| { | |
| "best_metric": 1.3940773010253906, | |
| "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000", | |
| "epoch": 49.999663186258, | |
| "eval_steps": 750, | |
| "global_step": 37100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "step": 742, | |
| "total_flos": 3.211629347340288e+16, | |
| "train_loss": 5.698867345434636, | |
| "train_runtime": 6114.1675, | |
| "train_samples_per_second": 15.538, | |
| "train_steps_per_second": 0.121 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.9989218328840974e-05, | |
| "loss": 10.3965, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 9.694682121276855, | |
| "eval_runtime": 84.6491, | |
| "eval_samples_per_second": 59.067, | |
| "eval_steps_per_second": 0.933, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.897978436657682e-05, | |
| "loss": 4.9343, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 3.2859976291656494, | |
| "eval_runtime": 84.3631, | |
| "eval_samples_per_second": 59.268, | |
| "eval_steps_per_second": 0.936, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.796900269541779e-05, | |
| "loss": 2.8798, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.4815261363983154, | |
| "eval_runtime": 84.3896, | |
| "eval_samples_per_second": 59.249, | |
| "eval_steps_per_second": 0.936, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.6958221024258764e-05, | |
| "loss": 2.1885, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 1.9960429668426514, | |
| "eval_runtime": 84.3112, | |
| "eval_samples_per_second": 59.304, | |
| "eval_steps_per_second": 0.937, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 4.594743935309973e-05, | |
| "loss": 1.7594, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 1.7031219005584717, | |
| "eval_runtime": 84.3933, | |
| "eval_samples_per_second": 59.246, | |
| "eval_steps_per_second": 0.936, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 4.4936657681940705e-05, | |
| "loss": 1.4881, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 1.558716893196106, | |
| "eval_runtime": 84.4241, | |
| "eval_samples_per_second": 59.225, | |
| "eval_steps_per_second": 0.936, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 4.392587601078167e-05, | |
| "loss": 1.2897, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 1.5603703260421753, | |
| "eval_runtime": 84.4569, | |
| "eval_samples_per_second": 59.202, | |
| "eval_steps_per_second": 0.935, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.8989218328840976e-05, | |
| "loss": 3.6553, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "eval_loss": 2.3138411045074463, | |
| "eval_runtime": 85.1227, | |
| "eval_samples_per_second": 58.739, | |
| "eval_steps_per_second": 0.928, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 1.8488, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 1.7765036821365356, | |
| "eval_runtime": 84.6118, | |
| "eval_samples_per_second": 59.093, | |
| "eval_steps_per_second": 0.934, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 1.4372, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 1.5598968267440796, | |
| "eval_runtime": 84.6222, | |
| "eval_samples_per_second": 59.086, | |
| "eval_steps_per_second": 0.934, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 4.595822102425876e-05, | |
| "loss": 1.2011, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "eval_loss": 1.4957914352416992, | |
| "eval_runtime": 84.6871, | |
| "eval_samples_per_second": 59.041, | |
| "eval_steps_per_second": 0.933, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 4.4947439353099734e-05, | |
| "loss": 1.0493, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "eval_loss": 1.4617092609405518, | |
| "eval_runtime": 84.4178, | |
| "eval_samples_per_second": 59.229, | |
| "eval_steps_per_second": 0.936, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 4.39366576819407e-05, | |
| "loss": 0.922, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "eval_loss": 1.3600549697875977, | |
| "eval_runtime": 84.2691, | |
| "eval_samples_per_second": 59.334, | |
| "eval_steps_per_second": 0.937, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 4.949528301886793e-05, | |
| "loss": 3.0742, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "eval_loss": 2.005005359649658, | |
| "eval_runtime": 84.8703, | |
| "eval_samples_per_second": 58.913, | |
| "eval_steps_per_second": 0.931, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 4.898989218328841e-05, | |
| "loss": 1.4983, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "eval_loss": 1.668813705444336, | |
| "eval_runtime": 84.5947, | |
| "eval_samples_per_second": 59.105, | |
| "eval_steps_per_second": 0.934, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 4.84845013477089e-05, | |
| "loss": 1.1598, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "eval_loss": 1.5255405902862549, | |
| "eval_runtime": 84.5763, | |
| "eval_samples_per_second": 59.118, | |
| "eval_steps_per_second": 0.934, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "learning_rate": 4.7979110512129385e-05, | |
| "loss": 0.9732, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "eval_loss": 1.4376968145370483, | |
| "eval_runtime": 84.6742, | |
| "eval_samples_per_second": 59.05, | |
| "eval_steps_per_second": 0.933, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 4.7473719676549865e-05, | |
| "loss": 0.8466, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "eval_loss": 1.4253113269805908, | |
| "eval_runtime": 84.5693, | |
| "eval_samples_per_second": 59.123, | |
| "eval_steps_per_second": 0.934, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 0.7497, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "eval_loss": 1.3664312362670898, | |
| "eval_runtime": 84.6297, | |
| "eval_samples_per_second": 59.081, | |
| "eval_steps_per_second": 0.933, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 4.899056603773585e-05, | |
| "loss": 2.6343, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "eval_loss": 1.8943818807601929, | |
| "eval_runtime": 84.158, | |
| "eval_samples_per_second": 59.412, | |
| "eval_steps_per_second": 0.939, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 1.2528, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "eval_loss": 1.6253798007965088, | |
| "eval_runtime": 83.8622, | |
| "eval_samples_per_second": 59.622, | |
| "eval_steps_per_second": 0.942, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 0.9735, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "eval_loss": 1.4834989309310913, | |
| "eval_runtime": 83.8392, | |
| "eval_samples_per_second": 59.638, | |
| "eval_steps_per_second": 0.942, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "learning_rate": 4.595822102425876e-05, | |
| "loss": 0.8205, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "eval_loss": 1.4433954954147339, | |
| "eval_runtime": 83.8368, | |
| "eval_samples_per_second": 59.64, | |
| "eval_steps_per_second": 0.942, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.4947439353099734e-05, | |
| "loss": 0.7195, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "eval_loss": 1.3940773010253906, | |
| "eval_runtime": 83.833, | |
| "eval_samples_per_second": 59.642, | |
| "eval_steps_per_second": 0.942, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 4.3938005390835576e-05, | |
| "loss": 0.633, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "eval_loss": 1.443783164024353, | |
| "eval_runtime": 83.8619, | |
| "eval_samples_per_second": 59.622, | |
| "eval_steps_per_second": 0.942, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "learning_rate": 4.899056603773585e-05, | |
| "loss": 2.3512, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "eval_loss": 1.8179031610488892, | |
| "eval_runtime": 84.7172, | |
| "eval_samples_per_second": 59.02, | |
| "eval_steps_per_second": 0.933, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 27.29, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 1.1042, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 27.29, | |
| "eval_loss": 1.5888350009918213, | |
| "eval_runtime": 84.3483, | |
| "eval_samples_per_second": 59.278, | |
| "eval_steps_per_second": 0.937, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 0.8597, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "eval_loss": 1.5137015581130981, | |
| "eval_runtime": 84.2921, | |
| "eval_samples_per_second": 59.318, | |
| "eval_steps_per_second": 0.937, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 29.31, | |
| "learning_rate": 4.595822102425876e-05, | |
| "loss": 0.7273, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 29.31, | |
| "eval_loss": 1.4939533472061157, | |
| "eval_runtime": 84.3697, | |
| "eval_samples_per_second": 59.263, | |
| "eval_steps_per_second": 0.936, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "learning_rate": 4.4948787061994616e-05, | |
| "loss": 0.6283, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "eval_loss": 1.4074889421463013, | |
| "eval_runtime": 84.3283, | |
| "eval_samples_per_second": 59.292, | |
| "eval_steps_per_second": 0.937, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 31.33, | |
| "learning_rate": 4.3939353099730465e-05, | |
| "loss": 0.5533, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 31.33, | |
| "eval_loss": 1.4201693534851074, | |
| "eval_runtime": 84.3754, | |
| "eval_samples_per_second": 59.259, | |
| "eval_steps_per_second": 0.936, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 4.899056603773585e-05, | |
| "loss": 2.2264, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "eval_loss": 1.830324649810791, | |
| "eval_runtime": 84.4012, | |
| "eval_samples_per_second": 59.241, | |
| "eval_steps_per_second": 0.936, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 33.36, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 1.0061, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 33.36, | |
| "eval_loss": 1.585161566734314, | |
| "eval_runtime": 84.0634, | |
| "eval_samples_per_second": 59.479, | |
| "eval_steps_per_second": 0.94, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 0.7859, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "eval_loss": 1.5000197887420654, | |
| "eval_runtime": 83.979, | |
| "eval_samples_per_second": 59.539, | |
| "eval_steps_per_second": 0.941, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 4.595956873315364e-05, | |
| "loss": 0.6611, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "eval_loss": 1.4847756624221802, | |
| "eval_runtime": 84.066, | |
| "eval_samples_per_second": 59.477, | |
| "eval_steps_per_second": 0.94, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 4.4948787061994616e-05, | |
| "loss": 0.571, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "eval_loss": 1.4602794647216797, | |
| "eval_runtime": 84.1634, | |
| "eval_samples_per_second": 59.408, | |
| "eval_steps_per_second": 0.939, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 37.4, | |
| "learning_rate": 4.3938005390835576e-05, | |
| "loss": 0.5044, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 37.4, | |
| "eval_loss": 1.4159477949142456, | |
| "eval_runtime": 84.0529, | |
| "eval_samples_per_second": 59.486, | |
| "eval_steps_per_second": 0.94, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 38.41, | |
| "learning_rate": 4.899056603773585e-05, | |
| "loss": 2.0783, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 38.41, | |
| "eval_loss": 1.7679896354675293, | |
| "eval_runtime": 85.4608, | |
| "eval_samples_per_second": 58.506, | |
| "eval_steps_per_second": 0.924, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 39.42, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 0.9177, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 39.42, | |
| "eval_loss": 1.6010451316833496, | |
| "eval_runtime": 85.1034, | |
| "eval_samples_per_second": 58.752, | |
| "eval_steps_per_second": 0.928, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 4.696900269541779e-05, | |
| "loss": 0.7137, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "eval_loss": 1.4925891160964966, | |
| "eval_runtime": 85.1688, | |
| "eval_samples_per_second": 58.707, | |
| "eval_steps_per_second": 0.928, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 41.44, | |
| "learning_rate": 4.595956873315364e-05, | |
| "loss": 0.596, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 41.44, | |
| "eval_loss": 1.5095667839050293, | |
| "eval_runtime": 85.1603, | |
| "eval_samples_per_second": 58.713, | |
| "eval_steps_per_second": 0.928, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "learning_rate": 4.4948787061994616e-05, | |
| "loss": 0.5146, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "eval_loss": 1.4808692932128906, | |
| "eval_runtime": 85.1817, | |
| "eval_samples_per_second": 58.698, | |
| "eval_steps_per_second": 0.927, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 43.46, | |
| "learning_rate": 4.3938005390835576e-05, | |
| "loss": 0.4453, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 43.46, | |
| "eval_loss": 1.5037322044372559, | |
| "eval_runtime": 85.2811, | |
| "eval_samples_per_second": 58.63, | |
| "eval_steps_per_second": 0.926, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "learning_rate": 4.949528301886793e-05, | |
| "loss": 2.0138, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "eval_loss": 1.798643708229065, | |
| "eval_runtime": 84.6945, | |
| "eval_samples_per_second": 59.036, | |
| "eval_steps_per_second": 0.933, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 45.48, | |
| "learning_rate": 4.898989218328841e-05, | |
| "loss": 0.8625, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 45.48, | |
| "eval_loss": 1.6345179080963135, | |
| "eval_runtime": 84.4707, | |
| "eval_samples_per_second": 59.192, | |
| "eval_steps_per_second": 0.935, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 46.49, | |
| "learning_rate": 4.848517520215634e-05, | |
| "loss": 0.6724, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 46.49, | |
| "eval_loss": 1.5662704706192017, | |
| "eval_runtime": 84.3899, | |
| "eval_samples_per_second": 59.249, | |
| "eval_steps_per_second": 0.936, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 47.51, | |
| "learning_rate": 4.7979784366576826e-05, | |
| "loss": 0.5584, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 47.51, | |
| "eval_loss": 1.5644365549087524, | |
| "eval_runtime": 84.4556, | |
| "eval_samples_per_second": 59.203, | |
| "eval_steps_per_second": 0.935, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "learning_rate": 4.7474393530997306e-05, | |
| "loss": 0.4816, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "eval_loss": 1.5659728050231934, | |
| "eval_runtime": 84.3909, | |
| "eval_samples_per_second": 59.248, | |
| "eval_steps_per_second": 0.936, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 49.53, | |
| "learning_rate": 4.6969676549865234e-05, | |
| "loss": 0.4128, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 49.53, | |
| "eval_loss": 1.4841716289520264, | |
| "eval_runtime": 84.3983, | |
| "eval_samples_per_second": 59.243, | |
| "eval_steps_per_second": 0.936, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 37100, | |
| "total_flos": 1.60568482342699e+18, | |
| "train_loss": 0.02558288409703504, | |
| "train_runtime": 2894.6287, | |
| "train_samples_per_second": 1640.97, | |
| "train_steps_per_second": 12.817 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 37100, | |
| "total_flos": 1.60568482342699e+18, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.9442, | |
| "train_samples_per_second": 2443166.931, | |
| "train_steps_per_second": 19082.42 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 37100, | |
| "total_flos": 1.60568482342699e+18, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.9174, | |
| "train_samples_per_second": 2477257.733, | |
| "train_steps_per_second": 19348.687 | |
| } | |
| ], | |
| "logging_steps": 750, | |
| "max_steps": 37100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 750, | |
| "total_flos": 1.60568482342699e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |