| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.964394532950291, | |
| "global_step": 100000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00010077565027123787, | |
| "loss": 0.4732, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00010075885246660077, | |
| "loss": 0.4445, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00010073086073069567, | |
| "loss": 0.4329, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001006916819700645, | |
| "loss": 0.4256, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001006414377109213, | |
| "loss": 0.421, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00010057993897463803, | |
| "loss": 0.4167, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010050729045131372, | |
| "loss": 0.4132, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00010042351006588448, | |
| "loss": 0.4107, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00010032861848990674, | |
| "loss": 0.4091, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001002228621438404, | |
| "loss": 0.4067, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.3877949118614197, | |
| "eval_runtime": 108.0468, | |
| "eval_samples_per_second": 46.276, | |
| "eval_steps_per_second": 0.731, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010010584325708389, | |
| "loss": 0.4038, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.997779155931062e-05, | |
| "loss": 0.402, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.983873864536092e-05, | |
| "loss": 0.401, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.968871882446063e-05, | |
| "loss": 0.4001, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.952776911175577e-05, | |
| "loss": 0.3987, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.935592921917959e-05, | |
| "loss": 0.3974, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.917361771757108e-05, | |
| "loss": 0.3954, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.898014889719868e-05, | |
| "loss": 0.3945, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.877592501404869e-05, | |
| "loss": 0.394, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.856099645730841e-05, | |
| "loss": 0.3926, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.37431180477142334, | |
| "eval_runtime": 106.4392, | |
| "eval_samples_per_second": 46.975, | |
| "eval_steps_per_second": 0.742, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.833541625738316e-05, | |
| "loss": 0.3929, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.809924007281187e-05, | |
| "loss": 0.3906, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.78525261765341e-05, | |
| "loss": 0.3899, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.759533544151208e-05, | |
| "loss": 0.3892, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.732773132571125e-05, | |
| "loss": 0.3889, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.705034604088048e-05, | |
| "loss": 0.3865, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.676213628592508e-05, | |
| "loss": 0.3865, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.64637187296151e-05, | |
| "loss": 0.3867, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.615516700201724e-05, | |
| "loss": 0.3858, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.583720443927501e-05, | |
| "loss": 0.3853, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.36506548523902893, | |
| "eval_runtime": 96.1419, | |
| "eval_samples_per_second": 52.006, | |
| "eval_steps_per_second": 0.822, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.550863512110018e-05, | |
| "loss": 0.3844, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.517016728422667e-05, | |
| "loss": 0.3834, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.482188444052858e-05, | |
| "loss": 0.3826, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.446387252358614e-05, | |
| "loss": 0.3824, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.40962198674828e-05, | |
| "loss": 0.3825, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.371901718501017e-05, | |
| "loss": 0.3804, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.333314023958391e-05, | |
| "loss": 0.3803, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.293713767144707e-05, | |
| "loss": 0.381, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.253187106312908e-05, | |
| "loss": 0.3793, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.211744040810141e-05, | |
| "loss": 0.3793, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.35968872904777527, | |
| "eval_runtime": 95.0235, | |
| "eval_samples_per_second": 52.619, | |
| "eval_steps_per_second": 0.831, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.169394796092694e-05, | |
| "loss": 0.4465, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.126149821203012e-05, | |
| "loss": 0.444, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.082019786191564e-05, | |
| "loss": 0.4435, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.037106452976014e-05, | |
| "loss": 0.4422, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.991240893598493e-05, | |
| "loss": 0.4446, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.944523560858406e-05, | |
| "loss": 0.4418, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.89696598155856e-05, | |
| "loss": 0.4412, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.848579889820028e-05, | |
| "loss": 0.4414, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.799377224186928e-05, | |
| "loss": 0.4407, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.749470933536528e-05, | |
| "loss": 0.4402, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.42174017429351807, | |
| "eval_runtime": 91.5901, | |
| "eval_samples_per_second": 54.591, | |
| "eval_steps_per_second": 0.863, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.698673310407346e-05, | |
| "loss": 0.4396, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 8.647096100588967e-05, | |
| "loss": 0.4381, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.594752029986149e-05, | |
| "loss": 0.4382, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.54165401371507e-05, | |
| "loss": 0.4386, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.487815152916725e-05, | |
| "loss": 0.4376, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.433248731524403e-05, | |
| "loss": 0.4361, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.377968212986092e-05, | |
| "loss": 0.4369, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.321987236942559e-05, | |
| "loss": 0.4367, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.265433627110443e-05, | |
| "loss": 0.4345, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.20809467414187e-05, | |
| "loss": 0.4349, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.41873496770858765, | |
| "eval_runtime": 67.332, | |
| "eval_samples_per_second": 74.259, | |
| "eval_steps_per_second": 1.173, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.150097177421913e-05, | |
| "loss": 0.4351, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.091455446965055e-05, | |
| "loss": 0.4346, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.032183951740807e-05, | |
| "loss": 0.4348, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 7.972417693488813e-05, | |
| "loss": 0.4339, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.911931879453039e-05, | |
| "loss": 0.4321, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 7.850860595403895e-05, | |
| "loss": 0.4327, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.789218909766887e-05, | |
| "loss": 0.432, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.727022031705582e-05, | |
| "loss": 0.432, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.664537309168187e-05, | |
| "loss": 0.4318, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.601278284364346e-05, | |
| "loss": 0.4311, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.4138348698616028, | |
| "eval_runtime": 71.9462, | |
| "eval_samples_per_second": 69.496, | |
| "eval_steps_per_second": 1.098, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.53751043867331e-05, | |
| "loss": 0.4304, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.473249505856825e-05, | |
| "loss": 0.43, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.408511341338508e-05, | |
| "loss": 0.4295, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.343311918291752e-05, | |
| "loss": 0.43, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.277667323698597e-05, | |
| "loss": 0.43, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.211593754380497e-05, | |
| "loss": 0.429, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.145107513002001e-05, | |
| "loss": 0.4289, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.078225004048314e-05, | |
| "loss": 0.4275, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.011097622316453e-05, | |
| "loss": 0.428, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.943472888404397e-05, | |
| "loss": 0.4275, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 0.4106511175632477, | |
| "eval_runtime": 94.0729, | |
| "eval_samples_per_second": 53.15, | |
| "eval_steps_per_second": 0.84, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.875501637243646e-05, | |
| "loss": 0.4269, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 6.807200639723347e-05, | |
| "loss": 0.4256, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 6.738586748092632e-05, | |
| "loss": 0.4273, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 6.669676891802565e-05, | |
| "loss": 0.4255, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.600626718034563e-05, | |
| "loss": 0.4255, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.531176515384238e-05, | |
| "loss": 0.4265, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 6.461621146309398e-05, | |
| "loss": 0.4257, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 6.39169899926586e-05, | |
| "loss": 0.4242, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 6.321566476924404e-05, | |
| "loss": 0.4236, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 6.2512408834355e-05, | |
| "loss": 0.4245, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 0.40728819370269775, | |
| "eval_runtime": 61.7603, | |
| "eval_samples_per_second": 80.958, | |
| "eval_steps_per_second": 1.279, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 6.180739570587037e-05, | |
| "loss": 0.4251, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 6.110079933523028e-05, | |
| "loss": 0.4228, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 6.039279406451614e-05, | |
| "loss": 0.4228, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 5.968355458343437e-05, | |
| "loss": 0.422, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 5.89732558862144e-05, | |
| "loss": 0.4224, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 5.826207322843129e-05, | |
| "loss": 0.4221, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 5.755160645640033e-05, | |
| "loss": 0.4215, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.6839183363622005e-05, | |
| "loss": 0.4212, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.612640286074268e-05, | |
| "loss": 0.4204, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.5413440815685914e-05, | |
| "loss": 0.4213, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.4042368531227112, | |
| "eval_runtime": 65.4775, | |
| "eval_samples_per_second": 76.362, | |
| "eval_steps_per_second": 1.207, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.4701898965206674e-05, | |
| "loss": 0.4199, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 5.398910105922212e-05, | |
| "loss": 0.4199, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 5.327807340052843e-05, | |
| "loss": 0.4194, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 5.25661416730201e-05, | |
| "loss": 0.4189, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 5.185490684450904e-05, | |
| "loss": 0.4188, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 5.114454440154674e-05, | |
| "loss": 0.4199, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 5.043522961543667e-05, | |
| "loss": 0.4186, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.972713749898855e-05, | |
| "loss": 0.418, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.902185464226454e-05, | |
| "loss": 0.419, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 4.831672833649923e-05, | |
| "loss": 0.418, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.40235766768455505, | |
| "eval_runtime": 50.0847, | |
| "eval_samples_per_second": 99.831, | |
| "eval_steps_per_second": 1.577, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 4.761334740888664e-05, | |
| "loss": 0.4173, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 4.691188540814576e-05, | |
| "loss": 0.4176, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.621391194692349e-05, | |
| "loss": 0.4166, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.551680180854116e-05, | |
| "loss": 0.4182, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.482212788828615e-05, | |
| "loss": 0.4169, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.413006158655363e-05, | |
| "loss": 0.4158, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.3440773660347955e-05, | |
| "loss": 0.4151, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.275443418115087e-05, | |
| "loss": 0.4146, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.207121249295896e-05, | |
| "loss": 0.4152, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.139127717050051e-05, | |
| "loss": 0.4143, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.39910149574279785, | |
| "eval_runtime": 73.8959, | |
| "eval_samples_per_second": 67.663, | |
| "eval_steps_per_second": 1.069, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 4.0714795977642255e-05, | |
| "loss": 0.4153, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.004327782200046e-05, | |
| "loss": 0.4146, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 3.937419699055001e-05, | |
| "loss": 0.4138, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 3.8709067973051936e-05, | |
| "loss": 0.4137, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 3.804805488013876e-05, | |
| "loss": 0.4131, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 3.739132080690021e-05, | |
| "loss": 0.4141, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 3.673902779264194e-05, | |
| "loss": 0.4123, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 3.609133678090475e-05, | |
| "loss": 0.4126, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 3.544840757975416e-05, | |
| "loss": 0.4124, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.481039882235021e-05, | |
| "loss": 0.4124, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 0.3964463174343109, | |
| "eval_runtime": 74.8784, | |
| "eval_samples_per_second": 66.775, | |
| "eval_steps_per_second": 1.055, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 3.4177467927807086e-05, | |
| "loss": 0.412, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.3549771062352226e-05, | |
| "loss": 0.4128, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.2928702236310036e-05, | |
| "loss": 0.411, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 3.231192548659413e-05, | |
| "loss": 0.4108, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 3.170084306064917e-05, | |
| "loss": 0.4106, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 3.1096810275663516e-05, | |
| "loss": 0.4112, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 3.0497555244481445e-05, | |
| "loss": 0.4106, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.9904442205778553e-05, | |
| "loss": 0.4106, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 2.9317617501322188e-05, | |
| "loss": 0.4104, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2.873722592132734e-05, | |
| "loss": 0.4096, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_loss": 0.3943169414997101, | |
| "eval_runtime": 90.0414, | |
| "eval_samples_per_second": 55.53, | |
| "eval_steps_per_second": 0.877, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.816341066873177e-05, | |
| "loss": 0.4098, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 2.75974407207991e-05, | |
| "loss": 0.4089, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 2.7037187352256104e-05, | |
| "loss": 0.4089, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 2.6483929770191072e-05, | |
| "loss": 0.4098, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.5937804482633846e-05, | |
| "loss": 0.4098, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 2.5400016613135313e-05, | |
| "loss": 0.4082, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.486854343481112e-05, | |
| "loss": 0.4086, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 2.4344601123401418e-05, | |
| "loss": 0.408, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.3828318953831648e-05, | |
| "loss": 0.409, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.3320833444621267e-05, | |
| "loss": 0.4079, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 0.39236390590667725, | |
| "eval_runtime": 57.2971, | |
| "eval_samples_per_second": 87.264, | |
| "eval_steps_per_second": 1.379, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 2.2820235842075488e-05, | |
| "loss": 0.4076, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.232767449569324e-05, | |
| "loss": 0.408, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 2.1843270937616385e-05, | |
| "loss": 0.4075, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 2.136808860049628e-05, | |
| "loss": 0.4075, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.090034022927794e-05, | |
| "loss": 0.4083, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 2.044110181973758e-05, | |
| "loss": 0.4072, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 1.9990486682081012e-05, | |
| "loss": 0.4066, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1.9549480970403115e-05, | |
| "loss": 0.4061, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 1.911642597471847e-05, | |
| "loss": 0.4062, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.869232109486083e-05, | |
| "loss": 0.4071, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_loss": 0.39048197865486145, | |
| "eval_runtime": 72.8664, | |
| "eval_samples_per_second": 68.619, | |
| "eval_steps_per_second": 1.084, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 1.8277270972363276e-05, | |
| "loss": 0.4063, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 1.787137801463301e-05, | |
| "loss": 0.4054, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 1.7474742369683822e-05, | |
| "loss": 0.4058, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.7087461901426146e-05, | |
| "loss": 0.4046, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 1.670963216552051e-05, | |
| "loss": 0.4057, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 1.634134638580067e-05, | |
| "loss": 0.4044, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.5982695431271973e-05, | |
| "loss": 0.4059, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.563514402048906e-05, | |
| "loss": 0.4044, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.52959863865947e-05, | |
| "loss": 0.4042, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 1.496672150482924e-05, | |
| "loss": 0.4046, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "eval_loss": 0.38925543427467346, | |
| "eval_runtime": 77.3103, | |
| "eval_samples_per_second": 64.674, | |
| "eval_steps_per_second": 1.022, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.4647430616375366e-05, | |
| "loss": 0.4042, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.433819250148215e-05, | |
| "loss": 0.4049, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 1.4039083460027203e-05, | |
| "loss": 0.4041, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.3750177292690856e-05, | |
| "loss": 0.4038, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.347154528274688e-05, | |
| "loss": 0.4047, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.3203782390038048e-05, | |
| "loss": 0.4036, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.2945881505195709e-05, | |
| "loss": 0.4044, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.2698453225696373e-05, | |
| "loss": 0.4045, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.2461558600765676e-05, | |
| "loss": 0.4031, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.2235256080607583e-05, | |
| "loss": 0.4026, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_loss": 0.3881285488605499, | |
| "eval_runtime": 133.2371, | |
| "eval_samples_per_second": 37.527, | |
| "eval_steps_per_second": 0.593, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.20196015019827e-05, | |
| "loss": 0.4036, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 1.1815047267485115e-05, | |
| "loss": 0.4037, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.162082400805151e-05, | |
| "loss": 0.4048, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 1.1437400292071077e-05, | |
| "loss": 0.4032, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.126482137660111e-05, | |
| "loss": 0.4032, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.1103129842906643e-05, | |
| "loss": 0.4029, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 1.0952365585954172e-05, | |
| "loss": 0.4023, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.0812565804568168e-05, | |
| "loss": 0.4027, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.0683764992252818e-05, | |
| "loss": 0.4022, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.0566219440353348e-05, | |
| "loss": 0.4027, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "eval_loss": 0.38710081577301025, | |
| "eval_runtime": 65.4468, | |
| "eval_samples_per_second": 76.398, | |
| "eval_steps_per_second": 1.207, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.0459487036725839e-05, | |
| "loss": 0.4031, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.0363840719071717e-05, | |
| "loss": 0.4023, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.0279462058166865e-05, | |
| "loss": 0.4025, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 1.0206033689125313e-05, | |
| "loss": 0.4028, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.0143753941878168e-05, | |
| "loss": 0.4023, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.0092638183021144e-05, | |
| "loss": 0.4019, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.0052699024602892e-05, | |
| "loss": 0.4014, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.0023946321013112e-05, | |
| "loss": 0.4018, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.0006411110358469e-05, | |
| "loss": 0.4024, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.0000027439232365e-05, | |
| "loss": 0.4024, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "eval_loss": 0.38628044724464417, | |
| "eval_runtime": 91.7648, | |
| "eval_samples_per_second": 54.487, | |
| "eval_steps_per_second": 0.861, | |
| "step": 100000 | |
| } | |
| ], | |
| "max_steps": 100000, | |
| "num_train_epochs": 9, | |
| "total_flos": 4.7098350596970145e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |