| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.788438098554762, | |
| "global_step": 75000, | |
| "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": 0.5268, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00010075885246660077, | |
| "loss": 0.5021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00010073086073069567, | |
| "loss": 0.4927, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001006916819700645, | |
| "loss": 0.4854, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00010064132585148025, | |
| "loss": 0.4834, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00010057980479956167, | |
| "loss": 0.4781, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010050713399370776, | |
| "loss": 0.4752, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00010042333136435246, | |
| "loss": 0.4725, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00010032881934692084, | |
| "loss": 0.4705, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001002228621438404, | |
| "loss": 0.4686, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.45014095306396484, | |
| "eval_runtime": 54.4029, | |
| "eval_samples_per_second": 91.907, | |
| "eval_steps_per_second": 1.452, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010010584325708389, | |
| "loss": 0.466, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.997779155931062e-05, | |
| "loss": 0.4638, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.983873864536092e-05, | |
| "loss": 0.4628, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.968871882446063e-05, | |
| "loss": 0.462, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.9528101893266e-05, | |
| "loss": 0.4628, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.935628373962941e-05, | |
| "loss": 0.4592, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.917361771757108e-05, | |
| "loss": 0.459, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.898014889719868e-05, | |
| "loss": 0.4576, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.877592501404869e-05, | |
| "loss": 0.4551, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.856099645730841e-05, | |
| "loss": 0.4551, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.43748965859413147, | |
| "eval_runtime": 115.0161, | |
| "eval_samples_per_second": 43.472, | |
| "eval_steps_per_second": 0.687, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.833541625738316e-05, | |
| "loss": 0.4543, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.809924007281187e-05, | |
| "loss": 0.4532, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.78525261765341e-05, | |
| "loss": 0.4529, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.759533544151208e-05, | |
| "loss": 0.4523, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.732827688303682e-05, | |
| "loss": 0.4506, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.705034604088048e-05, | |
| "loss": 0.4502, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.676213628592508e-05, | |
| "loss": 0.4493, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.64637187296151e-05, | |
| "loss": 0.449, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.615516700201724e-05, | |
| "loss": 0.448, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 9.583720443927501e-05, | |
| "loss": 0.4479, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.4363159239292145, | |
| "eval_runtime": 91.0649, | |
| "eval_samples_per_second": 54.906, | |
| "eval_steps_per_second": 0.868, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.550930216588928e-05, | |
| "loss": 0.4482, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.517085404351901e-05, | |
| "loss": 0.4455, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.48225907448766e-05, | |
| "loss": 0.4449, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.44645981987198e-05, | |
| "loss": 0.4454, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.409696473435264e-05, | |
| "loss": 0.4449, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.371978105983142e-05, | |
| "loss": 0.4436, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.333314023958391e-05, | |
| "loss": 0.4442, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.293713767144707e-05, | |
| "loss": 0.4429, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 9.25326907757735e-05, | |
| "loss": 0.4427, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 9.211827834753872e-05, | |
| "loss": 0.4428, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.4262467920780182, | |
| "eval_runtime": 57.1744, | |
| "eval_samples_per_second": 87.452, | |
| "eval_steps_per_second": 1.382, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.169565984405851e-05, | |
| "loss": 0.4442, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.126411941080688e-05, | |
| "loss": 0.4404, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.082376309845848e-05, | |
| "loss": 0.4418, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.037379052736644e-05, | |
| "loss": 0.44, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.991518638364486e-05, | |
| "loss": 0.4388, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.944806382100394e-05, | |
| "loss": 0.4389, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.897253809494634e-05, | |
| "loss": 0.4386, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.848872653432954e-05, | |
| "loss": 0.4373, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.799674851241666e-05, | |
| "loss": 0.438, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.749672541742298e-05, | |
| "loss": 0.4379, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.415912002325058, | |
| "eval_runtime": 93.156, | |
| "eval_samples_per_second": 53.673, | |
| "eval_steps_per_second": 0.848, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.698878062256518e-05, | |
| "loss": 0.4373, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 8.647407863447136e-05, | |
| "loss": 0.4359, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.595068355683772e-05, | |
| "loss": 0.4365, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.541974824203516e-05, | |
| "loss": 0.4344, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.488140369040804e-05, | |
| "loss": 0.4344, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.433578273041907e-05, | |
| "loss": 0.4349, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.378301998587581e-05, | |
| "loss": 0.4341, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.32232518427143e-05, | |
| "loss": 0.4346, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.26566164153479e-05, | |
| "loss": 0.433, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.208325351258954e-05, | |
| "loss": 0.4335, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.4103819727897644, | |
| "eval_runtime": 61.8163, | |
| "eval_samples_per_second": 80.885, | |
| "eval_steps_per_second": 1.278, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.150330460315606e-05, | |
| "loss": 0.4323, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.091691278076293e-05, | |
| "loss": 0.4309, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.032541429761075e-05, | |
| "loss": 0.4322, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 7.972658441054002e-05, | |
| "loss": 0.4309, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.912174998963153e-05, | |
| "loss": 0.4309, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 7.851106026872828e-05, | |
| "loss": 0.4299, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.789466592638097e-05, | |
| "loss": 0.4299, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.727271904867026e-05, | |
| "loss": 0.4292, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.664537309168187e-05, | |
| "loss": 0.4303, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.601405315441079e-05, | |
| "loss": 0.4293, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.407795786857605, | |
| "eval_runtime": 90.2448, | |
| "eval_samples_per_second": 55.405, | |
| "eval_steps_per_second": 0.875, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.537638471730726e-05, | |
| "loss": 0.4278, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.473378509304684e-05, | |
| "loss": 0.4286, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.408641283347138e-05, | |
| "loss": 0.4277, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.343442766799908e-05, | |
| "loss": 0.4275, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.27779904642137e-05, | |
| "loss": 0.4286, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.211858881603193e-05, | |
| "loss": 0.4275, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.145507628573625e-05, | |
| "loss": 0.4287, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.078627448111401e-05, | |
| "loss": 0.4272, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.011367403035232e-05, | |
| "loss": 0.427, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 6.943744088754813e-05, | |
| "loss": 0.4259, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 0.40401768684387207, | |
| "eval_runtime": 110.3924, | |
| "eval_samples_per_second": 45.293, | |
| "eval_steps_per_second": 0.716, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.875910464865927e-05, | |
| "loss": 0.4267, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 6.807611395649667e-05, | |
| "loss": 0.4258, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 6.73899933097511e-05, | |
| "loss": 0.4242, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 6.670091199842552e-05, | |
| "loss": 0.4243, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.600904004302253e-05, | |
| "loss": 0.4238, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.531454815259442e-05, | |
| "loss": 0.4244, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 6.461760768262325e-05, | |
| "loss": 0.4245, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 6.391839059274147e-05, | |
| "loss": 0.4226, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 6.321706940430336e-05, | |
| "loss": 0.4226, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 6.251522547425089e-05, | |
| "loss": 0.4211, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 0.40038520097732544, | |
| "eval_runtime": 61.219, | |
| "eval_samples_per_second": 81.674, | |
| "eval_steps_per_second": 1.29, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 6.181021902830414e-05, | |
| "loss": 0.4206, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 6.110362864358936e-05, | |
| "loss": 0.4223, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 6.039562866071103e-05, | |
| "loss": 0.4216, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 5.9686393768070895e-05, | |
| "loss": 0.4202, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 5.897609895876622e-05, | |
| "loss": 0.4201, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 5.826491948741281e-05, | |
| "loss": 0.4208, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 5.7554455195272715e-05, | |
| "loss": 0.4202, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.684203388517376e-05, | |
| "loss": 0.4197, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.6129254461650316e-05, | |
| "loss": 0.4205, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 5.541629279235954e-05, | |
| "loss": 0.4191, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.3981700539588928, | |
| "eval_runtime": 118.5137, | |
| "eval_samples_per_second": 42.189, | |
| "eval_steps_per_second": 0.667, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.470332478992507e-05, | |
| "loss": 0.419, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 5.399052636853316e-05, | |
| "loss": 0.4188, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 5.327807340052843e-05, | |
| "loss": 0.4188, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 5.256756489949676e-05, | |
| "loss": 0.4184, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 5.18563285019876e-05, | |
| "loss": 0.4178, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 5.114596413925449e-05, | |
| "loss": 0.4169, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 5.0436647083074565e-05, | |
| "loss": 0.4176, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.972855234681767e-05, | |
| "loss": 0.4171, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.902185464226454e-05, | |
| "loss": 0.4171, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 4.831672833649923e-05, | |
| "loss": 0.4167, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.39512524008750916, | |
| "eval_runtime": 60.7929, | |
| "eval_samples_per_second": 82.246, | |
| "eval_steps_per_second": 1.299, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 4.761334740888664e-05, | |
| "loss": 0.4157, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 4.691188540814576e-05, | |
| "loss": 0.4145, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.621391194692349e-05, | |
| "loss": 0.4146, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.551680180854116e-05, | |
| "loss": 0.4142, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.482212788828615e-05, | |
| "loss": 0.4159, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.413144300314575e-05, | |
| "loss": 0.4156, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.344214935022219e-05, | |
| "loss": 0.4134, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.275580380487631e-05, | |
| "loss": 0.4141, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.2072575712601445e-05, | |
| "loss": 0.4146, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.1392633649706e-05, | |
| "loss": 0.4137, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.3925502300262451, | |
| "eval_runtime": 93.7863, | |
| "eval_samples_per_second": 53.313, | |
| "eval_steps_per_second": 0.842, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 4.0717494800280484e-05, | |
| "loss": 0.414, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.0044619833152034e-05, | |
| "loss": 0.4127, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 3.937553126317129e-05, | |
| "loss": 0.4129, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 3.871039417793112e-05, | |
| "loss": 0.4125, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 3.804937269005464e-05, | |
| "loss": 0.4121, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 3.7392629896702916e-05, | |
| "loss": 0.4121, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 3.674032783933316e-05, | |
| "loss": 0.4119, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 3.609262746371739e-05, | |
| "loss": 0.4116, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 3.544968858023156e-05, | |
| "loss": 0.4107, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.481294084680979e-05, | |
| "loss": 0.412, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 0.38968759775161743, | |
| "eval_runtime": 78.1248, | |
| "eval_samples_per_second": 64.0, | |
| "eval_steps_per_second": 1.011, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 3.4181250060824136e-05, | |
| "loss": 0.4105, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.355352132804756e-05, | |
| "loss": 0.4104, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.293118057384647e-05, | |
| "loss": 0.4109, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 3.231438135148965e-05, | |
| "loss": 0.41, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 3.17044922751775e-05, | |
| "loss": 0.4098, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 3.109921943108062e-05, | |
| "loss": 0.4084, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 3.0499940127827767e-05, | |
| "loss": 0.4083, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.990680222861982e-05, | |
| "loss": 0.4088, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 2.9319952081358052e-05, | |
| "loss": 0.408, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2.8739534482535135e-05, | |
| "loss": 0.4077, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_loss": 0.38781091570854187, | |
| "eval_runtime": 90.5362, | |
| "eval_samples_per_second": 55.227, | |
| "eval_steps_per_second": 0.873, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.8166833668202425e-05, | |
| "loss": 0.4087, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 2.759969559696268e-05, | |
| "loss": 0.4088, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 2.703941452170851e-05, | |
| "loss": 0.4073, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 2.648612868341161e-05, | |
| "loss": 0.4084, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.5939974597073566e-05, | |
| "loss": 0.4077, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 2.5402157452548983e-05, | |
| "loss": 0.4072, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.487065441284431e-05, | |
| "loss": 0.4079, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 2.4346681719201903e-05, | |
| "loss": 0.4076, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.383036865404354e-05, | |
| "loss": 0.4069, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.332184260989229e-05, | |
| "loss": 0.4078, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_loss": 0.3861904740333557, | |
| "eval_runtime": 75.9418, | |
| "eval_samples_per_second": 65.84, | |
| "eval_steps_per_second": 1.04, | |
| "step": 75000 | |
| } | |
| ], | |
| "max_steps": 100000, | |
| "num_train_epochs": 9, | |
| "total_flos": 3.5323171476767716e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |