| { |
| "best_metric": 47.3367, |
| "best_model_checkpoint": "/scratch/st-amuham01-1/fenimi/transformers/examples/pytorch/translation/similar-languages-task/model_out_es-pt-tok/checkpoint-1704014", |
| "epoch": 35.0, |
| "global_step": 3371314, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 0.8042, |
| "step": 131078 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_bleu": 46.137, |
| "eval_gen_len": 73.7186, |
| "eval_loss": 0.7053773999214172, |
| "eval_runtime": 93.6018, |
| "eval_samples_per_second": 10.363, |
| "eval_steps_per_second": 0.331, |
| "step": 131078 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.9e-05, |
| "loss": 0.6488, |
| "step": 262156 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_bleu": 46.1742, |
| "eval_gen_len": 73.8876, |
| "eval_loss": 0.6584964990615845, |
| "eval_runtime": 91.805, |
| "eval_samples_per_second": 10.566, |
| "eval_steps_per_second": 0.338, |
| "step": 262156 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.85e-05, |
| "loss": 0.6069, |
| "step": 393234 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_bleu": 46.0956, |
| "eval_gen_len": 73.666, |
| "eval_loss": 0.6464588046073914, |
| "eval_runtime": 87.4692, |
| "eval_samples_per_second": 11.09, |
| "eval_steps_per_second": 0.354, |
| "step": 393234 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.5821, |
| "step": 524312 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_bleu": 46.326, |
| "eval_gen_len": 73.932, |
| "eval_loss": 0.6305918097496033, |
| "eval_runtime": 90.9772, |
| "eval_samples_per_second": 10.662, |
| "eval_steps_per_second": 0.341, |
| "step": 524312 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.75e-05, |
| "loss": 0.5648, |
| "step": 655390 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_bleu": 46.3267, |
| "eval_gen_len": 73.6505, |
| "eval_loss": 0.617319643497467, |
| "eval_runtime": 86.5507, |
| "eval_samples_per_second": 11.207, |
| "eval_steps_per_second": 0.358, |
| "step": 655390 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.5515, |
| "step": 786468 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_bleu": 46.6537, |
| "eval_gen_len": 73.8722, |
| "eval_loss": 0.6139377355575562, |
| "eval_runtime": 88.9058, |
| "eval_samples_per_second": 10.91, |
| "eval_steps_per_second": 0.349, |
| "step": 786468 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 4.6500000000000005e-05, |
| "loss": 0.541, |
| "step": 917546 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_bleu": 46.5628, |
| "eval_gen_len": 73.8412, |
| "eval_loss": 0.6046749353408813, |
| "eval_runtime": 87.2322, |
| "eval_samples_per_second": 11.12, |
| "eval_steps_per_second": 0.355, |
| "step": 917546 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.5323, |
| "step": 1048624 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_bleu": 46.5538, |
| "eval_gen_len": 73.8216, |
| "eval_loss": 0.5961582064628601, |
| "eval_runtime": 88.6262, |
| "eval_samples_per_second": 10.945, |
| "eval_steps_per_second": 0.35, |
| "step": 1048624 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 4.55e-05, |
| "loss": 0.525, |
| "step": 1179702 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_bleu": 46.543, |
| "eval_gen_len": 74.0711, |
| "eval_loss": 0.5961570739746094, |
| "eval_runtime": 90.5754, |
| "eval_samples_per_second": 10.709, |
| "eval_steps_per_second": 0.342, |
| "step": 1179702 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.5184, |
| "step": 1310780 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_bleu": 46.772, |
| "eval_gen_len": 73.8258, |
| "eval_loss": 0.5992215275764465, |
| "eval_runtime": 86.6687, |
| "eval_samples_per_second": 11.192, |
| "eval_steps_per_second": 0.358, |
| "step": 1310780 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 0.5126, |
| "step": 1441858 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_bleu": 46.875, |
| "eval_gen_len": 74.0124, |
| "eval_loss": 0.5917361378669739, |
| "eval_runtime": 91.2818, |
| "eval_samples_per_second": 10.626, |
| "eval_steps_per_second": 0.34, |
| "step": 1441858 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.5075, |
| "step": 1572936 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_bleu": 46.5982, |
| "eval_gen_len": 74.0639, |
| "eval_loss": 0.59002286195755, |
| "eval_runtime": 95.1271, |
| "eval_samples_per_second": 10.197, |
| "eval_steps_per_second": 0.326, |
| "step": 1572936 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 4.35e-05, |
| "loss": 0.503, |
| "step": 1704014 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_bleu": 47.3367, |
| "eval_gen_len": 73.9134, |
| "eval_loss": 0.591410756111145, |
| "eval_runtime": 87.7758, |
| "eval_samples_per_second": 11.051, |
| "eval_steps_per_second": 0.353, |
| "step": 1704014 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 4.3e-05, |
| "loss": 0.4987, |
| "step": 1835092 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_bleu": 46.5688, |
| "eval_gen_len": 73.9072, |
| "eval_loss": 0.5959733128547668, |
| "eval_runtime": 95.2654, |
| "eval_samples_per_second": 10.182, |
| "eval_steps_per_second": 0.325, |
| "step": 1835092 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 4.25e-05, |
| "loss": 0.4947, |
| "step": 1966170 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_bleu": 46.8246, |
| "eval_gen_len": 74.066, |
| "eval_loss": 0.5951239466667175, |
| "eval_runtime": 89.8542, |
| "eval_samples_per_second": 10.795, |
| "eval_steps_per_second": 0.345, |
| "step": 1966170 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 4.2e-05, |
| "loss": 0.4912, |
| "step": 2097248 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_bleu": 46.6078, |
| "eval_gen_len": 74.1052, |
| "eval_loss": 0.5862768888473511, |
| "eval_runtime": 90.8564, |
| "eval_samples_per_second": 10.676, |
| "eval_steps_per_second": 0.341, |
| "step": 2097248 |
| }, |
| { |
| "epoch": 17.0, |
| "learning_rate": 4.15e-05, |
| "loss": 0.4877, |
| "step": 2228326 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_bleu": 46.4987, |
| "eval_gen_len": 73.8402, |
| "eval_loss": 0.5898135304450989, |
| "eval_runtime": 93.1614, |
| "eval_samples_per_second": 10.412, |
| "eval_steps_per_second": 0.333, |
| "step": 2228326 |
| }, |
| { |
| "epoch": 24.0, |
| "learning_rate": 3.780262784911128e-05, |
| "loss": 0.4915, |
| "step": 2323575 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_bleu": 46.9695, |
| "eval_gen_len": 73.9588, |
| "eval_loss": 0.5856001973152161, |
| "eval_runtime": 77.7022, |
| "eval_samples_per_second": 12.484, |
| "eval_steps_per_second": 0.399, |
| "step": 2323575 |
| }, |
| { |
| "epoch": 25.0, |
| "learning_rate": 3.730262784911128e-05, |
| "loss": 0.4858, |
| "step": 2418824 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_bleu": 46.9834, |
| "eval_gen_len": 73.7845, |
| "eval_loss": 0.5880559682846069, |
| "eval_runtime": 76.2261, |
| "eval_samples_per_second": 12.725, |
| "eval_steps_per_second": 0.407, |
| "step": 2418824 |
| }, |
| { |
| "epoch": 26.0, |
| "learning_rate": 3.6802627849111274e-05, |
| "loss": 0.4819, |
| "step": 2514073 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_bleu": 47.2378, |
| "eval_gen_len": 73.7866, |
| "eval_loss": 0.5938757061958313, |
| "eval_runtime": 77.0503, |
| "eval_samples_per_second": 12.589, |
| "eval_steps_per_second": 0.402, |
| "step": 2514073 |
| }, |
| { |
| "epoch": 27.0, |
| "learning_rate": 3.6302627849111276e-05, |
| "loss": 0.4785, |
| "step": 2609322 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_bleu": 47.1579, |
| "eval_gen_len": 74.1351, |
| "eval_loss": 0.593238115310669, |
| "eval_runtime": 79.7831, |
| "eval_samples_per_second": 12.158, |
| "eval_steps_per_second": 0.389, |
| "step": 2609322 |
| }, |
| { |
| "epoch": 28.0, |
| "learning_rate": 3.5802627849111284e-05, |
| "loss": 0.4757, |
| "step": 2704571 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_bleu": 47.0974, |
| "eval_gen_len": 73.8289, |
| "eval_loss": 0.5946824550628662, |
| "eval_runtime": 77.1019, |
| "eval_samples_per_second": 12.581, |
| "eval_steps_per_second": 0.402, |
| "step": 2704571 |
| }, |
| { |
| "epoch": 29.0, |
| "learning_rate": 3.530262784911128e-05, |
| "loss": 0.4729, |
| "step": 2799820 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_bleu": 47.2814, |
| "eval_gen_len": 74.1485, |
| "eval_loss": 0.5900229811668396, |
| "eval_runtime": 76.5406, |
| "eval_samples_per_second": 12.673, |
| "eval_steps_per_second": 0.405, |
| "step": 2799820 |
| }, |
| { |
| "epoch": 30.0, |
| "learning_rate": 3.480262784911128e-05, |
| "loss": 0.4702, |
| "step": 2895069 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_bleu": 47.1382, |
| "eval_gen_len": 73.8495, |
| "eval_loss": 0.5961056351661682, |
| "eval_runtime": 77.883, |
| "eval_samples_per_second": 12.455, |
| "eval_steps_per_second": 0.398, |
| "step": 2895069 |
| }, |
| { |
| "epoch": 31.0, |
| "learning_rate": 3.430262784911128e-05, |
| "loss": 0.4678, |
| "step": 2990318 |
| }, |
| { |
| "epoch": 31.0, |
| "eval_bleu": 46.9917, |
| "eval_gen_len": 74.0526, |
| "eval_loss": 0.5983180999755859, |
| "eval_runtime": 77.7736, |
| "eval_samples_per_second": 12.472, |
| "eval_steps_per_second": 0.399, |
| "step": 2990318 |
| }, |
| { |
| "epoch": 32.0, |
| "learning_rate": 3.3802627849111276e-05, |
| "loss": 0.4654, |
| "step": 3085567 |
| }, |
| { |
| "epoch": 32.0, |
| "eval_bleu": 47.1391, |
| "eval_gen_len": 73.8381, |
| "eval_loss": 0.5979074835777283, |
| "eval_runtime": 79.7831, |
| "eval_samples_per_second": 12.158, |
| "eval_steps_per_second": 0.389, |
| "step": 3085567 |
| }, |
| { |
| "epoch": 33.0, |
| "learning_rate": 3.330262784911128e-05, |
| "loss": 0.4632, |
| "step": 3180816 |
| }, |
| { |
| "epoch": 33.0, |
| "eval_bleu": 46.5598, |
| "eval_gen_len": 73.8753, |
| "eval_loss": 0.5982452630996704, |
| "eval_runtime": 78.0544, |
| "eval_samples_per_second": 12.427, |
| "eval_steps_per_second": 0.397, |
| "step": 3180816 |
| }, |
| { |
| "epoch": 34.0, |
| "learning_rate": 3.280262784911128e-05, |
| "loss": 0.461, |
| "step": 3276065 |
| }, |
| { |
| "epoch": 34.0, |
| "eval_bleu": 46.503, |
| "eval_gen_len": 73.9577, |
| "eval_loss": 0.5941172242164612, |
| "eval_runtime": 77.6074, |
| "eval_samples_per_second": 12.499, |
| "eval_steps_per_second": 0.399, |
| "step": 3276065 |
| }, |
| { |
| "epoch": 35.0, |
| "learning_rate": 3.230262784911128e-05, |
| "loss": 0.459, |
| "step": 3371314 |
| }, |
| { |
| "epoch": 35.0, |
| "eval_bleu": 47.3154, |
| "eval_gen_len": 74.0649, |
| "eval_loss": 0.598816990852356, |
| "eval_runtime": 79.9962, |
| "eval_samples_per_second": 12.126, |
| "eval_steps_per_second": 0.388, |
| "step": 3371314 |
| } |
| ], |
| "max_steps": 9524900, |
| "num_train_epochs": 100, |
| "total_flos": 1.0411885225994306e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
