| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "global_step": 39800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.0907, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9955226182937622, | |
| "eval_runtime": 38.0064, | |
| "eval_samples_per_second": 20.891, | |
| "eval_steps_per_second": 1.316, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.937185929648241e-05, | |
| "loss": 1.4196, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.5548, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8669910430908203, | |
| "eval_runtime": 36.5925, | |
| "eval_samples_per_second": 21.698, | |
| "eval_steps_per_second": 1.366, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.874371859296483e-05, | |
| "loss": 0.9762, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.2508, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8083329796791077, | |
| "eval_runtime": 36.4935, | |
| "eval_samples_per_second": 21.757, | |
| "eval_steps_per_second": 1.37, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 4.8115577889447235e-05, | |
| "loss": 0.8703, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.5692, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7637783288955688, | |
| "eval_runtime": 36.123, | |
| "eval_samples_per_second": 21.98, | |
| "eval_steps_per_second": 1.384, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.3461, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7334607243537903, | |
| "eval_runtime": 36.0793, | |
| "eval_samples_per_second": 22.007, | |
| "eval_steps_per_second": 1.386, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 4.748743718592965e-05, | |
| "loss": 0.8098, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.399, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7078682780265808, | |
| "eval_runtime": 36.1012, | |
| "eval_samples_per_second": 21.994, | |
| "eval_steps_per_second": 1.385, | |
| "step": 2388 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 4.685929648241206e-05, | |
| "loss": 0.7592, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.3376, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6845763325691223, | |
| "eval_runtime": 35.9042, | |
| "eval_samples_per_second": 22.114, | |
| "eval_steps_per_second": 1.393, | |
| "step": 2786 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 4.6231155778894475e-05, | |
| "loss": 0.7167, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.4617, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6675065755844116, | |
| "eval_runtime": 35.9616, | |
| "eval_samples_per_second": 22.079, | |
| "eval_steps_per_second": 1.39, | |
| "step": 3184 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 4.5603015075376884e-05, | |
| "loss": 0.6881, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.438, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6496185660362244, | |
| "eval_runtime": 36.0502, | |
| "eval_samples_per_second": 22.025, | |
| "eval_steps_per_second": 1.387, | |
| "step": 3582 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 0.4397, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6296620965003967, | |
| "eval_runtime": 36.04, | |
| "eval_samples_per_second": 22.031, | |
| "eval_steps_per_second": 1.387, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 4.49748743718593e-05, | |
| "loss": 0.6543, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 0.4078, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6143925189971924, | |
| "eval_runtime": 36.2369, | |
| "eval_samples_per_second": 21.911, | |
| "eval_steps_per_second": 1.38, | |
| "step": 4378 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 4.434673366834171e-05, | |
| "loss": 0.6245, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 0.3468, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6090631484985352, | |
| "eval_runtime": 36.2496, | |
| "eval_samples_per_second": 21.904, | |
| "eval_steps_per_second": 1.379, | |
| "step": 4776 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 4.3718592964824124e-05, | |
| "loss": 0.5959, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 0.433, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.603904664516449, | |
| "eval_runtime": 36.0829, | |
| "eval_samples_per_second": 22.005, | |
| "eval_steps_per_second": 1.386, | |
| "step": 5174 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 4.309045226130653e-05, | |
| "loss": 0.5766, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 0.4332, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5970507264137268, | |
| "eval_runtime": 36.1622, | |
| "eval_samples_per_second": 21.957, | |
| "eval_steps_per_second": 1.383, | |
| "step": 5572 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 0.4291, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5931375622749329, | |
| "eval_runtime": 36.0907, | |
| "eval_samples_per_second": 22.0, | |
| "eval_steps_per_second": 1.385, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 4.246231155778895e-05, | |
| "loss": 0.5541, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 0.4504, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5876542329788208, | |
| "eval_runtime": 36.3841, | |
| "eval_samples_per_second": 21.823, | |
| "eval_steps_per_second": 1.374, | |
| "step": 6368 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 4.183417085427136e-05, | |
| "loss": 0.5331, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 0.4359, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5872967839241028, | |
| "eval_runtime": 36.0616, | |
| "eval_samples_per_second": 22.018, | |
| "eval_steps_per_second": 1.387, | |
| "step": 6766 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 4.120603015075377e-05, | |
| "loss": 0.5169, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 0.419, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5864170789718628, | |
| "eval_runtime": 36.0624, | |
| "eval_samples_per_second": 22.017, | |
| "eval_steps_per_second": 1.386, | |
| "step": 7164 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 4.057788944723618e-05, | |
| "loss": 0.4991, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 0.4191, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5880436897277832, | |
| "eval_runtime": 36.0649, | |
| "eval_samples_per_second": 22.016, | |
| "eval_steps_per_second": 1.386, | |
| "step": 7562 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 0.4535, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5844656825065613, | |
| "eval_runtime": 36.1564, | |
| "eval_samples_per_second": 21.96, | |
| "eval_steps_per_second": 1.383, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 20.1, | |
| "learning_rate": 3.9949748743718597e-05, | |
| "loss": 0.4827, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_bleu": 0.4614, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.588854968547821, | |
| "eval_runtime": 36.034, | |
| "eval_samples_per_second": 22.035, | |
| "eval_steps_per_second": 1.388, | |
| "step": 8358 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "learning_rate": 3.9321608040201005e-05, | |
| "loss": 0.4646, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_bleu": 0.4075, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5893688201904297, | |
| "eval_runtime": 36.2919, | |
| "eval_samples_per_second": 21.878, | |
| "eval_steps_per_second": 1.378, | |
| "step": 8756 | |
| }, | |
| { | |
| "epoch": 22.61, | |
| "learning_rate": 3.869346733668342e-05, | |
| "loss": 0.4523, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_bleu": 0.4399, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5904817581176758, | |
| "eval_runtime": 36.1578, | |
| "eval_samples_per_second": 21.959, | |
| "eval_steps_per_second": 1.383, | |
| "step": 9154 | |
| }, | |
| { | |
| "epoch": 23.87, | |
| "learning_rate": 3.806532663316583e-05, | |
| "loss": 0.437, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_bleu": 0.4369, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5984958410263062, | |
| "eval_runtime": 36.0725, | |
| "eval_samples_per_second": 22.011, | |
| "eval_steps_per_second": 1.386, | |
| "step": 9552 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_bleu": 0.4056, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5959633588790894, | |
| "eval_runtime": 35.9929, | |
| "eval_samples_per_second": 22.06, | |
| "eval_steps_per_second": 1.389, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 25.13, | |
| "learning_rate": 3.7437185929648245e-05, | |
| "loss": 0.4229, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_bleu": 0.4252, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.5961562395095825, | |
| "eval_runtime": 36.1884, | |
| "eval_samples_per_second": 21.941, | |
| "eval_steps_per_second": 1.382, | |
| "step": 10348 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 3.6809045226130654e-05, | |
| "loss": 0.4091, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_bleu": 0.4713, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6049270629882812, | |
| "eval_runtime": 36.1335, | |
| "eval_samples_per_second": 21.974, | |
| "eval_steps_per_second": 1.384, | |
| "step": 10746 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 3.618090452261307e-05, | |
| "loss": 0.3965, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_bleu": 0.4242, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6118378639221191, | |
| "eval_runtime": 36.0809, | |
| "eval_samples_per_second": 22.006, | |
| "eval_steps_per_second": 1.386, | |
| "step": 11144 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 3.555276381909548e-05, | |
| "loss": 0.3842, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_bleu": 0.3924, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6169702410697937, | |
| "eval_runtime": 35.9704, | |
| "eval_samples_per_second": 22.074, | |
| "eval_steps_per_second": 1.39, | |
| "step": 11542 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_bleu": 0.3984, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6114440560340881, | |
| "eval_runtime": 35.9519, | |
| "eval_samples_per_second": 22.085, | |
| "eval_steps_per_second": 1.391, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 30.15, | |
| "learning_rate": 3.4924623115577894e-05, | |
| "loss": 0.3718, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_bleu": 0.4186, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6303505301475525, | |
| "eval_runtime": 36.0633, | |
| "eval_samples_per_second": 22.017, | |
| "eval_steps_per_second": 1.386, | |
| "step": 12338 | |
| }, | |
| { | |
| "epoch": 31.41, | |
| "learning_rate": 3.42964824120603e-05, | |
| "loss": 0.3585, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_bleu": 0.3846, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6364237070083618, | |
| "eval_runtime": 36.1959, | |
| "eval_samples_per_second": 21.936, | |
| "eval_steps_per_second": 1.381, | |
| "step": 12736 | |
| }, | |
| { | |
| "epoch": 32.66, | |
| "learning_rate": 3.366834170854272e-05, | |
| "loss": 0.3473, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_bleu": 0.4058, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6325276494026184, | |
| "eval_runtime": 36.1326, | |
| "eval_samples_per_second": 21.975, | |
| "eval_steps_per_second": 1.384, | |
| "step": 13134 | |
| }, | |
| { | |
| "epoch": 33.92, | |
| "learning_rate": 3.3040201005025127e-05, | |
| "loss": 0.3377, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_bleu": 0.3669, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6433637142181396, | |
| "eval_runtime": 36.0557, | |
| "eval_samples_per_second": 22.021, | |
| "eval_steps_per_second": 1.387, | |
| "step": 13532 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_bleu": 0.396, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6559302806854248, | |
| "eval_runtime": 36.0966, | |
| "eval_samples_per_second": 21.997, | |
| "eval_steps_per_second": 1.385, | |
| "step": 13930 | |
| }, | |
| { | |
| "epoch": 35.18, | |
| "learning_rate": 3.241206030150754e-05, | |
| "loss": 0.3258, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_bleu": 0.4449, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6613517999649048, | |
| "eval_runtime": 36.0456, | |
| "eval_samples_per_second": 22.028, | |
| "eval_steps_per_second": 1.387, | |
| "step": 14328 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 3.178391959798995e-05, | |
| "loss": 0.3144, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_bleu": 0.3988, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6619016528129578, | |
| "eval_runtime": 36.1443, | |
| "eval_samples_per_second": 21.967, | |
| "eval_steps_per_second": 1.383, | |
| "step": 14726 | |
| }, | |
| { | |
| "epoch": 37.69, | |
| "learning_rate": 3.1155778894472366e-05, | |
| "loss": 0.3062, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_bleu": 0.4133, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.681207537651062, | |
| "eval_runtime": 36.0276, | |
| "eval_samples_per_second": 22.039, | |
| "eval_steps_per_second": 1.388, | |
| "step": 15124 | |
| }, | |
| { | |
| "epoch": 38.94, | |
| "learning_rate": 3.0527638190954775e-05, | |
| "loss": 0.2976, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_bleu": 0.4102, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.679516077041626, | |
| "eval_runtime": 35.9945, | |
| "eval_samples_per_second": 22.059, | |
| "eval_steps_per_second": 1.389, | |
| "step": 15522 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_bleu": 0.3953, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.679844856262207, | |
| "eval_runtime": 36.0821, | |
| "eval_samples_per_second": 22.005, | |
| "eval_steps_per_second": 1.386, | |
| "step": 15920 | |
| }, | |
| { | |
| "epoch": 40.2, | |
| "learning_rate": 2.989949748743719e-05, | |
| "loss": 0.2883, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_bleu": 0.3846, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7088426947593689, | |
| "eval_runtime": 36.412, | |
| "eval_samples_per_second": 21.806, | |
| "eval_steps_per_second": 1.373, | |
| "step": 16318 | |
| }, | |
| { | |
| "epoch": 41.46, | |
| "learning_rate": 2.9271356783919603e-05, | |
| "loss": 0.2791, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_bleu": 0.3701, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7109950184822083, | |
| "eval_runtime": 36.0424, | |
| "eval_samples_per_second": 22.03, | |
| "eval_steps_per_second": 1.387, | |
| "step": 16716 | |
| }, | |
| { | |
| "epoch": 42.71, | |
| "learning_rate": 2.8643216080402015e-05, | |
| "loss": 0.2701, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_bleu": 0.3985, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7159502506256104, | |
| "eval_runtime": 36.0448, | |
| "eval_samples_per_second": 22.028, | |
| "eval_steps_per_second": 1.387, | |
| "step": 17114 | |
| }, | |
| { | |
| "epoch": 43.97, | |
| "learning_rate": 2.8015075376884427e-05, | |
| "loss": 0.2619, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_bleu": 0.3654, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7150431275367737, | |
| "eval_runtime": 36.1383, | |
| "eval_samples_per_second": 21.971, | |
| "eval_steps_per_second": 1.384, | |
| "step": 17512 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_bleu": 0.394, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7196872234344482, | |
| "eval_runtime": 36.0028, | |
| "eval_samples_per_second": 22.054, | |
| "eval_steps_per_second": 1.389, | |
| "step": 17910 | |
| }, | |
| { | |
| "epoch": 45.23, | |
| "learning_rate": 2.738693467336684e-05, | |
| "loss": 0.2527, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_bleu": 0.4033, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7386982440948486, | |
| "eval_runtime": 36.1228, | |
| "eval_samples_per_second": 21.981, | |
| "eval_steps_per_second": 1.384, | |
| "step": 18308 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 2.6758793969849248e-05, | |
| "loss": 0.2444, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_bleu": 0.389, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7438174486160278, | |
| "eval_runtime": 36.1308, | |
| "eval_samples_per_second": 21.976, | |
| "eval_steps_per_second": 1.384, | |
| "step": 18706 | |
| }, | |
| { | |
| "epoch": 47.74, | |
| "learning_rate": 2.613065326633166e-05, | |
| "loss": 0.239, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_bleu": 0.3948, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.75967937707901, | |
| "eval_runtime": 36.1293, | |
| "eval_samples_per_second": 21.977, | |
| "eval_steps_per_second": 1.384, | |
| "step": 19104 | |
| }, | |
| { | |
| "epoch": 48.99, | |
| "learning_rate": 2.5502512562814072e-05, | |
| "loss": 0.2303, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_bleu": 0.3976, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7644997835159302, | |
| "eval_runtime": 35.9794, | |
| "eval_samples_per_second": 22.068, | |
| "eval_steps_per_second": 1.39, | |
| "step": 19502 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_bleu": 0.385, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7786132097244263, | |
| "eval_runtime": 36.1835, | |
| "eval_samples_per_second": 21.944, | |
| "eval_steps_per_second": 1.382, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 50.25, | |
| "learning_rate": 2.4874371859296484e-05, | |
| "loss": 0.2212, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_bleu": 0.3948, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7699110507965088, | |
| "eval_runtime": 36.1227, | |
| "eval_samples_per_second": 21.981, | |
| "eval_steps_per_second": 1.384, | |
| "step": 20298 | |
| }, | |
| { | |
| "epoch": 51.51, | |
| "learning_rate": 2.4246231155778896e-05, | |
| "loss": 0.2157, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_bleu": 0.4265, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7902213931083679, | |
| "eval_runtime": 36.0895, | |
| "eval_samples_per_second": 22.001, | |
| "eval_steps_per_second": 1.385, | |
| "step": 20696 | |
| }, | |
| { | |
| "epoch": 52.76, | |
| "learning_rate": 2.361809045226131e-05, | |
| "loss": 0.2108, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_bleu": 0.3924, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7906249761581421, | |
| "eval_runtime": 35.9244, | |
| "eval_samples_per_second": 22.102, | |
| "eval_steps_per_second": 1.392, | |
| "step": 21094 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_bleu": 0.3849, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8097977042198181, | |
| "eval_runtime": 36.3421, | |
| "eval_samples_per_second": 21.848, | |
| "eval_steps_per_second": 1.376, | |
| "step": 21492 | |
| }, | |
| { | |
| "epoch": 54.02, | |
| "learning_rate": 2.298994974874372e-05, | |
| "loss": 0.2041, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_bleu": 0.3888, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8166631460189819, | |
| "eval_runtime": 36.1502, | |
| "eval_samples_per_second": 21.964, | |
| "eval_steps_per_second": 1.383, | |
| "step": 21890 | |
| }, | |
| { | |
| "epoch": 55.28, | |
| "learning_rate": 2.2361809045226133e-05, | |
| "loss": 0.1959, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_bleu": 0.4139, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8316635489463806, | |
| "eval_runtime": 36.2244, | |
| "eval_samples_per_second": 21.919, | |
| "eval_steps_per_second": 1.38, | |
| "step": 22288 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 2.1733668341708545e-05, | |
| "loss": 0.1899, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_bleu": 0.4136, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8344787359237671, | |
| "eval_runtime": 36.367, | |
| "eval_samples_per_second": 21.833, | |
| "eval_steps_per_second": 1.375, | |
| "step": 22686 | |
| }, | |
| { | |
| "epoch": 57.79, | |
| "learning_rate": 2.1105527638190957e-05, | |
| "loss": 0.1868, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_bleu": 0.4093, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.848408043384552, | |
| "eval_runtime": 36.1717, | |
| "eval_samples_per_second": 21.951, | |
| "eval_steps_per_second": 1.382, | |
| "step": 23084 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_bleu": 0.4013, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8663375973701477, | |
| "eval_runtime": 36.2951, | |
| "eval_samples_per_second": 21.876, | |
| "eval_steps_per_second": 1.378, | |
| "step": 23482 | |
| }, | |
| { | |
| "epoch": 59.05, | |
| "learning_rate": 2.047738693467337e-05, | |
| "loss": 0.1815, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_bleu": 0.3858, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8709424734115601, | |
| "eval_runtime": 36.2881, | |
| "eval_samples_per_second": 21.88, | |
| "eval_steps_per_second": 1.378, | |
| "step": 23880 | |
| }, | |
| { | |
| "epoch": 60.3, | |
| "learning_rate": 1.984924623115578e-05, | |
| "loss": 0.1744, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_bleu": 0.3716, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8845000863075256, | |
| "eval_runtime": 36.3319, | |
| "eval_samples_per_second": 21.854, | |
| "eval_steps_per_second": 1.376, | |
| "step": 24278 | |
| }, | |
| { | |
| "epoch": 61.56, | |
| "learning_rate": 1.9221105527638193e-05, | |
| "loss": 0.1709, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_bleu": 0.3781, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.878656268119812, | |
| "eval_runtime": 36.3634, | |
| "eval_samples_per_second": 21.835, | |
| "eval_steps_per_second": 1.375, | |
| "step": 24676 | |
| }, | |
| { | |
| "epoch": 62.81, | |
| "learning_rate": 1.8592964824120602e-05, | |
| "loss": 0.1659, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_bleu": 0.3642, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8844317197799683, | |
| "eval_runtime": 36.2676, | |
| "eval_samples_per_second": 21.893, | |
| "eval_steps_per_second": 1.379, | |
| "step": 25074 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_bleu": 0.3818, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9034352898597717, | |
| "eval_runtime": 36.4466, | |
| "eval_samples_per_second": 21.785, | |
| "eval_steps_per_second": 1.372, | |
| "step": 25472 | |
| }, | |
| { | |
| "epoch": 64.07, | |
| "learning_rate": 1.7964824120603014e-05, | |
| "loss": 0.1625, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_bleu": 0.3522, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9116728901863098, | |
| "eval_runtime": 36.294, | |
| "eval_samples_per_second": 21.877, | |
| "eval_steps_per_second": 1.378, | |
| "step": 25870 | |
| }, | |
| { | |
| "epoch": 65.33, | |
| "learning_rate": 1.7336683417085427e-05, | |
| "loss": 0.1568, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_bleu": 0.3892, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.905901312828064, | |
| "eval_runtime": 36.6662, | |
| "eval_samples_per_second": 21.655, | |
| "eval_steps_per_second": 1.364, | |
| "step": 26268 | |
| }, | |
| { | |
| "epoch": 66.58, | |
| "learning_rate": 1.670854271356784e-05, | |
| "loss": 0.1539, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_bleu": 0.398, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9159536957740784, | |
| "eval_runtime": 36.246, | |
| "eval_samples_per_second": 21.906, | |
| "eval_steps_per_second": 1.379, | |
| "step": 26666 | |
| }, | |
| { | |
| "epoch": 67.84, | |
| "learning_rate": 1.608040201005025e-05, | |
| "loss": 0.1501, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_bleu": 0.3831, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9332515001296997, | |
| "eval_runtime": 36.3025, | |
| "eval_samples_per_second": 21.872, | |
| "eval_steps_per_second": 1.377, | |
| "step": 27064 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_bleu": 0.4036, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9350541234016418, | |
| "eval_runtime": 36.3012, | |
| "eval_samples_per_second": 21.873, | |
| "eval_steps_per_second": 1.377, | |
| "step": 27462 | |
| }, | |
| { | |
| "epoch": 69.1, | |
| "learning_rate": 1.5452261306532663e-05, | |
| "loss": 0.1461, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_bleu": 0.3727, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9484046697616577, | |
| "eval_runtime": 36.3461, | |
| "eval_samples_per_second": 21.846, | |
| "eval_steps_per_second": 1.376, | |
| "step": 27860 | |
| }, | |
| { | |
| "epoch": 70.35, | |
| "learning_rate": 1.4824120603015077e-05, | |
| "loss": 0.1413, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_bleu": 0.3638, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9522455930709839, | |
| "eval_runtime": 36.2785, | |
| "eval_samples_per_second": 21.886, | |
| "eval_steps_per_second": 1.378, | |
| "step": 28258 | |
| }, | |
| { | |
| "epoch": 71.61, | |
| "learning_rate": 1.4195979899497489e-05, | |
| "loss": 0.1405, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_bleu": 0.3501, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.97245192527771, | |
| "eval_runtime": 36.3096, | |
| "eval_samples_per_second": 21.868, | |
| "eval_steps_per_second": 1.377, | |
| "step": 28656 | |
| }, | |
| { | |
| "epoch": 72.86, | |
| "learning_rate": 1.3567839195979901e-05, | |
| "loss": 0.1365, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_bleu": 0.372, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9698021411895752, | |
| "eval_runtime": 36.0935, | |
| "eval_samples_per_second": 21.998, | |
| "eval_steps_per_second": 1.385, | |
| "step": 29054 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_bleu": 0.3727, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9703381657600403, | |
| "eval_runtime": 36.1692, | |
| "eval_samples_per_second": 21.952, | |
| "eval_steps_per_second": 1.382, | |
| "step": 29452 | |
| }, | |
| { | |
| "epoch": 74.12, | |
| "learning_rate": 1.2939698492462313e-05, | |
| "loss": 0.1328, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_bleu": 0.3834, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9797690510749817, | |
| "eval_runtime": 36.3947, | |
| "eval_samples_per_second": 21.816, | |
| "eval_steps_per_second": 1.374, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 75.38, | |
| "learning_rate": 1.2311557788944725e-05, | |
| "loss": 0.1298, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_bleu": 0.4008, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9849729537963867, | |
| "eval_runtime": 36.4039, | |
| "eval_samples_per_second": 21.811, | |
| "eval_steps_per_second": 1.373, | |
| "step": 30248 | |
| }, | |
| { | |
| "epoch": 76.63, | |
| "learning_rate": 1.1683417085427137e-05, | |
| "loss": 0.1283, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_bleu": 0.3815, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9988215565681458, | |
| "eval_runtime": 36.385, | |
| "eval_samples_per_second": 21.822, | |
| "eval_steps_per_second": 1.374, | |
| "step": 30646 | |
| }, | |
| { | |
| "epoch": 77.89, | |
| "learning_rate": 1.105527638190955e-05, | |
| "loss": 0.1247, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_bleu": 0.3621, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9895645380020142, | |
| "eval_runtime": 36.1282, | |
| "eval_samples_per_second": 21.977, | |
| "eval_steps_per_second": 1.384, | |
| "step": 31044 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_bleu": 0.3761, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0034637451171875, | |
| "eval_runtime": 36.0695, | |
| "eval_samples_per_second": 22.013, | |
| "eval_steps_per_second": 1.386, | |
| "step": 31442 | |
| }, | |
| { | |
| "epoch": 79.15, | |
| "learning_rate": 1.042713567839196e-05, | |
| "loss": 0.1222, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_bleu": 0.3729, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0222601890563965, | |
| "eval_runtime": 36.0319, | |
| "eval_samples_per_second": 22.036, | |
| "eval_steps_per_second": 1.388, | |
| "step": 31840 | |
| }, | |
| { | |
| "epoch": 80.4, | |
| "learning_rate": 9.798994974874372e-06, | |
| "loss": 0.1195, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_bleu": 0.3866, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0171366930007935, | |
| "eval_runtime": 36.1451, | |
| "eval_samples_per_second": 21.967, | |
| "eval_steps_per_second": 1.383, | |
| "step": 32238 | |
| }, | |
| { | |
| "epoch": 81.66, | |
| "learning_rate": 9.170854271356784e-06, | |
| "loss": 0.1189, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_bleu": 0.3698, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0247294902801514, | |
| "eval_runtime": 36.1151, | |
| "eval_samples_per_second": 21.985, | |
| "eval_steps_per_second": 1.384, | |
| "step": 32636 | |
| }, | |
| { | |
| "epoch": 82.91, | |
| "learning_rate": 8.542713567839196e-06, | |
| "loss": 0.1175, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_bleu": 0.3657, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0150783061981201, | |
| "eval_runtime": 36.212, | |
| "eval_samples_per_second": 21.926, | |
| "eval_steps_per_second": 1.381, | |
| "step": 33034 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_bleu": 0.3786, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0387886762619019, | |
| "eval_runtime": 36.1399, | |
| "eval_samples_per_second": 21.97, | |
| "eval_steps_per_second": 1.384, | |
| "step": 33432 | |
| }, | |
| { | |
| "epoch": 84.17, | |
| "learning_rate": 7.914572864321608e-06, | |
| "loss": 0.1146, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_bleu": 0.3737, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0412553548812866, | |
| "eval_runtime": 36.1355, | |
| "eval_samples_per_second": 21.973, | |
| "eval_steps_per_second": 1.384, | |
| "step": 33830 | |
| }, | |
| { | |
| "epoch": 85.43, | |
| "learning_rate": 7.28643216080402e-06, | |
| "loss": 0.1124, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_bleu": 0.3803, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0402462482452393, | |
| "eval_runtime": 36.3349, | |
| "eval_samples_per_second": 21.852, | |
| "eval_steps_per_second": 1.376, | |
| "step": 34228 | |
| }, | |
| { | |
| "epoch": 86.68, | |
| "learning_rate": 6.658291457286432e-06, | |
| "loss": 0.1125, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_bleu": 0.3746, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0519098043441772, | |
| "eval_runtime": 36.2307, | |
| "eval_samples_per_second": 21.915, | |
| "eval_steps_per_second": 1.38, | |
| "step": 34626 | |
| }, | |
| { | |
| "epoch": 87.94, | |
| "learning_rate": 6.030150753768844e-06, | |
| "loss": 0.1102, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_bleu": 0.3863, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.054201364517212, | |
| "eval_runtime": 36.1231, | |
| "eval_samples_per_second": 21.98, | |
| "eval_steps_per_second": 1.384, | |
| "step": 35024 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_bleu": 0.3839, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0626344680786133, | |
| "eval_runtime": 36.1414, | |
| "eval_samples_per_second": 21.969, | |
| "eval_steps_per_second": 1.383, | |
| "step": 35422 | |
| }, | |
| { | |
| "epoch": 89.2, | |
| "learning_rate": 5.402010050251256e-06, | |
| "loss": 0.1075, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_bleu": 0.3615, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.060184359550476, | |
| "eval_runtime": 36.2676, | |
| "eval_samples_per_second": 21.893, | |
| "eval_steps_per_second": 1.379, | |
| "step": 35820 | |
| }, | |
| { | |
| "epoch": 90.45, | |
| "learning_rate": 4.773869346733668e-06, | |
| "loss": 0.1069, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_bleu": 0.3692, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0700898170471191, | |
| "eval_runtime": 36.428, | |
| "eval_samples_per_second": 21.796, | |
| "eval_steps_per_second": 1.373, | |
| "step": 36218 | |
| }, | |
| { | |
| "epoch": 91.71, | |
| "learning_rate": 4.1457286432160804e-06, | |
| "loss": 0.1062, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_bleu": 0.3719, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.069925308227539, | |
| "eval_runtime": 36.0404, | |
| "eval_samples_per_second": 22.031, | |
| "eval_steps_per_second": 1.387, | |
| "step": 36616 | |
| }, | |
| { | |
| "epoch": 92.96, | |
| "learning_rate": 3.5175879396984926e-06, | |
| "loss": 0.1051, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_bleu": 0.3667, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0732213258743286, | |
| "eval_runtime": 36.1316, | |
| "eval_samples_per_second": 21.975, | |
| "eval_steps_per_second": 1.384, | |
| "step": 37014 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_bleu": 0.3701, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0749058723449707, | |
| "eval_runtime": 36.2293, | |
| "eval_samples_per_second": 21.916, | |
| "eval_steps_per_second": 1.38, | |
| "step": 37412 | |
| }, | |
| { | |
| "epoch": 94.22, | |
| "learning_rate": 2.8894472361809047e-06, | |
| "loss": 0.1041, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_bleu": 0.3744, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0795801877975464, | |
| "eval_runtime": 36.2285, | |
| "eval_samples_per_second": 21.916, | |
| "eval_steps_per_second": 1.38, | |
| "step": 37810 | |
| }, | |
| { | |
| "epoch": 95.48, | |
| "learning_rate": 2.261306532663317e-06, | |
| "loss": 0.1034, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_bleu": 0.3771, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0823085308074951, | |
| "eval_runtime": 36.0893, | |
| "eval_samples_per_second": 22.001, | |
| "eval_steps_per_second": 1.385, | |
| "step": 38208 | |
| }, | |
| { | |
| "epoch": 96.73, | |
| "learning_rate": 1.6331658291457288e-06, | |
| "loss": 0.1031, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_bleu": 0.3775, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0796533823013306, | |
| "eval_runtime": 36.264, | |
| "eval_samples_per_second": 21.895, | |
| "eval_steps_per_second": 1.379, | |
| "step": 38606 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "learning_rate": 1.0050251256281407e-06, | |
| "loss": 0.1015, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_bleu": 0.3822, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0842037200927734, | |
| "eval_runtime": 36.1692, | |
| "eval_samples_per_second": 21.952, | |
| "eval_steps_per_second": 1.382, | |
| "step": 39004 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_bleu": 0.3839, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0859404802322388, | |
| "eval_runtime": 36.1094, | |
| "eval_samples_per_second": 21.989, | |
| "eval_steps_per_second": 1.385, | |
| "step": 39402 | |
| }, | |
| { | |
| "epoch": 99.25, | |
| "learning_rate": 3.7688442211055275e-07, | |
| "loss": 0.1007, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_bleu": 0.3829, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0861998796463013, | |
| "eval_runtime": 36.126, | |
| "eval_samples_per_second": 21.979, | |
| "eval_steps_per_second": 1.384, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 39800, | |
| "total_flos": 2.2595375365462426e+17, | |
| "train_loss": 0.31051562630351465, | |
| "train_runtime": 21104.6673, | |
| "train_samples_per_second": 30.107, | |
| "train_steps_per_second": 1.886 | |
| } | |
| ], | |
| "max_steps": 39800, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.2595375365462426e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |