-06, | |
| "loss": 1.8061, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 9.353730385598887e-06, | |
| "loss": 1.6723, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "gpt4_scores": 0.73, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "std": 0.10959014554237986, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.8371697664260864, | |
| "eval_runtime": 4.9576, | |
| "eval_samples_per_second": 4.639, | |
| "eval_steps_per_second": 1.21, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.322171915289635e-06, | |
| "loss": 1.7486, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 9.289917066174887e-06, | |
| "loss": 1.7675, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 9.256971035084786e-06, | |
| "loss": 1.7188, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 9.223339130211194e-06, | |
| "loss": 1.7628, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 9.189026770252437e-06, | |
| "loss": 1.6931, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 9.154039483540273e-06, | |
| "loss": 1.5731, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 9.118382907149164e-06, | |
| "loss": 1.7763, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 9.08206278598805e-06, | |
| "loss": 1.7601, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 1.6893, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 9.007455422593077e-06, | |
| "loss": 1.7848, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 8.969180200933048e-06, | |
| "loss": 1.7517, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 8.930265473713939e-06, | |
| "loss": 1.6602, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 8.890717510790763e-06, | |
| "loss": 1.6003, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 8.850542684044078e-06, | |
| "loss": 1.6532, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "gpt4_scores": 0.65, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "std": 0.1298075498574717, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.8295962810516357, | |
| "eval_runtime": 4.9535, | |
| "eval_samples_per_second": 4.643, | |
| "eval_steps_per_second": 1.211, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 8.809747466353356e-06, | |
| "loss": 1.597, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 8.768338430554083e-06, | |
| "loss": 1.7247, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 8.726322248378775e-06, | |
| "loss": 1.7433, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 8.683705689382025e-06, | |
| "loss": 1.6082, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 8.640495619849821e-06, | |
| "loss": 1.6855, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.596699001693257e-06, | |
| "loss": 1.5826, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 8.552322891326846e-06, | |
| "loss": 1.6749, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 8.507374438531606e-06, | |
| "loss": 1.649, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 8.461860885303116e-06, | |
| "loss": 1.6959, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 8.415789564684673e-06, | |
| "loss": 1.6805, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 8.36916789958584e-06, | |
| "loss": 1.67, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 8.322003401586463e-06, | |
| "loss": 1.6226, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 8.274303669726427e-06, | |
| "loss": 1.6525, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 8.226076389281316e-06, | |
| "loss": 1.7187, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "gpt4_scores": 0.74, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "std": 0.11153474794878948, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.8273346424102783, | |
| "eval_runtime": 4.923, | |
| "eval_samples_per_second": 4.672, | |
| "eval_steps_per_second": 1.219, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 8.177329330524182e-06, | |
| "loss": 1.6103, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 8.128070347473609e-06, | |
| "loss": 1.546, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 8.078307376628292e-06, | |
| "loss": 1.551, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 8.028048435688333e-06, | |
| "loss": 1.6379, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 7.97730162226344e-06, | |
| "loss": 1.61, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 7.92607511256826e-06, | |
| "loss": 1.6151, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 7.874377160105037e-06, | |
| "loss": 1.6989, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 7.822216094333847e-06, | |
| "loss": 1.6711, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 7.769600319330553e-06, | |
| "loss": 1.6344, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 7.716538312432767e-06, | |
| "loss": 1.6, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 7.663038622873999e-06, | |
| "loss": 1.6563, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 7.60910987040623e-06, | |
| "loss": 1.5933, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 7.554760743911104e-06, | |
| "loss": 1.6445, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.6945, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "gpt4_scores": 0.71, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "std": 0.10904127658827183, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.8345035314559937, | |
| "eval_runtime": 4.9576, | |
| "eval_samples_per_second": 4.639, | |
| "eval_steps_per_second": 1.21, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 7.444836461603195e-06, | |
| "loss": 1.6089, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 7.3892790165483164e-06, | |
| "loss": 1.6294, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 7.333336616128369e-06, | |
| "loss": 1.6516, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 7.2770182736595164e-06, | |
| "loss": 1.4944, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 7.2203330630288714e-06, | |
| "loss": 1.5007, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 7.163290117232542e-06, | |
| "loss": 1.5207, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 7.105898626904134e-06, | |
| "loss": 1.6485, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.048167838833977e-06, | |
| "loss": 1.554, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 6.990107054479313e-06, | |
| "loss": 1.5661, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 6.931725628465643e-06, | |
| "loss": 1.496, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.873032967079562e-06, | |
| "loss": 1.554, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 6.814038526753205e-06, | |
| "loss": 1.574, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 6.75475181254068e-06, | |
| "loss": 1.5494, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "gpt4_scores": 0.5700000000000001, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "std": 0.13787675656179324, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.8451542854309082, | |
| "eval_runtime": 4.9243, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 1.218, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 6.695182376586603e-06, | |
| "loss": 1.6572, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 6.635339816587109e-06, | |
| "loss": 1.5122, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 6.5752337742434644e-06, | |
| "loss": 1.4632, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 6.514873933708637e-06, | |
| "loss": 1.4757, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 6.454270020026996e-06, | |
| "loss": 1.5465, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 6.39343179756744e-06, | |
| "loss": 1.5713, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 6.332369068450175e-06, | |
| "loss": 1.5246, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 6.271091670967437e-06, | |
| "loss": 1.478, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 6.209609477998339e-06, | |
| "loss": 1.5593, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 6.1479323954182055e-06, | |
| "loss": 1.5553, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 6.08607036050254e-06, | |
| "loss": 1.5434, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 6.024033340325954e-06, | |
| "loss": 1.4686, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 5.961831330156306e-06, | |
| "loss": 1.4344, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 5.89947435184427e-06, | |
| "loss": 1.5329, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "gpt4_scores": 0.6, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "std": 0.14352700094407322, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.8664953708648682, | |
| "eval_runtime": 4.9654, | |
| "eval_samples_per_second": 4.632, | |
| "eval_steps_per_second": 1.208, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 5.8369724522086545e-06, | |
| "loss": 1.5753, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 5.774335701417662e-06, | |
| "loss": 1.4623, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 5.711574191366427e-06, | |
| "loss": 1.4908, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 5.648698034051009e-06, | |
| "loss": 1.4846, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 5.585717359939192e-06, | |
| "loss": 1.4591, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 1.4508, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 5.459483065760138e-06, | |
| "loss": 1.4282, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 5.396249784283943e-06, | |
| "loss": 1.4565, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 5.33295265991652e-06, | |
| "loss": 1.5174, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 5.26960189095093e-06, | |
| "loss": 1.4063, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 5.206207684323337e-06, | |
| "loss": 1.4412, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 5.142780253968481e-06, | |
| "loss": 1.5706, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 5.07932981917404e-06, | |
| "loss": 1.4704, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 5.015866602934112e-06, | |
| "loss": 1.4105, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "gpt4_scores": 0.5700000000000001, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "std": 0.12653062870309306, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.8876867294311523, | |
| "eval_runtime": 4.9571, | |
| "eval_samples_per_second": 4.64, | |
| "eval_steps_per_second": 1.21, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 4.952400830302117e-06, | |
| "loss": 1.3259, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 4.888942726743353e-06, | |
| "loss": 1.371, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.825502516487497e-06, | |
| "loss": 1.4825, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 4.762090420881289e-06, | |
| "loss": 1.3511, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 4.6987166567417085e-06, | |
| "loss": 1.4314, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 4.635391434709847e-06, | |
| "loss": 1.4736, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 4.572124957605803e-06, | |
| "loss": 1.4653, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 4.5089274187848144e-06, | |
| "loss": 1.4053, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 4.445809000494945e-06, | |
| "loss": 1.4959, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 4.382779872236527e-06, | |
| "loss": 1.4142, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 4.319850189123681e-06, | |
| "loss": 1.3764, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 4.257030090248142e-06, | |
| "loss": 1.5262, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 4.194329697045681e-06, | |
| "loss": 1.4114, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 1.3862, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "gpt4_scores": 0.64, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "std": 0.13505554412907303, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.9065581560134888, | |
| "eval_runtime": 4.9613, | |
| "eval_samples_per_second": 4.636, | |
| "eval_steps_per_second": 1.209, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 4.06932841534185e-06, | |
| "loss": 1.4282, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 4.007047666771274e-06, | |
| "loss": 1.3369, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 3.944926900490452e-06, | |
| "loss": 1.4198, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 3.882976125260229e-06, | |
| "loss": 1.3799, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 3.821205322452863e-06, | |
| "loss": 1.4461, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 3.7596244444438577e-06, | |
| "loss": 1.4154, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 3.69824341300844e-06, | |
| "loss": 1.3719, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 3.637072117723012e-06, | |
| "loss": 1.3079, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 3.5761204143717387e-06, | |
| "loss": 1.3786, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 3.5153981233586277e-06, | |
| "loss": 1.3406, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 1.3967, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 3.394680873574546e-06, | |
| "loss": 1.4914, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 3.3347053645005965e-06, | |
| "loss": 1.4126, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "gpt4_scores": 0.53, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "std": 0.14356183336806477, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.9303113222122192, | |
| "eval_runtime": 4.9701, | |
| "eval_samples_per_second": 4.628, | |
| "eval_steps_per_second": 1.207, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.274998164025148e-06, | |
| "loss": 1.4012, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 3.2155688920406415e-06, | |
| "loss": 1.4258, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 3.156427123660297e-06, | |
| "loss": 1.3023, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 3.097582387675385e-06, | |
| "loss": 1.3797, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 3.0390441650199727e-06, | |
| "loss": 1.335, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 2.980821887243377e-06, | |
| "loss": 1.388, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 2.9229249349905686e-06, | |
| "loss": 1.2886, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 2.8653626364907918e-06, | |
| "loss": 1.3144, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 2.8081442660546126e-06, | |
| "loss": 1.3285, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 2.751279042579672e-06, | |
| "loss": 1.4061, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 2.694776128065345e-06, | |
| "loss": 1.3877, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 2.6386446261365874e-06, | |
| "loss": 1.2318, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 2.5828935805771804e-06, | |
| "loss": 1.3826, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 2.527531973872617e-06, | |
| "loss": 1.388, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "gpt4_scores": 0.62, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "std": 0.1362350909274112, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.9448539018630981, | |
| "eval_runtime": 4.9425, | |
| "eval_samples_per_second": 4.654, | |
| "eval_steps_per_second": 1.214, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 2.4725687257628533e-06, | |
| "loss": 1.524, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 2.418012691805191e-06, | |
| "loss": 1.3961, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 2.363872661947488e-06, | |
| "loss": 1.3303, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 2.310157359111938e-06, | |
| "loss": 1.3642, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 2.2568754377896516e-06, | |
| "loss": 1.3532, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.204035482646267e-06, | |
| "loss": 1.2528, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 2.1516460071388062e-06, | |
| "loss": 1.3888, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 2.09971545214401e-06, | |
| "loss": 1.269, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 2.0482521845983522e-06, | |
| "loss": 1.3103, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 1.9972644961499853e-06, | |
| "loss": 1.3151, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 1.946760601822809e-06, | |
| "loss": 1.3055, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 1.8967486386928819e-06, | |
| "loss": 1.3414, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 1.8472366645773892e-06, | |
| "loss": 1.3481, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 1.798232656736389e-06, | |
| "loss": 1.3653, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "gpt4_scores": 0.605, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "std": 0.13312588027877975, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.9636751413345337, | |
| "eval_runtime": 4.9484, | |
| "eval_samples_per_second": 4.648, | |
| "eval_steps_per_second": 1.213, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 1.7497445105875377e-06, | |
| "loss": 1.4389, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 1.7017800384339928e-06, | |
| "loss": 1.3568, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 1.3535, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 1.6074529422143398e-06, | |
| "loss": 1.2696, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 1.561105515921915e-06, | |
| "loss": 1.2854, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 1.5153121567235334e-06, | |
| "loss": 1.2779, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 1.470080242744218e-06, | |
| "loss": 1.3024, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 1.4254170616501828e-06, | |
| "loss": 1.3081, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 1.3813298094746491e-06, | |
| "loss": 1.2898, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 1.3378255894584463e-06, | |
| "loss": 1.2944, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 15.78, | |
| "learning_rate": 1.2949114109055417e-06, | |
| "loss": 1.3638, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 1.2525941880537307e-06, | |
| "loss": 1.3272, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 1.210880738960616e-06, | |
| "loss": 1.2646, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 1.361, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "gpt4_scores": 0.5999999999999999, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "std": 0.1319090595827292, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.9738112688064575, | |
| "eval_runtime": 4.9552, | |
| "eval_samples_per_second": 4.642, | |
| "eval_steps_per_second": 1.211, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 1.1292919468045876e-06, | |
| "loss": 1.2656, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 16.15, | |
| "learning_rate": 1.0894297491479044e-06, | |
| "loss": 1.376, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 16.22, | |
| "learning_rate": 1.0501976139444191e-06, | |
| "loss": 1.2771, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 1.0116018621892237e-06, | |
| "loss": 1.2919, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 9.73648712344707e-07, | |
| "loss": 1.3542, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 9.363442793386606e-07, | |
| "loss": 1.275, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 8.996945735790447e-07, | |
| "loss": 1.3197, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 8.637054999856148e-07, | |
| "loss": 1.3272, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 16.65, | |
| "learning_rate": 8.283828570385239e-07, | |
| "loss": 1.2585, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 7.937323358440935e-07, | |
| "loss": 1.2851, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 7.597595192178702e-07, | |
| "loss": 1.2787, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 7.264698807851328e-07, | |
| "loss": 1.3594, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 6.938687840989972e-07, | |
| "loss": 1.2944, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "gpt4_scores": 0.6100000000000001, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "std": 0.1352405264704334, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.9819345474243164, | |
| "eval_runtime": 4.9634, | |
| "eval_samples_per_second": 4.634, | |
| "eval_steps_per_second": 1.209, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 6.619614817762537e-07, | |
| "loss": 1.3019, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 6.307531146510754e-07, | |
| "loss": 1.2263, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 6.002487109467347e-07, | |
| "loss": 1.2774, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 5.704531854654721e-07, | |
| "loss": 1.3117, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 5.413713387966329e-07, | |
| "loss": 1.3669, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 5.130078565432089e-07, | |
| "loss": 1.3741, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 4.853673085668947e-07, | |
| "loss": 1.259, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 4.58454148251814e-07, | |
| "loss": 1.2952, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 1.2957, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 17.67, | |
| "learning_rate": 4.0682721746773346e-07, | |
| "loss": 1.2796, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 3.821217650159453e-07, | |
| "loss": 1.3251, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 3.581603349196372e-07, | |
| "loss": 1.2795, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "learning_rate": 3.3494678779157464e-07, | |
| "loss": 1.2337, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 3.1248486374726884e-07, | |
| "loss": 1.3433, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "gpt4_scores": 0.5599999999999999, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "std": 0.14573949361789343, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.9856066703796387, | |
| "eval_runtime": 4.9567, | |
| "eval_samples_per_second": 4.64, | |
| "eval_steps_per_second": 1.21, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 2.9077818180237693e-07, | |
| "loss": 1.2889, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 2.6983023928961406e-07, | |
| "loss": 1.3571, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 2.4964441129527337e-07, | |
| "loss": 1.2855, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 2.3022395011543687e-07, | |
| "loss": 1.2844, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 2.1157198473197417e-07, | |
| "loss": 1.3131, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 1.9369152030840553e-07, | |
| "loss": 1.2825, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 1.765854377057219e-07, | |
| "loss": 1.2378, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 1.6025649301821877e-07, | |
| "loss": 1.3067, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 1.4470731712944885e-07, | |
| "loss": 1.367, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 1.2994041528833267e-07, | |
| "loss": 1.2553, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 1.1595816670552429e-07, | |
| "loss": 1.392, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 1.0276282417007399e-07, | |
| "loss": 1.2524, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 9.035651368646647e-08, | |
| "loss": 1.2067, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 7.874123413208145e-08, | |
| "loss": 1.2058, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "gpt4_scores": 0.5399999999999999, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "std": 0.1422673539502299, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.9871299266815186, | |
| "eval_runtime": 4.9631, | |
| "eval_samples_per_second": 4.634, | |
| "eval_steps_per_second": 1.209, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 6.791885693514134e-08, | |
| "loss": 1.2248, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 5.7891125773187896e-08, | |
| "loss": 1.3235, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.865965629214819e-08, | |
| "loss": 1.337, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 4.02259358460233e-08, | |
| "loss": 1.2373, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 3.25913232572489e-08, | |
| "loss": 1.2713, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 2.57570485977654e-08, | |
| "loss": 1.2856, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 1.9724212990830938e-08, | |
| "loss": 1.3416, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 1.449378843361271e-08, | |
| "loss": 1.2418, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 1.006661764057837e-08, | |
| "loss": 1.2665, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 6.4434139077201865e-09, | |
| "loss": 1.2837, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 3.6247609976319818e-09, | |
| "loss": 1.2405, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 1.61111304545436e-09, | |
| "loss": 1.3201, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 4.027944857032395e-10, | |
| "loss": 1.37, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2904, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "gpt4_scores": 0.59, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "std": 0.130728726758888, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.987522840499878, | |
| "eval_runtime": 4.9557, | |
| "eval_samples_per_second": 4.641, | |
| "eval_steps_per_second": 1.211, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 1100, | |
| "total_flos": 3.792475205866291e+16, | |
| "train_loss": 1.2573659207604149, | |
| "train_runtime": 10567.2291, | |
| "train_samples_per_second": 0.411, | |
| "train_steps_per_second": 0.104 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 1100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 55, | |
| "total_flos": 3.792475205866291e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |