| { | |
| "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": 0.1048, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.1654638051986694, | |
| "eval_runtime": 35.8, | |
| "eval_samples_per_second": 22.207, | |
| "eval_steps_per_second": 1.397, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.937185929648241e-05, | |
| "loss": 1.5993, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.0762, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0294471979141235, | |
| "eval_runtime": 35.6457, | |
| "eval_samples_per_second": 22.303, | |
| "eval_steps_per_second": 1.403, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.874371859296483e-05, | |
| "loss": 1.1714, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.0863, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9574553370475769, | |
| "eval_runtime": 35.6866, | |
| "eval_samples_per_second": 22.277, | |
| "eval_steps_per_second": 1.401, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 4.8115577889447235e-05, | |
| "loss": 1.0539, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.0769, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9043193459510803, | |
| "eval_runtime": 35.4817, | |
| "eval_samples_per_second": 22.406, | |
| "eval_steps_per_second": 1.409, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.0792, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8518753051757812, | |
| "eval_runtime": 35.6246, | |
| "eval_samples_per_second": 22.316, | |
| "eval_steps_per_second": 1.404, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 4.748743718592965e-05, | |
| "loss": 0.9762, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.0563, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8147059679031372, | |
| "eval_runtime": 35.5873, | |
| "eval_samples_per_second": 22.339, | |
| "eval_steps_per_second": 1.405, | |
| "step": 2388 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 4.685929648241206e-05, | |
| "loss": 0.9072, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.0856, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7833035588264465, | |
| "eval_runtime": 35.6208, | |
| "eval_samples_per_second": 22.318, | |
| "eval_steps_per_second": 1.404, | |
| "step": 2786 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 4.6231155778894475e-05, | |
| "loss": 0.8502, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.091, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7526289820671082, | |
| "eval_runtime": 35.6502, | |
| "eval_samples_per_second": 22.3, | |
| "eval_steps_per_second": 1.403, | |
| "step": 3184 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 4.5603015075376884e-05, | |
| "loss": 0.8081, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.1344, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7389398813247681, | |
| "eval_runtime": 35.7611, | |
| "eval_samples_per_second": 22.231, | |
| "eval_steps_per_second": 1.398, | |
| "step": 3582 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 0.1271, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.718666672706604, | |
| "eval_runtime": 35.7669, | |
| "eval_samples_per_second": 22.227, | |
| "eval_steps_per_second": 1.398, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 4.49748743718593e-05, | |
| "loss": 0.7683, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 0.1299, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7038307189941406, | |
| "eval_runtime": 35.6501, | |
| "eval_samples_per_second": 22.3, | |
| "eval_steps_per_second": 1.403, | |
| "step": 4378 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 4.434673366834171e-05, | |
| "loss": 0.7318, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 0.1213, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6900615692138672, | |
| "eval_runtime": 35.6533, | |
| "eval_samples_per_second": 22.298, | |
| "eval_steps_per_second": 1.402, | |
| "step": 4776 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 4.3718592964824124e-05, | |
| "loss": 0.6998, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 0.1583, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6753336787223816, | |
| "eval_runtime": 35.6402, | |
| "eval_samples_per_second": 22.306, | |
| "eval_steps_per_second": 1.403, | |
| "step": 5174 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 4.309045226130653e-05, | |
| "loss": 0.6683, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 0.145, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6631056070327759, | |
| "eval_runtime": 35.7643, | |
| "eval_samples_per_second": 22.229, | |
| "eval_steps_per_second": 1.398, | |
| "step": 5572 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 0.1516, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6530159711837769, | |
| "eval_runtime": 35.7246, | |
| "eval_samples_per_second": 22.254, | |
| "eval_steps_per_second": 1.4, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 4.246231155778895e-05, | |
| "loss": 0.6406, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 0.1599, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6454012393951416, | |
| "eval_runtime": 35.7142, | |
| "eval_samples_per_second": 22.26, | |
| "eval_steps_per_second": 1.4, | |
| "step": 6368 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 4.183417085427136e-05, | |
| "loss": 0.6128, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 0.1478, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6383265256881714, | |
| "eval_runtime": 35.664, | |
| "eval_samples_per_second": 22.291, | |
| "eval_steps_per_second": 1.402, | |
| "step": 6766 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 4.120603015075377e-05, | |
| "loss": 0.5911, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 0.1571, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6369075179100037, | |
| "eval_runtime": 35.6591, | |
| "eval_samples_per_second": 22.294, | |
| "eval_steps_per_second": 1.402, | |
| "step": 7164 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 4.057788944723618e-05, | |
| "loss": 0.5721, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 0.1668, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6339399814605713, | |
| "eval_runtime": 35.6693, | |
| "eval_samples_per_second": 22.288, | |
| "eval_steps_per_second": 1.402, | |
| "step": 7562 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 0.1611, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6295469403266907, | |
| "eval_runtime": 35.5912, | |
| "eval_samples_per_second": 22.337, | |
| "eval_steps_per_second": 1.405, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 20.1, | |
| "learning_rate": 3.9949748743718597e-05, | |
| "loss": 0.547, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_bleu": 0.1722, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6267198324203491, | |
| "eval_runtime": 35.8366, | |
| "eval_samples_per_second": 22.184, | |
| "eval_steps_per_second": 1.395, | |
| "step": 8358 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "learning_rate": 3.9321608040201005e-05, | |
| "loss": 0.529, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_bleu": 0.1656, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6275119781494141, | |
| "eval_runtime": 35.667, | |
| "eval_samples_per_second": 22.289, | |
| "eval_steps_per_second": 1.402, | |
| "step": 8756 | |
| }, | |
| { | |
| "epoch": 22.61, | |
| "learning_rate": 3.869346733668342e-05, | |
| "loss": 0.5115, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_bleu": 0.1684, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6284548044204712, | |
| "eval_runtime": 35.6512, | |
| "eval_samples_per_second": 22.299, | |
| "eval_steps_per_second": 1.402, | |
| "step": 9154 | |
| }, | |
| { | |
| "epoch": 23.87, | |
| "learning_rate": 3.806532663316583e-05, | |
| "loss": 0.4934, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_bleu": 0.1696, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6268807053565979, | |
| "eval_runtime": 35.7633, | |
| "eval_samples_per_second": 22.229, | |
| "eval_steps_per_second": 1.398, | |
| "step": 9552 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_bleu": 0.182, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6358157992362976, | |
| "eval_runtime": 36.0997, | |
| "eval_samples_per_second": 22.022, | |
| "eval_steps_per_second": 1.385, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 25.13, | |
| "learning_rate": 3.7437185929648245e-05, | |
| "loss": 0.4773, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_bleu": 0.1699, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6337732672691345, | |
| "eval_runtime": 35.9321, | |
| "eval_samples_per_second": 22.125, | |
| "eval_steps_per_second": 1.392, | |
| "step": 10348 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 3.6809045226130654e-05, | |
| "loss": 0.4591, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_bleu": 0.1855, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6358336806297302, | |
| "eval_runtime": 35.7576, | |
| "eval_samples_per_second": 22.233, | |
| "eval_steps_per_second": 1.398, | |
| "step": 10746 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 3.618090452261307e-05, | |
| "loss": 0.4449, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_bleu": 0.1759, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6440271735191345, | |
| "eval_runtime": 35.6217, | |
| "eval_samples_per_second": 22.318, | |
| "eval_steps_per_second": 1.404, | |
| "step": 11144 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 3.555276381909548e-05, | |
| "loss": 0.4285, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_bleu": 0.1786, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6438360810279846, | |
| "eval_runtime": 35.5837, | |
| "eval_samples_per_second": 22.342, | |
| "eval_steps_per_second": 1.405, | |
| "step": 11542 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_bleu": 0.1874, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.647448718547821, | |
| "eval_runtime": 35.5495, | |
| "eval_samples_per_second": 22.363, | |
| "eval_steps_per_second": 1.406, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 30.15, | |
| "learning_rate": 3.4924623115577894e-05, | |
| "loss": 0.4137, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_bleu": 0.1968, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.651654839515686, | |
| "eval_runtime": 35.6719, | |
| "eval_samples_per_second": 22.286, | |
| "eval_steps_per_second": 1.402, | |
| "step": 12338 | |
| }, | |
| { | |
| "epoch": 31.41, | |
| "learning_rate": 3.42964824120603e-05, | |
| "loss": 0.4012, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_bleu": 0.1735, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6562197804450989, | |
| "eval_runtime": 35.627, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.403, | |
| "step": 12736 | |
| }, | |
| { | |
| "epoch": 32.66, | |
| "learning_rate": 3.366834170854272e-05, | |
| "loss": 0.3858, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_bleu": 0.18, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6581218838691711, | |
| "eval_runtime": 35.6835, | |
| "eval_samples_per_second": 22.279, | |
| "eval_steps_per_second": 1.401, | |
| "step": 13134 | |
| }, | |
| { | |
| "epoch": 33.92, | |
| "learning_rate": 3.3040201005025127e-05, | |
| "loss": 0.3753, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_bleu": 0.1837, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6713840961456299, | |
| "eval_runtime": 36.1204, | |
| "eval_samples_per_second": 22.01, | |
| "eval_steps_per_second": 1.384, | |
| "step": 13532 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_bleu": 0.177, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6749709844589233, | |
| "eval_runtime": 35.6201, | |
| "eval_samples_per_second": 22.319, | |
| "eval_steps_per_second": 1.404, | |
| "step": 13930 | |
| }, | |
| { | |
| "epoch": 35.18, | |
| "learning_rate": 3.241206030150754e-05, | |
| "loss": 0.3613, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_bleu": 0.177, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6772740483283997, | |
| "eval_runtime": 35.673, | |
| "eval_samples_per_second": 22.286, | |
| "eval_steps_per_second": 1.402, | |
| "step": 14328 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 3.178391959798995e-05, | |
| "loss": 0.3493, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_bleu": 0.1859, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.6915194392204285, | |
| "eval_runtime": 36.1411, | |
| "eval_samples_per_second": 21.997, | |
| "eval_steps_per_second": 1.383, | |
| "step": 14726 | |
| }, | |
| { | |
| "epoch": 37.69, | |
| "learning_rate": 3.1155778894472366e-05, | |
| "loss": 0.339, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_bleu": 0.1756, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7031569480895996, | |
| "eval_runtime": 36.1897, | |
| "eval_samples_per_second": 21.968, | |
| "eval_steps_per_second": 1.382, | |
| "step": 15124 | |
| }, | |
| { | |
| "epoch": 38.94, | |
| "learning_rate": 3.0527638190954775e-05, | |
| "loss": 0.3263, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_bleu": 0.1844, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7003222703933716, | |
| "eval_runtime": 36.2516, | |
| "eval_samples_per_second": 21.93, | |
| "eval_steps_per_second": 1.379, | |
| "step": 15522 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_bleu": 0.1795, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7169303297996521, | |
| "eval_runtime": 36.3049, | |
| "eval_samples_per_second": 21.898, | |
| "eval_steps_per_second": 1.377, | |
| "step": 15920 | |
| }, | |
| { | |
| "epoch": 40.2, | |
| "learning_rate": 2.989949748743719e-05, | |
| "loss": 0.3153, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_bleu": 0.1903, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7180814743041992, | |
| "eval_runtime": 36.2151, | |
| "eval_samples_per_second": 21.952, | |
| "eval_steps_per_second": 1.381, | |
| "step": 16318 | |
| }, | |
| { | |
| "epoch": 41.46, | |
| "learning_rate": 2.9271356783919603e-05, | |
| "loss": 0.3047, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_bleu": 0.1864, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7283141613006592, | |
| "eval_runtime": 36.2969, | |
| "eval_samples_per_second": 21.903, | |
| "eval_steps_per_second": 1.378, | |
| "step": 16716 | |
| }, | |
| { | |
| "epoch": 42.71, | |
| "learning_rate": 2.8643216080402015e-05, | |
| "loss": 0.2933, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_bleu": 0.188, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7462304830551147, | |
| "eval_runtime": 35.9176, | |
| "eval_samples_per_second": 22.134, | |
| "eval_steps_per_second": 1.392, | |
| "step": 17114 | |
| }, | |
| { | |
| "epoch": 43.97, | |
| "learning_rate": 2.8015075376884427e-05, | |
| "loss": 0.2888, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_bleu": 0.1841, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7420201301574707, | |
| "eval_runtime": 36.2045, | |
| "eval_samples_per_second": 21.959, | |
| "eval_steps_per_second": 1.381, | |
| "step": 17512 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_bleu": 0.1748, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7574421167373657, | |
| "eval_runtime": 36.2479, | |
| "eval_samples_per_second": 21.932, | |
| "eval_steps_per_second": 1.379, | |
| "step": 17910 | |
| }, | |
| { | |
| "epoch": 45.23, | |
| "learning_rate": 2.738693467336684e-05, | |
| "loss": 0.2762, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_bleu": 0.1747, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7617235779762268, | |
| "eval_runtime": 36.159, | |
| "eval_samples_per_second": 21.986, | |
| "eval_steps_per_second": 1.383, | |
| "step": 18308 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 2.6758793969849248e-05, | |
| "loss": 0.2671, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_bleu": 0.1743, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7677585482597351, | |
| "eval_runtime": 36.1812, | |
| "eval_samples_per_second": 21.973, | |
| "eval_steps_per_second": 1.382, | |
| "step": 18706 | |
| }, | |
| { | |
| "epoch": 47.74, | |
| "learning_rate": 2.613065326633166e-05, | |
| "loss": 0.2585, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_bleu": 0.1902, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7697047591209412, | |
| "eval_runtime": 36.1036, | |
| "eval_samples_per_second": 22.02, | |
| "eval_steps_per_second": 1.385, | |
| "step": 19104 | |
| }, | |
| { | |
| "epoch": 48.99, | |
| "learning_rate": 2.5502512562814072e-05, | |
| "loss": 0.252, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_bleu": 0.208, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7865097522735596, | |
| "eval_runtime": 36.1641, | |
| "eval_samples_per_second": 21.983, | |
| "eval_steps_per_second": 1.383, | |
| "step": 19502 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_bleu": 0.1777, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8058604001998901, | |
| "eval_runtime": 36.0936, | |
| "eval_samples_per_second": 22.026, | |
| "eval_steps_per_second": 1.385, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 50.25, | |
| "learning_rate": 2.4874371859296484e-05, | |
| "loss": 0.2411, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_bleu": 0.212, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.7906444072723389, | |
| "eval_runtime": 36.7349, | |
| "eval_samples_per_second": 21.642, | |
| "eval_steps_per_second": 1.361, | |
| "step": 20298 | |
| }, | |
| { | |
| "epoch": 51.51, | |
| "learning_rate": 2.4246231155778896e-05, | |
| "loss": 0.2358, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_bleu": 0.1778, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8143441081047058, | |
| "eval_runtime": 36.1702, | |
| "eval_samples_per_second": 21.979, | |
| "eval_steps_per_second": 1.382, | |
| "step": 20696 | |
| }, | |
| { | |
| "epoch": 52.76, | |
| "learning_rate": 2.361809045226131e-05, | |
| "loss": 0.2273, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_bleu": 0.218, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8184289932250977, | |
| "eval_runtime": 36.341, | |
| "eval_samples_per_second": 21.876, | |
| "eval_steps_per_second": 1.376, | |
| "step": 21094 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_bleu": 0.2243, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8261227607727051, | |
| "eval_runtime": 36.1608, | |
| "eval_samples_per_second": 21.985, | |
| "eval_steps_per_second": 1.383, | |
| "step": 21492 | |
| }, | |
| { | |
| "epoch": 54.02, | |
| "learning_rate": 2.298994974874372e-05, | |
| "loss": 0.223, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_bleu": 0.2196, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8429352641105652, | |
| "eval_runtime": 35.7014, | |
| "eval_samples_per_second": 22.268, | |
| "eval_steps_per_second": 1.401, | |
| "step": 21890 | |
| }, | |
| { | |
| "epoch": 55.28, | |
| "learning_rate": 2.2361809045226133e-05, | |
| "loss": 0.2131, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_bleu": 0.2402, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.847459077835083, | |
| "eval_runtime": 35.7383, | |
| "eval_samples_per_second": 22.245, | |
| "eval_steps_per_second": 1.399, | |
| "step": 22288 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 2.1733668341708545e-05, | |
| "loss": 0.2083, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_bleu": 0.2163, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8617640733718872, | |
| "eval_runtime": 35.56, | |
| "eval_samples_per_second": 22.357, | |
| "eval_steps_per_second": 1.406, | |
| "step": 22686 | |
| }, | |
| { | |
| "epoch": 57.79, | |
| "learning_rate": 2.1105527638190957e-05, | |
| "loss": 0.202, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_bleu": 0.2164, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8572230339050293, | |
| "eval_runtime": 35.5968, | |
| "eval_samples_per_second": 22.333, | |
| "eval_steps_per_second": 1.405, | |
| "step": 23084 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_bleu": 0.217, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.873598575592041, | |
| "eval_runtime": 35.5807, | |
| "eval_samples_per_second": 22.344, | |
| "eval_steps_per_second": 1.405, | |
| "step": 23482 | |
| }, | |
| { | |
| "epoch": 59.05, | |
| "learning_rate": 2.047738693467337e-05, | |
| "loss": 0.1968, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_bleu": 0.2166, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8894439339637756, | |
| "eval_runtime": 35.6815, | |
| "eval_samples_per_second": 22.28, | |
| "eval_steps_per_second": 1.401, | |
| "step": 23880 | |
| }, | |
| { | |
| "epoch": 60.3, | |
| "learning_rate": 1.984924623115578e-05, | |
| "loss": 0.1904, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_bleu": 0.2241, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.8927697539329529, | |
| "eval_runtime": 35.5709, | |
| "eval_samples_per_second": 22.35, | |
| "eval_steps_per_second": 1.406, | |
| "step": 24278 | |
| }, | |
| { | |
| "epoch": 61.56, | |
| "learning_rate": 1.9221105527638193e-05, | |
| "loss": 0.1847, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_bleu": 0.2219, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9057827591896057, | |
| "eval_runtime": 35.9775, | |
| "eval_samples_per_second": 22.097, | |
| "eval_steps_per_second": 1.39, | |
| "step": 24676 | |
| }, | |
| { | |
| "epoch": 62.81, | |
| "learning_rate": 1.8592964824120602e-05, | |
| "loss": 0.1803, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_bleu": 0.2336, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9056702852249146, | |
| "eval_runtime": 35.7167, | |
| "eval_samples_per_second": 22.259, | |
| "eval_steps_per_second": 1.4, | |
| "step": 25074 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_bleu": 0.2156, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9173711538314819, | |
| "eval_runtime": 35.7315, | |
| "eval_samples_per_second": 22.249, | |
| "eval_steps_per_second": 1.399, | |
| "step": 25472 | |
| }, | |
| { | |
| "epoch": 64.07, | |
| "learning_rate": 1.7964824120603014e-05, | |
| "loss": 0.1758, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_bleu": 0.1951, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.922991156578064, | |
| "eval_runtime": 35.7331, | |
| "eval_samples_per_second": 22.248, | |
| "eval_steps_per_second": 1.399, | |
| "step": 25870 | |
| }, | |
| { | |
| "epoch": 65.33, | |
| "learning_rate": 1.7336683417085427e-05, | |
| "loss": 0.1701, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_bleu": 0.2249, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9349916577339172, | |
| "eval_runtime": 35.6317, | |
| "eval_samples_per_second": 22.312, | |
| "eval_steps_per_second": 1.403, | |
| "step": 26268 | |
| }, | |
| { | |
| "epoch": 66.58, | |
| "learning_rate": 1.670854271356784e-05, | |
| "loss": 0.1673, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_bleu": 0.2224, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9416642189025879, | |
| "eval_runtime": 35.7511, | |
| "eval_samples_per_second": 22.237, | |
| "eval_steps_per_second": 1.399, | |
| "step": 26666 | |
| }, | |
| { | |
| "epoch": 67.84, | |
| "learning_rate": 1.608040201005025e-05, | |
| "loss": 0.1614, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_bleu": 0.2161, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9508859515190125, | |
| "eval_runtime": 35.6367, | |
| "eval_samples_per_second": 22.308, | |
| "eval_steps_per_second": 1.403, | |
| "step": 27064 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_bleu": 0.2183, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9652993083000183, | |
| "eval_runtime": 35.6263, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.403, | |
| "step": 27462 | |
| }, | |
| { | |
| "epoch": 69.1, | |
| "learning_rate": 1.5452261306532663e-05, | |
| "loss": 0.1578, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_bleu": 0.2113, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9633088111877441, | |
| "eval_runtime": 35.7594, | |
| "eval_samples_per_second": 22.232, | |
| "eval_steps_per_second": 1.398, | |
| "step": 27860 | |
| }, | |
| { | |
| "epoch": 70.35, | |
| "learning_rate": 1.4824120603015077e-05, | |
| "loss": 0.1536, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_bleu": 0.2177, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9783052802085876, | |
| "eval_runtime": 35.5411, | |
| "eval_samples_per_second": 22.368, | |
| "eval_steps_per_second": 1.407, | |
| "step": 28258 | |
| }, | |
| { | |
| "epoch": 71.61, | |
| "learning_rate": 1.4195979899497489e-05, | |
| "loss": 0.1513, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_bleu": 0.2179, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9754663109779358, | |
| "eval_runtime": 35.6862, | |
| "eval_samples_per_second": 22.278, | |
| "eval_steps_per_second": 1.401, | |
| "step": 28656 | |
| }, | |
| { | |
| "epoch": 72.86, | |
| "learning_rate": 1.3567839195979901e-05, | |
| "loss": 0.147, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_bleu": 0.2273, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9910703897476196, | |
| "eval_runtime": 35.9105, | |
| "eval_samples_per_second": 22.138, | |
| "eval_steps_per_second": 1.392, | |
| "step": 29054 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_bleu": 0.2157, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9854773283004761, | |
| "eval_runtime": 35.6352, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 1.403, | |
| "step": 29452 | |
| }, | |
| { | |
| "epoch": 74.12, | |
| "learning_rate": 1.2939698492462313e-05, | |
| "loss": 0.1443, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_bleu": 0.2169, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 0.9998270273208618, | |
| "eval_runtime": 35.64, | |
| "eval_samples_per_second": 22.306, | |
| "eval_steps_per_second": 1.403, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 75.38, | |
| "learning_rate": 1.2311557788944725e-05, | |
| "loss": 0.1401, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_bleu": 0.2124, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0127789974212646, | |
| "eval_runtime": 35.7323, | |
| "eval_samples_per_second": 22.249, | |
| "eval_steps_per_second": 1.399, | |
| "step": 30248 | |
| }, | |
| { | |
| "epoch": 76.63, | |
| "learning_rate": 1.1683417085427137e-05, | |
| "loss": 0.1377, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_bleu": 0.2159, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0114222764968872, | |
| "eval_runtime": 35.7601, | |
| "eval_samples_per_second": 22.231, | |
| "eval_steps_per_second": 1.398, | |
| "step": 30646 | |
| }, | |
| { | |
| "epoch": 77.89, | |
| "learning_rate": 1.105527638190955e-05, | |
| "loss": 0.1342, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_bleu": 0.2152, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0248533487319946, | |
| "eval_runtime": 35.6808, | |
| "eval_samples_per_second": 22.281, | |
| "eval_steps_per_second": 1.401, | |
| "step": 31044 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_bleu": 0.2233, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0258084535598755, | |
| "eval_runtime": 35.6984, | |
| "eval_samples_per_second": 22.27, | |
| "eval_steps_per_second": 1.401, | |
| "step": 31442 | |
| }, | |
| { | |
| "epoch": 79.15, | |
| "learning_rate": 1.042713567839196e-05, | |
| "loss": 0.1336, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_bleu": 0.2194, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0308655500411987, | |
| "eval_runtime": 35.6369, | |
| "eval_samples_per_second": 22.308, | |
| "eval_steps_per_second": 1.403, | |
| "step": 31840 | |
| }, | |
| { | |
| "epoch": 80.4, | |
| "learning_rate": 9.798994974874372e-06, | |
| "loss": 0.1307, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_bleu": 0.2122, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.032060146331787, | |
| "eval_runtime": 35.5991, | |
| "eval_samples_per_second": 22.332, | |
| "eval_steps_per_second": 1.405, | |
| "step": 32238 | |
| }, | |
| { | |
| "epoch": 81.66, | |
| "learning_rate": 9.170854271356784e-06, | |
| "loss": 0.1277, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_bleu": 0.2191, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.034020185470581, | |
| "eval_runtime": 35.662, | |
| "eval_samples_per_second": 22.293, | |
| "eval_steps_per_second": 1.402, | |
| "step": 32636 | |
| }, | |
| { | |
| "epoch": 82.91, | |
| "learning_rate": 8.542713567839196e-06, | |
| "loss": 0.1262, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_bleu": 0.2123, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0493375062942505, | |
| "eval_runtime": 35.6012, | |
| "eval_samples_per_second": 22.331, | |
| "eval_steps_per_second": 1.404, | |
| "step": 33034 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_bleu": 0.2273, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0544501543045044, | |
| "eval_runtime": 35.7115, | |
| "eval_samples_per_second": 22.262, | |
| "eval_steps_per_second": 1.4, | |
| "step": 33432 | |
| }, | |
| { | |
| "epoch": 84.17, | |
| "learning_rate": 7.914572864321608e-06, | |
| "loss": 0.1233, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_bleu": 0.2184, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0550196170806885, | |
| "eval_runtime": 35.6365, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 1.403, | |
| "step": 33830 | |
| }, | |
| { | |
| "epoch": 85.43, | |
| "learning_rate": 7.28643216080402e-06, | |
| "loss": 0.1233, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_bleu": 0.2241, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0545953512191772, | |
| "eval_runtime": 35.7457, | |
| "eval_samples_per_second": 22.24, | |
| "eval_steps_per_second": 1.399, | |
| "step": 34228 | |
| }, | |
| { | |
| "epoch": 86.68, | |
| "learning_rate": 6.658291457286432e-06, | |
| "loss": 0.1205, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_bleu": 0.2246, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0695993900299072, | |
| "eval_runtime": 35.6623, | |
| "eval_samples_per_second": 22.292, | |
| "eval_steps_per_second": 1.402, | |
| "step": 34626 | |
| }, | |
| { | |
| "epoch": 87.94, | |
| "learning_rate": 6.030150753768844e-06, | |
| "loss": 0.1189, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_bleu": 0.2237, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0730416774749756, | |
| "eval_runtime": 35.8819, | |
| "eval_samples_per_second": 22.156, | |
| "eval_steps_per_second": 1.393, | |
| "step": 35024 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_bleu": 0.2308, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.068780541419983, | |
| "eval_runtime": 35.7114, | |
| "eval_samples_per_second": 22.262, | |
| "eval_steps_per_second": 1.4, | |
| "step": 35422 | |
| }, | |
| { | |
| "epoch": 89.2, | |
| "learning_rate": 5.402010050251256e-06, | |
| "loss": 0.1173, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_bleu": 0.2267, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0783226490020752, | |
| "eval_runtime": 35.7523, | |
| "eval_samples_per_second": 22.236, | |
| "eval_steps_per_second": 1.399, | |
| "step": 35820 | |
| }, | |
| { | |
| "epoch": 90.45, | |
| "learning_rate": 4.773869346733668e-06, | |
| "loss": 0.1154, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_bleu": 0.2262, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0766741037368774, | |
| "eval_runtime": 35.7535, | |
| "eval_samples_per_second": 22.236, | |
| "eval_steps_per_second": 1.398, | |
| "step": 36218 | |
| }, | |
| { | |
| "epoch": 91.71, | |
| "learning_rate": 4.1457286432160804e-06, | |
| "loss": 0.115, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_bleu": 0.2214, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0834720134735107, | |
| "eval_runtime": 35.7567, | |
| "eval_samples_per_second": 22.234, | |
| "eval_steps_per_second": 1.398, | |
| "step": 36616 | |
| }, | |
| { | |
| "epoch": 92.96, | |
| "learning_rate": 3.5175879396984926e-06, | |
| "loss": 0.1136, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_bleu": 0.2284, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0788373947143555, | |
| "eval_runtime": 35.8397, | |
| "eval_samples_per_second": 22.182, | |
| "eval_steps_per_second": 1.395, | |
| "step": 37014 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_bleu": 0.2269, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0876238346099854, | |
| "eval_runtime": 35.7552, | |
| "eval_samples_per_second": 22.235, | |
| "eval_steps_per_second": 1.398, | |
| "step": 37412 | |
| }, | |
| { | |
| "epoch": 94.22, | |
| "learning_rate": 2.8894472361809047e-06, | |
| "loss": 0.1126, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_bleu": 0.2212, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0935641527175903, | |
| "eval_runtime": 35.7207, | |
| "eval_samples_per_second": 22.256, | |
| "eval_steps_per_second": 1.4, | |
| "step": 37810 | |
| }, | |
| { | |
| "epoch": 95.48, | |
| "learning_rate": 2.261306532663317e-06, | |
| "loss": 0.1118, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_bleu": 0.2207, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0917831659317017, | |
| "eval_runtime": 35.5884, | |
| "eval_samples_per_second": 22.339, | |
| "eval_steps_per_second": 1.405, | |
| "step": 38208 | |
| }, | |
| { | |
| "epoch": 96.73, | |
| "learning_rate": 1.6331658291457288e-06, | |
| "loss": 0.111, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_bleu": 0.2217, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0943822860717773, | |
| "eval_runtime": 35.7423, | |
| "eval_samples_per_second": 22.243, | |
| "eval_steps_per_second": 1.399, | |
| "step": 38606 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "learning_rate": 1.0050251256281407e-06, | |
| "loss": 0.1106, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_bleu": 0.2203, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0962368249893188, | |
| "eval_runtime": 35.6215, | |
| "eval_samples_per_second": 22.318, | |
| "eval_steps_per_second": 1.404, | |
| "step": 39004 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_bleu": 0.2182, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.0994266271591187, | |
| "eval_runtime": 35.6909, | |
| "eval_samples_per_second": 22.275, | |
| "eval_steps_per_second": 1.401, | |
| "step": 39402 | |
| }, | |
| { | |
| "epoch": 99.25, | |
| "learning_rate": 3.7688442211055275e-07, | |
| "loss": 0.1088, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_bleu": 0.2193, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.099919319152832, | |
| "eval_runtime": 35.8327, | |
| "eval_samples_per_second": 22.186, | |
| "eval_steps_per_second": 1.395, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 39800, | |
| "total_flos": 2.262748628238336e+17, | |
| "train_loss": 0.35148891755683936, | |
| "train_runtime": 21066.5572, | |
| "train_samples_per_second": 30.204, | |
| "train_steps_per_second": 1.889 | |
| } | |
| ], | |
| "max_steps": 39800, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.262748628238336e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |