| { | |
| "best_metric": 1.3336918354034424, | |
| "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-44000", | |
| "epoch": 9.803921568627452, | |
| "eval_steps": 500, | |
| "global_step": 44500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9833333333333335e-05, | |
| "loss": 4.6196, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 3.7452237606048584, | |
| "eval_runtime": 43.586, | |
| "eval_samples_per_second": 208.278, | |
| "eval_steps_per_second": 13.032, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9666666666666666e-05, | |
| "loss": 3.5915, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 3.2064383029937744, | |
| "eval_runtime": 43.0726, | |
| "eval_samples_per_second": 210.76, | |
| "eval_steps_per_second": 13.187, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.95e-05, | |
| "loss": 3.1484, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.8919074535369873, | |
| "eval_runtime": 42.8255, | |
| "eval_samples_per_second": 211.977, | |
| "eval_steps_per_second": 13.263, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.9333333333333333e-05, | |
| "loss": 2.902, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.679006338119507, | |
| "eval_runtime": 43.6162, | |
| "eval_samples_per_second": 208.134, | |
| "eval_steps_per_second": 13.023, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.916666666666667e-05, | |
| "loss": 2.7296, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.5206823348999023, | |
| "eval_runtime": 42.8291, | |
| "eval_samples_per_second": 211.959, | |
| "eval_steps_per_second": 13.262, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.9000333333333335e-05, | |
| "loss": 2.6105, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.394014835357666, | |
| "eval_runtime": 42.8022, | |
| "eval_samples_per_second": 212.092, | |
| "eval_steps_per_second": 13.27, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.883366666666667e-05, | |
| "loss": 2.5068, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 2.30385422706604, | |
| "eval_runtime": 44.6981, | |
| "eval_samples_per_second": 203.096, | |
| "eval_steps_per_second": 12.707, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.8667000000000003e-05, | |
| "loss": 2.3848, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.2251899242401123, | |
| "eval_runtime": 42.8042, | |
| "eval_samples_per_second": 212.082, | |
| "eval_steps_per_second": 13.27, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.8500333333333337e-05, | |
| "loss": 2.3391, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.148716449737549, | |
| "eval_runtime": 43.0552, | |
| "eval_samples_per_second": 210.845, | |
| "eval_steps_per_second": 13.192, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.8334e-05, | |
| "loss": 2.1994, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 2.091869354248047, | |
| "eval_runtime": 43.5857, | |
| "eval_samples_per_second": 208.279, | |
| "eval_steps_per_second": 13.032, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.8167333333333335e-05, | |
| "loss": 2.1446, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 2.0449471473693848, | |
| "eval_runtime": 43.2545, | |
| "eval_samples_per_second": 209.874, | |
| "eval_steps_per_second": 13.132, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.800066666666667e-05, | |
| "loss": 2.1012, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 2.0015575885772705, | |
| "eval_runtime": 43.2116, | |
| "eval_samples_per_second": 210.083, | |
| "eval_steps_per_second": 13.145, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.7834000000000002e-05, | |
| "loss": 2.0542, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.951575517654419, | |
| "eval_runtime": 43.3919, | |
| "eval_samples_per_second": 209.209, | |
| "eval_steps_per_second": 13.09, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.7667333333333333e-05, | |
| "loss": 2.0216, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.9161829948425293, | |
| "eval_runtime": 43.6948, | |
| "eval_samples_per_second": 207.759, | |
| "eval_steps_per_second": 12.999, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.7500666666666667e-05, | |
| "loss": 1.9926, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 1.8790709972381592, | |
| "eval_runtime": 44.1328, | |
| "eval_samples_per_second": 205.698, | |
| "eval_steps_per_second": 12.87, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.7334e-05, | |
| "loss": 1.9278, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.845486044883728, | |
| "eval_runtime": 44.2649, | |
| "eval_samples_per_second": 205.084, | |
| "eval_steps_per_second": 12.832, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.7167333333333334e-05, | |
| "loss": 1.9305, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.8124595880508423, | |
| "eval_runtime": 43.561, | |
| "eval_samples_per_second": 208.398, | |
| "eval_steps_per_second": 13.039, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.7000666666666668e-05, | |
| "loss": 1.905, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 1.7888203859329224, | |
| "eval_runtime": 43.4924, | |
| "eval_samples_per_second": 208.726, | |
| "eval_steps_per_second": 13.06, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.6834666666666667e-05, | |
| "loss": 1.828, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 1.7763384580612183, | |
| "eval_runtime": 43.5326, | |
| "eval_samples_per_second": 208.534, | |
| "eval_steps_per_second": 13.048, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6668e-05, | |
| "loss": 1.808, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 1.7431403398513794, | |
| "eval_runtime": 43.6327, | |
| "eval_samples_per_second": 208.055, | |
| "eval_steps_per_second": 13.018, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.6501333333333334e-05, | |
| "loss": 1.7434, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 1.7204526662826538, | |
| "eval_runtime": 44.0612, | |
| "eval_samples_per_second": 206.032, | |
| "eval_steps_per_second": 12.891, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.6334666666666668e-05, | |
| "loss": 1.7527, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 1.7068791389465332, | |
| "eval_runtime": 43.4892, | |
| "eval_samples_per_second": 208.741, | |
| "eval_steps_per_second": 13.061, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.6168333333333336e-05, | |
| "loss": 1.6977, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.6881217956542969, | |
| "eval_runtime": 43.1769, | |
| "eval_samples_per_second": 210.252, | |
| "eval_steps_per_second": 13.155, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.600166666666667e-05, | |
| "loss": 1.6854, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 1.6784749031066895, | |
| "eval_runtime": 42.7581, | |
| "eval_samples_per_second": 212.311, | |
| "eval_steps_per_second": 13.284, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.5835e-05, | |
| "loss": 1.6603, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 1.6570212841033936, | |
| "eval_runtime": 42.6669, | |
| "eval_samples_per_second": 212.765, | |
| "eval_steps_per_second": 13.312, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.5668333333333334e-05, | |
| "loss": 1.6725, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 1.6376469135284424, | |
| "eval_runtime": 43.1686, | |
| "eval_samples_per_second": 210.292, | |
| "eval_steps_per_second": 13.158, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.5501666666666668e-05, | |
| "loss": 1.6384, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 1.6240772008895874, | |
| "eval_runtime": 43.2327, | |
| "eval_samples_per_second": 209.98, | |
| "eval_steps_per_second": 13.138, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.5335e-05, | |
| "loss": 1.5917, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 1.6128900051116943, | |
| "eval_runtime": 42.9712, | |
| "eval_samples_per_second": 211.258, | |
| "eval_steps_per_second": 13.218, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.5168333333333334e-05, | |
| "loss": 1.591, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 1.6054280996322632, | |
| "eval_runtime": 43.0919, | |
| "eval_samples_per_second": 210.666, | |
| "eval_steps_per_second": 13.181, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1.5001666666666667e-05, | |
| "loss": 1.5936, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 1.5842323303222656, | |
| "eval_runtime": 43.5874, | |
| "eval_samples_per_second": 208.271, | |
| "eval_steps_per_second": 13.031, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.4835000000000001e-05, | |
| "loss": 1.6031, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 1.5732085704803467, | |
| "eval_runtime": 42.6594, | |
| "eval_samples_per_second": 212.802, | |
| "eval_steps_per_second": 13.315, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.4668666666666669e-05, | |
| "loss": 1.554, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_loss": 1.5651994943618774, | |
| "eval_runtime": 42.8927, | |
| "eval_samples_per_second": 211.645, | |
| "eval_steps_per_second": 13.242, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.4502000000000001e-05, | |
| "loss": 1.5284, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 1.5577419996261597, | |
| "eval_runtime": 43.6635, | |
| "eval_samples_per_second": 207.908, | |
| "eval_steps_per_second": 13.009, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.4335666666666667e-05, | |
| "loss": 1.5219, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 1.544019103050232, | |
| "eval_runtime": 43.4005, | |
| "eval_samples_per_second": 209.168, | |
| "eval_steps_per_second": 13.087, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.4169000000000001e-05, | |
| "loss": 1.5173, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 1.5335613489151, | |
| "eval_runtime": 43.512, | |
| "eval_samples_per_second": 208.632, | |
| "eval_steps_per_second": 13.054, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.4002333333333335e-05, | |
| "loss": 1.4781, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 1.5262504816055298, | |
| "eval_runtime": 43.3365, | |
| "eval_samples_per_second": 209.477, | |
| "eval_steps_per_second": 13.107, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.3835666666666667e-05, | |
| "loss": 1.4771, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_loss": 1.519882082939148, | |
| "eval_runtime": 43.8272, | |
| "eval_samples_per_second": 207.132, | |
| "eval_steps_per_second": 12.96, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 1.3669e-05, | |
| "loss": 1.4613, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_loss": 1.5142260789871216, | |
| "eval_runtime": 43.3978, | |
| "eval_samples_per_second": 209.181, | |
| "eval_steps_per_second": 13.088, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 1.3502333333333335e-05, | |
| "loss": 1.452, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_loss": 1.503504753112793, | |
| "eval_runtime": 43.2384, | |
| "eval_samples_per_second": 209.952, | |
| "eval_steps_per_second": 13.136, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1.3335666666666667e-05, | |
| "loss": 1.4563, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 1.495379090309143, | |
| "eval_runtime": 43.6248, | |
| "eval_samples_per_second": 208.093, | |
| "eval_steps_per_second": 13.02, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1.3169e-05, | |
| "loss": 1.46, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_loss": 1.4834085702896118, | |
| "eval_runtime": 43.9437, | |
| "eval_samples_per_second": 206.583, | |
| "eval_steps_per_second": 12.926, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1.3002333333333334e-05, | |
| "loss": 1.4284, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 1.4811300039291382, | |
| "eval_runtime": 43.2207, | |
| "eval_samples_per_second": 210.038, | |
| "eval_steps_per_second": 13.142, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.2836000000000002e-05, | |
| "loss": 1.4527, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 1.4702121019363403, | |
| "eval_runtime": 43.7967, | |
| "eval_samples_per_second": 207.276, | |
| "eval_steps_per_second": 12.969, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.2669333333333334e-05, | |
| "loss": 1.4375, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 1.4648058414459229, | |
| "eval_runtime": 43.2759, | |
| "eval_samples_per_second": 209.77, | |
| "eval_steps_per_second": 13.125, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 1.2502666666666668e-05, | |
| "loss": 1.4093, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_loss": 1.452415108680725, | |
| "eval_runtime": 43.4383, | |
| "eval_samples_per_second": 208.986, | |
| "eval_steps_per_second": 13.076, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.2336000000000002e-05, | |
| "loss": 1.3688, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_loss": 1.4525853395462036, | |
| "eval_runtime": 44.7597, | |
| "eval_samples_per_second": 202.816, | |
| "eval_steps_per_second": 12.69, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 1.2169333333333336e-05, | |
| "loss": 1.3704, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "eval_loss": 1.4470324516296387, | |
| "eval_runtime": 45.0353, | |
| "eval_samples_per_second": 201.575, | |
| "eval_steps_per_second": 12.612, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 1.2003e-05, | |
| "loss": 1.3672, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "eval_loss": 1.4429727792739868, | |
| "eval_runtime": 48.0671, | |
| "eval_samples_per_second": 188.861, | |
| "eval_steps_per_second": 11.817, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 1.1836333333333334e-05, | |
| "loss": 1.3484, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "eval_loss": 1.4372690916061401, | |
| "eval_runtime": 45.4091, | |
| "eval_samples_per_second": 199.916, | |
| "eval_steps_per_second": 12.508, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 1.1669666666666668e-05, | |
| "loss": 1.3446, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "eval_loss": 1.4315961599349976, | |
| "eval_runtime": 44.7878, | |
| "eval_samples_per_second": 202.689, | |
| "eval_steps_per_second": 12.682, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1.1503000000000002e-05, | |
| "loss": 1.3445, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_loss": 1.4315000772476196, | |
| "eval_runtime": 45.134, | |
| "eval_samples_per_second": 201.134, | |
| "eval_steps_per_second": 12.585, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1.1336333333333334e-05, | |
| "loss": 1.3236, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 1.424834132194519, | |
| "eval_runtime": 44.2677, | |
| "eval_samples_per_second": 205.07, | |
| "eval_steps_per_second": 12.831, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 1.1169666666666667e-05, | |
| "loss": 1.3061, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "eval_loss": 1.4215062856674194, | |
| "eval_runtime": 44.2542, | |
| "eval_samples_per_second": 205.133, | |
| "eval_steps_per_second": 12.835, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 1.1003000000000001e-05, | |
| "loss": 1.3083, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_loss": 1.4195761680603027, | |
| "eval_runtime": 44.381, | |
| "eval_samples_per_second": 204.547, | |
| "eval_steps_per_second": 12.798, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.0836333333333333e-05, | |
| "loss": 1.2689, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.4157874584197998, | |
| "eval_runtime": 44.2987, | |
| "eval_samples_per_second": 204.927, | |
| "eval_steps_per_second": 12.822, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 1.0669666666666667e-05, | |
| "loss": 1.2813, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "eval_loss": 1.4157196283340454, | |
| "eval_runtime": 44.6759, | |
| "eval_samples_per_second": 203.197, | |
| "eval_steps_per_second": 12.714, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.0503333333333335e-05, | |
| "loss": 1.2863, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "eval_loss": 1.41006338596344, | |
| "eval_runtime": 44.666, | |
| "eval_samples_per_second": 203.242, | |
| "eval_steps_per_second": 12.717, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.0336666666666669e-05, | |
| "loss": 1.2668, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "eval_loss": 1.403244972229004, | |
| "eval_runtime": 44.6624, | |
| "eval_samples_per_second": 203.258, | |
| "eval_steps_per_second": 12.718, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.017e-05, | |
| "loss": 1.2631, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_loss": 1.4050610065460205, | |
| "eval_runtime": 44.987, | |
| "eval_samples_per_second": 201.792, | |
| "eval_steps_per_second": 12.626, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 1.0003333333333333e-05, | |
| "loss": 1.2543, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "eval_loss": 1.3968815803527832, | |
| "eval_runtime": 45.3856, | |
| "eval_samples_per_second": 200.019, | |
| "eval_steps_per_second": 12.515, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 9.836666666666668e-06, | |
| "loss": 1.2552, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "eval_loss": 1.3993921279907227, | |
| "eval_runtime": 44.6433, | |
| "eval_samples_per_second": 203.345, | |
| "eval_steps_per_second": 12.723, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 9.67e-06, | |
| "loss": 1.2626, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "eval_loss": 1.387181043624878, | |
| "eval_runtime": 44.4948, | |
| "eval_samples_per_second": 204.024, | |
| "eval_steps_per_second": 12.766, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 9.503333333333334e-06, | |
| "loss": 1.2396, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_loss": 1.3914097547531128, | |
| "eval_runtime": 44.936, | |
| "eval_samples_per_second": 202.021, | |
| "eval_steps_per_second": 12.64, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 9.336666666666666e-06, | |
| "loss": 1.2419, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "eval_loss": 1.3853869438171387, | |
| "eval_runtime": 44.4747, | |
| "eval_samples_per_second": 204.116, | |
| "eval_steps_per_second": 12.771, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 9.17e-06, | |
| "loss": 1.2421, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "eval_loss": 1.3801844120025635, | |
| "eval_runtime": 44.8621, | |
| "eval_samples_per_second": 202.353, | |
| "eval_steps_per_second": 12.661, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 9.003333333333334e-06, | |
| "loss": 1.2177, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "eval_loss": 1.380096673965454, | |
| "eval_runtime": 45.1593, | |
| "eval_samples_per_second": 201.022, | |
| "eval_steps_per_second": 12.578, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 8.836666666666668e-06, | |
| "loss": 1.2292, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_loss": 1.3730745315551758, | |
| "eval_runtime": 44.6177, | |
| "eval_samples_per_second": 203.462, | |
| "eval_steps_per_second": 12.73, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.67e-06, | |
| "loss": 1.2131, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_loss": 1.370631217956543, | |
| "eval_runtime": 45.0076, | |
| "eval_samples_per_second": 201.699, | |
| "eval_steps_per_second": 12.62, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 8.503666666666668e-06, | |
| "loss": 1.227, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "eval_loss": 1.3661019802093506, | |
| "eval_runtime": 44.9507, | |
| "eval_samples_per_second": 201.955, | |
| "eval_steps_per_second": 12.636, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 8.337e-06, | |
| "loss": 1.2158, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_loss": 1.3633307218551636, | |
| "eval_runtime": 44.5235, | |
| "eval_samples_per_second": 203.892, | |
| "eval_steps_per_second": 12.757, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 8.170333333333334e-06, | |
| "loss": 1.2194, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "eval_loss": 1.3616106510162354, | |
| "eval_runtime": 45.4373, | |
| "eval_samples_per_second": 199.792, | |
| "eval_steps_per_second": 12.501, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 8.004e-06, | |
| "loss": 1.2261, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "eval_loss": 1.357163429260254, | |
| "eval_runtime": 45.4325, | |
| "eval_samples_per_second": 199.813, | |
| "eval_steps_per_second": 12.502, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 7.837666666666666e-06, | |
| "loss": 1.218, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_loss": 1.3611406087875366, | |
| "eval_runtime": 44.5114, | |
| "eval_samples_per_second": 203.948, | |
| "eval_steps_per_second": 12.761, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 7.671e-06, | |
| "loss": 1.1658, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_loss": 1.356821060180664, | |
| "eval_runtime": 44.6544, | |
| "eval_samples_per_second": 203.295, | |
| "eval_steps_per_second": 12.72, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 7.504333333333334e-06, | |
| "loss": 1.1652, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_loss": 1.35381281375885, | |
| "eval_runtime": 45.0638, | |
| "eval_samples_per_second": 201.448, | |
| "eval_steps_per_second": 12.604, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 7.3376666666666675e-06, | |
| "loss": 1.1686, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "eval_loss": 1.3533384799957275, | |
| "eval_runtime": 44.2795, | |
| "eval_samples_per_second": 205.016, | |
| "eval_steps_per_second": 12.828, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.1710000000000005e-06, | |
| "loss": 1.1666, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "eval_loss": 1.3513332605361938, | |
| "eval_runtime": 44.2333, | |
| "eval_samples_per_second": 205.23, | |
| "eval_steps_per_second": 12.841, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 7.004333333333334e-06, | |
| "loss": 1.1827, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 1.3496123552322388, | |
| "eval_runtime": 44.8817, | |
| "eval_samples_per_second": 202.265, | |
| "eval_steps_per_second": 12.655, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.837666666666667e-06, | |
| "loss": 1.1643, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_loss": 1.3474962711334229, | |
| "eval_runtime": 44.7028, | |
| "eval_samples_per_second": 203.074, | |
| "eval_steps_per_second": 12.706, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 6.671000000000001e-06, | |
| "loss": 1.1651, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "eval_loss": 1.3451054096221924, | |
| "eval_runtime": 44.3384, | |
| "eval_samples_per_second": 204.743, | |
| "eval_steps_per_second": 12.811, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 6.504333333333334e-06, | |
| "loss": 1.1696, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_loss": 1.3412760496139526, | |
| "eval_runtime": 44.0851, | |
| "eval_samples_per_second": 205.92, | |
| "eval_steps_per_second": 12.884, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 6.337666666666668e-06, | |
| "loss": 1.1582, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 1.3448957204818726, | |
| "eval_runtime": 43.2139, | |
| "eval_samples_per_second": 210.071, | |
| "eval_steps_per_second": 13.144, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 6.171000000000001e-06, | |
| "loss": 1.152, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_loss": 1.3436229228973389, | |
| "eval_runtime": 43.5301, | |
| "eval_samples_per_second": 208.545, | |
| "eval_steps_per_second": 13.048, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 6.004666666666668e-06, | |
| "loss": 1.1177, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "eval_loss": 1.3422951698303223, | |
| "eval_runtime": 43.2428, | |
| "eval_samples_per_second": 209.931, | |
| "eval_steps_per_second": 13.135, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 5.838000000000001e-06, | |
| "loss": 1.1195, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_loss": 1.340394139289856, | |
| "eval_runtime": 43.8891, | |
| "eval_samples_per_second": 206.839, | |
| "eval_steps_per_second": 12.942, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 5.6713333333333345e-06, | |
| "loss": 1.1389, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_loss": 1.3390538692474365, | |
| "eval_runtime": 43.1572, | |
| "eval_samples_per_second": 210.347, | |
| "eval_steps_per_second": 13.161, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 5.5046666666666674e-06, | |
| "loss": 1.1316, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "eval_loss": 1.3349236249923706, | |
| "eval_runtime": 43.9132, | |
| "eval_samples_per_second": 206.726, | |
| "eval_steps_per_second": 12.935, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 5.3383333333333345e-06, | |
| "loss": 1.1376, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "eval_loss": 1.3336918354034424, | |
| "eval_runtime": 43.0007, | |
| "eval_samples_per_second": 211.113, | |
| "eval_steps_per_second": 13.209, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 5.171666666666667e-06, | |
| "loss": 1.1407, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 1.33429753780365, | |
| "eval_runtime": 43.2578, | |
| "eval_samples_per_second": 209.858, | |
| "eval_steps_per_second": 13.131, | |
| "step": 44500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 60000, | |
| "num_train_epochs": 14, | |
| "save_steps": 500, | |
| "total_flos": 4.509775151903539e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |