| { |
| "best_metric": 2.6055867671966553, |
| "best_model_checkpoint": "learning_source_20260316/protein_sequence/bert-output/protein_sequence-medium/checkpoint-33000", |
| "epoch": 3413.940256045519, |
| "eval_steps": 100, |
| "global_step": 60000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 5.689900426742532, |
| "grad_norm": 1.3084443807601929, |
| "learning_rate": 3e-06, |
| "loss": 3.0162, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.689900426742532, |
| "eval_loss": 2.7116549015045166, |
| "eval_runtime": 24.0347, |
| "eval_samples_per_second": 57.999, |
| "eval_steps_per_second": 7.281, |
| "step": 100 |
| }, |
| { |
| "epoch": 11.379800853485063, |
| "grad_norm": 1.1205779314041138, |
| "learning_rate": 6e-06, |
| "loss": 2.7064, |
| "step": 200 |
| }, |
| { |
| "epoch": 11.379800853485063, |
| "eval_loss": 2.694298267364502, |
| "eval_runtime": 24.0236, |
| "eval_samples_per_second": 58.026, |
| "eval_steps_per_second": 7.285, |
| "step": 200 |
| }, |
| { |
| "epoch": 17.069701280227594, |
| "grad_norm": 0.6339058876037598, |
| "learning_rate": 5.989966555183947e-06, |
| "loss": 2.6845, |
| "step": 300 |
| }, |
| { |
| "epoch": 17.069701280227594, |
| "eval_loss": 2.6842806339263916, |
| "eval_runtime": 24.0267, |
| "eval_samples_per_second": 58.019, |
| "eval_steps_per_second": 7.284, |
| "step": 300 |
| }, |
| { |
| "epoch": 22.759601706970127, |
| "grad_norm": 0.6396139860153198, |
| "learning_rate": 5.979933110367893e-06, |
| "loss": 2.6786, |
| "step": 400 |
| }, |
| { |
| "epoch": 22.759601706970127, |
| "eval_loss": 2.6777021884918213, |
| "eval_runtime": 23.6734, |
| "eval_samples_per_second": 58.885, |
| "eval_steps_per_second": 7.392, |
| "step": 400 |
| }, |
| { |
| "epoch": 28.44950213371266, |
| "grad_norm": 0.4754956364631653, |
| "learning_rate": 5.96989966555184e-06, |
| "loss": 2.6752, |
| "step": 500 |
| }, |
| { |
| "epoch": 28.44950213371266, |
| "eval_loss": 2.672980785369873, |
| "eval_runtime": 24.0309, |
| "eval_samples_per_second": 58.009, |
| "eval_steps_per_second": 7.282, |
| "step": 500 |
| }, |
| { |
| "epoch": 34.13940256045519, |
| "grad_norm": 0.5028958320617676, |
| "learning_rate": 5.959866220735786e-06, |
| "loss": 2.6735, |
| "step": 600 |
| }, |
| { |
| "epoch": 34.13940256045519, |
| "eval_loss": 2.673126220703125, |
| "eval_runtime": 23.6782, |
| "eval_samples_per_second": 58.873, |
| "eval_steps_per_second": 7.391, |
| "step": 600 |
| }, |
| { |
| "epoch": 39.82930298719772, |
| "grad_norm": 0.6218613386154175, |
| "learning_rate": 5.949832775919732e-06, |
| "loss": 2.6725, |
| "step": 700 |
| }, |
| { |
| "epoch": 39.82930298719772, |
| "eval_loss": 2.666964292526245, |
| "eval_runtime": 24.0295, |
| "eval_samples_per_second": 58.012, |
| "eval_steps_per_second": 7.283, |
| "step": 700 |
| }, |
| { |
| "epoch": 45.519203413940254, |
| "grad_norm": 0.5778615474700928, |
| "learning_rate": 5.939799331103679e-06, |
| "loss": 2.6709, |
| "step": 800 |
| }, |
| { |
| "epoch": 45.519203413940254, |
| "eval_loss": 2.6644680500030518, |
| "eval_runtime": 24.0251, |
| "eval_samples_per_second": 58.023, |
| "eval_steps_per_second": 7.284, |
| "step": 800 |
| }, |
| { |
| "epoch": 51.209103840682786, |
| "grad_norm": 0.46084001660346985, |
| "learning_rate": 5.929765886287626e-06, |
| "loss": 2.6703, |
| "step": 900 |
| }, |
| { |
| "epoch": 51.209103840682786, |
| "eval_loss": 2.6703662872314453, |
| "eval_runtime": 24.0429, |
| "eval_samples_per_second": 57.98, |
| "eval_steps_per_second": 7.279, |
| "step": 900 |
| }, |
| { |
| "epoch": 56.89900426742532, |
| "grad_norm": 0.3723374307155609, |
| "learning_rate": 5.919732441471572e-06, |
| "loss": 2.6698, |
| "step": 1000 |
| }, |
| { |
| "epoch": 56.89900426742532, |
| "eval_loss": 2.6655778884887695, |
| "eval_runtime": 24.0375, |
| "eval_samples_per_second": 57.993, |
| "eval_steps_per_second": 7.28, |
| "step": 1000 |
| }, |
| { |
| "epoch": 62.58890469416785, |
| "grad_norm": 0.3526281714439392, |
| "learning_rate": 5.9096989966555185e-06, |
| "loss": 2.6685, |
| "step": 1100 |
| }, |
| { |
| "epoch": 62.58890469416785, |
| "eval_loss": 2.6650660037994385, |
| "eval_runtime": 23.6507, |
| "eval_samples_per_second": 58.941, |
| "eval_steps_per_second": 7.399, |
| "step": 1100 |
| }, |
| { |
| "epoch": 68.27880512091038, |
| "grad_norm": 0.4236809313297272, |
| "learning_rate": 5.899665551839465e-06, |
| "loss": 2.6679, |
| "step": 1200 |
| }, |
| { |
| "epoch": 68.27880512091038, |
| "eval_loss": 2.66703200340271, |
| "eval_runtime": 23.992, |
| "eval_samples_per_second": 58.103, |
| "eval_steps_per_second": 7.294, |
| "step": 1200 |
| }, |
| { |
| "epoch": 73.96870554765292, |
| "grad_norm": 0.36087411642074585, |
| "learning_rate": 5.889632107023412e-06, |
| "loss": 2.6681, |
| "step": 1300 |
| }, |
| { |
| "epoch": 73.96870554765292, |
| "eval_loss": 2.661330461502075, |
| "eval_runtime": 24.024, |
| "eval_samples_per_second": 58.025, |
| "eval_steps_per_second": 7.284, |
| "step": 1300 |
| }, |
| { |
| "epoch": 79.65860597439544, |
| "grad_norm": 0.40879154205322266, |
| "learning_rate": 5.879598662207358e-06, |
| "loss": 2.6674, |
| "step": 1400 |
| }, |
| { |
| "epoch": 79.65860597439544, |
| "eval_loss": 2.6664044857025146, |
| "eval_runtime": 23.6778, |
| "eval_samples_per_second": 58.874, |
| "eval_steps_per_second": 7.391, |
| "step": 1400 |
| }, |
| { |
| "epoch": 85.34850640113798, |
| "grad_norm": 0.3477596044540405, |
| "learning_rate": 5.869565217391305e-06, |
| "loss": 2.6676, |
| "step": 1500 |
| }, |
| { |
| "epoch": 85.34850640113798, |
| "eval_loss": 2.6639652252197266, |
| "eval_runtime": 24.0594, |
| "eval_samples_per_second": 57.94, |
| "eval_steps_per_second": 7.274, |
| "step": 1500 |
| }, |
| { |
| "epoch": 91.03840682788051, |
| "grad_norm": 0.39076292514801025, |
| "learning_rate": 5.8595317725752514e-06, |
| "loss": 2.6678, |
| "step": 1600 |
| }, |
| { |
| "epoch": 91.03840682788051, |
| "eval_loss": 2.665249824523926, |
| "eval_runtime": 24.0245, |
| "eval_samples_per_second": 58.024, |
| "eval_steps_per_second": 7.284, |
| "step": 1600 |
| }, |
| { |
| "epoch": 96.72830725462305, |
| "grad_norm": 0.4453221261501312, |
| "learning_rate": 5.849498327759197e-06, |
| "loss": 2.6672, |
| "step": 1700 |
| }, |
| { |
| "epoch": 96.72830725462305, |
| "eval_loss": 2.6631760597229004, |
| "eval_runtime": 24.0462, |
| "eval_samples_per_second": 57.972, |
| "eval_steps_per_second": 7.278, |
| "step": 1700 |
| }, |
| { |
| "epoch": 102.41820768136557, |
| "grad_norm": 0.4177381694316864, |
| "learning_rate": 5.839464882943144e-06, |
| "loss": 2.6669, |
| "step": 1800 |
| }, |
| { |
| "epoch": 102.41820768136557, |
| "eval_loss": 2.6606359481811523, |
| "eval_runtime": 24.0304, |
| "eval_samples_per_second": 58.01, |
| "eval_steps_per_second": 7.282, |
| "step": 1800 |
| }, |
| { |
| "epoch": 108.10810810810811, |
| "grad_norm": 0.29331672191619873, |
| "learning_rate": 5.829431438127091e-06, |
| "loss": 2.6663, |
| "step": 1900 |
| }, |
| { |
| "epoch": 108.10810810810811, |
| "eval_loss": 2.662499189376831, |
| "eval_runtime": 23.6649, |
| "eval_samples_per_second": 58.906, |
| "eval_steps_per_second": 7.395, |
| "step": 1900 |
| }, |
| { |
| "epoch": 113.79800853485064, |
| "grad_norm": 0.25176671147346497, |
| "learning_rate": 5.819397993311037e-06, |
| "loss": 2.6661, |
| "step": 2000 |
| }, |
| { |
| "epoch": 113.79800853485064, |
| "eval_loss": 2.662942409515381, |
| "eval_runtime": 24.0202, |
| "eval_samples_per_second": 58.034, |
| "eval_steps_per_second": 7.286, |
| "step": 2000 |
| }, |
| { |
| "epoch": 119.48790896159318, |
| "grad_norm": 0.34689632058143616, |
| "learning_rate": 5.8093645484949836e-06, |
| "loss": 2.666, |
| "step": 2100 |
| }, |
| { |
| "epoch": 119.48790896159318, |
| "eval_loss": 2.6656811237335205, |
| "eval_runtime": 24.0348, |
| "eval_samples_per_second": 57.999, |
| "eval_steps_per_second": 7.281, |
| "step": 2100 |
| }, |
| { |
| "epoch": 125.1778093883357, |
| "grad_norm": 0.36021965742111206, |
| "learning_rate": 5.79933110367893e-06, |
| "loss": 2.6662, |
| "step": 2200 |
| }, |
| { |
| "epoch": 125.1778093883357, |
| "eval_loss": 2.6633687019348145, |
| "eval_runtime": 24.0228, |
| "eval_samples_per_second": 58.028, |
| "eval_steps_per_second": 7.285, |
| "step": 2200 |
| }, |
| { |
| "epoch": 130.86770981507823, |
| "grad_norm": 0.35580527782440186, |
| "learning_rate": 5.789297658862876e-06, |
| "loss": 2.6659, |
| "step": 2300 |
| }, |
| { |
| "epoch": 130.86770981507823, |
| "eval_loss": 2.6656627655029297, |
| "eval_runtime": 24.0299, |
| "eval_samples_per_second": 58.011, |
| "eval_steps_per_second": 7.283, |
| "step": 2300 |
| }, |
| { |
| "epoch": 136.55761024182075, |
| "grad_norm": 0.33932358026504517, |
| "learning_rate": 5.779264214046823e-06, |
| "loss": 2.666, |
| "step": 2400 |
| }, |
| { |
| "epoch": 136.55761024182075, |
| "eval_loss": 2.662867784500122, |
| "eval_runtime": 23.985, |
| "eval_samples_per_second": 58.12, |
| "eval_steps_per_second": 7.296, |
| "step": 2400 |
| }, |
| { |
| "epoch": 142.2475106685633, |
| "grad_norm": 0.25131767988204956, |
| "learning_rate": 5.76923076923077e-06, |
| "loss": 2.6657, |
| "step": 2500 |
| }, |
| { |
| "epoch": 142.2475106685633, |
| "eval_loss": 2.665088415145874, |
| "eval_runtime": 23.9717, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 2500 |
| }, |
| { |
| "epoch": 147.93741109530583, |
| "grad_norm": 0.3472673296928406, |
| "learning_rate": 5.759197324414716e-06, |
| "loss": 2.6655, |
| "step": 2600 |
| }, |
| { |
| "epoch": 147.93741109530583, |
| "eval_loss": 2.664132833480835, |
| "eval_runtime": 23.99, |
| "eval_samples_per_second": 58.107, |
| "eval_steps_per_second": 7.295, |
| "step": 2600 |
| }, |
| { |
| "epoch": 153.62731152204836, |
| "grad_norm": 0.36761701107025146, |
| "learning_rate": 5.7491638795986624e-06, |
| "loss": 2.666, |
| "step": 2700 |
| }, |
| { |
| "epoch": 153.62731152204836, |
| "eval_loss": 2.6648921966552734, |
| "eval_runtime": 23.9945, |
| "eval_samples_per_second": 58.097, |
| "eval_steps_per_second": 7.293, |
| "step": 2700 |
| }, |
| { |
| "epoch": 159.31721194879088, |
| "grad_norm": 0.2883091866970062, |
| "learning_rate": 5.739130434782609e-06, |
| "loss": 2.666, |
| "step": 2800 |
| }, |
| { |
| "epoch": 159.31721194879088, |
| "eval_loss": 2.6666293144226074, |
| "eval_runtime": 23.6521, |
| "eval_samples_per_second": 58.938, |
| "eval_steps_per_second": 7.399, |
| "step": 2800 |
| }, |
| { |
| "epoch": 165.00711237553344, |
| "grad_norm": 0.28055015206336975, |
| "learning_rate": 5.729096989966555e-06, |
| "loss": 2.6651, |
| "step": 2900 |
| }, |
| { |
| "epoch": 165.00711237553344, |
| "eval_loss": 2.664830207824707, |
| "eval_runtime": 23.9951, |
| "eval_samples_per_second": 58.095, |
| "eval_steps_per_second": 7.293, |
| "step": 2900 |
| }, |
| { |
| "epoch": 170.69701280227596, |
| "grad_norm": 0.24984011054039001, |
| "learning_rate": 5.719063545150502e-06, |
| "loss": 2.6649, |
| "step": 3000 |
| }, |
| { |
| "epoch": 170.69701280227596, |
| "eval_loss": 2.6661195755004883, |
| "eval_runtime": 24.0098, |
| "eval_samples_per_second": 58.06, |
| "eval_steps_per_second": 7.289, |
| "step": 3000 |
| }, |
| { |
| "epoch": 176.3869132290185, |
| "grad_norm": 0.3036094307899475, |
| "learning_rate": 5.709030100334449e-06, |
| "loss": 2.6647, |
| "step": 3100 |
| }, |
| { |
| "epoch": 176.3869132290185, |
| "eval_loss": 2.663729667663574, |
| "eval_runtime": 23.6531, |
| "eval_samples_per_second": 58.935, |
| "eval_steps_per_second": 7.399, |
| "step": 3100 |
| }, |
| { |
| "epoch": 182.07681365576101, |
| "grad_norm": 0.35330143570899963, |
| "learning_rate": 5.698996655518395e-06, |
| "loss": 2.665, |
| "step": 3200 |
| }, |
| { |
| "epoch": 182.07681365576101, |
| "eval_loss": 2.6598894596099854, |
| "eval_runtime": 24.0054, |
| "eval_samples_per_second": 58.07, |
| "eval_steps_per_second": 7.29, |
| "step": 3200 |
| }, |
| { |
| "epoch": 187.76671408250357, |
| "grad_norm": 0.27144384384155273, |
| "learning_rate": 5.688963210702341e-06, |
| "loss": 2.6646, |
| "step": 3300 |
| }, |
| { |
| "epoch": 187.76671408250357, |
| "eval_loss": 2.6629762649536133, |
| "eval_runtime": 23.991, |
| "eval_samples_per_second": 58.105, |
| "eval_steps_per_second": 7.294, |
| "step": 3300 |
| }, |
| { |
| "epoch": 193.4566145092461, |
| "grad_norm": 0.16871358454227448, |
| "learning_rate": 5.678929765886288e-06, |
| "loss": 2.6644, |
| "step": 3400 |
| }, |
| { |
| "epoch": 193.4566145092461, |
| "eval_loss": 2.6613662242889404, |
| "eval_runtime": 23.9942, |
| "eval_samples_per_second": 58.097, |
| "eval_steps_per_second": 7.293, |
| "step": 3400 |
| }, |
| { |
| "epoch": 199.14651493598862, |
| "grad_norm": 0.23622137308120728, |
| "learning_rate": 5.668896321070235e-06, |
| "loss": 2.6647, |
| "step": 3500 |
| }, |
| { |
| "epoch": 199.14651493598862, |
| "eval_loss": 2.665132522583008, |
| "eval_runtime": 23.9894, |
| "eval_samples_per_second": 58.109, |
| "eval_steps_per_second": 7.295, |
| "step": 3500 |
| }, |
| { |
| "epoch": 204.83641536273115, |
| "grad_norm": 0.22713766992092133, |
| "learning_rate": 5.658862876254181e-06, |
| "loss": 2.665, |
| "step": 3600 |
| }, |
| { |
| "epoch": 204.83641536273115, |
| "eval_loss": 2.6628506183624268, |
| "eval_runtime": 24.0029, |
| "eval_samples_per_second": 58.076, |
| "eval_steps_per_second": 7.291, |
| "step": 3600 |
| }, |
| { |
| "epoch": 210.52631578947367, |
| "grad_norm": 0.2724650502204895, |
| "learning_rate": 5.6488294314381275e-06, |
| "loss": 2.6645, |
| "step": 3700 |
| }, |
| { |
| "epoch": 210.52631578947367, |
| "eval_loss": 2.662940740585327, |
| "eval_runtime": 24.0035, |
| "eval_samples_per_second": 58.075, |
| "eval_steps_per_second": 7.291, |
| "step": 3700 |
| }, |
| { |
| "epoch": 216.21621621621622, |
| "grad_norm": 0.2551960349082947, |
| "learning_rate": 5.638795986622074e-06, |
| "loss": 2.6652, |
| "step": 3800 |
| }, |
| { |
| "epoch": 216.21621621621622, |
| "eval_loss": 2.66235089302063, |
| "eval_runtime": 23.6518, |
| "eval_samples_per_second": 58.939, |
| "eval_steps_per_second": 7.399, |
| "step": 3800 |
| }, |
| { |
| "epoch": 221.90611664295875, |
| "grad_norm": 0.23962050676345825, |
| "learning_rate": 5.62876254180602e-06, |
| "loss": 2.6647, |
| "step": 3900 |
| }, |
| { |
| "epoch": 221.90611664295875, |
| "eval_loss": 2.659684896469116, |
| "eval_runtime": 24.0133, |
| "eval_samples_per_second": 58.051, |
| "eval_steps_per_second": 7.288, |
| "step": 3900 |
| }, |
| { |
| "epoch": 227.59601706970128, |
| "grad_norm": 0.21915219724178314, |
| "learning_rate": 5.618729096989967e-06, |
| "loss": 2.6648, |
| "step": 4000 |
| }, |
| { |
| "epoch": 227.59601706970128, |
| "eval_loss": 2.6648192405700684, |
| "eval_runtime": 24.0019, |
| "eval_samples_per_second": 58.079, |
| "eval_steps_per_second": 7.291, |
| "step": 4000 |
| }, |
| { |
| "epoch": 233.2859174964438, |
| "grad_norm": 0.236517071723938, |
| "learning_rate": 5.608695652173914e-06, |
| "loss": 2.6644, |
| "step": 4100 |
| }, |
| { |
| "epoch": 233.2859174964438, |
| "eval_loss": 2.664208173751831, |
| "eval_runtime": 23.9969, |
| "eval_samples_per_second": 58.091, |
| "eval_steps_per_second": 7.293, |
| "step": 4100 |
| }, |
| { |
| "epoch": 238.97581792318636, |
| "grad_norm": 0.2850896716117859, |
| "learning_rate": 5.59866220735786e-06, |
| "loss": 2.6645, |
| "step": 4200 |
| }, |
| { |
| "epoch": 238.97581792318636, |
| "eval_loss": 2.6635079383850098, |
| "eval_runtime": 24.0086, |
| "eval_samples_per_second": 58.063, |
| "eval_steps_per_second": 7.289, |
| "step": 4200 |
| }, |
| { |
| "epoch": 244.66571834992888, |
| "grad_norm": 0.19473238289356232, |
| "learning_rate": 5.588628762541806e-06, |
| "loss": 2.664, |
| "step": 4300 |
| }, |
| { |
| "epoch": 244.66571834992888, |
| "eval_loss": 2.6625959873199463, |
| "eval_runtime": 23.986, |
| "eval_samples_per_second": 58.117, |
| "eval_steps_per_second": 7.296, |
| "step": 4300 |
| }, |
| { |
| "epoch": 250.3556187766714, |
| "grad_norm": 0.3315108120441437, |
| "learning_rate": 5.578595317725753e-06, |
| "loss": 2.6641, |
| "step": 4400 |
| }, |
| { |
| "epoch": 250.3556187766714, |
| "eval_loss": 2.6661853790283203, |
| "eval_runtime": 23.993, |
| "eval_samples_per_second": 58.1, |
| "eval_steps_per_second": 7.294, |
| "step": 4400 |
| }, |
| { |
| "epoch": 256.04551920341396, |
| "grad_norm": 0.1736942082643509, |
| "learning_rate": 5.568561872909699e-06, |
| "loss": 2.6646, |
| "step": 4500 |
| }, |
| { |
| "epoch": 256.04551920341396, |
| "eval_loss": 2.662870168685913, |
| "eval_runtime": 24.0136, |
| "eval_samples_per_second": 58.05, |
| "eval_steps_per_second": 7.288, |
| "step": 4500 |
| }, |
| { |
| "epoch": 261.73541963015646, |
| "grad_norm": 0.28544047474861145, |
| "learning_rate": 5.558528428093646e-06, |
| "loss": 2.6643, |
| "step": 4600 |
| }, |
| { |
| "epoch": 261.73541963015646, |
| "eval_loss": 2.664302349090576, |
| "eval_runtime": 23.6666, |
| "eval_samples_per_second": 58.902, |
| "eval_steps_per_second": 7.394, |
| "step": 4600 |
| }, |
| { |
| "epoch": 267.425320056899, |
| "grad_norm": 0.2484113723039627, |
| "learning_rate": 5.548494983277593e-06, |
| "loss": 2.6647, |
| "step": 4700 |
| }, |
| { |
| "epoch": 267.425320056899, |
| "eval_loss": 2.6621506214141846, |
| "eval_runtime": 24.002, |
| "eval_samples_per_second": 58.078, |
| "eval_steps_per_second": 7.291, |
| "step": 4700 |
| }, |
| { |
| "epoch": 273.1152204836415, |
| "grad_norm": 0.2153732031583786, |
| "learning_rate": 5.5384615384615385e-06, |
| "loss": 2.6642, |
| "step": 4800 |
| }, |
| { |
| "epoch": 273.1152204836415, |
| "eval_loss": 2.661278009414673, |
| "eval_runtime": 23.9926, |
| "eval_samples_per_second": 58.101, |
| "eval_steps_per_second": 7.294, |
| "step": 4800 |
| }, |
| { |
| "epoch": 278.80512091038406, |
| "grad_norm": 0.2783970832824707, |
| "learning_rate": 5.528428093645485e-06, |
| "loss": 2.6645, |
| "step": 4900 |
| }, |
| { |
| "epoch": 278.80512091038406, |
| "eval_loss": 2.6649537086486816, |
| "eval_runtime": 24.0036, |
| "eval_samples_per_second": 58.075, |
| "eval_steps_per_second": 7.291, |
| "step": 4900 |
| }, |
| { |
| "epoch": 284.4950213371266, |
| "grad_norm": 0.19151923060417175, |
| "learning_rate": 5.518394648829432e-06, |
| "loss": 2.6639, |
| "step": 5000 |
| }, |
| { |
| "epoch": 284.4950213371266, |
| "eval_loss": 2.6626217365264893, |
| "eval_runtime": 24.0086, |
| "eval_samples_per_second": 58.062, |
| "eval_steps_per_second": 7.289, |
| "step": 5000 |
| }, |
| { |
| "epoch": 290.1849217638691, |
| "grad_norm": 0.2797650992870331, |
| "learning_rate": 5.508361204013378e-06, |
| "loss": 2.6638, |
| "step": 5100 |
| }, |
| { |
| "epoch": 290.1849217638691, |
| "eval_loss": 2.6611075401306152, |
| "eval_runtime": 24.0032, |
| "eval_samples_per_second": 58.076, |
| "eval_steps_per_second": 7.291, |
| "step": 5100 |
| }, |
| { |
| "epoch": 295.87482219061167, |
| "grad_norm": 0.20348067581653595, |
| "learning_rate": 5.498327759197324e-06, |
| "loss": 2.6641, |
| "step": 5200 |
| }, |
| { |
| "epoch": 295.87482219061167, |
| "eval_loss": 2.6633517742156982, |
| "eval_runtime": 23.9937, |
| "eval_samples_per_second": 58.099, |
| "eval_steps_per_second": 7.294, |
| "step": 5200 |
| }, |
| { |
| "epoch": 301.5647226173542, |
| "grad_norm": 0.28533390164375305, |
| "learning_rate": 5.488294314381271e-06, |
| "loss": 2.6644, |
| "step": 5300 |
| }, |
| { |
| "epoch": 301.5647226173542, |
| "eval_loss": 2.6602139472961426, |
| "eval_runtime": 23.9892, |
| "eval_samples_per_second": 58.109, |
| "eval_steps_per_second": 7.295, |
| "step": 5300 |
| }, |
| { |
| "epoch": 307.2546230440967, |
| "grad_norm": 0.20466282963752747, |
| "learning_rate": 5.478260869565217e-06, |
| "loss": 2.664, |
| "step": 5400 |
| }, |
| { |
| "epoch": 307.2546230440967, |
| "eval_loss": 2.6633496284484863, |
| "eval_runtime": 23.9996, |
| "eval_samples_per_second": 58.084, |
| "eval_steps_per_second": 7.292, |
| "step": 5400 |
| }, |
| { |
| "epoch": 312.9445234708393, |
| "grad_norm": 0.2744331657886505, |
| "learning_rate": 5.468227424749163e-06, |
| "loss": 2.6642, |
| "step": 5500 |
| }, |
| { |
| "epoch": 312.9445234708393, |
| "eval_loss": 2.66107439994812, |
| "eval_runtime": 23.6506, |
| "eval_samples_per_second": 58.941, |
| "eval_steps_per_second": 7.399, |
| "step": 5500 |
| }, |
| { |
| "epoch": 318.63442389758177, |
| "grad_norm": 0.1974910944700241, |
| "learning_rate": 5.45819397993311e-06, |
| "loss": 2.6639, |
| "step": 5600 |
| }, |
| { |
| "epoch": 318.63442389758177, |
| "eval_loss": 2.6617164611816406, |
| "eval_runtime": 23.9925, |
| "eval_samples_per_second": 58.101, |
| "eval_steps_per_second": 7.294, |
| "step": 5600 |
| }, |
| { |
| "epoch": 324.3243243243243, |
| "grad_norm": 0.2324630171060562, |
| "learning_rate": 5.448160535117057e-06, |
| "loss": 2.6639, |
| "step": 5700 |
| }, |
| { |
| "epoch": 324.3243243243243, |
| "eval_loss": 2.662553071975708, |
| "eval_runtime": 23.9969, |
| "eval_samples_per_second": 58.091, |
| "eval_steps_per_second": 7.293, |
| "step": 5700 |
| }, |
| { |
| "epoch": 330.0142247510669, |
| "grad_norm": 0.19881758093833923, |
| "learning_rate": 5.438127090301003e-06, |
| "loss": 2.6642, |
| "step": 5800 |
| }, |
| { |
| "epoch": 330.0142247510669, |
| "eval_loss": 2.6611857414245605, |
| "eval_runtime": 23.9913, |
| "eval_samples_per_second": 58.104, |
| "eval_steps_per_second": 7.294, |
| "step": 5800 |
| }, |
| { |
| "epoch": 335.7041251778094, |
| "grad_norm": 0.2262159287929535, |
| "learning_rate": 5.4280936454849495e-06, |
| "loss": 2.664, |
| "step": 5900 |
| }, |
| { |
| "epoch": 335.7041251778094, |
| "eval_loss": 2.663783073425293, |
| "eval_runtime": 23.9991, |
| "eval_samples_per_second": 58.086, |
| "eval_steps_per_second": 7.292, |
| "step": 5900 |
| }, |
| { |
| "epoch": 341.3940256045519, |
| "grad_norm": 0.19771187007427216, |
| "learning_rate": 5.418060200668896e-06, |
| "loss": 2.6638, |
| "step": 6000 |
| }, |
| { |
| "epoch": 341.3940256045519, |
| "eval_loss": 2.6637065410614014, |
| "eval_runtime": 23.9906, |
| "eval_samples_per_second": 58.106, |
| "eval_steps_per_second": 7.295, |
| "step": 6000 |
| }, |
| { |
| "epoch": 347.0839260312944, |
| "grad_norm": 0.21087121963500977, |
| "learning_rate": 5.408026755852843e-06, |
| "loss": 2.664, |
| "step": 6100 |
| }, |
| { |
| "epoch": 347.0839260312944, |
| "eval_loss": 2.6605749130249023, |
| "eval_runtime": 23.9813, |
| "eval_samples_per_second": 58.129, |
| "eval_steps_per_second": 7.297, |
| "step": 6100 |
| }, |
| { |
| "epoch": 352.773826458037, |
| "grad_norm": 0.16268645226955414, |
| "learning_rate": 5.397993311036789e-06, |
| "loss": 2.6642, |
| "step": 6200 |
| }, |
| { |
| "epoch": 352.773826458037, |
| "eval_loss": 2.66109299659729, |
| "eval_runtime": 23.9898, |
| "eval_samples_per_second": 58.108, |
| "eval_steps_per_second": 7.295, |
| "step": 6200 |
| }, |
| { |
| "epoch": 358.46372688477953, |
| "grad_norm": 0.17065826058387756, |
| "learning_rate": 5.387959866220736e-06, |
| "loss": 2.6637, |
| "step": 6300 |
| }, |
| { |
| "epoch": 358.46372688477953, |
| "eval_loss": 2.662609100341797, |
| "eval_runtime": 23.6456, |
| "eval_samples_per_second": 58.954, |
| "eval_steps_per_second": 7.401, |
| "step": 6300 |
| }, |
| { |
| "epoch": 364.15362731152203, |
| "grad_norm": 0.21785375475883484, |
| "learning_rate": 5.3779264214046825e-06, |
| "loss": 2.6637, |
| "step": 6400 |
| }, |
| { |
| "epoch": 364.15362731152203, |
| "eval_loss": 2.6664772033691406, |
| "eval_runtime": 24.0047, |
| "eval_samples_per_second": 58.072, |
| "eval_steps_per_second": 7.29, |
| "step": 6400 |
| }, |
| { |
| "epoch": 369.8435277382646, |
| "grad_norm": 0.26267367601394653, |
| "learning_rate": 5.367892976588628e-06, |
| "loss": 2.6637, |
| "step": 6500 |
| }, |
| { |
| "epoch": 369.8435277382646, |
| "eval_loss": 2.6627228260040283, |
| "eval_runtime": 23.9957, |
| "eval_samples_per_second": 58.094, |
| "eval_steps_per_second": 7.293, |
| "step": 6500 |
| }, |
| { |
| "epoch": 375.53342816500714, |
| "grad_norm": 0.21765349805355072, |
| "learning_rate": 5.357859531772575e-06, |
| "loss": 2.6636, |
| "step": 6600 |
| }, |
| { |
| "epoch": 375.53342816500714, |
| "eval_loss": 2.663877487182617, |
| "eval_runtime": 24.0007, |
| "eval_samples_per_second": 58.082, |
| "eval_steps_per_second": 7.291, |
| "step": 6600 |
| }, |
| { |
| "epoch": 381.22332859174963, |
| "grad_norm": 0.25031423568725586, |
| "learning_rate": 5.347826086956522e-06, |
| "loss": 2.6632, |
| "step": 6700 |
| }, |
| { |
| "epoch": 381.22332859174963, |
| "eval_loss": 2.659921884536743, |
| "eval_runtime": 24.0127, |
| "eval_samples_per_second": 58.053, |
| "eval_steps_per_second": 7.288, |
| "step": 6700 |
| }, |
| { |
| "epoch": 386.9132290184922, |
| "grad_norm": 0.19761057198047638, |
| "learning_rate": 5.337792642140468e-06, |
| "loss": 2.6643, |
| "step": 6800 |
| }, |
| { |
| "epoch": 386.9132290184922, |
| "eval_loss": 2.6612935066223145, |
| "eval_runtime": 24.0055, |
| "eval_samples_per_second": 58.07, |
| "eval_steps_per_second": 7.29, |
| "step": 6800 |
| }, |
| { |
| "epoch": 392.6031294452347, |
| "grad_norm": 0.2031594067811966, |
| "learning_rate": 5.327759197324415e-06, |
| "loss": 2.6639, |
| "step": 6900 |
| }, |
| { |
| "epoch": 392.6031294452347, |
| "eval_loss": 2.6605868339538574, |
| "eval_runtime": 23.9939, |
| "eval_samples_per_second": 58.098, |
| "eval_steps_per_second": 7.294, |
| "step": 6900 |
| }, |
| { |
| "epoch": 398.29302987197724, |
| "grad_norm": 0.23052236437797546, |
| "learning_rate": 5.317725752508361e-06, |
| "loss": 2.6636, |
| "step": 7000 |
| }, |
| { |
| "epoch": 398.29302987197724, |
| "eval_loss": 2.6643214225769043, |
| "eval_runtime": 23.9814, |
| "eval_samples_per_second": 58.128, |
| "eval_steps_per_second": 7.297, |
| "step": 7000 |
| }, |
| { |
| "epoch": 403.9829302987198, |
| "grad_norm": 0.22435928881168365, |
| "learning_rate": 5.307692307692307e-06, |
| "loss": 2.6641, |
| "step": 7100 |
| }, |
| { |
| "epoch": 403.9829302987198, |
| "eval_loss": 2.6603801250457764, |
| "eval_runtime": 23.6345, |
| "eval_samples_per_second": 58.982, |
| "eval_steps_per_second": 7.404, |
| "step": 7100 |
| }, |
| { |
| "epoch": 409.6728307254623, |
| "grad_norm": 0.25684019923210144, |
| "learning_rate": 5.297658862876254e-06, |
| "loss": 2.6629, |
| "step": 7200 |
| }, |
| { |
| "epoch": 409.6728307254623, |
| "eval_loss": 2.661247968673706, |
| "eval_runtime": 24.0023, |
| "eval_samples_per_second": 58.078, |
| "eval_steps_per_second": 7.291, |
| "step": 7200 |
| }, |
| { |
| "epoch": 415.36273115220484, |
| "grad_norm": 0.1864226758480072, |
| "learning_rate": 5.287625418060201e-06, |
| "loss": 2.6635, |
| "step": 7300 |
| }, |
| { |
| "epoch": 415.36273115220484, |
| "eval_loss": 2.6621150970458984, |
| "eval_runtime": 23.632, |
| "eval_samples_per_second": 58.988, |
| "eval_steps_per_second": 7.405, |
| "step": 7300 |
| }, |
| { |
| "epoch": 421.05263157894734, |
| "grad_norm": 0.2722451090812683, |
| "learning_rate": 5.277591973244147e-06, |
| "loss": 2.6632, |
| "step": 7400 |
| }, |
| { |
| "epoch": 421.05263157894734, |
| "eval_loss": 2.6618592739105225, |
| "eval_runtime": 24.0004, |
| "eval_samples_per_second": 58.082, |
| "eval_steps_per_second": 7.292, |
| "step": 7400 |
| }, |
| { |
| "epoch": 426.7425320056899, |
| "grad_norm": 0.22736287117004395, |
| "learning_rate": 5.2675585284280935e-06, |
| "loss": 2.6634, |
| "step": 7500 |
| }, |
| { |
| "epoch": 426.7425320056899, |
| "eval_loss": 2.664785385131836, |
| "eval_runtime": 23.9908, |
| "eval_samples_per_second": 58.106, |
| "eval_steps_per_second": 7.294, |
| "step": 7500 |
| }, |
| { |
| "epoch": 432.43243243243245, |
| "grad_norm": 0.2094627469778061, |
| "learning_rate": 5.25752508361204e-06, |
| "loss": 2.663, |
| "step": 7600 |
| }, |
| { |
| "epoch": 432.43243243243245, |
| "eval_loss": 2.6618707180023193, |
| "eval_runtime": 23.9741, |
| "eval_samples_per_second": 58.146, |
| "eval_steps_per_second": 7.3, |
| "step": 7600 |
| }, |
| { |
| "epoch": 438.12233285917495, |
| "grad_norm": 0.19710348546504974, |
| "learning_rate": 5.247491638795986e-06, |
| "loss": 2.6633, |
| "step": 7700 |
| }, |
| { |
| "epoch": 438.12233285917495, |
| "eval_loss": 2.660637617111206, |
| "eval_runtime": 23.9987, |
| "eval_samples_per_second": 58.087, |
| "eval_steps_per_second": 7.292, |
| "step": 7700 |
| }, |
| { |
| "epoch": 443.8122332859175, |
| "grad_norm": 0.23215074837207794, |
| "learning_rate": 5.237458193979933e-06, |
| "loss": 2.6635, |
| "step": 7800 |
| }, |
| { |
| "epoch": 443.8122332859175, |
| "eval_loss": 2.6619646549224854, |
| "eval_runtime": 24.0021, |
| "eval_samples_per_second": 58.078, |
| "eval_steps_per_second": 7.291, |
| "step": 7800 |
| }, |
| { |
| "epoch": 449.50213371266005, |
| "grad_norm": 0.2374960482120514, |
| "learning_rate": 5.22742474916388e-06, |
| "loss": 2.6632, |
| "step": 7900 |
| }, |
| { |
| "epoch": 449.50213371266005, |
| "eval_loss": 2.660618305206299, |
| "eval_runtime": 23.9883, |
| "eval_samples_per_second": 58.112, |
| "eval_steps_per_second": 7.295, |
| "step": 7900 |
| }, |
| { |
| "epoch": 455.19203413940255, |
| "grad_norm": 0.22597618401050568, |
| "learning_rate": 5.2173913043478265e-06, |
| "loss": 2.6628, |
| "step": 8000 |
| }, |
| { |
| "epoch": 455.19203413940255, |
| "eval_loss": 2.6641225814819336, |
| "eval_runtime": 23.9895, |
| "eval_samples_per_second": 58.109, |
| "eval_steps_per_second": 7.295, |
| "step": 8000 |
| }, |
| { |
| "epoch": 460.8819345661451, |
| "grad_norm": 0.16886833310127258, |
| "learning_rate": 5.207357859531772e-06, |
| "loss": 2.6624, |
| "step": 8100 |
| }, |
| { |
| "epoch": 460.8819345661451, |
| "eval_loss": 2.663078784942627, |
| "eval_runtime": 23.999, |
| "eval_samples_per_second": 58.086, |
| "eval_steps_per_second": 7.292, |
| "step": 8100 |
| }, |
| { |
| "epoch": 466.5718349928876, |
| "grad_norm": 0.23887428641319275, |
| "learning_rate": 5.197324414715719e-06, |
| "loss": 2.6627, |
| "step": 8200 |
| }, |
| { |
| "epoch": 466.5718349928876, |
| "eval_loss": 2.661996841430664, |
| "eval_runtime": 23.676, |
| "eval_samples_per_second": 58.878, |
| "eval_steps_per_second": 7.391, |
| "step": 8200 |
| }, |
| { |
| "epoch": 472.26173541963016, |
| "grad_norm": 0.21171975135803223, |
| "learning_rate": 5.187290969899666e-06, |
| "loss": 2.6628, |
| "step": 8300 |
| }, |
| { |
| "epoch": 472.26173541963016, |
| "eval_loss": 2.661268711090088, |
| "eval_runtime": 24.009, |
| "eval_samples_per_second": 58.062, |
| "eval_steps_per_second": 7.289, |
| "step": 8300 |
| }, |
| { |
| "epoch": 477.9516358463727, |
| "grad_norm": 0.2626218795776367, |
| "learning_rate": 5.177257525083612e-06, |
| "loss": 2.6627, |
| "step": 8400 |
| }, |
| { |
| "epoch": 477.9516358463727, |
| "eval_loss": 2.6632938385009766, |
| "eval_runtime": 23.9972, |
| "eval_samples_per_second": 58.09, |
| "eval_steps_per_second": 7.293, |
| "step": 8400 |
| }, |
| { |
| "epoch": 483.6415362731152, |
| "grad_norm": 0.2506119906902313, |
| "learning_rate": 5.167224080267559e-06, |
| "loss": 2.6626, |
| "step": 8500 |
| }, |
| { |
| "epoch": 483.6415362731152, |
| "eval_loss": 2.6621577739715576, |
| "eval_runtime": 24.0009, |
| "eval_samples_per_second": 58.081, |
| "eval_steps_per_second": 7.291, |
| "step": 8500 |
| }, |
| { |
| "epoch": 489.33143669985776, |
| "grad_norm": 0.20735953748226166, |
| "learning_rate": 5.157190635451505e-06, |
| "loss": 2.6629, |
| "step": 8600 |
| }, |
| { |
| "epoch": 489.33143669985776, |
| "eval_loss": 2.6636762619018555, |
| "eval_runtime": 23.9985, |
| "eval_samples_per_second": 58.087, |
| "eval_steps_per_second": 7.292, |
| "step": 8600 |
| }, |
| { |
| "epoch": 495.02133712660026, |
| "grad_norm": 0.2238348424434662, |
| "learning_rate": 5.147157190635451e-06, |
| "loss": 2.6627, |
| "step": 8700 |
| }, |
| { |
| "epoch": 495.02133712660026, |
| "eval_loss": 2.6605405807495117, |
| "eval_runtime": 24.0031, |
| "eval_samples_per_second": 58.076, |
| "eval_steps_per_second": 7.291, |
| "step": 8700 |
| }, |
| { |
| "epoch": 500.7112375533428, |
| "grad_norm": 0.25992342829704285, |
| "learning_rate": 5.137123745819398e-06, |
| "loss": 2.6627, |
| "step": 8800 |
| }, |
| { |
| "epoch": 500.7112375533428, |
| "eval_loss": 2.6636483669281006, |
| "eval_runtime": 23.9915, |
| "eval_samples_per_second": 58.104, |
| "eval_steps_per_second": 7.294, |
| "step": 8800 |
| }, |
| { |
| "epoch": 506.40113798008537, |
| "grad_norm": 0.16477429866790771, |
| "learning_rate": 5.127090301003345e-06, |
| "loss": 2.6626, |
| "step": 8900 |
| }, |
| { |
| "epoch": 506.40113798008537, |
| "eval_loss": 2.6633760929107666, |
| "eval_runtime": 23.6486, |
| "eval_samples_per_second": 58.946, |
| "eval_steps_per_second": 7.4, |
| "step": 8900 |
| }, |
| { |
| "epoch": 512.0910384068279, |
| "grad_norm": 0.1675286740064621, |
| "learning_rate": 5.117056856187291e-06, |
| "loss": 2.6618, |
| "step": 9000 |
| }, |
| { |
| "epoch": 512.0910384068279, |
| "eval_loss": 2.6642019748687744, |
| "eval_runtime": 23.9989, |
| "eval_samples_per_second": 58.086, |
| "eval_steps_per_second": 7.292, |
| "step": 9000 |
| }, |
| { |
| "epoch": 517.7809388335704, |
| "grad_norm": 0.26264622807502747, |
| "learning_rate": 5.1070234113712375e-06, |
| "loss": 2.6613, |
| "step": 9100 |
| }, |
| { |
| "epoch": 517.7809388335704, |
| "eval_loss": 2.6624467372894287, |
| "eval_runtime": 23.9956, |
| "eval_samples_per_second": 58.094, |
| "eval_steps_per_second": 7.293, |
| "step": 9100 |
| }, |
| { |
| "epoch": 523.4708392603129, |
| "grad_norm": 0.20508848130702972, |
| "learning_rate": 5.096989966555184e-06, |
| "loss": 2.6592, |
| "step": 9200 |
| }, |
| { |
| "epoch": 523.4708392603129, |
| "eval_loss": 2.6613006591796875, |
| "eval_runtime": 24.0077, |
| "eval_samples_per_second": 58.065, |
| "eval_steps_per_second": 7.289, |
| "step": 9200 |
| }, |
| { |
| "epoch": 529.1607396870555, |
| "grad_norm": 0.20402471721172333, |
| "learning_rate": 5.08695652173913e-06, |
| "loss": 2.6572, |
| "step": 9300 |
| }, |
| { |
| "epoch": 529.1607396870555, |
| "eval_loss": 2.6541850566864014, |
| "eval_runtime": 23.9913, |
| "eval_samples_per_second": 58.105, |
| "eval_steps_per_second": 7.294, |
| "step": 9300 |
| }, |
| { |
| "epoch": 534.850640113798, |
| "grad_norm": 0.2935788929462433, |
| "learning_rate": 5.076923076923077e-06, |
| "loss": 2.6539, |
| "step": 9400 |
| }, |
| { |
| "epoch": 534.850640113798, |
| "eval_loss": 2.6466681957244873, |
| "eval_runtime": 24.0031, |
| "eval_samples_per_second": 58.076, |
| "eval_steps_per_second": 7.291, |
| "step": 9400 |
| }, |
| { |
| "epoch": 540.5405405405405, |
| "grad_norm": 0.22674228250980377, |
| "learning_rate": 5.066889632107024e-06, |
| "loss": 2.6516, |
| "step": 9500 |
| }, |
| { |
| "epoch": 540.5405405405405, |
| "eval_loss": 2.643643379211426, |
| "eval_runtime": 23.9831, |
| "eval_samples_per_second": 58.124, |
| "eval_steps_per_second": 7.297, |
| "step": 9500 |
| }, |
| { |
| "epoch": 546.230440967283, |
| "grad_norm": 0.20724594593048096, |
| "learning_rate": 5.05685618729097e-06, |
| "loss": 2.6499, |
| "step": 9600 |
| }, |
| { |
| "epoch": 546.230440967283, |
| "eval_loss": 2.6470532417297363, |
| "eval_runtime": 23.9913, |
| "eval_samples_per_second": 58.104, |
| "eval_steps_per_second": 7.294, |
| "step": 9600 |
| }, |
| { |
| "epoch": 551.9203413940256, |
| "grad_norm": 0.22264239192008972, |
| "learning_rate": 5.046822742474916e-06, |
| "loss": 2.6484, |
| "step": 9700 |
| }, |
| { |
| "epoch": 551.9203413940256, |
| "eval_loss": 2.6430468559265137, |
| "eval_runtime": 23.6338, |
| "eval_samples_per_second": 58.983, |
| "eval_steps_per_second": 7.405, |
| "step": 9700 |
| }, |
| { |
| "epoch": 557.6102418207681, |
| "grad_norm": 0.2465650737285614, |
| "learning_rate": 5.036789297658863e-06, |
| "loss": 2.6469, |
| "step": 9800 |
| }, |
| { |
| "epoch": 557.6102418207681, |
| "eval_loss": 2.641869068145752, |
| "eval_runtime": 23.9904, |
| "eval_samples_per_second": 58.107, |
| "eval_steps_per_second": 7.295, |
| "step": 9800 |
| }, |
| { |
| "epoch": 563.3001422475106, |
| "grad_norm": 0.22635580599308014, |
| "learning_rate": 5.02675585284281e-06, |
| "loss": 2.6458, |
| "step": 9900 |
| }, |
| { |
| "epoch": 563.3001422475106, |
| "eval_loss": 2.6428213119506836, |
| "eval_runtime": 23.9892, |
| "eval_samples_per_second": 58.11, |
| "eval_steps_per_second": 7.295, |
| "step": 9900 |
| }, |
| { |
| "epoch": 568.9900426742532, |
| "grad_norm": 0.26153308153152466, |
| "learning_rate": 5.016722408026756e-06, |
| "loss": 2.6446, |
| "step": 10000 |
| }, |
| { |
| "epoch": 568.9900426742532, |
| "eval_loss": 2.639491081237793, |
| "eval_runtime": 23.9942, |
| "eval_samples_per_second": 58.097, |
| "eval_steps_per_second": 7.293, |
| "step": 10000 |
| }, |
| { |
| "epoch": 574.6799431009957, |
| "grad_norm": 0.21078501641750336, |
| "learning_rate": 5.0066889632107026e-06, |
| "loss": 2.6441, |
| "step": 10100 |
| }, |
| { |
| "epoch": 574.6799431009957, |
| "eval_loss": 2.641256809234619, |
| "eval_runtime": 23.6406, |
| "eval_samples_per_second": 58.966, |
| "eval_steps_per_second": 7.403, |
| "step": 10100 |
| }, |
| { |
| "epoch": 580.3698435277382, |
| "grad_norm": 0.24298006296157837, |
| "learning_rate": 4.996655518394649e-06, |
| "loss": 2.6428, |
| "step": 10200 |
| }, |
| { |
| "epoch": 580.3698435277382, |
| "eval_loss": 2.635876417160034, |
| "eval_runtime": 23.9845, |
| "eval_samples_per_second": 58.121, |
| "eval_steps_per_second": 7.296, |
| "step": 10200 |
| }, |
| { |
| "epoch": 586.0597439544808, |
| "grad_norm": 0.24525369703769684, |
| "learning_rate": 4.986622073578595e-06, |
| "loss": 2.6422, |
| "step": 10300 |
| }, |
| { |
| "epoch": 586.0597439544808, |
| "eval_loss": 2.637178421020508, |
| "eval_runtime": 23.9878, |
| "eval_samples_per_second": 58.113, |
| "eval_steps_per_second": 7.295, |
| "step": 10300 |
| }, |
| { |
| "epoch": 591.7496443812233, |
| "grad_norm": 0.20690536499023438, |
| "learning_rate": 4.976588628762542e-06, |
| "loss": 2.6415, |
| "step": 10400 |
| }, |
| { |
| "epoch": 591.7496443812233, |
| "eval_loss": 2.6367316246032715, |
| "eval_runtime": 24.0107, |
| "eval_samples_per_second": 58.057, |
| "eval_steps_per_second": 7.288, |
| "step": 10400 |
| }, |
| { |
| "epoch": 597.4395448079658, |
| "grad_norm": 0.2113800048828125, |
| "learning_rate": 4.966555183946489e-06, |
| "loss": 2.6403, |
| "step": 10500 |
| }, |
| { |
| "epoch": 597.4395448079658, |
| "eval_loss": 2.6348278522491455, |
| "eval_runtime": 23.9887, |
| "eval_samples_per_second": 58.111, |
| "eval_steps_per_second": 7.295, |
| "step": 10500 |
| }, |
| { |
| "epoch": 603.1294452347084, |
| "grad_norm": 0.261877179145813, |
| "learning_rate": 4.956521739130435e-06, |
| "loss": 2.6402, |
| "step": 10600 |
| }, |
| { |
| "epoch": 603.1294452347084, |
| "eval_loss": 2.636289358139038, |
| "eval_runtime": 23.9838, |
| "eval_samples_per_second": 58.123, |
| "eval_steps_per_second": 7.297, |
| "step": 10600 |
| }, |
| { |
| "epoch": 608.8193456614509, |
| "grad_norm": 0.19519160687923431, |
| "learning_rate": 4.9464882943143815e-06, |
| "loss": 2.6397, |
| "step": 10700 |
| }, |
| { |
| "epoch": 608.8193456614509, |
| "eval_loss": 2.6352500915527344, |
| "eval_runtime": 23.9822, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 10700 |
| }, |
| { |
| "epoch": 614.5092460881934, |
| "grad_norm": 0.1956864595413208, |
| "learning_rate": 4.936454849498328e-06, |
| "loss": 2.6389, |
| "step": 10800 |
| }, |
| { |
| "epoch": 614.5092460881934, |
| "eval_loss": 2.6334805488586426, |
| "eval_runtime": 23.9978, |
| "eval_samples_per_second": 58.089, |
| "eval_steps_per_second": 7.292, |
| "step": 10800 |
| }, |
| { |
| "epoch": 620.1991465149359, |
| "grad_norm": 0.23185935616493225, |
| "learning_rate": 4.926421404682274e-06, |
| "loss": 2.6382, |
| "step": 10900 |
| }, |
| { |
| "epoch": 620.1991465149359, |
| "eval_loss": 2.6361021995544434, |
| "eval_runtime": 23.6451, |
| "eval_samples_per_second": 58.955, |
| "eval_steps_per_second": 7.401, |
| "step": 10900 |
| }, |
| { |
| "epoch": 625.8890469416785, |
| "grad_norm": 0.20759572088718414, |
| "learning_rate": 4.916387959866221e-06, |
| "loss": 2.6382, |
| "step": 11000 |
| }, |
| { |
| "epoch": 625.8890469416785, |
| "eval_loss": 2.634660243988037, |
| "eval_runtime": 23.9847, |
| "eval_samples_per_second": 58.12, |
| "eval_steps_per_second": 7.296, |
| "step": 11000 |
| }, |
| { |
| "epoch": 631.578947368421, |
| "grad_norm": 0.24066907167434692, |
| "learning_rate": 4.906354515050168e-06, |
| "loss": 2.6372, |
| "step": 11100 |
| }, |
| { |
| "epoch": 631.578947368421, |
| "eval_loss": 2.6299962997436523, |
| "eval_runtime": 23.979, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.298, |
| "step": 11100 |
| }, |
| { |
| "epoch": 637.2688477951635, |
| "grad_norm": 0.23204158246517181, |
| "learning_rate": 4.8963210702341136e-06, |
| "loss": 2.637, |
| "step": 11200 |
| }, |
| { |
| "epoch": 637.2688477951635, |
| "eval_loss": 2.631197690963745, |
| "eval_runtime": 23.6362, |
| "eval_samples_per_second": 58.977, |
| "eval_steps_per_second": 7.404, |
| "step": 11200 |
| }, |
| { |
| "epoch": 642.9587482219061, |
| "grad_norm": 0.21934348344802856, |
| "learning_rate": 4.88628762541806e-06, |
| "loss": 2.6363, |
| "step": 11300 |
| }, |
| { |
| "epoch": 642.9587482219061, |
| "eval_loss": 2.629666566848755, |
| "eval_runtime": 23.9798, |
| "eval_samples_per_second": 58.132, |
| "eval_steps_per_second": 7.298, |
| "step": 11300 |
| }, |
| { |
| "epoch": 648.6486486486486, |
| "grad_norm": 0.18657149374485016, |
| "learning_rate": 4.876254180602007e-06, |
| "loss": 2.6358, |
| "step": 11400 |
| }, |
| { |
| "epoch": 648.6486486486486, |
| "eval_loss": 2.632611036300659, |
| "eval_runtime": 23.9657, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 11400 |
| }, |
| { |
| "epoch": 654.3385490753911, |
| "grad_norm": 0.2166602909564972, |
| "learning_rate": 4.866220735785953e-06, |
| "loss": 2.6355, |
| "step": 11500 |
| }, |
| { |
| "epoch": 654.3385490753911, |
| "eval_loss": 2.6293506622314453, |
| "eval_runtime": 23.6252, |
| "eval_samples_per_second": 59.005, |
| "eval_steps_per_second": 7.407, |
| "step": 11500 |
| }, |
| { |
| "epoch": 660.0284495021338, |
| "grad_norm": 0.20717021822929382, |
| "learning_rate": 4.8561872909699e-06, |
| "loss": 2.6356, |
| "step": 11600 |
| }, |
| { |
| "epoch": 660.0284495021338, |
| "eval_loss": 2.6316463947296143, |
| "eval_runtime": 23.968, |
| "eval_samples_per_second": 58.161, |
| "eval_steps_per_second": 7.301, |
| "step": 11600 |
| }, |
| { |
| "epoch": 665.7183499288763, |
| "grad_norm": 0.22796860337257385, |
| "learning_rate": 4.8461538461538465e-06, |
| "loss": 2.6347, |
| "step": 11700 |
| }, |
| { |
| "epoch": 665.7183499288763, |
| "eval_loss": 2.6268954277038574, |
| "eval_runtime": 23.9849, |
| "eval_samples_per_second": 58.12, |
| "eval_steps_per_second": 7.296, |
| "step": 11700 |
| }, |
| { |
| "epoch": 671.4082503556187, |
| "grad_norm": 0.20367011427879333, |
| "learning_rate": 4.8361204013377925e-06, |
| "loss": 2.6345, |
| "step": 11800 |
| }, |
| { |
| "epoch": 671.4082503556187, |
| "eval_loss": 2.63277530670166, |
| "eval_runtime": 23.9971, |
| "eval_samples_per_second": 58.09, |
| "eval_steps_per_second": 7.293, |
| "step": 11800 |
| }, |
| { |
| "epoch": 677.0981507823614, |
| "grad_norm": 0.186284601688385, |
| "learning_rate": 4.826086956521739e-06, |
| "loss": 2.6344, |
| "step": 11900 |
| }, |
| { |
| "epoch": 677.0981507823614, |
| "eval_loss": 2.6296372413635254, |
| "eval_runtime": 23.6255, |
| "eval_samples_per_second": 59.004, |
| "eval_steps_per_second": 7.407, |
| "step": 11900 |
| }, |
| { |
| "epoch": 682.7880512091039, |
| "grad_norm": 0.16128043830394745, |
| "learning_rate": 4.816053511705686e-06, |
| "loss": 2.634, |
| "step": 12000 |
| }, |
| { |
| "epoch": 682.7880512091039, |
| "eval_loss": 2.6282401084899902, |
| "eval_runtime": 23.9698, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 12000 |
| }, |
| { |
| "epoch": 688.4779516358464, |
| "grad_norm": 0.21663859486579895, |
| "learning_rate": 4.806020066889633e-06, |
| "loss": 2.6336, |
| "step": 12100 |
| }, |
| { |
| "epoch": 688.4779516358464, |
| "eval_loss": 2.62992525100708, |
| "eval_runtime": 23.9831, |
| "eval_samples_per_second": 58.124, |
| "eval_steps_per_second": 7.297, |
| "step": 12100 |
| }, |
| { |
| "epoch": 694.1678520625888, |
| "grad_norm": 0.15192851424217224, |
| "learning_rate": 4.795986622073579e-06, |
| "loss": 2.6328, |
| "step": 12200 |
| }, |
| { |
| "epoch": 694.1678520625888, |
| "eval_loss": 2.628678321838379, |
| "eval_runtime": 23.9973, |
| "eval_samples_per_second": 58.09, |
| "eval_steps_per_second": 7.292, |
| "step": 12200 |
| }, |
| { |
| "epoch": 699.8577524893315, |
| "grad_norm": 0.22168278694152832, |
| "learning_rate": 4.785953177257525e-06, |
| "loss": 2.6323, |
| "step": 12300 |
| }, |
| { |
| "epoch": 699.8577524893315, |
| "eval_loss": 2.6261205673217773, |
| "eval_runtime": 24.0543, |
| "eval_samples_per_second": 57.952, |
| "eval_steps_per_second": 7.275, |
| "step": 12300 |
| }, |
| { |
| "epoch": 705.547652916074, |
| "grad_norm": 0.1755346953868866, |
| "learning_rate": 4.775919732441472e-06, |
| "loss": 2.6324, |
| "step": 12400 |
| }, |
| { |
| "epoch": 705.547652916074, |
| "eval_loss": 2.6293275356292725, |
| "eval_runtime": 23.6313, |
| "eval_samples_per_second": 58.99, |
| "eval_steps_per_second": 7.405, |
| "step": 12400 |
| }, |
| { |
| "epoch": 711.2375533428165, |
| "grad_norm": 0.21894784271717072, |
| "learning_rate": 4.765886287625418e-06, |
| "loss": 2.6321, |
| "step": 12500 |
| }, |
| { |
| "epoch": 711.2375533428165, |
| "eval_loss": 2.627187967300415, |
| "eval_runtime": 23.9772, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 12500 |
| }, |
| { |
| "epoch": 716.9274537695591, |
| "grad_norm": 0.1610960066318512, |
| "learning_rate": 4.755852842809365e-06, |
| "loss": 2.6319, |
| "step": 12600 |
| }, |
| { |
| "epoch": 716.9274537695591, |
| "eval_loss": 2.6290180683135986, |
| "eval_runtime": 23.9949, |
| "eval_samples_per_second": 58.096, |
| "eval_steps_per_second": 7.293, |
| "step": 12600 |
| }, |
| { |
| "epoch": 722.6173541963016, |
| "grad_norm": 0.24491451680660248, |
| "learning_rate": 4.745819397993312e-06, |
| "loss": 2.6317, |
| "step": 12700 |
| }, |
| { |
| "epoch": 722.6173541963016, |
| "eval_loss": 2.6274964809417725, |
| "eval_runtime": 23.9713, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 12700 |
| }, |
| { |
| "epoch": 728.3072546230441, |
| "grad_norm": 0.16983364522457123, |
| "learning_rate": 4.7357859531772575e-06, |
| "loss": 2.6318, |
| "step": 12800 |
| }, |
| { |
| "epoch": 728.3072546230441, |
| "eval_loss": 2.6273210048675537, |
| "eval_runtime": 23.978, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 12800 |
| }, |
| { |
| "epoch": 733.9971550497867, |
| "grad_norm": 0.17345738410949707, |
| "learning_rate": 4.725752508361204e-06, |
| "loss": 2.6311, |
| "step": 12900 |
| }, |
| { |
| "epoch": 733.9971550497867, |
| "eval_loss": 2.6259231567382812, |
| "eval_runtime": 24.0133, |
| "eval_samples_per_second": 58.051, |
| "eval_steps_per_second": 7.288, |
| "step": 12900 |
| }, |
| { |
| "epoch": 739.6870554765292, |
| "grad_norm": 0.21643972396850586, |
| "learning_rate": 4.715719063545151e-06, |
| "loss": 2.631, |
| "step": 13000 |
| }, |
| { |
| "epoch": 739.6870554765292, |
| "eval_loss": 2.6242847442626953, |
| "eval_runtime": 23.975, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 13000 |
| }, |
| { |
| "epoch": 745.3769559032717, |
| "grad_norm": 0.1840481460094452, |
| "learning_rate": 4.705685618729097e-06, |
| "loss": 2.6308, |
| "step": 13100 |
| }, |
| { |
| "epoch": 745.3769559032717, |
| "eval_loss": 2.6283822059631348, |
| "eval_runtime": 24.0095, |
| "eval_samples_per_second": 58.06, |
| "eval_steps_per_second": 7.289, |
| "step": 13100 |
| }, |
| { |
| "epoch": 751.0668563300143, |
| "grad_norm": 0.23446989059448242, |
| "learning_rate": 4.695652173913044e-06, |
| "loss": 2.6304, |
| "step": 13200 |
| }, |
| { |
| "epoch": 751.0668563300143, |
| "eval_loss": 2.629518985748291, |
| "eval_runtime": 23.978, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 13200 |
| }, |
| { |
| "epoch": 756.7567567567568, |
| "grad_norm": 0.19253458082675934, |
| "learning_rate": 4.6856187290969905e-06, |
| "loss": 2.6298, |
| "step": 13300 |
| }, |
| { |
| "epoch": 756.7567567567568, |
| "eval_loss": 2.624861001968384, |
| "eval_runtime": 23.9689, |
| "eval_samples_per_second": 58.159, |
| "eval_steps_per_second": 7.301, |
| "step": 13300 |
| }, |
| { |
| "epoch": 762.4466571834993, |
| "grad_norm": 0.18916001915931702, |
| "learning_rate": 4.675585284280936e-06, |
| "loss": 2.6295, |
| "step": 13400 |
| }, |
| { |
| "epoch": 762.4466571834993, |
| "eval_loss": 2.6245834827423096, |
| "eval_runtime": 23.6275, |
| "eval_samples_per_second": 58.999, |
| "eval_steps_per_second": 7.407, |
| "step": 13400 |
| }, |
| { |
| "epoch": 768.1365576102418, |
| "grad_norm": 0.18140235543251038, |
| "learning_rate": 4.665551839464883e-06, |
| "loss": 2.6294, |
| "step": 13500 |
| }, |
| { |
| "epoch": 768.1365576102418, |
| "eval_loss": 2.6280317306518555, |
| "eval_runtime": 23.9728, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 13500 |
| }, |
| { |
| "epoch": 773.8264580369844, |
| "grad_norm": 0.2032419890165329, |
| "learning_rate": 4.65551839464883e-06, |
| "loss": 2.6296, |
| "step": 13600 |
| }, |
| { |
| "epoch": 773.8264580369844, |
| "eval_loss": 2.625180721282959, |
| "eval_runtime": 23.9783, |
| "eval_samples_per_second": 58.136, |
| "eval_steps_per_second": 7.298, |
| "step": 13600 |
| }, |
| { |
| "epoch": 779.5163584637269, |
| "grad_norm": 0.19860903918743134, |
| "learning_rate": 4.645484949832776e-06, |
| "loss": 2.6285, |
| "step": 13700 |
| }, |
| { |
| "epoch": 779.5163584637269, |
| "eval_loss": 2.6238112449645996, |
| "eval_runtime": 23.6456, |
| "eval_samples_per_second": 58.954, |
| "eval_steps_per_second": 7.401, |
| "step": 13700 |
| }, |
| { |
| "epoch": 785.2062588904694, |
| "grad_norm": 0.19440245628356934, |
| "learning_rate": 4.635451505016723e-06, |
| "loss": 2.6288, |
| "step": 13800 |
| }, |
| { |
| "epoch": 785.2062588904694, |
| "eval_loss": 2.625662088394165, |
| "eval_runtime": 23.9906, |
| "eval_samples_per_second": 58.106, |
| "eval_steps_per_second": 7.295, |
| "step": 13800 |
| }, |
| { |
| "epoch": 790.896159317212, |
| "grad_norm": 0.2409134954214096, |
| "learning_rate": 4.625418060200669e-06, |
| "loss": 2.6283, |
| "step": 13900 |
| }, |
| { |
| "epoch": 790.896159317212, |
| "eval_loss": 2.626107931137085, |
| "eval_runtime": 23.9912, |
| "eval_samples_per_second": 58.105, |
| "eval_steps_per_second": 7.294, |
| "step": 13900 |
| }, |
| { |
| "epoch": 796.5860597439545, |
| "grad_norm": 0.19188816845417023, |
| "learning_rate": 4.615384615384616e-06, |
| "loss": 2.6282, |
| "step": 14000 |
| }, |
| { |
| "epoch": 796.5860597439545, |
| "eval_loss": 2.6254701614379883, |
| "eval_runtime": 23.969, |
| "eval_samples_per_second": 58.158, |
| "eval_steps_per_second": 7.301, |
| "step": 14000 |
| }, |
| { |
| "epoch": 802.275960170697, |
| "grad_norm": 0.2168819010257721, |
| "learning_rate": 4.605351170568562e-06, |
| "loss": 2.6277, |
| "step": 14100 |
| }, |
| { |
| "epoch": 802.275960170697, |
| "eval_loss": 2.6247129440307617, |
| "eval_runtime": 23.9775, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 14100 |
| }, |
| { |
| "epoch": 807.9658605974396, |
| "grad_norm": 0.21990340948104858, |
| "learning_rate": 4.595317725752509e-06, |
| "loss": 2.6282, |
| "step": 14200 |
| }, |
| { |
| "epoch": 807.9658605974396, |
| "eval_loss": 2.6232125759124756, |
| "eval_runtime": 23.9967, |
| "eval_samples_per_second": 58.091, |
| "eval_steps_per_second": 7.293, |
| "step": 14200 |
| }, |
| { |
| "epoch": 813.6557610241821, |
| "grad_norm": 0.21468599140644073, |
| "learning_rate": 4.585284280936456e-06, |
| "loss": 2.6275, |
| "step": 14300 |
| }, |
| { |
| "epoch": 813.6557610241821, |
| "eval_loss": 2.622816324234009, |
| "eval_runtime": 23.9966, |
| "eval_samples_per_second": 58.092, |
| "eval_steps_per_second": 7.293, |
| "step": 14300 |
| }, |
| { |
| "epoch": 819.3456614509246, |
| "grad_norm": 0.18678580224514008, |
| "learning_rate": 4.5752508361204015e-06, |
| "loss": 2.6269, |
| "step": 14400 |
| }, |
| { |
| "epoch": 819.3456614509246, |
| "eval_loss": 2.6258599758148193, |
| "eval_runtime": 23.9926, |
| "eval_samples_per_second": 58.101, |
| "eval_steps_per_second": 7.294, |
| "step": 14400 |
| }, |
| { |
| "epoch": 825.0355618776672, |
| "grad_norm": 0.18838590383529663, |
| "learning_rate": 4.565217391304348e-06, |
| "loss": 2.6267, |
| "step": 14500 |
| }, |
| { |
| "epoch": 825.0355618776672, |
| "eval_loss": 2.6210570335388184, |
| "eval_runtime": 23.9725, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 14500 |
| }, |
| { |
| "epoch": 830.7254623044097, |
| "grad_norm": 0.19508691132068634, |
| "learning_rate": 4.555183946488295e-06, |
| "loss": 2.6266, |
| "step": 14600 |
| }, |
| { |
| "epoch": 830.7254623044097, |
| "eval_loss": 2.6242544651031494, |
| "eval_runtime": 23.6209, |
| "eval_samples_per_second": 59.016, |
| "eval_steps_per_second": 7.409, |
| "step": 14600 |
| }, |
| { |
| "epoch": 836.4153627311522, |
| "grad_norm": 0.16247296333312988, |
| "learning_rate": 4.545150501672241e-06, |
| "loss": 2.6269, |
| "step": 14700 |
| }, |
| { |
| "epoch": 836.4153627311522, |
| "eval_loss": 2.622783899307251, |
| "eval_runtime": 24.0053, |
| "eval_samples_per_second": 58.071, |
| "eval_steps_per_second": 7.29, |
| "step": 14700 |
| }, |
| { |
| "epoch": 842.1052631578947, |
| "grad_norm": 0.16786298155784607, |
| "learning_rate": 4.535117056856188e-06, |
| "loss": 2.6265, |
| "step": 14800 |
| }, |
| { |
| "epoch": 842.1052631578947, |
| "eval_loss": 2.6206467151641846, |
| "eval_runtime": 23.9727, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 14800 |
| }, |
| { |
| "epoch": 847.7951635846373, |
| "grad_norm": 0.16687853634357452, |
| "learning_rate": 4.5250836120401345e-06, |
| "loss": 2.6264, |
| "step": 14900 |
| }, |
| { |
| "epoch": 847.7951635846373, |
| "eval_loss": 2.622387409210205, |
| "eval_runtime": 23.9866, |
| "eval_samples_per_second": 58.116, |
| "eval_steps_per_second": 7.296, |
| "step": 14900 |
| }, |
| { |
| "epoch": 853.4850640113798, |
| "grad_norm": 0.16502691805362701, |
| "learning_rate": 4.51505016722408e-06, |
| "loss": 2.6256, |
| "step": 15000 |
| }, |
| { |
| "epoch": 853.4850640113798, |
| "eval_loss": 2.6233725547790527, |
| "eval_runtime": 23.9809, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.297, |
| "step": 15000 |
| }, |
| { |
| "epoch": 859.1749644381223, |
| "grad_norm": 0.1729804426431656, |
| "learning_rate": 4.505016722408027e-06, |
| "loss": 2.6261, |
| "step": 15100 |
| }, |
| { |
| "epoch": 859.1749644381223, |
| "eval_loss": 2.6231296062469482, |
| "eval_runtime": 23.6331, |
| "eval_samples_per_second": 58.985, |
| "eval_steps_per_second": 7.405, |
| "step": 15100 |
| }, |
| { |
| "epoch": 864.8648648648649, |
| "grad_norm": 0.1754722148180008, |
| "learning_rate": 4.494983277591973e-06, |
| "loss": 2.6255, |
| "step": 15200 |
| }, |
| { |
| "epoch": 864.8648648648649, |
| "eval_loss": 2.6251132488250732, |
| "eval_runtime": 23.9803, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 15200 |
| }, |
| { |
| "epoch": 870.5547652916074, |
| "grad_norm": 0.18603281676769257, |
| "learning_rate": 4.48494983277592e-06, |
| "loss": 2.6254, |
| "step": 15300 |
| }, |
| { |
| "epoch": 870.5547652916074, |
| "eval_loss": 2.62117600440979, |
| "eval_runtime": 23.9772, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 15300 |
| }, |
| { |
| "epoch": 876.2446657183499, |
| "grad_norm": 0.1606762558221817, |
| "learning_rate": 4.474916387959866e-06, |
| "loss": 2.6254, |
| "step": 15400 |
| }, |
| { |
| "epoch": 876.2446657183499, |
| "eval_loss": 2.6225478649139404, |
| "eval_runtime": 23.9822, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 15400 |
| }, |
| { |
| "epoch": 881.9345661450925, |
| "grad_norm": 0.2024741768836975, |
| "learning_rate": 4.4648829431438125e-06, |
| "loss": 2.6253, |
| "step": 15500 |
| }, |
| { |
| "epoch": 881.9345661450925, |
| "eval_loss": 2.6233015060424805, |
| "eval_runtime": 23.9634, |
| "eval_samples_per_second": 58.172, |
| "eval_steps_per_second": 7.303, |
| "step": 15500 |
| }, |
| { |
| "epoch": 887.624466571835, |
| "grad_norm": 0.15303322672843933, |
| "learning_rate": 4.454849498327759e-06, |
| "loss": 2.625, |
| "step": 15600 |
| }, |
| { |
| "epoch": 887.624466571835, |
| "eval_loss": 2.6242151260375977, |
| "eval_runtime": 23.9778, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 15600 |
| }, |
| { |
| "epoch": 893.3143669985775, |
| "grad_norm": 0.1664353907108307, |
| "learning_rate": 4.444816053511705e-06, |
| "loss": 2.6249, |
| "step": 15700 |
| }, |
| { |
| "epoch": 893.3143669985775, |
| "eval_loss": 2.6248691082000732, |
| "eval_runtime": 23.6226, |
| "eval_samples_per_second": 59.011, |
| "eval_steps_per_second": 7.408, |
| "step": 15700 |
| }, |
| { |
| "epoch": 899.0042674253201, |
| "grad_norm": 0.19236522912979126, |
| "learning_rate": 4.434782608695652e-06, |
| "loss": 2.6246, |
| "step": 15800 |
| }, |
| { |
| "epoch": 899.0042674253201, |
| "eval_loss": 2.621826410293579, |
| "eval_runtime": 23.9772, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 15800 |
| }, |
| { |
| "epoch": 904.6941678520626, |
| "grad_norm": 0.18655799329280853, |
| "learning_rate": 4.424749163879599e-06, |
| "loss": 2.6245, |
| "step": 15900 |
| }, |
| { |
| "epoch": 904.6941678520626, |
| "eval_loss": 2.6243951320648193, |
| "eval_runtime": 23.976, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 15900 |
| }, |
| { |
| "epoch": 910.3840682788051, |
| "grad_norm": 0.1743532419204712, |
| "learning_rate": 4.414715719063545e-06, |
| "loss": 2.6241, |
| "step": 16000 |
| }, |
| { |
| "epoch": 910.3840682788051, |
| "eval_loss": 2.6209657192230225, |
| "eval_runtime": 23.9767, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 16000 |
| }, |
| { |
| "epoch": 916.0739687055476, |
| "grad_norm": 0.1673664003610611, |
| "learning_rate": 4.404682274247491e-06, |
| "loss": 2.6244, |
| "step": 16100 |
| }, |
| { |
| "epoch": 916.0739687055476, |
| "eval_loss": 2.619206190109253, |
| "eval_runtime": 23.9866, |
| "eval_samples_per_second": 58.116, |
| "eval_steps_per_second": 7.296, |
| "step": 16100 |
| }, |
| { |
| "epoch": 921.7638691322902, |
| "grad_norm": 0.19697995483875275, |
| "learning_rate": 4.394648829431438e-06, |
| "loss": 2.6236, |
| "step": 16200 |
| }, |
| { |
| "epoch": 921.7638691322902, |
| "eval_loss": 2.625276565551758, |
| "eval_runtime": 23.6215, |
| "eval_samples_per_second": 59.014, |
| "eval_steps_per_second": 7.409, |
| "step": 16200 |
| }, |
| { |
| "epoch": 927.4537695590327, |
| "grad_norm": 0.21309681236743927, |
| "learning_rate": 4.384615384615384e-06, |
| "loss": 2.6238, |
| "step": 16300 |
| }, |
| { |
| "epoch": 927.4537695590327, |
| "eval_loss": 2.6223998069763184, |
| "eval_runtime": 23.9648, |
| "eval_samples_per_second": 58.169, |
| "eval_steps_per_second": 7.302, |
| "step": 16300 |
| }, |
| { |
| "epoch": 933.1436699857752, |
| "grad_norm": 0.18199092149734497, |
| "learning_rate": 4.374581939799331e-06, |
| "loss": 2.6235, |
| "step": 16400 |
| }, |
| { |
| "epoch": 933.1436699857752, |
| "eval_loss": 2.621734380722046, |
| "eval_runtime": 24.0006, |
| "eval_samples_per_second": 58.082, |
| "eval_steps_per_second": 7.291, |
| "step": 16400 |
| }, |
| { |
| "epoch": 938.8335704125178, |
| "grad_norm": 0.1346639096736908, |
| "learning_rate": 4.364548494983278e-06, |
| "loss": 2.6229, |
| "step": 16500 |
| }, |
| { |
| "epoch": 938.8335704125178, |
| "eval_loss": 2.6209397315979004, |
| "eval_runtime": 23.9903, |
| "eval_samples_per_second": 58.107, |
| "eval_steps_per_second": 7.295, |
| "step": 16500 |
| }, |
| { |
| "epoch": 944.5234708392603, |
| "grad_norm": 0.172411248087883, |
| "learning_rate": 4.354515050167224e-06, |
| "loss": 2.6234, |
| "step": 16600 |
| }, |
| { |
| "epoch": 944.5234708392603, |
| "eval_loss": 2.622432231903076, |
| "eval_runtime": 23.6313, |
| "eval_samples_per_second": 58.99, |
| "eval_steps_per_second": 7.405, |
| "step": 16600 |
| }, |
| { |
| "epoch": 950.2133712660028, |
| "grad_norm": 0.18165941536426544, |
| "learning_rate": 4.34448160535117e-06, |
| "loss": 2.6233, |
| "step": 16700 |
| }, |
| { |
| "epoch": 950.2133712660028, |
| "eval_loss": 2.622363567352295, |
| "eval_runtime": 23.9675, |
| "eval_samples_per_second": 58.162, |
| "eval_steps_per_second": 7.302, |
| "step": 16700 |
| }, |
| { |
| "epoch": 955.9032716927454, |
| "grad_norm": 0.1533946692943573, |
| "learning_rate": 4.334448160535117e-06, |
| "loss": 2.6231, |
| "step": 16800 |
| }, |
| { |
| "epoch": 955.9032716927454, |
| "eval_loss": 2.622138738632202, |
| "eval_runtime": 23.984, |
| "eval_samples_per_second": 58.122, |
| "eval_steps_per_second": 7.297, |
| "step": 16800 |
| }, |
| { |
| "epoch": 961.5931721194879, |
| "grad_norm": 0.16410088539123535, |
| "learning_rate": 4.324414715719064e-06, |
| "loss": 2.623, |
| "step": 16900 |
| }, |
| { |
| "epoch": 961.5931721194879, |
| "eval_loss": 2.6216089725494385, |
| "eval_runtime": 22.7206, |
| "eval_samples_per_second": 61.354, |
| "eval_steps_per_second": 7.702, |
| "step": 16900 |
| }, |
| { |
| "epoch": 967.2830725462304, |
| "grad_norm": 0.1414816975593567, |
| "learning_rate": 4.31438127090301e-06, |
| "loss": 2.6231, |
| "step": 17000 |
| }, |
| { |
| "epoch": 967.2830725462304, |
| "eval_loss": 2.620095729827881, |
| "eval_runtime": 23.9864, |
| "eval_samples_per_second": 58.116, |
| "eval_steps_per_second": 7.296, |
| "step": 17000 |
| }, |
| { |
| "epoch": 972.972972972973, |
| "grad_norm": 0.1808498054742813, |
| "learning_rate": 4.3043478260869565e-06, |
| "loss": 2.6226, |
| "step": 17100 |
| }, |
| { |
| "epoch": 972.972972972973, |
| "eval_loss": 2.620466947555542, |
| "eval_runtime": 23.6354, |
| "eval_samples_per_second": 58.979, |
| "eval_steps_per_second": 7.404, |
| "step": 17100 |
| }, |
| { |
| "epoch": 978.6628733997155, |
| "grad_norm": 0.18205687403678894, |
| "learning_rate": 4.294314381270903e-06, |
| "loss": 2.6222, |
| "step": 17200 |
| }, |
| { |
| "epoch": 978.6628733997155, |
| "eval_loss": 2.622086763381958, |
| "eval_runtime": 23.9861, |
| "eval_samples_per_second": 58.117, |
| "eval_steps_per_second": 7.296, |
| "step": 17200 |
| }, |
| { |
| "epoch": 984.352773826458, |
| "grad_norm": 0.16486555337905884, |
| "learning_rate": 4.284280936454849e-06, |
| "loss": 2.6226, |
| "step": 17300 |
| }, |
| { |
| "epoch": 984.352773826458, |
| "eval_loss": 2.6206889152526855, |
| "eval_runtime": 23.9904, |
| "eval_samples_per_second": 58.107, |
| "eval_steps_per_second": 7.295, |
| "step": 17300 |
| }, |
| { |
| "epoch": 990.0426742532005, |
| "grad_norm": 0.17627450823783875, |
| "learning_rate": 4.274247491638796e-06, |
| "loss": 2.6221, |
| "step": 17400 |
| }, |
| { |
| "epoch": 990.0426742532005, |
| "eval_loss": 2.6199347972869873, |
| "eval_runtime": 24.0002, |
| "eval_samples_per_second": 58.083, |
| "eval_steps_per_second": 7.292, |
| "step": 17400 |
| }, |
| { |
| "epoch": 995.7325746799431, |
| "grad_norm": 0.179404616355896, |
| "learning_rate": 4.264214046822743e-06, |
| "loss": 2.622, |
| "step": 17500 |
| }, |
| { |
| "epoch": 995.7325746799431, |
| "eval_loss": 2.6224658489227295, |
| "eval_runtime": 23.9811, |
| "eval_samples_per_second": 58.129, |
| "eval_steps_per_second": 7.297, |
| "step": 17500 |
| }, |
| { |
| "epoch": 1001.4224751066856, |
| "grad_norm": 0.1570415049791336, |
| "learning_rate": 4.254180602006689e-06, |
| "loss": 2.6221, |
| "step": 17600 |
| }, |
| { |
| "epoch": 1001.4224751066856, |
| "eval_loss": 2.6203651428222656, |
| "eval_runtime": 23.9819, |
| "eval_samples_per_second": 58.127, |
| "eval_steps_per_second": 7.297, |
| "step": 17600 |
| }, |
| { |
| "epoch": 1007.1123755334281, |
| "grad_norm": 0.166086807847023, |
| "learning_rate": 4.244147157190635e-06, |
| "loss": 2.6216, |
| "step": 17700 |
| }, |
| { |
| "epoch": 1007.1123755334281, |
| "eval_loss": 2.619248390197754, |
| "eval_runtime": 23.9859, |
| "eval_samples_per_second": 58.118, |
| "eval_steps_per_second": 7.296, |
| "step": 17700 |
| }, |
| { |
| "epoch": 1012.8022759601707, |
| "grad_norm": 0.20893247425556183, |
| "learning_rate": 4.234113712374582e-06, |
| "loss": 2.6218, |
| "step": 17800 |
| }, |
| { |
| "epoch": 1012.8022759601707, |
| "eval_loss": 2.6189231872558594, |
| "eval_runtime": 23.9924, |
| "eval_samples_per_second": 58.102, |
| "eval_steps_per_second": 7.294, |
| "step": 17800 |
| }, |
| { |
| "epoch": 1018.4921763869132, |
| "grad_norm": 0.1779673546552658, |
| "learning_rate": 4.224080267558528e-06, |
| "loss": 2.6213, |
| "step": 17900 |
| }, |
| { |
| "epoch": 1018.4921763869132, |
| "eval_loss": 2.6191885471343994, |
| "eval_runtime": 23.6149, |
| "eval_samples_per_second": 59.031, |
| "eval_steps_per_second": 7.411, |
| "step": 17900 |
| }, |
| { |
| "epoch": 1024.1820768136558, |
| "grad_norm": 0.1736188530921936, |
| "learning_rate": 4.214046822742475e-06, |
| "loss": 2.621, |
| "step": 18000 |
| }, |
| { |
| "epoch": 1024.1820768136558, |
| "eval_loss": 2.619549036026001, |
| "eval_runtime": 23.9787, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 18000 |
| }, |
| { |
| "epoch": 1029.8719772403983, |
| "grad_norm": 0.17679837346076965, |
| "learning_rate": 4.2040133779264216e-06, |
| "loss": 2.6215, |
| "step": 18100 |
| }, |
| { |
| "epoch": 1029.8719772403983, |
| "eval_loss": 2.620149612426758, |
| "eval_runtime": 23.9841, |
| "eval_samples_per_second": 58.122, |
| "eval_steps_per_second": 7.296, |
| "step": 18100 |
| }, |
| { |
| "epoch": 1035.5618776671408, |
| "grad_norm": 0.18855205178260803, |
| "learning_rate": 4.1939799331103675e-06, |
| "loss": 2.6209, |
| "step": 18200 |
| }, |
| { |
| "epoch": 1035.5618776671408, |
| "eval_loss": 2.620770215988159, |
| "eval_runtime": 23.9826, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 18200 |
| }, |
| { |
| "epoch": 1041.2517780938833, |
| "grad_norm": 0.15188181400299072, |
| "learning_rate": 4.183946488294314e-06, |
| "loss": 2.6209, |
| "step": 18300 |
| }, |
| { |
| "epoch": 1041.2517780938833, |
| "eval_loss": 2.6219208240509033, |
| "eval_runtime": 23.99, |
| "eval_samples_per_second": 58.108, |
| "eval_steps_per_second": 7.295, |
| "step": 18300 |
| }, |
| { |
| "epoch": 1046.9416785206258, |
| "grad_norm": 0.19299472868442535, |
| "learning_rate": 4.173913043478261e-06, |
| "loss": 2.6207, |
| "step": 18400 |
| }, |
| { |
| "epoch": 1046.9416785206258, |
| "eval_loss": 2.6227285861968994, |
| "eval_runtime": 23.9808, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.298, |
| "step": 18400 |
| }, |
| { |
| "epoch": 1052.6315789473683, |
| "grad_norm": 0.19672277569770813, |
| "learning_rate": 4.163879598662208e-06, |
| "loss": 2.6208, |
| "step": 18500 |
| }, |
| { |
| "epoch": 1052.6315789473683, |
| "eval_loss": 2.6191093921661377, |
| "eval_runtime": 23.979, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.298, |
| "step": 18500 |
| }, |
| { |
| "epoch": 1058.321479374111, |
| "grad_norm": 0.15439458191394806, |
| "learning_rate": 4.153846153846154e-06, |
| "loss": 2.6209, |
| "step": 18600 |
| }, |
| { |
| "epoch": 1058.321479374111, |
| "eval_loss": 2.6170802116394043, |
| "eval_runtime": 23.6298, |
| "eval_samples_per_second": 58.993, |
| "eval_steps_per_second": 7.406, |
| "step": 18600 |
| }, |
| { |
| "epoch": 1064.0113798008535, |
| "grad_norm": 0.16907408833503723, |
| "learning_rate": 4.1438127090301005e-06, |
| "loss": 2.6204, |
| "step": 18700 |
| }, |
| { |
| "epoch": 1064.0113798008535, |
| "eval_loss": 2.616074323654175, |
| "eval_runtime": 23.9815, |
| "eval_samples_per_second": 58.128, |
| "eval_steps_per_second": 7.297, |
| "step": 18700 |
| }, |
| { |
| "epoch": 1069.701280227596, |
| "grad_norm": 0.15719492733478546, |
| "learning_rate": 4.133779264214047e-06, |
| "loss": 2.6202, |
| "step": 18800 |
| }, |
| { |
| "epoch": 1069.701280227596, |
| "eval_loss": 2.6210148334503174, |
| "eval_runtime": 23.9903, |
| "eval_samples_per_second": 58.107, |
| "eval_steps_per_second": 7.295, |
| "step": 18800 |
| }, |
| { |
| "epoch": 1075.3911806543385, |
| "grad_norm": 0.17413724958896637, |
| "learning_rate": 4.123745819397993e-06, |
| "loss": 2.6198, |
| "step": 18900 |
| }, |
| { |
| "epoch": 1075.3911806543385, |
| "eval_loss": 2.6156530380249023, |
| "eval_runtime": 23.991, |
| "eval_samples_per_second": 58.105, |
| "eval_steps_per_second": 7.294, |
| "step": 18900 |
| }, |
| { |
| "epoch": 1081.081081081081, |
| "grad_norm": 0.2030758559703827, |
| "learning_rate": 4.11371237458194e-06, |
| "loss": 2.6196, |
| "step": 19000 |
| }, |
| { |
| "epoch": 1081.081081081081, |
| "eval_loss": 2.619901180267334, |
| "eval_runtime": 23.9766, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 19000 |
| }, |
| { |
| "epoch": 1086.7709815078235, |
| "grad_norm": 0.1614978164434433, |
| "learning_rate": 4.103678929765887e-06, |
| "loss": 2.6191, |
| "step": 19100 |
| }, |
| { |
| "epoch": 1086.7709815078235, |
| "eval_loss": 2.6212069988250732, |
| "eval_runtime": 23.9883, |
| "eval_samples_per_second": 58.112, |
| "eval_steps_per_second": 7.295, |
| "step": 19100 |
| }, |
| { |
| "epoch": 1092.460881934566, |
| "grad_norm": 0.17999444901943207, |
| "learning_rate": 4.0936454849498326e-06, |
| "loss": 2.6194, |
| "step": 19200 |
| }, |
| { |
| "epoch": 1092.460881934566, |
| "eval_loss": 2.6198325157165527, |
| "eval_runtime": 23.9861, |
| "eval_samples_per_second": 58.117, |
| "eval_steps_per_second": 7.296, |
| "step": 19200 |
| }, |
| { |
| "epoch": 1098.1507823613088, |
| "grad_norm": 0.18121473491191864, |
| "learning_rate": 4.083612040133779e-06, |
| "loss": 2.6197, |
| "step": 19300 |
| }, |
| { |
| "epoch": 1098.1507823613088, |
| "eval_loss": 2.6189935207366943, |
| "eval_runtime": 23.9907, |
| "eval_samples_per_second": 58.106, |
| "eval_steps_per_second": 7.295, |
| "step": 19300 |
| }, |
| { |
| "epoch": 1103.8406827880513, |
| "grad_norm": 0.21219174563884735, |
| "learning_rate": 4.073578595317726e-06, |
| "loss": 2.6195, |
| "step": 19400 |
| }, |
| { |
| "epoch": 1103.8406827880513, |
| "eval_loss": 2.620710611343384, |
| "eval_runtime": 21.6561, |
| "eval_samples_per_second": 64.37, |
| "eval_steps_per_second": 8.081, |
| "step": 19400 |
| }, |
| { |
| "epoch": 1109.5305832147938, |
| "grad_norm": 0.17006872594356537, |
| "learning_rate": 4.063545150501672e-06, |
| "loss": 2.6191, |
| "step": 19500 |
| }, |
| { |
| "epoch": 1109.5305832147938, |
| "eval_loss": 2.6186723709106445, |
| "eval_runtime": 23.9787, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 19500 |
| }, |
| { |
| "epoch": 1115.2204836415362, |
| "grad_norm": 0.18167956173419952, |
| "learning_rate": 4.053511705685619e-06, |
| "loss": 2.6184, |
| "step": 19600 |
| }, |
| { |
| "epoch": 1115.2204836415362, |
| "eval_loss": 2.6187093257904053, |
| "eval_runtime": 23.6119, |
| "eval_samples_per_second": 59.038, |
| "eval_steps_per_second": 7.412, |
| "step": 19600 |
| }, |
| { |
| "epoch": 1120.9103840682787, |
| "grad_norm": 0.17147672176361084, |
| "learning_rate": 4.0434782608695655e-06, |
| "loss": 2.6191, |
| "step": 19700 |
| }, |
| { |
| "epoch": 1120.9103840682787, |
| "eval_loss": 2.6219475269317627, |
| "eval_runtime": 23.9735, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 19700 |
| }, |
| { |
| "epoch": 1126.6002844950212, |
| "grad_norm": 0.1981355994939804, |
| "learning_rate": 4.0334448160535115e-06, |
| "loss": 2.619, |
| "step": 19800 |
| }, |
| { |
| "epoch": 1126.6002844950212, |
| "eval_loss": 2.61908221244812, |
| "eval_runtime": 23.9658, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 19800 |
| }, |
| { |
| "epoch": 1132.290184921764, |
| "grad_norm": 0.17601875960826874, |
| "learning_rate": 4.023411371237458e-06, |
| "loss": 2.6185, |
| "step": 19900 |
| }, |
| { |
| "epoch": 1132.290184921764, |
| "eval_loss": 2.6192004680633545, |
| "eval_runtime": 23.9779, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 19900 |
| }, |
| { |
| "epoch": 1137.9800853485065, |
| "grad_norm": 0.16543589532375336, |
| "learning_rate": 4.013377926421405e-06, |
| "loss": 2.6186, |
| "step": 20000 |
| }, |
| { |
| "epoch": 1137.9800853485065, |
| "eval_loss": 2.617563247680664, |
| "eval_runtime": 23.9718, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 20000 |
| }, |
| { |
| "epoch": 1143.669985775249, |
| "grad_norm": 0.1984323263168335, |
| "learning_rate": 4.003344481605351e-06, |
| "loss": 2.6177, |
| "step": 20100 |
| }, |
| { |
| "epoch": 1143.669985775249, |
| "eval_loss": 2.6192288398742676, |
| "eval_runtime": 23.959, |
| "eval_samples_per_second": 58.183, |
| "eval_steps_per_second": 7.304, |
| "step": 20100 |
| }, |
| { |
| "epoch": 1149.3598862019915, |
| "grad_norm": 0.1759239286184311, |
| "learning_rate": 3.993311036789298e-06, |
| "loss": 2.618, |
| "step": 20200 |
| }, |
| { |
| "epoch": 1149.3598862019915, |
| "eval_loss": 2.6187233924865723, |
| "eval_runtime": 23.9823, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 20200 |
| }, |
| { |
| "epoch": 1155.049786628734, |
| "grad_norm": 0.174777090549469, |
| "learning_rate": 3.9832775919732444e-06, |
| "loss": 2.618, |
| "step": 20300 |
| }, |
| { |
| "epoch": 1155.049786628734, |
| "eval_loss": 2.6186254024505615, |
| "eval_runtime": 23.6342, |
| "eval_samples_per_second": 58.982, |
| "eval_steps_per_second": 7.405, |
| "step": 20300 |
| }, |
| { |
| "epoch": 1160.7396870554765, |
| "grad_norm": 0.16251406073570251, |
| "learning_rate": 3.97324414715719e-06, |
| "loss": 2.6176, |
| "step": 20400 |
| }, |
| { |
| "epoch": 1160.7396870554765, |
| "eval_loss": 2.617729425430298, |
| "eval_runtime": 23.9981, |
| "eval_samples_per_second": 58.088, |
| "eval_steps_per_second": 7.292, |
| "step": 20400 |
| }, |
| { |
| "epoch": 1166.429587482219, |
| "grad_norm": 0.14838360249996185, |
| "learning_rate": 3.963210702341137e-06, |
| "loss": 2.6181, |
| "step": 20500 |
| }, |
| { |
| "epoch": 1166.429587482219, |
| "eval_loss": 2.6153714656829834, |
| "eval_runtime": 23.9768, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 20500 |
| }, |
| { |
| "epoch": 1172.1194879089617, |
| "grad_norm": 0.1753985583782196, |
| "learning_rate": 3.953177257525084e-06, |
| "loss": 2.6179, |
| "step": 20600 |
| }, |
| { |
| "epoch": 1172.1194879089617, |
| "eval_loss": 2.618314743041992, |
| "eval_runtime": 23.9673, |
| "eval_samples_per_second": 58.163, |
| "eval_steps_per_second": 7.302, |
| "step": 20600 |
| }, |
| { |
| "epoch": 1177.8093883357042, |
| "grad_norm": 0.18267270922660828, |
| "learning_rate": 3.943143812709031e-06, |
| "loss": 2.6176, |
| "step": 20700 |
| }, |
| { |
| "epoch": 1177.8093883357042, |
| "eval_loss": 2.6154963970184326, |
| "eval_runtime": 23.9756, |
| "eval_samples_per_second": 58.142, |
| "eval_steps_per_second": 7.299, |
| "step": 20700 |
| }, |
| { |
| "epoch": 1183.4992887624467, |
| "grad_norm": 0.16119986772537231, |
| "learning_rate": 3.9331103678929765e-06, |
| "loss": 2.6176, |
| "step": 20800 |
| }, |
| { |
| "epoch": 1183.4992887624467, |
| "eval_loss": 2.6163604259490967, |
| "eval_runtime": 23.9848, |
| "eval_samples_per_second": 58.12, |
| "eval_steps_per_second": 7.296, |
| "step": 20800 |
| }, |
| { |
| "epoch": 1189.1891891891892, |
| "grad_norm": 0.1592591255903244, |
| "learning_rate": 3.923076923076923e-06, |
| "loss": 2.6166, |
| "step": 20900 |
| }, |
| { |
| "epoch": 1189.1891891891892, |
| "eval_loss": 2.617856979370117, |
| "eval_runtime": 23.6131, |
| "eval_samples_per_second": 59.035, |
| "eval_steps_per_second": 7.411, |
| "step": 20900 |
| }, |
| { |
| "epoch": 1194.8790896159317, |
| "grad_norm": 0.16023056209087372, |
| "learning_rate": 3.91304347826087e-06, |
| "loss": 2.6173, |
| "step": 21000 |
| }, |
| { |
| "epoch": 1194.8790896159317, |
| "eval_loss": 2.61501407623291, |
| "eval_runtime": 23.9703, |
| "eval_samples_per_second": 58.155, |
| "eval_steps_per_second": 7.301, |
| "step": 21000 |
| }, |
| { |
| "epoch": 1200.5689900426742, |
| "grad_norm": 0.1646001935005188, |
| "learning_rate": 3.903010033444816e-06, |
| "loss": 2.6172, |
| "step": 21100 |
| }, |
| { |
| "epoch": 1200.5689900426742, |
| "eval_loss": 2.6198084354400635, |
| "eval_runtime": 23.9829, |
| "eval_samples_per_second": 58.125, |
| "eval_steps_per_second": 7.297, |
| "step": 21100 |
| }, |
| { |
| "epoch": 1206.2588904694169, |
| "grad_norm": 0.1908738762140274, |
| "learning_rate": 3.892976588628763e-06, |
| "loss": 2.6164, |
| "step": 21200 |
| }, |
| { |
| "epoch": 1206.2588904694169, |
| "eval_loss": 2.6190242767333984, |
| "eval_runtime": 23.976, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 21200 |
| }, |
| { |
| "epoch": 1211.9487908961594, |
| "grad_norm": 0.16407649219036102, |
| "learning_rate": 3.8829431438127095e-06, |
| "loss": 2.6163, |
| "step": 21300 |
| }, |
| { |
| "epoch": 1211.9487908961594, |
| "eval_loss": 2.6163718700408936, |
| "eval_runtime": 23.986, |
| "eval_samples_per_second": 58.117, |
| "eval_steps_per_second": 7.296, |
| "step": 21300 |
| }, |
| { |
| "epoch": 1217.6386913229019, |
| "grad_norm": 0.16749687492847443, |
| "learning_rate": 3.8729096989966554e-06, |
| "loss": 2.6163, |
| "step": 21400 |
| }, |
| { |
| "epoch": 1217.6386913229019, |
| "eval_loss": 2.6182687282562256, |
| "eval_runtime": 23.9719, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 21400 |
| }, |
| { |
| "epoch": 1223.3285917496444, |
| "grad_norm": 0.1730409562587738, |
| "learning_rate": 3.862876254180602e-06, |
| "loss": 2.617, |
| "step": 21500 |
| }, |
| { |
| "epoch": 1223.3285917496444, |
| "eval_loss": 2.619847059249878, |
| "eval_runtime": 23.6171, |
| "eval_samples_per_second": 59.025, |
| "eval_steps_per_second": 7.41, |
| "step": 21500 |
| }, |
| { |
| "epoch": 1229.0184921763869, |
| "grad_norm": 0.17030537128448486, |
| "learning_rate": 3.852842809364549e-06, |
| "loss": 2.6168, |
| "step": 21600 |
| }, |
| { |
| "epoch": 1229.0184921763869, |
| "eval_loss": 2.6159706115722656, |
| "eval_runtime": 23.9563, |
| "eval_samples_per_second": 58.189, |
| "eval_steps_per_second": 7.305, |
| "step": 21600 |
| }, |
| { |
| "epoch": 1234.7083926031294, |
| "grad_norm": 0.15996751189231873, |
| "learning_rate": 3.842809364548495e-06, |
| "loss": 2.6159, |
| "step": 21700 |
| }, |
| { |
| "epoch": 1234.7083926031294, |
| "eval_loss": 2.6217665672302246, |
| "eval_runtime": 23.6191, |
| "eval_samples_per_second": 59.02, |
| "eval_steps_per_second": 7.409, |
| "step": 21700 |
| }, |
| { |
| "epoch": 1240.3982930298719, |
| "grad_norm": 0.18178878724575043, |
| "learning_rate": 3.832775919732442e-06, |
| "loss": 2.6154, |
| "step": 21800 |
| }, |
| { |
| "epoch": 1240.3982930298719, |
| "eval_loss": 2.6181161403656006, |
| "eval_runtime": 23.9747, |
| "eval_samples_per_second": 58.145, |
| "eval_steps_per_second": 7.299, |
| "step": 21800 |
| }, |
| { |
| "epoch": 1246.0881934566146, |
| "grad_norm": 0.1834726333618164, |
| "learning_rate": 3.822742474916388e-06, |
| "loss": 2.6158, |
| "step": 21900 |
| }, |
| { |
| "epoch": 1246.0881934566146, |
| "eval_loss": 2.6183881759643555, |
| "eval_runtime": 23.9644, |
| "eval_samples_per_second": 58.17, |
| "eval_steps_per_second": 7.302, |
| "step": 21900 |
| }, |
| { |
| "epoch": 1251.778093883357, |
| "grad_norm": 0.18116818368434906, |
| "learning_rate": 3.8127090301003347e-06, |
| "loss": 2.6151, |
| "step": 22000 |
| }, |
| { |
| "epoch": 1251.778093883357, |
| "eval_loss": 2.6145451068878174, |
| "eval_runtime": 23.9726, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 22000 |
| }, |
| { |
| "epoch": 1257.4679943100996, |
| "grad_norm": 0.17791162431240082, |
| "learning_rate": 3.802675585284281e-06, |
| "loss": 2.6155, |
| "step": 22100 |
| }, |
| { |
| "epoch": 1257.4679943100996, |
| "eval_loss": 2.615226984024048, |
| "eval_runtime": 23.9896, |
| "eval_samples_per_second": 58.109, |
| "eval_steps_per_second": 7.295, |
| "step": 22100 |
| }, |
| { |
| "epoch": 1263.157894736842, |
| "grad_norm": 0.18372969329357147, |
| "learning_rate": 3.792642140468228e-06, |
| "loss": 2.6156, |
| "step": 22200 |
| }, |
| { |
| "epoch": 1263.157894736842, |
| "eval_loss": 2.6180429458618164, |
| "eval_runtime": 23.9809, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.297, |
| "step": 22200 |
| }, |
| { |
| "epoch": 1268.8477951635846, |
| "grad_norm": 0.1649881899356842, |
| "learning_rate": 3.782608695652174e-06, |
| "loss": 2.6154, |
| "step": 22300 |
| }, |
| { |
| "epoch": 1268.8477951635846, |
| "eval_loss": 2.618147850036621, |
| "eval_runtime": 23.9875, |
| "eval_samples_per_second": 58.114, |
| "eval_steps_per_second": 7.295, |
| "step": 22300 |
| }, |
| { |
| "epoch": 1274.537695590327, |
| "grad_norm": 0.185517817735672, |
| "learning_rate": 3.7725752508361205e-06, |
| "loss": 2.6147, |
| "step": 22400 |
| }, |
| { |
| "epoch": 1274.537695590327, |
| "eval_loss": 2.614933729171753, |
| "eval_runtime": 23.98, |
| "eval_samples_per_second": 58.132, |
| "eval_steps_per_second": 7.298, |
| "step": 22400 |
| }, |
| { |
| "epoch": 1280.2275960170698, |
| "grad_norm": 0.18541164696216583, |
| "learning_rate": 3.7625418060200673e-06, |
| "loss": 2.615, |
| "step": 22500 |
| }, |
| { |
| "epoch": 1280.2275960170698, |
| "eval_loss": 2.614748477935791, |
| "eval_runtime": 23.9792, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.298, |
| "step": 22500 |
| }, |
| { |
| "epoch": 1285.9174964438123, |
| "grad_norm": 0.1989043653011322, |
| "learning_rate": 3.7525083612040136e-06, |
| "loss": 2.6149, |
| "step": 22600 |
| }, |
| { |
| "epoch": 1285.9174964438123, |
| "eval_loss": 2.6172001361846924, |
| "eval_runtime": 23.6321, |
| "eval_samples_per_second": 58.988, |
| "eval_steps_per_second": 7.405, |
| "step": 22600 |
| }, |
| { |
| "epoch": 1291.6073968705548, |
| "grad_norm": 0.18920746445655823, |
| "learning_rate": 3.74247491638796e-06, |
| "loss": 2.6152, |
| "step": 22700 |
| }, |
| { |
| "epoch": 1291.6073968705548, |
| "eval_loss": 2.613987445831299, |
| "eval_runtime": 23.9748, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 22700 |
| }, |
| { |
| "epoch": 1297.2972972972973, |
| "grad_norm": 0.1757652908563614, |
| "learning_rate": 3.7324414715719067e-06, |
| "loss": 2.6146, |
| "step": 22800 |
| }, |
| { |
| "epoch": 1297.2972972972973, |
| "eval_loss": 2.6179261207580566, |
| "eval_runtime": 23.9716, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 22800 |
| }, |
| { |
| "epoch": 1302.9871977240398, |
| "grad_norm": 0.21378381550312042, |
| "learning_rate": 3.722408026755853e-06, |
| "loss": 2.6139, |
| "step": 22900 |
| }, |
| { |
| "epoch": 1302.9871977240398, |
| "eval_loss": 2.6163623332977295, |
| "eval_runtime": 23.9779, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 22900 |
| }, |
| { |
| "epoch": 1308.6770981507823, |
| "grad_norm": 0.2038387954235077, |
| "learning_rate": 3.7123745819398e-06, |
| "loss": 2.6142, |
| "step": 23000 |
| }, |
| { |
| "epoch": 1308.6770981507823, |
| "eval_loss": 2.615541934967041, |
| "eval_runtime": 23.9618, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 23000 |
| }, |
| { |
| "epoch": 1314.3669985775248, |
| "grad_norm": 0.13637392222881317, |
| "learning_rate": 3.702341137123746e-06, |
| "loss": 2.6141, |
| "step": 23100 |
| }, |
| { |
| "epoch": 1314.3669985775248, |
| "eval_loss": 2.6169161796569824, |
| "eval_runtime": 23.9822, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 23100 |
| }, |
| { |
| "epoch": 1320.0568990042675, |
| "grad_norm": 0.18610434234142303, |
| "learning_rate": 3.6923076923076925e-06, |
| "loss": 2.614, |
| "step": 23200 |
| }, |
| { |
| "epoch": 1320.0568990042675, |
| "eval_loss": 2.6124112606048584, |
| "eval_runtime": 23.9616, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 23200 |
| }, |
| { |
| "epoch": 1325.74679943101, |
| "grad_norm": 0.17579494416713715, |
| "learning_rate": 3.6822742474916393e-06, |
| "loss": 2.6138, |
| "step": 23300 |
| }, |
| { |
| "epoch": 1325.74679943101, |
| "eval_loss": 2.615485429763794, |
| "eval_runtime": 23.9777, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 23300 |
| }, |
| { |
| "epoch": 1331.4366998577525, |
| "grad_norm": 0.1542961448431015, |
| "learning_rate": 3.6722408026755856e-06, |
| "loss": 2.6135, |
| "step": 23400 |
| }, |
| { |
| "epoch": 1331.4366998577525, |
| "eval_loss": 2.6187291145324707, |
| "eval_runtime": 23.6277, |
| "eval_samples_per_second": 58.999, |
| "eval_steps_per_second": 7.407, |
| "step": 23400 |
| }, |
| { |
| "epoch": 1337.126600284495, |
| "grad_norm": 0.17543186247348785, |
| "learning_rate": 3.662207357859532e-06, |
| "loss": 2.6138, |
| "step": 23500 |
| }, |
| { |
| "epoch": 1337.126600284495, |
| "eval_loss": 2.614956855773926, |
| "eval_runtime": 23.9548, |
| "eval_samples_per_second": 58.193, |
| "eval_steps_per_second": 7.305, |
| "step": 23500 |
| }, |
| { |
| "epoch": 1342.8165007112375, |
| "grad_norm": 0.16438443958759308, |
| "learning_rate": 3.6521739130434787e-06, |
| "loss": 2.614, |
| "step": 23600 |
| }, |
| { |
| "epoch": 1342.8165007112375, |
| "eval_loss": 2.615394353866577, |
| "eval_runtime": 23.9594, |
| "eval_samples_per_second": 58.182, |
| "eval_steps_per_second": 7.304, |
| "step": 23600 |
| }, |
| { |
| "epoch": 1348.50640113798, |
| "grad_norm": 0.16566355526447296, |
| "learning_rate": 3.642140468227425e-06, |
| "loss": 2.6133, |
| "step": 23700 |
| }, |
| { |
| "epoch": 1348.50640113798, |
| "eval_loss": 2.6109862327575684, |
| "eval_runtime": 23.973, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 23700 |
| }, |
| { |
| "epoch": 1354.1963015647227, |
| "grad_norm": 0.19186396896839142, |
| "learning_rate": 3.6321070234113714e-06, |
| "loss": 2.6132, |
| "step": 23800 |
| }, |
| { |
| "epoch": 1354.1963015647227, |
| "eval_loss": 2.61553692817688, |
| "eval_runtime": 23.9667, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 23800 |
| }, |
| { |
| "epoch": 1359.8862019914652, |
| "grad_norm": 0.1499451845884323, |
| "learning_rate": 3.622073578595318e-06, |
| "loss": 2.6129, |
| "step": 23900 |
| }, |
| { |
| "epoch": 1359.8862019914652, |
| "eval_loss": 2.6135051250457764, |
| "eval_runtime": 23.9621, |
| "eval_samples_per_second": 58.175, |
| "eval_steps_per_second": 7.303, |
| "step": 23900 |
| }, |
| { |
| "epoch": 1365.5761024182077, |
| "grad_norm": 0.17722682654857635, |
| "learning_rate": 3.6120401337792645e-06, |
| "loss": 2.6132, |
| "step": 24000 |
| }, |
| { |
| "epoch": 1365.5761024182077, |
| "eval_loss": 2.6139628887176514, |
| "eval_runtime": 23.966, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 24000 |
| }, |
| { |
| "epoch": 1371.2660028449502, |
| "grad_norm": 0.17891627550125122, |
| "learning_rate": 3.6020066889632112e-06, |
| "loss": 2.6127, |
| "step": 24100 |
| }, |
| { |
| "epoch": 1371.2660028449502, |
| "eval_loss": 2.616461992263794, |
| "eval_runtime": 23.6223, |
| "eval_samples_per_second": 59.012, |
| "eval_steps_per_second": 7.408, |
| "step": 24100 |
| }, |
| { |
| "epoch": 1376.9559032716927, |
| "grad_norm": 0.1613658368587494, |
| "learning_rate": 3.5919732441471576e-06, |
| "loss": 2.6129, |
| "step": 24200 |
| }, |
| { |
| "epoch": 1376.9559032716927, |
| "eval_loss": 2.6160008907318115, |
| "eval_runtime": 23.9933, |
| "eval_samples_per_second": 58.1, |
| "eval_steps_per_second": 7.294, |
| "step": 24200 |
| }, |
| { |
| "epoch": 1382.6458036984352, |
| "grad_norm": 0.16486230492591858, |
| "learning_rate": 3.581939799331104e-06, |
| "loss": 2.6126, |
| "step": 24300 |
| }, |
| { |
| "epoch": 1382.6458036984352, |
| "eval_loss": 2.617274761199951, |
| "eval_runtime": 23.9711, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 24300 |
| }, |
| { |
| "epoch": 1388.3357041251777, |
| "grad_norm": 0.17561286687850952, |
| "learning_rate": 3.5719063545150507e-06, |
| "loss": 2.6121, |
| "step": 24400 |
| }, |
| { |
| "epoch": 1388.3357041251777, |
| "eval_loss": 2.615642786026001, |
| "eval_runtime": 23.9873, |
| "eval_samples_per_second": 58.114, |
| "eval_steps_per_second": 7.296, |
| "step": 24400 |
| }, |
| { |
| "epoch": 1394.0256045519204, |
| "grad_norm": 0.2206220030784607, |
| "learning_rate": 3.561872909698997e-06, |
| "loss": 2.6121, |
| "step": 24500 |
| }, |
| { |
| "epoch": 1394.0256045519204, |
| "eval_loss": 2.6155807971954346, |
| "eval_runtime": 24.072, |
| "eval_samples_per_second": 57.91, |
| "eval_steps_per_second": 7.27, |
| "step": 24500 |
| }, |
| { |
| "epoch": 1399.715504978663, |
| "grad_norm": 0.17727740108966827, |
| "learning_rate": 3.5518394648829434e-06, |
| "loss": 2.6116, |
| "step": 24600 |
| }, |
| { |
| "epoch": 1399.715504978663, |
| "eval_loss": 2.6150245666503906, |
| "eval_runtime": 23.9542, |
| "eval_samples_per_second": 58.194, |
| "eval_steps_per_second": 7.306, |
| "step": 24600 |
| }, |
| { |
| "epoch": 1405.4054054054054, |
| "grad_norm": 0.23213492333889008, |
| "learning_rate": 3.54180602006689e-06, |
| "loss": 2.6122, |
| "step": 24700 |
| }, |
| { |
| "epoch": 1405.4054054054054, |
| "eval_loss": 2.6127638816833496, |
| "eval_runtime": 23.9798, |
| "eval_samples_per_second": 58.132, |
| "eval_steps_per_second": 7.298, |
| "step": 24700 |
| }, |
| { |
| "epoch": 1411.095305832148, |
| "grad_norm": 0.19061516225337982, |
| "learning_rate": 3.5317725752508365e-06, |
| "loss": 2.6114, |
| "step": 24800 |
| }, |
| { |
| "epoch": 1411.095305832148, |
| "eval_loss": 2.6152596473693848, |
| "eval_runtime": 23.9762, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 24800 |
| }, |
| { |
| "epoch": 1416.7852062588904, |
| "grad_norm": 0.21451649069786072, |
| "learning_rate": 3.521739130434783e-06, |
| "loss": 2.6117, |
| "step": 24900 |
| }, |
| { |
| "epoch": 1416.7852062588904, |
| "eval_loss": 2.616278886795044, |
| "eval_runtime": 23.6278, |
| "eval_samples_per_second": 58.998, |
| "eval_steps_per_second": 7.407, |
| "step": 24900 |
| }, |
| { |
| "epoch": 1422.475106685633, |
| "grad_norm": 0.19627918303012848, |
| "learning_rate": 3.5117056856187296e-06, |
| "loss": 2.6115, |
| "step": 25000 |
| }, |
| { |
| "epoch": 1422.475106685633, |
| "eval_loss": 2.6146152019500732, |
| "eval_runtime": 23.9995, |
| "eval_samples_per_second": 58.084, |
| "eval_steps_per_second": 7.292, |
| "step": 25000 |
| }, |
| { |
| "epoch": 1428.1650071123756, |
| "grad_norm": 0.1765471249818802, |
| "learning_rate": 3.501672240802676e-06, |
| "loss": 2.6117, |
| "step": 25100 |
| }, |
| { |
| "epoch": 1428.1650071123756, |
| "eval_loss": 2.612539768218994, |
| "eval_runtime": 23.6206, |
| "eval_samples_per_second": 59.016, |
| "eval_steps_per_second": 7.409, |
| "step": 25100 |
| }, |
| { |
| "epoch": 1433.8549075391181, |
| "grad_norm": 0.1898675262928009, |
| "learning_rate": 3.491638795986622e-06, |
| "loss": 2.6114, |
| "step": 25200 |
| }, |
| { |
| "epoch": 1433.8549075391181, |
| "eval_loss": 2.6151158809661865, |
| "eval_runtime": 23.9639, |
| "eval_samples_per_second": 58.171, |
| "eval_steps_per_second": 7.303, |
| "step": 25200 |
| }, |
| { |
| "epoch": 1439.5448079658606, |
| "grad_norm": 0.16476163268089294, |
| "learning_rate": 3.481605351170568e-06, |
| "loss": 2.6113, |
| "step": 25300 |
| }, |
| { |
| "epoch": 1439.5448079658606, |
| "eval_loss": 2.6140201091766357, |
| "eval_runtime": 23.9566, |
| "eval_samples_per_second": 58.188, |
| "eval_steps_per_second": 7.305, |
| "step": 25300 |
| }, |
| { |
| "epoch": 1445.2347083926031, |
| "grad_norm": 0.18662914633750916, |
| "learning_rate": 3.471571906354515e-06, |
| "loss": 2.6105, |
| "step": 25400 |
| }, |
| { |
| "epoch": 1445.2347083926031, |
| "eval_loss": 2.615382194519043, |
| "eval_runtime": 23.9571, |
| "eval_samples_per_second": 58.187, |
| "eval_steps_per_second": 7.305, |
| "step": 25400 |
| }, |
| { |
| "epoch": 1450.9246088193456, |
| "grad_norm": 0.19092458486557007, |
| "learning_rate": 3.4615384615384613e-06, |
| "loss": 2.6109, |
| "step": 25500 |
| }, |
| { |
| "epoch": 1450.9246088193456, |
| "eval_loss": 2.6135177612304688, |
| "eval_runtime": 23.9762, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 25500 |
| }, |
| { |
| "epoch": 1456.6145092460881, |
| "grad_norm": 0.1783183068037033, |
| "learning_rate": 3.4515050167224076e-06, |
| "loss": 2.6106, |
| "step": 25600 |
| }, |
| { |
| "epoch": 1456.6145092460881, |
| "eval_loss": 2.611865282058716, |
| "eval_runtime": 23.9618, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 25600 |
| }, |
| { |
| "epoch": 1462.3044096728306, |
| "grad_norm": 0.19193953275680542, |
| "learning_rate": 3.4414715719063544e-06, |
| "loss": 2.6107, |
| "step": 25700 |
| }, |
| { |
| "epoch": 1462.3044096728306, |
| "eval_loss": 2.6173393726348877, |
| "eval_runtime": 23.9925, |
| "eval_samples_per_second": 58.101, |
| "eval_steps_per_second": 7.294, |
| "step": 25700 |
| }, |
| { |
| "epoch": 1467.9943100995733, |
| "grad_norm": 0.16849613189697266, |
| "learning_rate": 3.4314381270903007e-06, |
| "loss": 2.6109, |
| "step": 25800 |
| }, |
| { |
| "epoch": 1467.9943100995733, |
| "eval_loss": 2.612614631652832, |
| "eval_runtime": 23.9774, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 25800 |
| }, |
| { |
| "epoch": 1473.6842105263158, |
| "grad_norm": 0.19681937992572784, |
| "learning_rate": 3.4214046822742475e-06, |
| "loss": 2.6099, |
| "step": 25900 |
| }, |
| { |
| "epoch": 1473.6842105263158, |
| "eval_loss": 2.6156296730041504, |
| "eval_runtime": 23.621, |
| "eval_samples_per_second": 59.015, |
| "eval_steps_per_second": 7.409, |
| "step": 25900 |
| }, |
| { |
| "epoch": 1479.3741109530583, |
| "grad_norm": 0.18242304027080536, |
| "learning_rate": 3.411371237458194e-06, |
| "loss": 2.6102, |
| "step": 26000 |
| }, |
| { |
| "epoch": 1479.3741109530583, |
| "eval_loss": 2.613642454147339, |
| "eval_runtime": 23.9764, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 26000 |
| }, |
| { |
| "epoch": 1485.0640113798008, |
| "grad_norm": 0.16466517746448517, |
| "learning_rate": 3.40133779264214e-06, |
| "loss": 2.6104, |
| "step": 26100 |
| }, |
| { |
| "epoch": 1485.0640113798008, |
| "eval_loss": 2.613408327102661, |
| "eval_runtime": 23.9744, |
| "eval_samples_per_second": 58.145, |
| "eval_steps_per_second": 7.299, |
| "step": 26100 |
| }, |
| { |
| "epoch": 1490.7539118065433, |
| "grad_norm": 0.19841539859771729, |
| "learning_rate": 3.391304347826087e-06, |
| "loss": 2.6099, |
| "step": 26200 |
| }, |
| { |
| "epoch": 1490.7539118065433, |
| "eval_loss": 2.6156742572784424, |
| "eval_runtime": 23.9736, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 26200 |
| }, |
| { |
| "epoch": 1496.4438122332858, |
| "grad_norm": 0.18455518782138824, |
| "learning_rate": 3.3812709030100333e-06, |
| "loss": 2.61, |
| "step": 26300 |
| }, |
| { |
| "epoch": 1496.4438122332858, |
| "eval_loss": 2.6147565841674805, |
| "eval_runtime": 23.9688, |
| "eval_samples_per_second": 58.159, |
| "eval_steps_per_second": 7.301, |
| "step": 26300 |
| }, |
| { |
| "epoch": 1502.1337126600286, |
| "grad_norm": 0.1784888654947281, |
| "learning_rate": 3.3712374581939796e-06, |
| "loss": 2.6098, |
| "step": 26400 |
| }, |
| { |
| "epoch": 1502.1337126600286, |
| "eval_loss": 2.614964723587036, |
| "eval_runtime": 23.6319, |
| "eval_samples_per_second": 58.988, |
| "eval_steps_per_second": 7.405, |
| "step": 26400 |
| }, |
| { |
| "epoch": 1507.823613086771, |
| "grad_norm": 0.17167048156261444, |
| "learning_rate": 3.3612040133779264e-06, |
| "loss": 2.6094, |
| "step": 26500 |
| }, |
| { |
| "epoch": 1507.823613086771, |
| "eval_loss": 2.6146252155303955, |
| "eval_runtime": 23.9509, |
| "eval_samples_per_second": 58.202, |
| "eval_steps_per_second": 7.307, |
| "step": 26500 |
| }, |
| { |
| "epoch": 1513.5135135135135, |
| "grad_norm": 0.17414234578609467, |
| "learning_rate": 3.3511705685618727e-06, |
| "loss": 2.6097, |
| "step": 26600 |
| }, |
| { |
| "epoch": 1513.5135135135135, |
| "eval_loss": 2.6143181324005127, |
| "eval_runtime": 23.9631, |
| "eval_samples_per_second": 58.173, |
| "eval_steps_per_second": 7.303, |
| "step": 26600 |
| }, |
| { |
| "epoch": 1519.203413940256, |
| "grad_norm": 0.18100158870220184, |
| "learning_rate": 3.3411371237458195e-06, |
| "loss": 2.6096, |
| "step": 26700 |
| }, |
| { |
| "epoch": 1519.203413940256, |
| "eval_loss": 2.6159329414367676, |
| "eval_runtime": 23.9773, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 26700 |
| }, |
| { |
| "epoch": 1524.8933143669985, |
| "grad_norm": 0.16772860288619995, |
| "learning_rate": 3.331103678929766e-06, |
| "loss": 2.6094, |
| "step": 26800 |
| }, |
| { |
| "epoch": 1524.8933143669985, |
| "eval_loss": 2.6139376163482666, |
| "eval_runtime": 23.9804, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 26800 |
| }, |
| { |
| "epoch": 1530.583214793741, |
| "grad_norm": 0.17105814814567566, |
| "learning_rate": 3.321070234113712e-06, |
| "loss": 2.6095, |
| "step": 26900 |
| }, |
| { |
| "epoch": 1530.583214793741, |
| "eval_loss": 2.617861747741699, |
| "eval_runtime": 23.9713, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 26900 |
| }, |
| { |
| "epoch": 1536.2731152204835, |
| "grad_norm": 0.16764415800571442, |
| "learning_rate": 3.311036789297659e-06, |
| "loss": 2.6093, |
| "step": 27000 |
| }, |
| { |
| "epoch": 1536.2731152204835, |
| "eval_loss": 2.617765188217163, |
| "eval_runtime": 23.9839, |
| "eval_samples_per_second": 58.122, |
| "eval_steps_per_second": 7.297, |
| "step": 27000 |
| }, |
| { |
| "epoch": 1541.9630156472263, |
| "grad_norm": 0.18489839136600494, |
| "learning_rate": 3.3010033444816052e-06, |
| "loss": 2.6094, |
| "step": 27100 |
| }, |
| { |
| "epoch": 1541.9630156472263, |
| "eval_loss": 2.614982843399048, |
| "eval_runtime": 23.9739, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 27100 |
| }, |
| { |
| "epoch": 1547.6529160739688, |
| "grad_norm": 0.18775135278701782, |
| "learning_rate": 3.2909698996655516e-06, |
| "loss": 2.6086, |
| "step": 27200 |
| }, |
| { |
| "epoch": 1547.6529160739688, |
| "eval_loss": 2.6160266399383545, |
| "eval_runtime": 23.9808, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.297, |
| "step": 27200 |
| }, |
| { |
| "epoch": 1553.3428165007113, |
| "grad_norm": 0.16984674334526062, |
| "learning_rate": 3.2809364548494983e-06, |
| "loss": 2.6085, |
| "step": 27300 |
| }, |
| { |
| "epoch": 1553.3428165007113, |
| "eval_loss": 2.615583896636963, |
| "eval_runtime": 23.6298, |
| "eval_samples_per_second": 58.993, |
| "eval_steps_per_second": 7.406, |
| "step": 27300 |
| }, |
| { |
| "epoch": 1559.0327169274537, |
| "grad_norm": 0.16006973385810852, |
| "learning_rate": 3.2709030100334447e-06, |
| "loss": 2.6083, |
| "step": 27400 |
| }, |
| { |
| "epoch": 1559.0327169274537, |
| "eval_loss": 2.616664409637451, |
| "eval_runtime": 23.9836, |
| "eval_samples_per_second": 58.123, |
| "eval_steps_per_second": 7.297, |
| "step": 27400 |
| }, |
| { |
| "epoch": 1564.7226173541962, |
| "grad_norm": 0.2134248912334442, |
| "learning_rate": 3.260869565217391e-06, |
| "loss": 2.6087, |
| "step": 27500 |
| }, |
| { |
| "epoch": 1564.7226173541962, |
| "eval_loss": 2.6122682094573975, |
| "eval_runtime": 23.9759, |
| "eval_samples_per_second": 58.142, |
| "eval_steps_per_second": 7.299, |
| "step": 27500 |
| }, |
| { |
| "epoch": 1570.4125177809387, |
| "grad_norm": 0.18280279636383057, |
| "learning_rate": 3.2508361204013378e-06, |
| "loss": 2.6084, |
| "step": 27600 |
| }, |
| { |
| "epoch": 1570.4125177809387, |
| "eval_loss": 2.61324143409729, |
| "eval_runtime": 23.9718, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 27600 |
| }, |
| { |
| "epoch": 1576.1024182076815, |
| "grad_norm": 0.1901465803384781, |
| "learning_rate": 3.240802675585284e-06, |
| "loss": 2.6078, |
| "step": 27700 |
| }, |
| { |
| "epoch": 1576.1024182076815, |
| "eval_loss": 2.6125519275665283, |
| "eval_runtime": 23.9757, |
| "eval_samples_per_second": 58.142, |
| "eval_steps_per_second": 7.299, |
| "step": 27700 |
| }, |
| { |
| "epoch": 1581.792318634424, |
| "grad_norm": 0.18895883858203888, |
| "learning_rate": 3.230769230769231e-06, |
| "loss": 2.608, |
| "step": 27800 |
| }, |
| { |
| "epoch": 1581.792318634424, |
| "eval_loss": 2.6131763458251953, |
| "eval_runtime": 23.9778, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 27800 |
| }, |
| { |
| "epoch": 1587.4822190611665, |
| "grad_norm": 0.17906545102596283, |
| "learning_rate": 3.2207357859531772e-06, |
| "loss": 2.608, |
| "step": 27900 |
| }, |
| { |
| "epoch": 1587.4822190611665, |
| "eval_loss": 2.613011598587036, |
| "eval_runtime": 23.9936, |
| "eval_samples_per_second": 58.099, |
| "eval_steps_per_second": 7.294, |
| "step": 27900 |
| }, |
| { |
| "epoch": 1593.172119487909, |
| "grad_norm": 0.16846366226673126, |
| "learning_rate": 3.2107023411371236e-06, |
| "loss": 2.6079, |
| "step": 28000 |
| }, |
| { |
| "epoch": 1593.172119487909, |
| "eval_loss": 2.6157352924346924, |
| "eval_runtime": 23.9922, |
| "eval_samples_per_second": 58.102, |
| "eval_steps_per_second": 7.294, |
| "step": 28000 |
| }, |
| { |
| "epoch": 1598.8620199146515, |
| "grad_norm": 0.1816137433052063, |
| "learning_rate": 3.2006688963210703e-06, |
| "loss": 2.6076, |
| "step": 28100 |
| }, |
| { |
| "epoch": 1598.8620199146515, |
| "eval_loss": 2.6187076568603516, |
| "eval_runtime": 23.9742, |
| "eval_samples_per_second": 58.146, |
| "eval_steps_per_second": 7.3, |
| "step": 28100 |
| }, |
| { |
| "epoch": 1604.551920341394, |
| "grad_norm": 0.19645364582538605, |
| "learning_rate": 3.1906354515050167e-06, |
| "loss": 2.6076, |
| "step": 28200 |
| }, |
| { |
| "epoch": 1604.551920341394, |
| "eval_loss": 2.6162264347076416, |
| "eval_runtime": 23.6332, |
| "eval_samples_per_second": 58.985, |
| "eval_steps_per_second": 7.405, |
| "step": 28200 |
| }, |
| { |
| "epoch": 1610.2418207681364, |
| "grad_norm": 0.16714365780353546, |
| "learning_rate": 3.180602006688963e-06, |
| "loss": 2.6079, |
| "step": 28300 |
| }, |
| { |
| "epoch": 1610.2418207681364, |
| "eval_loss": 2.6153204441070557, |
| "eval_runtime": 23.9767, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 28300 |
| }, |
| { |
| "epoch": 1615.9317211948792, |
| "grad_norm": 0.21319107711315155, |
| "learning_rate": 3.1705685618729098e-06, |
| "loss": 2.6079, |
| "step": 28400 |
| }, |
| { |
| "epoch": 1615.9317211948792, |
| "eval_loss": 2.6141254901885986, |
| "eval_runtime": 23.9806, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.298, |
| "step": 28400 |
| }, |
| { |
| "epoch": 1621.6216216216217, |
| "grad_norm": 0.18718905746936798, |
| "learning_rate": 3.160535117056856e-06, |
| "loss": 2.6072, |
| "step": 28500 |
| }, |
| { |
| "epoch": 1621.6216216216217, |
| "eval_loss": 2.6125545501708984, |
| "eval_runtime": 23.9842, |
| "eval_samples_per_second": 58.122, |
| "eval_steps_per_second": 7.296, |
| "step": 28500 |
| }, |
| { |
| "epoch": 1627.3115220483642, |
| "grad_norm": 0.15945301949977875, |
| "learning_rate": 3.1505016722408024e-06, |
| "loss": 2.6068, |
| "step": 28600 |
| }, |
| { |
| "epoch": 1627.3115220483642, |
| "eval_loss": 2.6133553981781006, |
| "eval_runtime": 23.9727, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 28600 |
| }, |
| { |
| "epoch": 1633.0014224751067, |
| "grad_norm": 0.17413286864757538, |
| "learning_rate": 3.140468227424749e-06, |
| "loss": 2.6067, |
| "step": 28700 |
| }, |
| { |
| "epoch": 1633.0014224751067, |
| "eval_loss": 2.6167733669281006, |
| "eval_runtime": 23.9797, |
| "eval_samples_per_second": 58.132, |
| "eval_steps_per_second": 7.298, |
| "step": 28700 |
| }, |
| { |
| "epoch": 1638.6913229018492, |
| "grad_norm": 0.19335277378559113, |
| "learning_rate": 3.1304347826086955e-06, |
| "loss": 2.6071, |
| "step": 28800 |
| }, |
| { |
| "epoch": 1638.6913229018492, |
| "eval_loss": 2.6125223636627197, |
| "eval_runtime": 23.9933, |
| "eval_samples_per_second": 58.1, |
| "eval_steps_per_second": 7.294, |
| "step": 28800 |
| }, |
| { |
| "epoch": 1644.3812233285917, |
| "grad_norm": 0.20571838319301605, |
| "learning_rate": 3.1204013377926423e-06, |
| "loss": 2.6066, |
| "step": 28900 |
| }, |
| { |
| "epoch": 1644.3812233285917, |
| "eval_loss": 2.615057945251465, |
| "eval_runtime": 23.9707, |
| "eval_samples_per_second": 58.154, |
| "eval_steps_per_second": 7.301, |
| "step": 28900 |
| }, |
| { |
| "epoch": 1650.0711237553344, |
| "grad_norm": 0.1820344775915146, |
| "learning_rate": 3.1103678929765886e-06, |
| "loss": 2.6065, |
| "step": 29000 |
| }, |
| { |
| "epoch": 1650.0711237553344, |
| "eval_loss": 2.610342025756836, |
| "eval_runtime": 23.6162, |
| "eval_samples_per_second": 59.027, |
| "eval_steps_per_second": 7.41, |
| "step": 29000 |
| }, |
| { |
| "epoch": 1655.7610241820769, |
| "grad_norm": 0.19376899302005768, |
| "learning_rate": 3.100334448160535e-06, |
| "loss": 2.6061, |
| "step": 29100 |
| }, |
| { |
| "epoch": 1655.7610241820769, |
| "eval_loss": 2.6109142303466797, |
| "eval_runtime": 23.9605, |
| "eval_samples_per_second": 58.179, |
| "eval_steps_per_second": 7.304, |
| "step": 29100 |
| }, |
| { |
| "epoch": 1661.4509246088194, |
| "grad_norm": 0.17542988061904907, |
| "learning_rate": 3.0903010033444818e-06, |
| "loss": 2.6069, |
| "step": 29200 |
| }, |
| { |
| "epoch": 1661.4509246088194, |
| "eval_loss": 2.613027572631836, |
| "eval_runtime": 23.9699, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 29200 |
| }, |
| { |
| "epoch": 1667.1408250355619, |
| "grad_norm": 0.20546042919158936, |
| "learning_rate": 3.080267558528428e-06, |
| "loss": 2.6058, |
| "step": 29300 |
| }, |
| { |
| "epoch": 1667.1408250355619, |
| "eval_loss": 2.6125547885894775, |
| "eval_runtime": 24.0161, |
| "eval_samples_per_second": 58.044, |
| "eval_steps_per_second": 7.287, |
| "step": 29300 |
| }, |
| { |
| "epoch": 1672.8307254623044, |
| "grad_norm": 0.18211744725704193, |
| "learning_rate": 3.0702341137123744e-06, |
| "loss": 2.6056, |
| "step": 29400 |
| }, |
| { |
| "epoch": 1672.8307254623044, |
| "eval_loss": 2.6160383224487305, |
| "eval_runtime": 23.9708, |
| "eval_samples_per_second": 58.154, |
| "eval_steps_per_second": 7.301, |
| "step": 29400 |
| }, |
| { |
| "epoch": 1678.5206258890469, |
| "grad_norm": 0.20983801782131195, |
| "learning_rate": 3.060200668896321e-06, |
| "loss": 2.6061, |
| "step": 29500 |
| }, |
| { |
| "epoch": 1678.5206258890469, |
| "eval_loss": 2.61398983001709, |
| "eval_runtime": 23.9666, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 29500 |
| }, |
| { |
| "epoch": 1684.2105263157894, |
| "grad_norm": 0.20594222843647003, |
| "learning_rate": 3.0501672240802675e-06, |
| "loss": 2.606, |
| "step": 29600 |
| }, |
| { |
| "epoch": 1684.2105263157894, |
| "eval_loss": 2.6141202449798584, |
| "eval_runtime": 23.9797, |
| "eval_samples_per_second": 58.132, |
| "eval_steps_per_second": 7.298, |
| "step": 29600 |
| }, |
| { |
| "epoch": 1689.900426742532, |
| "grad_norm": 0.19307450950145721, |
| "learning_rate": 3.0401337792642143e-06, |
| "loss": 2.6061, |
| "step": 29700 |
| }, |
| { |
| "epoch": 1689.900426742532, |
| "eval_loss": 2.614793062210083, |
| "eval_runtime": 23.6149, |
| "eval_samples_per_second": 59.03, |
| "eval_steps_per_second": 7.411, |
| "step": 29700 |
| }, |
| { |
| "epoch": 1695.5903271692746, |
| "grad_norm": 0.23280702531337738, |
| "learning_rate": 3.0301003344481606e-06, |
| "loss": 2.6057, |
| "step": 29800 |
| }, |
| { |
| "epoch": 1695.5903271692746, |
| "eval_loss": 2.6146321296691895, |
| "eval_runtime": 23.9761, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 29800 |
| }, |
| { |
| "epoch": 1701.280227596017, |
| "grad_norm": 0.18242600560188293, |
| "learning_rate": 3.020066889632107e-06, |
| "loss": 2.6054, |
| "step": 29900 |
| }, |
| { |
| "epoch": 1701.280227596017, |
| "eval_loss": 2.618605136871338, |
| "eval_runtime": 23.9512, |
| "eval_samples_per_second": 58.202, |
| "eval_steps_per_second": 7.307, |
| "step": 29900 |
| }, |
| { |
| "epoch": 1706.9701280227596, |
| "grad_norm": 0.18484260141849518, |
| "learning_rate": 3.0100334448160537e-06, |
| "loss": 2.6055, |
| "step": 30000 |
| }, |
| { |
| "epoch": 1706.9701280227596, |
| "eval_loss": 2.613018274307251, |
| "eval_runtime": 23.9772, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 30000 |
| }, |
| { |
| "epoch": 1712.660028449502, |
| "grad_norm": 0.19655726850032806, |
| "learning_rate": 3e-06, |
| "loss": 2.6048, |
| "step": 30100 |
| }, |
| { |
| "epoch": 1712.660028449502, |
| "eval_loss": 2.615434408187866, |
| "eval_runtime": 23.978, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 30100 |
| }, |
| { |
| "epoch": 1718.3499288762446, |
| "grad_norm": 0.21742597222328186, |
| "learning_rate": 2.9899665551839464e-06, |
| "loss": 2.6059, |
| "step": 30200 |
| }, |
| { |
| "epoch": 1718.3499288762446, |
| "eval_loss": 2.6120095252990723, |
| "eval_runtime": 23.9631, |
| "eval_samples_per_second": 58.173, |
| "eval_steps_per_second": 7.303, |
| "step": 30200 |
| }, |
| { |
| "epoch": 1724.0398293029873, |
| "grad_norm": 0.22138410806655884, |
| "learning_rate": 2.979933110367893e-06, |
| "loss": 2.6048, |
| "step": 30300 |
| }, |
| { |
| "epoch": 1724.0398293029873, |
| "eval_loss": 2.613083600997925, |
| "eval_runtime": 23.9653, |
| "eval_samples_per_second": 58.167, |
| "eval_steps_per_second": 7.302, |
| "step": 30300 |
| }, |
| { |
| "epoch": 1729.7297297297298, |
| "grad_norm": 0.1965727061033249, |
| "learning_rate": 2.9698996655518395e-06, |
| "loss": 2.6046, |
| "step": 30400 |
| }, |
| { |
| "epoch": 1729.7297297297298, |
| "eval_loss": 2.6135008335113525, |
| "eval_runtime": 23.9769, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 30400 |
| }, |
| { |
| "epoch": 1735.4196301564723, |
| "grad_norm": 0.1746743619441986, |
| "learning_rate": 2.959866220735786e-06, |
| "loss": 2.6047, |
| "step": 30500 |
| }, |
| { |
| "epoch": 1735.4196301564723, |
| "eval_loss": 2.615384578704834, |
| "eval_runtime": 23.6157, |
| "eval_samples_per_second": 59.029, |
| "eval_steps_per_second": 7.41, |
| "step": 30500 |
| }, |
| { |
| "epoch": 1741.1095305832148, |
| "grad_norm": 0.18516981601715088, |
| "learning_rate": 2.9498327759197326e-06, |
| "loss": 2.6041, |
| "step": 30600 |
| }, |
| { |
| "epoch": 1741.1095305832148, |
| "eval_loss": 2.61470103263855, |
| "eval_runtime": 23.9702, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 30600 |
| }, |
| { |
| "epoch": 1746.7994310099573, |
| "grad_norm": 0.18617106974124908, |
| "learning_rate": 2.939799331103679e-06, |
| "loss": 2.604, |
| "step": 30700 |
| }, |
| { |
| "epoch": 1746.7994310099573, |
| "eval_loss": 2.60992169380188, |
| "eval_runtime": 23.9721, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 30700 |
| }, |
| { |
| "epoch": 1752.4893314366998, |
| "grad_norm": 0.1985541135072708, |
| "learning_rate": 2.9297658862876257e-06, |
| "loss": 2.6044, |
| "step": 30800 |
| }, |
| { |
| "epoch": 1752.4893314366998, |
| "eval_loss": 2.610335350036621, |
| "eval_runtime": 23.6291, |
| "eval_samples_per_second": 58.995, |
| "eval_steps_per_second": 7.406, |
| "step": 30800 |
| }, |
| { |
| "epoch": 1758.1792318634423, |
| "grad_norm": 0.181779146194458, |
| "learning_rate": 2.919732441471572e-06, |
| "loss": 2.6038, |
| "step": 30900 |
| }, |
| { |
| "epoch": 1758.1792318634423, |
| "eval_loss": 2.6195976734161377, |
| "eval_runtime": 23.9725, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 30900 |
| }, |
| { |
| "epoch": 1763.869132290185, |
| "grad_norm": 0.21061445772647858, |
| "learning_rate": 2.9096989966555184e-06, |
| "loss": 2.6035, |
| "step": 31000 |
| }, |
| { |
| "epoch": 1763.869132290185, |
| "eval_loss": 2.6109161376953125, |
| "eval_runtime": 23.9629, |
| "eval_samples_per_second": 58.173, |
| "eval_steps_per_second": 7.303, |
| "step": 31000 |
| }, |
| { |
| "epoch": 1769.5590327169275, |
| "grad_norm": 0.17267170548439026, |
| "learning_rate": 2.899665551839465e-06, |
| "loss": 2.6034, |
| "step": 31100 |
| }, |
| { |
| "epoch": 1769.5590327169275, |
| "eval_loss": 2.6139283180236816, |
| "eval_runtime": 23.9656, |
| "eval_samples_per_second": 58.167, |
| "eval_steps_per_second": 7.302, |
| "step": 31100 |
| }, |
| { |
| "epoch": 1775.24893314367, |
| "grad_norm": 0.19237692654132843, |
| "learning_rate": 2.8896321070234115e-06, |
| "loss": 2.6033, |
| "step": 31200 |
| }, |
| { |
| "epoch": 1775.24893314367, |
| "eval_loss": 2.6118404865264893, |
| "eval_runtime": 23.964, |
| "eval_samples_per_second": 58.17, |
| "eval_steps_per_second": 7.303, |
| "step": 31200 |
| }, |
| { |
| "epoch": 1780.9388335704125, |
| "grad_norm": 0.17256025969982147, |
| "learning_rate": 2.879598662207358e-06, |
| "loss": 2.6033, |
| "step": 31300 |
| }, |
| { |
| "epoch": 1780.9388335704125, |
| "eval_loss": 2.6103038787841797, |
| "eval_runtime": 23.6141, |
| "eval_samples_per_second": 59.032, |
| "eval_steps_per_second": 7.411, |
| "step": 31300 |
| }, |
| { |
| "epoch": 1786.628733997155, |
| "grad_norm": 0.19163106381893158, |
| "learning_rate": 2.8695652173913046e-06, |
| "loss": 2.6031, |
| "step": 31400 |
| }, |
| { |
| "epoch": 1786.628733997155, |
| "eval_loss": 2.611341953277588, |
| "eval_runtime": 23.9739, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 31400 |
| }, |
| { |
| "epoch": 1792.3186344238975, |
| "grad_norm": 0.18413276970386505, |
| "learning_rate": 2.859531772575251e-06, |
| "loss": 2.6027, |
| "step": 31500 |
| }, |
| { |
| "epoch": 1792.3186344238975, |
| "eval_loss": 2.6132729053497314, |
| "eval_runtime": 23.9559, |
| "eval_samples_per_second": 58.19, |
| "eval_steps_per_second": 7.305, |
| "step": 31500 |
| }, |
| { |
| "epoch": 1798.0085348506402, |
| "grad_norm": 0.20607994496822357, |
| "learning_rate": 2.8494983277591977e-06, |
| "loss": 2.6024, |
| "step": 31600 |
| }, |
| { |
| "epoch": 1798.0085348506402, |
| "eval_loss": 2.610116958618164, |
| "eval_runtime": 23.9884, |
| "eval_samples_per_second": 58.112, |
| "eval_steps_per_second": 7.295, |
| "step": 31600 |
| }, |
| { |
| "epoch": 1803.6984352773827, |
| "grad_norm": 0.19761328399181366, |
| "learning_rate": 2.839464882943144e-06, |
| "loss": 2.6026, |
| "step": 31700 |
| }, |
| { |
| "epoch": 1803.6984352773827, |
| "eval_loss": 2.612351179122925, |
| "eval_runtime": 23.9662, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.302, |
| "step": 31700 |
| }, |
| { |
| "epoch": 1809.3883357041252, |
| "grad_norm": 0.20598149299621582, |
| "learning_rate": 2.8294314381270904e-06, |
| "loss": 2.6021, |
| "step": 31800 |
| }, |
| { |
| "epoch": 1809.3883357041252, |
| "eval_loss": 2.610358238220215, |
| "eval_runtime": 23.9737, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 31800 |
| }, |
| { |
| "epoch": 1815.0782361308677, |
| "grad_norm": 0.18823176622390747, |
| "learning_rate": 2.819397993311037e-06, |
| "loss": 2.6019, |
| "step": 31900 |
| }, |
| { |
| "epoch": 1815.0782361308677, |
| "eval_loss": 2.6109814643859863, |
| "eval_runtime": 23.9697, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 31900 |
| }, |
| { |
| "epoch": 1820.7681365576102, |
| "grad_norm": 0.1910698264837265, |
| "learning_rate": 2.8093645484949835e-06, |
| "loss": 2.6015, |
| "step": 32000 |
| }, |
| { |
| "epoch": 1820.7681365576102, |
| "eval_loss": 2.6069202423095703, |
| "eval_runtime": 23.6158, |
| "eval_samples_per_second": 59.028, |
| "eval_steps_per_second": 7.41, |
| "step": 32000 |
| }, |
| { |
| "epoch": 1826.4580369843527, |
| "grad_norm": 0.18724623322486877, |
| "learning_rate": 2.79933110367893e-06, |
| "loss": 2.6009, |
| "step": 32100 |
| }, |
| { |
| "epoch": 1826.4580369843527, |
| "eval_loss": 2.610833168029785, |
| "eval_runtime": 23.9646, |
| "eval_samples_per_second": 58.169, |
| "eval_steps_per_second": 7.302, |
| "step": 32100 |
| }, |
| { |
| "epoch": 1832.1479374110952, |
| "grad_norm": 0.20118850469589233, |
| "learning_rate": 2.7892976588628766e-06, |
| "loss": 2.6008, |
| "step": 32200 |
| }, |
| { |
| "epoch": 1832.1479374110952, |
| "eval_loss": 2.611131191253662, |
| "eval_runtime": 23.9699, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 32200 |
| }, |
| { |
| "epoch": 1837.837837837838, |
| "grad_norm": 0.18612216413021088, |
| "learning_rate": 2.779264214046823e-06, |
| "loss": 2.6003, |
| "step": 32300 |
| }, |
| { |
| "epoch": 1837.837837837838, |
| "eval_loss": 2.6071786880493164, |
| "eval_runtime": 23.6255, |
| "eval_samples_per_second": 59.004, |
| "eval_steps_per_second": 7.407, |
| "step": 32300 |
| }, |
| { |
| "epoch": 1843.5277382645804, |
| "grad_norm": 0.22030840814113617, |
| "learning_rate": 2.7692307692307693e-06, |
| "loss": 2.6006, |
| "step": 32400 |
| }, |
| { |
| "epoch": 1843.5277382645804, |
| "eval_loss": 2.611001968383789, |
| "eval_runtime": 23.9793, |
| "eval_samples_per_second": 58.133, |
| "eval_steps_per_second": 7.298, |
| "step": 32400 |
| }, |
| { |
| "epoch": 1849.217638691323, |
| "grad_norm": 0.1993936002254486, |
| "learning_rate": 2.759197324414716e-06, |
| "loss": 2.5998, |
| "step": 32500 |
| }, |
| { |
| "epoch": 1849.217638691323, |
| "eval_loss": 2.610430955886841, |
| "eval_runtime": 23.9674, |
| "eval_samples_per_second": 58.162, |
| "eval_steps_per_second": 7.302, |
| "step": 32500 |
| }, |
| { |
| "epoch": 1854.9075391180654, |
| "grad_norm": 0.20003485679626465, |
| "learning_rate": 2.749163879598662e-06, |
| "loss": 2.5992, |
| "step": 32600 |
| }, |
| { |
| "epoch": 1854.9075391180654, |
| "eval_loss": 2.608316421508789, |
| "eval_runtime": 23.6265, |
| "eval_samples_per_second": 59.002, |
| "eval_steps_per_second": 7.407, |
| "step": 32600 |
| }, |
| { |
| "epoch": 1860.597439544808, |
| "grad_norm": 0.191485196352005, |
| "learning_rate": 2.7391304347826087e-06, |
| "loss": 2.5994, |
| "step": 32700 |
| }, |
| { |
| "epoch": 1860.597439544808, |
| "eval_loss": 2.606895923614502, |
| "eval_runtime": 23.9721, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 32700 |
| }, |
| { |
| "epoch": 1866.2873399715504, |
| "grad_norm": 0.22254496812820435, |
| "learning_rate": 2.729096989966555e-06, |
| "loss": 2.5987, |
| "step": 32800 |
| }, |
| { |
| "epoch": 1866.2873399715504, |
| "eval_loss": 2.609882116317749, |
| "eval_runtime": 23.6229, |
| "eval_samples_per_second": 59.01, |
| "eval_steps_per_second": 7.408, |
| "step": 32800 |
| }, |
| { |
| "epoch": 1871.9772403982931, |
| "grad_norm": 0.21001747250556946, |
| "learning_rate": 2.7190635451505014e-06, |
| "loss": 2.5986, |
| "step": 32900 |
| }, |
| { |
| "epoch": 1871.9772403982931, |
| "eval_loss": 2.609361410140991, |
| "eval_runtime": 23.9824, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 32900 |
| }, |
| { |
| "epoch": 1877.6671408250356, |
| "grad_norm": 0.2182328701019287, |
| "learning_rate": 2.709030100334448e-06, |
| "loss": 2.5982, |
| "step": 33000 |
| }, |
| { |
| "epoch": 1877.6671408250356, |
| "eval_loss": 2.6055867671966553, |
| "eval_runtime": 23.9808, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.297, |
| "step": 33000 |
| }, |
| { |
| "epoch": 1883.3570412517781, |
| "grad_norm": 0.2228955626487732, |
| "learning_rate": 2.6989966555183945e-06, |
| "loss": 2.5981, |
| "step": 33100 |
| }, |
| { |
| "epoch": 1883.3570412517781, |
| "eval_loss": 2.6094181537628174, |
| "eval_runtime": 23.9937, |
| "eval_samples_per_second": 58.099, |
| "eval_steps_per_second": 7.294, |
| "step": 33100 |
| }, |
| { |
| "epoch": 1889.0469416785206, |
| "grad_norm": 0.20408956706523895, |
| "learning_rate": 2.6889632107023413e-06, |
| "loss": 2.5976, |
| "step": 33200 |
| }, |
| { |
| "epoch": 1889.0469416785206, |
| "eval_loss": 2.610013484954834, |
| "eval_runtime": 23.9779, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 33200 |
| }, |
| { |
| "epoch": 1894.7368421052631, |
| "grad_norm": 0.18041720986366272, |
| "learning_rate": 2.6789297658862876e-06, |
| "loss": 2.5966, |
| "step": 33300 |
| }, |
| { |
| "epoch": 1894.7368421052631, |
| "eval_loss": 2.6073315143585205, |
| "eval_runtime": 23.9719, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 33300 |
| }, |
| { |
| "epoch": 1900.4267425320056, |
| "grad_norm": 0.21475084125995636, |
| "learning_rate": 2.668896321070234e-06, |
| "loss": 2.5971, |
| "step": 33400 |
| }, |
| { |
| "epoch": 1900.4267425320056, |
| "eval_loss": 2.6072559356689453, |
| "eval_runtime": 23.9644, |
| "eval_samples_per_second": 58.17, |
| "eval_steps_per_second": 7.303, |
| "step": 33400 |
| }, |
| { |
| "epoch": 1906.1166429587481, |
| "grad_norm": 0.20976944267749786, |
| "learning_rate": 2.6588628762541807e-06, |
| "loss": 2.5975, |
| "step": 33500 |
| }, |
| { |
| "epoch": 1906.1166429587481, |
| "eval_loss": 2.610696315765381, |
| "eval_runtime": 23.9698, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 33500 |
| }, |
| { |
| "epoch": 1911.8065433854908, |
| "grad_norm": 0.22089052200317383, |
| "learning_rate": 2.648829431438127e-06, |
| "loss": 2.5967, |
| "step": 33600 |
| }, |
| { |
| "epoch": 1911.8065433854908, |
| "eval_loss": 2.610421895980835, |
| "eval_runtime": 23.9697, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 33600 |
| }, |
| { |
| "epoch": 1917.4964438122333, |
| "grad_norm": 0.2476435750722885, |
| "learning_rate": 2.6387959866220734e-06, |
| "loss": 2.5967, |
| "step": 33700 |
| }, |
| { |
| "epoch": 1917.4964438122333, |
| "eval_loss": 2.609027862548828, |
| "eval_runtime": 23.9693, |
| "eval_samples_per_second": 58.158, |
| "eval_steps_per_second": 7.301, |
| "step": 33700 |
| }, |
| { |
| "epoch": 1923.1863442389758, |
| "grad_norm": 0.2400488555431366, |
| "learning_rate": 2.62876254180602e-06, |
| "loss": 2.5963, |
| "step": 33800 |
| }, |
| { |
| "epoch": 1923.1863442389758, |
| "eval_loss": 2.606323480606079, |
| "eval_runtime": 23.9793, |
| "eval_samples_per_second": 58.133, |
| "eval_steps_per_second": 7.298, |
| "step": 33800 |
| }, |
| { |
| "epoch": 1928.8762446657183, |
| "grad_norm": 0.22055935859680176, |
| "learning_rate": 2.6187290969899665e-06, |
| "loss": 2.596, |
| "step": 33900 |
| }, |
| { |
| "epoch": 1928.8762446657183, |
| "eval_loss": 2.6059587001800537, |
| "eval_runtime": 23.9784, |
| "eval_samples_per_second": 58.136, |
| "eval_steps_per_second": 7.298, |
| "step": 33900 |
| }, |
| { |
| "epoch": 1934.5661450924608, |
| "grad_norm": 0.19678466022014618, |
| "learning_rate": 2.6086956521739132e-06, |
| "loss": 2.5958, |
| "step": 34000 |
| }, |
| { |
| "epoch": 1934.5661450924608, |
| "eval_loss": 2.607278347015381, |
| "eval_runtime": 23.9722, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 34000 |
| }, |
| { |
| "epoch": 1940.2560455192033, |
| "grad_norm": 0.19066280126571655, |
| "learning_rate": 2.5986622073578596e-06, |
| "loss": 2.596, |
| "step": 34100 |
| }, |
| { |
| "epoch": 1940.2560455192033, |
| "eval_loss": 2.6062145233154297, |
| "eval_runtime": 23.9754, |
| "eval_samples_per_second": 58.143, |
| "eval_steps_per_second": 7.299, |
| "step": 34100 |
| }, |
| { |
| "epoch": 1945.945945945946, |
| "grad_norm": 0.18578113615512848, |
| "learning_rate": 2.588628762541806e-06, |
| "loss": 2.5956, |
| "step": 34200 |
| }, |
| { |
| "epoch": 1945.945945945946, |
| "eval_loss": 2.6075074672698975, |
| "eval_runtime": 23.9661, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.302, |
| "step": 34200 |
| }, |
| { |
| "epoch": 1951.6358463726885, |
| "grad_norm": 0.1975042223930359, |
| "learning_rate": 2.5785953177257527e-06, |
| "loss": 2.595, |
| "step": 34300 |
| }, |
| { |
| "epoch": 1951.6358463726885, |
| "eval_loss": 2.6064653396606445, |
| "eval_runtime": 23.9808, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.298, |
| "step": 34300 |
| }, |
| { |
| "epoch": 1957.325746799431, |
| "grad_norm": 0.19423623383045197, |
| "learning_rate": 2.568561872909699e-06, |
| "loss": 2.595, |
| "step": 34400 |
| }, |
| { |
| "epoch": 1957.325746799431, |
| "eval_loss": 2.611752510070801, |
| "eval_runtime": 23.6289, |
| "eval_samples_per_second": 58.996, |
| "eval_steps_per_second": 7.406, |
| "step": 34400 |
| }, |
| { |
| "epoch": 1963.0156472261735, |
| "grad_norm": 0.2097640186548233, |
| "learning_rate": 2.5585284280936454e-06, |
| "loss": 2.595, |
| "step": 34500 |
| }, |
| { |
| "epoch": 1963.0156472261735, |
| "eval_loss": 2.6093528270721436, |
| "eval_runtime": 23.9769, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 34500 |
| }, |
| { |
| "epoch": 1968.705547652916, |
| "grad_norm": 0.21185003221035004, |
| "learning_rate": 2.548494983277592e-06, |
| "loss": 2.5948, |
| "step": 34600 |
| }, |
| { |
| "epoch": 1968.705547652916, |
| "eval_loss": 2.608447551727295, |
| "eval_runtime": 23.9828, |
| "eval_samples_per_second": 58.125, |
| "eval_steps_per_second": 7.297, |
| "step": 34600 |
| }, |
| { |
| "epoch": 1974.3954480796585, |
| "grad_norm": 0.20163875818252563, |
| "learning_rate": 2.5384615384615385e-06, |
| "loss": 2.595, |
| "step": 34700 |
| }, |
| { |
| "epoch": 1974.3954480796585, |
| "eval_loss": 2.6056010723114014, |
| "eval_runtime": 23.9675, |
| "eval_samples_per_second": 58.162, |
| "eval_steps_per_second": 7.302, |
| "step": 34700 |
| }, |
| { |
| "epoch": 1980.085348506401, |
| "grad_norm": 0.2156960666179657, |
| "learning_rate": 2.528428093645485e-06, |
| "loss": 2.5939, |
| "step": 34800 |
| }, |
| { |
| "epoch": 1980.085348506401, |
| "eval_loss": 2.608295440673828, |
| "eval_runtime": 23.9789, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 34800 |
| }, |
| { |
| "epoch": 1985.7752489331438, |
| "grad_norm": 0.21288277208805084, |
| "learning_rate": 2.5183946488294316e-06, |
| "loss": 2.5941, |
| "step": 34900 |
| }, |
| { |
| "epoch": 1985.7752489331438, |
| "eval_loss": 2.6072516441345215, |
| "eval_runtime": 23.9694, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 34900 |
| }, |
| { |
| "epoch": 1991.4651493598863, |
| "grad_norm": 0.19131049513816833, |
| "learning_rate": 2.508361204013378e-06, |
| "loss": 2.5936, |
| "step": 35000 |
| }, |
| { |
| "epoch": 1991.4651493598863, |
| "eval_loss": 2.607457160949707, |
| "eval_runtime": 23.9676, |
| "eval_samples_per_second": 58.162, |
| "eval_steps_per_second": 7.302, |
| "step": 35000 |
| }, |
| { |
| "epoch": 1997.1550497866288, |
| "grad_norm": 0.20999549329280853, |
| "learning_rate": 2.4983277591973247e-06, |
| "loss": 2.5942, |
| "step": 35100 |
| }, |
| { |
| "epoch": 1997.1550497866288, |
| "eval_loss": 2.6048200130462646, |
| "eval_runtime": 23.9476, |
| "eval_samples_per_second": 58.211, |
| "eval_steps_per_second": 7.308, |
| "step": 35100 |
| }, |
| { |
| "epoch": 2002.8449502133712, |
| "grad_norm": 0.22608843445777893, |
| "learning_rate": 2.488294314381271e-06, |
| "loss": 2.5936, |
| "step": 35200 |
| }, |
| { |
| "epoch": 2002.8449502133712, |
| "eval_loss": 2.6086690425872803, |
| "eval_runtime": 23.9613, |
| "eval_samples_per_second": 58.177, |
| "eval_steps_per_second": 7.303, |
| "step": 35200 |
| }, |
| { |
| "epoch": 2008.5348506401137, |
| "grad_norm": 0.21249240636825562, |
| "learning_rate": 2.4782608695652173e-06, |
| "loss": 2.5937, |
| "step": 35300 |
| }, |
| { |
| "epoch": 2008.5348506401137, |
| "eval_loss": 2.609616994857788, |
| "eval_runtime": 23.984, |
| "eval_samples_per_second": 58.122, |
| "eval_steps_per_second": 7.297, |
| "step": 35300 |
| }, |
| { |
| "epoch": 2014.2247510668562, |
| "grad_norm": 0.18126103281974792, |
| "learning_rate": 2.468227424749164e-06, |
| "loss": 2.593, |
| "step": 35400 |
| }, |
| { |
| "epoch": 2014.2247510668562, |
| "eval_loss": 2.607325792312622, |
| "eval_runtime": 23.6173, |
| "eval_samples_per_second": 59.025, |
| "eval_steps_per_second": 7.41, |
| "step": 35400 |
| }, |
| { |
| "epoch": 2019.914651493599, |
| "grad_norm": 0.21532674133777618, |
| "learning_rate": 2.4581939799331104e-06, |
| "loss": 2.593, |
| "step": 35500 |
| }, |
| { |
| "epoch": 2019.914651493599, |
| "eval_loss": 2.605360269546509, |
| "eval_runtime": 23.9754, |
| "eval_samples_per_second": 58.143, |
| "eval_steps_per_second": 7.299, |
| "step": 35500 |
| }, |
| { |
| "epoch": 2025.6045519203415, |
| "grad_norm": 0.22612471878528595, |
| "learning_rate": 2.4481605351170568e-06, |
| "loss": 2.5933, |
| "step": 35600 |
| }, |
| { |
| "epoch": 2025.6045519203415, |
| "eval_loss": 2.607989549636841, |
| "eval_runtime": 23.988, |
| "eval_samples_per_second": 58.112, |
| "eval_steps_per_second": 7.295, |
| "step": 35600 |
| }, |
| { |
| "epoch": 2031.294452347084, |
| "grad_norm": 0.20216602087020874, |
| "learning_rate": 2.4381270903010035e-06, |
| "loss": 2.5932, |
| "step": 35700 |
| }, |
| { |
| "epoch": 2031.294452347084, |
| "eval_loss": 2.606175184249878, |
| "eval_runtime": 23.9791, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.298, |
| "step": 35700 |
| }, |
| { |
| "epoch": 2036.9843527738265, |
| "grad_norm": 0.19835437834262848, |
| "learning_rate": 2.42809364548495e-06, |
| "loss": 2.5925, |
| "step": 35800 |
| }, |
| { |
| "epoch": 2036.9843527738265, |
| "eval_loss": 2.607192277908325, |
| "eval_runtime": 23.9678, |
| "eval_samples_per_second": 58.161, |
| "eval_steps_per_second": 7.301, |
| "step": 35800 |
| }, |
| { |
| "epoch": 2042.674253200569, |
| "grad_norm": 0.24524998664855957, |
| "learning_rate": 2.4180602006688962e-06, |
| "loss": 2.5933, |
| "step": 35900 |
| }, |
| { |
| "epoch": 2042.674253200569, |
| "eval_loss": 2.606074094772339, |
| "eval_runtime": 23.9751, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 35900 |
| }, |
| { |
| "epoch": 2048.3641536273117, |
| "grad_norm": 0.2061767429113388, |
| "learning_rate": 2.408026755852843e-06, |
| "loss": 2.5923, |
| "step": 36000 |
| }, |
| { |
| "epoch": 2048.3641536273117, |
| "eval_loss": 2.606078624725342, |
| "eval_runtime": 23.9619, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 36000 |
| }, |
| { |
| "epoch": 2054.054054054054, |
| "grad_norm": 0.2126512974500656, |
| "learning_rate": 2.3979933110367893e-06, |
| "loss": 2.5923, |
| "step": 36100 |
| }, |
| { |
| "epoch": 2054.054054054054, |
| "eval_loss": 2.6044681072235107, |
| "eval_runtime": 23.9651, |
| "eval_samples_per_second": 58.168, |
| "eval_steps_per_second": 7.302, |
| "step": 36100 |
| }, |
| { |
| "epoch": 2059.7439544807967, |
| "grad_norm": 0.19873598217964172, |
| "learning_rate": 2.387959866220736e-06, |
| "loss": 2.5917, |
| "step": 36200 |
| }, |
| { |
| "epoch": 2059.7439544807967, |
| "eval_loss": 2.6049787998199463, |
| "eval_runtime": 23.9985, |
| "eval_samples_per_second": 58.087, |
| "eval_steps_per_second": 7.292, |
| "step": 36200 |
| }, |
| { |
| "epoch": 2065.433854907539, |
| "grad_norm": 0.22740136086940765, |
| "learning_rate": 2.3779264214046824e-06, |
| "loss": 2.592, |
| "step": 36300 |
| }, |
| { |
| "epoch": 2065.433854907539, |
| "eval_loss": 2.6051523685455322, |
| "eval_runtime": 23.9778, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 36300 |
| }, |
| { |
| "epoch": 2071.1237553342817, |
| "grad_norm": 0.23417142033576965, |
| "learning_rate": 2.3678929765886288e-06, |
| "loss": 2.5919, |
| "step": 36400 |
| }, |
| { |
| "epoch": 2071.1237553342817, |
| "eval_loss": 2.6095163822174072, |
| "eval_runtime": 23.9947, |
| "eval_samples_per_second": 58.096, |
| "eval_steps_per_second": 7.293, |
| "step": 36400 |
| }, |
| { |
| "epoch": 2076.813655761024, |
| "grad_norm": 0.201192244887352, |
| "learning_rate": 2.3578595317725755e-06, |
| "loss": 2.5914, |
| "step": 36500 |
| }, |
| { |
| "epoch": 2076.813655761024, |
| "eval_loss": 2.6050267219543457, |
| "eval_runtime": 23.6283, |
| "eval_samples_per_second": 58.997, |
| "eval_steps_per_second": 7.406, |
| "step": 36500 |
| }, |
| { |
| "epoch": 2082.5035561877667, |
| "grad_norm": 0.21296341717243195, |
| "learning_rate": 2.347826086956522e-06, |
| "loss": 2.592, |
| "step": 36600 |
| }, |
| { |
| "epoch": 2082.5035561877667, |
| "eval_loss": 2.6075668334960938, |
| "eval_runtime": 23.9712, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 36600 |
| }, |
| { |
| "epoch": 2088.193456614509, |
| "grad_norm": 0.21053853631019592, |
| "learning_rate": 2.337792642140468e-06, |
| "loss": 2.5917, |
| "step": 36700 |
| }, |
| { |
| "epoch": 2088.193456614509, |
| "eval_loss": 2.606757879257202, |
| "eval_runtime": 23.9742, |
| "eval_samples_per_second": 58.146, |
| "eval_steps_per_second": 7.3, |
| "step": 36700 |
| }, |
| { |
| "epoch": 2093.8833570412517, |
| "grad_norm": 0.1819269359111786, |
| "learning_rate": 2.327759197324415e-06, |
| "loss": 2.5913, |
| "step": 36800 |
| }, |
| { |
| "epoch": 2093.8833570412517, |
| "eval_loss": 2.606837272644043, |
| "eval_runtime": 23.9719, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 36800 |
| }, |
| { |
| "epoch": 2099.573257467994, |
| "grad_norm": 0.2274492383003235, |
| "learning_rate": 2.3177257525083613e-06, |
| "loss": 2.5913, |
| "step": 36900 |
| }, |
| { |
| "epoch": 2099.573257467994, |
| "eval_loss": 2.607267379760742, |
| "eval_runtime": 23.9826, |
| "eval_samples_per_second": 58.125, |
| "eval_steps_per_second": 7.297, |
| "step": 36900 |
| }, |
| { |
| "epoch": 2105.2631578947367, |
| "grad_norm": 0.2047816663980484, |
| "learning_rate": 2.307692307692308e-06, |
| "loss": 2.5913, |
| "step": 37000 |
| }, |
| { |
| "epoch": 2105.2631578947367, |
| "eval_loss": 2.605915069580078, |
| "eval_runtime": 23.9786, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 37000 |
| }, |
| { |
| "epoch": 2110.953058321479, |
| "grad_norm": 0.22065645456314087, |
| "learning_rate": 2.2976588628762544e-06, |
| "loss": 2.5911, |
| "step": 37100 |
| }, |
| { |
| "epoch": 2110.953058321479, |
| "eval_loss": 2.6056876182556152, |
| "eval_runtime": 23.9857, |
| "eval_samples_per_second": 58.118, |
| "eval_steps_per_second": 7.296, |
| "step": 37100 |
| }, |
| { |
| "epoch": 2116.642958748222, |
| "grad_norm": 0.23279725015163422, |
| "learning_rate": 2.2876254180602008e-06, |
| "loss": 2.5909, |
| "step": 37200 |
| }, |
| { |
| "epoch": 2116.642958748222, |
| "eval_loss": 2.6096079349517822, |
| "eval_runtime": 23.9666, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 37200 |
| }, |
| { |
| "epoch": 2122.3328591749646, |
| "grad_norm": 0.20520757138729095, |
| "learning_rate": 2.2775919732441475e-06, |
| "loss": 2.5913, |
| "step": 37300 |
| }, |
| { |
| "epoch": 2122.3328591749646, |
| "eval_loss": 2.605616569519043, |
| "eval_runtime": 23.9741, |
| "eval_samples_per_second": 58.146, |
| "eval_steps_per_second": 7.3, |
| "step": 37300 |
| }, |
| { |
| "epoch": 2128.022759601707, |
| "grad_norm": 0.21737107634544373, |
| "learning_rate": 2.267558528428094e-06, |
| "loss": 2.5909, |
| "step": 37400 |
| }, |
| { |
| "epoch": 2128.022759601707, |
| "eval_loss": 2.6048943996429443, |
| "eval_runtime": 23.6318, |
| "eval_samples_per_second": 58.988, |
| "eval_steps_per_second": 7.405, |
| "step": 37400 |
| }, |
| { |
| "epoch": 2133.7126600284496, |
| "grad_norm": 0.20358791947364807, |
| "learning_rate": 2.25752508361204e-06, |
| "loss": 2.5909, |
| "step": 37500 |
| }, |
| { |
| "epoch": 2133.7126600284496, |
| "eval_loss": 2.6061489582061768, |
| "eval_runtime": 23.9684, |
| "eval_samples_per_second": 58.16, |
| "eval_steps_per_second": 7.301, |
| "step": 37500 |
| }, |
| { |
| "epoch": 2139.402560455192, |
| "grad_norm": 0.22121722996234894, |
| "learning_rate": 2.2474916387959865e-06, |
| "loss": 2.5907, |
| "step": 37600 |
| }, |
| { |
| "epoch": 2139.402560455192, |
| "eval_loss": 2.6052770614624023, |
| "eval_runtime": 23.9516, |
| "eval_samples_per_second": 58.201, |
| "eval_steps_per_second": 7.306, |
| "step": 37600 |
| }, |
| { |
| "epoch": 2145.0924608819346, |
| "grad_norm": 0.22327056527137756, |
| "learning_rate": 2.237458193979933e-06, |
| "loss": 2.59, |
| "step": 37700 |
| }, |
| { |
| "epoch": 2145.0924608819346, |
| "eval_loss": 2.609347343444824, |
| "eval_runtime": 23.9602, |
| "eval_samples_per_second": 58.18, |
| "eval_steps_per_second": 7.304, |
| "step": 37700 |
| }, |
| { |
| "epoch": 2150.782361308677, |
| "grad_norm": 0.2154139280319214, |
| "learning_rate": 2.2274247491638796e-06, |
| "loss": 2.5906, |
| "step": 37800 |
| }, |
| { |
| "epoch": 2150.782361308677, |
| "eval_loss": 2.6085565090179443, |
| "eval_runtime": 23.9701, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 37800 |
| }, |
| { |
| "epoch": 2156.4722617354196, |
| "grad_norm": 0.2098981738090515, |
| "learning_rate": 2.217391304347826e-06, |
| "loss": 2.5904, |
| "step": 37900 |
| }, |
| { |
| "epoch": 2156.4722617354196, |
| "eval_loss": 2.6086554527282715, |
| "eval_runtime": 23.9713, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 37900 |
| }, |
| { |
| "epoch": 2162.162162162162, |
| "grad_norm": 0.23115159571170807, |
| "learning_rate": 2.2073578595317723e-06, |
| "loss": 2.5904, |
| "step": 38000 |
| }, |
| { |
| "epoch": 2162.162162162162, |
| "eval_loss": 2.6087803840637207, |
| "eval_runtime": 23.9789, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 38000 |
| }, |
| { |
| "epoch": 2167.8520625889046, |
| "grad_norm": 0.21658512949943542, |
| "learning_rate": 2.197324414715719e-06, |
| "loss": 2.59, |
| "step": 38100 |
| }, |
| { |
| "epoch": 2167.8520625889046, |
| "eval_loss": 2.6069300174713135, |
| "eval_runtime": 23.9659, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 38100 |
| }, |
| { |
| "epoch": 2173.541963015647, |
| "grad_norm": 0.20112384855747223, |
| "learning_rate": 2.1872909698996654e-06, |
| "loss": 2.5901, |
| "step": 38200 |
| }, |
| { |
| "epoch": 2173.541963015647, |
| "eval_loss": 2.6072750091552734, |
| "eval_runtime": 23.6174, |
| "eval_samples_per_second": 59.024, |
| "eval_steps_per_second": 7.41, |
| "step": 38200 |
| }, |
| { |
| "epoch": 2179.2318634423896, |
| "grad_norm": 0.21559318900108337, |
| "learning_rate": 2.177257525083612e-06, |
| "loss": 2.5899, |
| "step": 38300 |
| }, |
| { |
| "epoch": 2179.2318634423896, |
| "eval_loss": 2.609740734100342, |
| "eval_runtime": 23.9734, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 38300 |
| }, |
| { |
| "epoch": 2184.921763869132, |
| "grad_norm": 0.2399979680776596, |
| "learning_rate": 2.1672240802675585e-06, |
| "loss": 2.5898, |
| "step": 38400 |
| }, |
| { |
| "epoch": 2184.921763869132, |
| "eval_loss": 2.6082592010498047, |
| "eval_runtime": 23.9721, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 38400 |
| }, |
| { |
| "epoch": 2190.611664295875, |
| "grad_norm": 0.20176702737808228, |
| "learning_rate": 2.157190635451505e-06, |
| "loss": 2.5898, |
| "step": 38500 |
| }, |
| { |
| "epoch": 2190.611664295875, |
| "eval_loss": 2.609528064727783, |
| "eval_runtime": 23.9695, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 38500 |
| }, |
| { |
| "epoch": 2196.3015647226175, |
| "grad_norm": 0.2130006104707718, |
| "learning_rate": 2.1471571906354516e-06, |
| "loss": 2.5896, |
| "step": 38600 |
| }, |
| { |
| "epoch": 2196.3015647226175, |
| "eval_loss": 2.6067283153533936, |
| "eval_runtime": 23.9785, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 38600 |
| }, |
| { |
| "epoch": 2201.99146514936, |
| "grad_norm": 0.19360195100307465, |
| "learning_rate": 2.137123745819398e-06, |
| "loss": 2.5897, |
| "step": 38700 |
| }, |
| { |
| "epoch": 2201.99146514936, |
| "eval_loss": 2.6070244312286377, |
| "eval_runtime": 23.9734, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 38700 |
| }, |
| { |
| "epoch": 2207.6813655761025, |
| "grad_norm": 0.21760191023349762, |
| "learning_rate": 2.1270903010033443e-06, |
| "loss": 2.589, |
| "step": 38800 |
| }, |
| { |
| "epoch": 2207.6813655761025, |
| "eval_loss": 2.6102993488311768, |
| "eval_runtime": 23.9663, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.302, |
| "step": 38800 |
| }, |
| { |
| "epoch": 2213.371266002845, |
| "grad_norm": 0.21763825416564941, |
| "learning_rate": 2.117056856187291e-06, |
| "loss": 2.5895, |
| "step": 38900 |
| }, |
| { |
| "epoch": 2213.371266002845, |
| "eval_loss": 2.6087794303894043, |
| "eval_runtime": 23.9613, |
| "eval_samples_per_second": 58.177, |
| "eval_steps_per_second": 7.303, |
| "step": 38900 |
| }, |
| { |
| "epoch": 2219.0611664295875, |
| "grad_norm": 0.2202463299036026, |
| "learning_rate": 2.1070234113712374e-06, |
| "loss": 2.5887, |
| "step": 39000 |
| }, |
| { |
| "epoch": 2219.0611664295875, |
| "eval_loss": 2.6068382263183594, |
| "eval_runtime": 23.9826, |
| "eval_samples_per_second": 58.125, |
| "eval_steps_per_second": 7.297, |
| "step": 39000 |
| }, |
| { |
| "epoch": 2224.75106685633, |
| "grad_norm": 0.21476009488105774, |
| "learning_rate": 2.0969899665551837e-06, |
| "loss": 2.5889, |
| "step": 39100 |
| }, |
| { |
| "epoch": 2224.75106685633, |
| "eval_loss": 2.608288049697876, |
| "eval_runtime": 23.6185, |
| "eval_samples_per_second": 59.021, |
| "eval_steps_per_second": 7.409, |
| "step": 39100 |
| }, |
| { |
| "epoch": 2230.4409672830725, |
| "grad_norm": 0.24493220448493958, |
| "learning_rate": 2.0869565217391305e-06, |
| "loss": 2.589, |
| "step": 39200 |
| }, |
| { |
| "epoch": 2230.4409672830725, |
| "eval_loss": 2.6087050437927246, |
| "eval_runtime": 23.9767, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 39200 |
| }, |
| { |
| "epoch": 2236.130867709815, |
| "grad_norm": 0.20519843697547913, |
| "learning_rate": 2.076923076923077e-06, |
| "loss": 2.5888, |
| "step": 39300 |
| }, |
| { |
| "epoch": 2236.130867709815, |
| "eval_loss": 2.6077113151550293, |
| "eval_runtime": 23.9716, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 39300 |
| }, |
| { |
| "epoch": 2241.8207681365575, |
| "grad_norm": 0.21633167564868927, |
| "learning_rate": 2.0668896321070236e-06, |
| "loss": 2.5889, |
| "step": 39400 |
| }, |
| { |
| "epoch": 2241.8207681365575, |
| "eval_loss": 2.606517791748047, |
| "eval_runtime": 23.9694, |
| "eval_samples_per_second": 58.158, |
| "eval_steps_per_second": 7.301, |
| "step": 39400 |
| }, |
| { |
| "epoch": 2247.5106685633, |
| "grad_norm": 0.21099114418029785, |
| "learning_rate": 2.05685618729097e-06, |
| "loss": 2.5889, |
| "step": 39500 |
| }, |
| { |
| "epoch": 2247.5106685633, |
| "eval_loss": 2.6069552898406982, |
| "eval_runtime": 23.9796, |
| "eval_samples_per_second": 58.133, |
| "eval_steps_per_second": 7.298, |
| "step": 39500 |
| }, |
| { |
| "epoch": 2253.2005689900425, |
| "grad_norm": 0.21585485339164734, |
| "learning_rate": 2.0468227424749163e-06, |
| "loss": 2.5885, |
| "step": 39600 |
| }, |
| { |
| "epoch": 2253.2005689900425, |
| "eval_loss": 2.6081788539886475, |
| "eval_runtime": 23.9947, |
| "eval_samples_per_second": 58.096, |
| "eval_steps_per_second": 7.293, |
| "step": 39600 |
| }, |
| { |
| "epoch": 2258.890469416785, |
| "grad_norm": 0.22519052028656006, |
| "learning_rate": 2.036789297658863e-06, |
| "loss": 2.5887, |
| "step": 39700 |
| }, |
| { |
| "epoch": 2258.890469416785, |
| "eval_loss": 2.607969284057617, |
| "eval_runtime": 23.9681, |
| "eval_samples_per_second": 58.161, |
| "eval_steps_per_second": 7.301, |
| "step": 39700 |
| }, |
| { |
| "epoch": 2264.580369843528, |
| "grad_norm": 0.22348664700984955, |
| "learning_rate": 2.0267558528428094e-06, |
| "loss": 2.5885, |
| "step": 39800 |
| }, |
| { |
| "epoch": 2264.580369843528, |
| "eval_loss": 2.605234146118164, |
| "eval_runtime": 23.9762, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 39800 |
| }, |
| { |
| "epoch": 2270.2702702702704, |
| "grad_norm": 0.22468328475952148, |
| "learning_rate": 2.0167224080267557e-06, |
| "loss": 2.5879, |
| "step": 39900 |
| }, |
| { |
| "epoch": 2270.2702702702704, |
| "eval_loss": 2.6086230278015137, |
| "eval_runtime": 23.9804, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 39900 |
| }, |
| { |
| "epoch": 2275.960170697013, |
| "grad_norm": 0.22100846469402313, |
| "learning_rate": 2.0066889632107025e-06, |
| "loss": 2.5881, |
| "step": 40000 |
| }, |
| { |
| "epoch": 2275.960170697013, |
| "eval_loss": 2.6064453125, |
| "eval_runtime": 23.619, |
| "eval_samples_per_second": 59.02, |
| "eval_steps_per_second": 7.409, |
| "step": 40000 |
| }, |
| { |
| "epoch": 2281.6500711237554, |
| "grad_norm": 0.22934798896312714, |
| "learning_rate": 1.996655518394649e-06, |
| "loss": 2.588, |
| "step": 40100 |
| }, |
| { |
| "epoch": 2281.6500711237554, |
| "eval_loss": 2.609809398651123, |
| "eval_runtime": 23.9742, |
| "eval_samples_per_second": 58.146, |
| "eval_steps_per_second": 7.3, |
| "step": 40100 |
| }, |
| { |
| "epoch": 2287.339971550498, |
| "grad_norm": 0.22776305675506592, |
| "learning_rate": 1.986622073578595e-06, |
| "loss": 2.5879, |
| "step": 40200 |
| }, |
| { |
| "epoch": 2287.339971550498, |
| "eval_loss": 2.610957622528076, |
| "eval_runtime": 23.9692, |
| "eval_samples_per_second": 58.158, |
| "eval_steps_per_second": 7.301, |
| "step": 40200 |
| }, |
| { |
| "epoch": 2293.0298719772404, |
| "grad_norm": 0.24109528958797455, |
| "learning_rate": 1.976588628762542e-06, |
| "loss": 2.5873, |
| "step": 40300 |
| }, |
| { |
| "epoch": 2293.0298719772404, |
| "eval_loss": 2.6117520332336426, |
| "eval_runtime": 23.9749, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 40300 |
| }, |
| { |
| "epoch": 2298.719772403983, |
| "grad_norm": 0.20761537551879883, |
| "learning_rate": 1.9665551839464883e-06, |
| "loss": 2.5882, |
| "step": 40400 |
| }, |
| { |
| "epoch": 2298.719772403983, |
| "eval_loss": 2.6076319217681885, |
| "eval_runtime": 23.9837, |
| "eval_samples_per_second": 58.123, |
| "eval_steps_per_second": 7.297, |
| "step": 40400 |
| }, |
| { |
| "epoch": 2304.4096728307254, |
| "grad_norm": 0.2197142243385315, |
| "learning_rate": 1.956521739130435e-06, |
| "loss": 2.5876, |
| "step": 40500 |
| }, |
| { |
| "epoch": 2304.4096728307254, |
| "eval_loss": 2.6088201999664307, |
| "eval_runtime": 23.9737, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 40500 |
| }, |
| { |
| "epoch": 2310.099573257468, |
| "grad_norm": 0.21660037338733673, |
| "learning_rate": 1.9464882943143814e-06, |
| "loss": 2.5877, |
| "step": 40600 |
| }, |
| { |
| "epoch": 2310.099573257468, |
| "eval_loss": 2.6094954013824463, |
| "eval_runtime": 23.9699, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 40600 |
| }, |
| { |
| "epoch": 2315.7894736842104, |
| "grad_norm": 0.2162291556596756, |
| "learning_rate": 1.9364548494983277e-06, |
| "loss": 2.5874, |
| "step": 40700 |
| }, |
| { |
| "epoch": 2315.7894736842104, |
| "eval_loss": 2.6068737506866455, |
| "eval_runtime": 23.9747, |
| "eval_samples_per_second": 58.145, |
| "eval_steps_per_second": 7.299, |
| "step": 40700 |
| }, |
| { |
| "epoch": 2321.479374110953, |
| "grad_norm": 0.20265834033489227, |
| "learning_rate": 1.9264214046822745e-06, |
| "loss": 2.5874, |
| "step": 40800 |
| }, |
| { |
| "epoch": 2321.479374110953, |
| "eval_loss": 2.6073391437530518, |
| "eval_runtime": 23.634, |
| "eval_samples_per_second": 58.983, |
| "eval_steps_per_second": 7.405, |
| "step": 40800 |
| }, |
| { |
| "epoch": 2327.1692745376954, |
| "grad_norm": 0.23362219333648682, |
| "learning_rate": 1.916387959866221e-06, |
| "loss": 2.5869, |
| "step": 40900 |
| }, |
| { |
| "epoch": 2327.1692745376954, |
| "eval_loss": 2.6071267127990723, |
| "eval_runtime": 23.9719, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 40900 |
| }, |
| { |
| "epoch": 2332.859174964438, |
| "grad_norm": 0.2258542776107788, |
| "learning_rate": 1.9063545150501674e-06, |
| "loss": 2.587, |
| "step": 41000 |
| }, |
| { |
| "epoch": 2332.859174964438, |
| "eval_loss": 2.608017683029175, |
| "eval_runtime": 23.9627, |
| "eval_samples_per_second": 58.174, |
| "eval_steps_per_second": 7.303, |
| "step": 41000 |
| }, |
| { |
| "epoch": 2338.549075391181, |
| "grad_norm": 0.2063855081796646, |
| "learning_rate": 1.896321070234114e-06, |
| "loss": 2.5865, |
| "step": 41100 |
| }, |
| { |
| "epoch": 2338.549075391181, |
| "eval_loss": 2.6086549758911133, |
| "eval_runtime": 23.9754, |
| "eval_samples_per_second": 58.143, |
| "eval_steps_per_second": 7.299, |
| "step": 41100 |
| }, |
| { |
| "epoch": 2344.2389758179233, |
| "grad_norm": 0.23593726754188538, |
| "learning_rate": 1.8862876254180603e-06, |
| "loss": 2.5868, |
| "step": 41200 |
| }, |
| { |
| "epoch": 2344.2389758179233, |
| "eval_loss": 2.6107077598571777, |
| "eval_runtime": 23.9719, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 41200 |
| }, |
| { |
| "epoch": 2349.928876244666, |
| "grad_norm": 0.21962851285934448, |
| "learning_rate": 1.8762541806020068e-06, |
| "loss": 2.5868, |
| "step": 41300 |
| }, |
| { |
| "epoch": 2349.928876244666, |
| "eval_loss": 2.6100499629974365, |
| "eval_runtime": 23.9651, |
| "eval_samples_per_second": 58.168, |
| "eval_steps_per_second": 7.302, |
| "step": 41300 |
| }, |
| { |
| "epoch": 2355.6187766714083, |
| "grad_norm": 0.21013060212135315, |
| "learning_rate": 1.8662207357859534e-06, |
| "loss": 2.5868, |
| "step": 41400 |
| }, |
| { |
| "epoch": 2355.6187766714083, |
| "eval_loss": 2.611445426940918, |
| "eval_runtime": 23.9689, |
| "eval_samples_per_second": 58.159, |
| "eval_steps_per_second": 7.301, |
| "step": 41400 |
| }, |
| { |
| "epoch": 2361.308677098151, |
| "grad_norm": 0.21894079446792603, |
| "learning_rate": 1.8561872909699e-06, |
| "loss": 2.5867, |
| "step": 41500 |
| }, |
| { |
| "epoch": 2361.308677098151, |
| "eval_loss": 2.607694149017334, |
| "eval_runtime": 23.9659, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 41500 |
| }, |
| { |
| "epoch": 2366.9985775248933, |
| "grad_norm": 0.23075686395168304, |
| "learning_rate": 1.8461538461538462e-06, |
| "loss": 2.5868, |
| "step": 41600 |
| }, |
| { |
| "epoch": 2366.9985775248933, |
| "eval_loss": 2.6095731258392334, |
| "eval_runtime": 23.955, |
| "eval_samples_per_second": 58.192, |
| "eval_steps_per_second": 7.305, |
| "step": 41600 |
| }, |
| { |
| "epoch": 2372.688477951636, |
| "grad_norm": 0.20675238966941833, |
| "learning_rate": 1.8361204013377928e-06, |
| "loss": 2.5861, |
| "step": 41700 |
| }, |
| { |
| "epoch": 2372.688477951636, |
| "eval_loss": 2.609567880630493, |
| "eval_runtime": 23.6274, |
| "eval_samples_per_second": 58.999, |
| "eval_steps_per_second": 7.407, |
| "step": 41700 |
| }, |
| { |
| "epoch": 2378.3783783783783, |
| "grad_norm": 0.22343020141124725, |
| "learning_rate": 1.8260869565217394e-06, |
| "loss": 2.5866, |
| "step": 41800 |
| }, |
| { |
| "epoch": 2378.3783783783783, |
| "eval_loss": 2.6095831394195557, |
| "eval_runtime": 23.9726, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 41800 |
| }, |
| { |
| "epoch": 2384.068278805121, |
| "grad_norm": 0.21456314623355865, |
| "learning_rate": 1.8160535117056857e-06, |
| "loss": 2.5865, |
| "step": 41900 |
| }, |
| { |
| "epoch": 2384.068278805121, |
| "eval_loss": 2.608867883682251, |
| "eval_runtime": 23.9641, |
| "eval_samples_per_second": 58.17, |
| "eval_steps_per_second": 7.303, |
| "step": 41900 |
| }, |
| { |
| "epoch": 2389.7581792318633, |
| "grad_norm": 0.21167542040348053, |
| "learning_rate": 1.8060200668896322e-06, |
| "loss": 2.5861, |
| "step": 42000 |
| }, |
| { |
| "epoch": 2389.7581792318633, |
| "eval_loss": 2.6074702739715576, |
| "eval_runtime": 23.9714, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 42000 |
| }, |
| { |
| "epoch": 2395.448079658606, |
| "grad_norm": 0.2520188093185425, |
| "learning_rate": 1.7959866220735788e-06, |
| "loss": 2.5857, |
| "step": 42100 |
| }, |
| { |
| "epoch": 2395.448079658606, |
| "eval_loss": 2.606618881225586, |
| "eval_runtime": 23.9735, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 42100 |
| }, |
| { |
| "epoch": 2401.1379800853483, |
| "grad_norm": 0.2366916537284851, |
| "learning_rate": 1.7859531772575253e-06, |
| "loss": 2.5864, |
| "step": 42200 |
| }, |
| { |
| "epoch": 2401.1379800853483, |
| "eval_loss": 2.6078577041625977, |
| "eval_runtime": 23.9739, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 42200 |
| }, |
| { |
| "epoch": 2406.827880512091, |
| "grad_norm": 0.22600212693214417, |
| "learning_rate": 1.7759197324414717e-06, |
| "loss": 2.5863, |
| "step": 42300 |
| }, |
| { |
| "epoch": 2406.827880512091, |
| "eval_loss": 2.6072797775268555, |
| "eval_runtime": 23.9618, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 42300 |
| }, |
| { |
| "epoch": 2412.5177809388338, |
| "grad_norm": 0.2162897288799286, |
| "learning_rate": 1.7658862876254182e-06, |
| "loss": 2.5856, |
| "step": 42400 |
| }, |
| { |
| "epoch": 2412.5177809388338, |
| "eval_loss": 2.6077022552490234, |
| "eval_runtime": 23.6377, |
| "eval_samples_per_second": 58.973, |
| "eval_steps_per_second": 7.403, |
| "step": 42400 |
| }, |
| { |
| "epoch": 2418.2076813655763, |
| "grad_norm": 0.22395272552967072, |
| "learning_rate": 1.7558528428093648e-06, |
| "loss": 2.5855, |
| "step": 42500 |
| }, |
| { |
| "epoch": 2418.2076813655763, |
| "eval_loss": 2.6070289611816406, |
| "eval_runtime": 23.9804, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 42500 |
| }, |
| { |
| "epoch": 2423.8975817923188, |
| "grad_norm": 0.21771951019763947, |
| "learning_rate": 1.745819397993311e-06, |
| "loss": 2.5856, |
| "step": 42600 |
| }, |
| { |
| "epoch": 2423.8975817923188, |
| "eval_loss": 2.6128346920013428, |
| "eval_runtime": 23.6285, |
| "eval_samples_per_second": 58.996, |
| "eval_steps_per_second": 7.406, |
| "step": 42600 |
| }, |
| { |
| "epoch": 2429.5874822190613, |
| "grad_norm": 0.23614706099033356, |
| "learning_rate": 1.7357859531772575e-06, |
| "loss": 2.5856, |
| "step": 42700 |
| }, |
| { |
| "epoch": 2429.5874822190613, |
| "eval_loss": 2.611271858215332, |
| "eval_runtime": 23.9785, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 42700 |
| }, |
| { |
| "epoch": 2435.2773826458038, |
| "grad_norm": 0.22254329919815063, |
| "learning_rate": 1.7257525083612038e-06, |
| "loss": 2.5861, |
| "step": 42800 |
| }, |
| { |
| "epoch": 2435.2773826458038, |
| "eval_loss": 2.609328031539917, |
| "eval_runtime": 23.9834, |
| "eval_samples_per_second": 58.124, |
| "eval_steps_per_second": 7.297, |
| "step": 42800 |
| }, |
| { |
| "epoch": 2440.9672830725463, |
| "grad_norm": 0.24362125992774963, |
| "learning_rate": 1.7157190635451504e-06, |
| "loss": 2.585, |
| "step": 42900 |
| }, |
| { |
| "epoch": 2440.9672830725463, |
| "eval_loss": 2.610111713409424, |
| "eval_runtime": 23.9838, |
| "eval_samples_per_second": 58.123, |
| "eval_steps_per_second": 7.297, |
| "step": 42900 |
| }, |
| { |
| "epoch": 2446.6571834992887, |
| "grad_norm": 0.20748943090438843, |
| "learning_rate": 1.705685618729097e-06, |
| "loss": 2.5854, |
| "step": 43000 |
| }, |
| { |
| "epoch": 2446.6571834992887, |
| "eval_loss": 2.6088545322418213, |
| "eval_runtime": 23.9817, |
| "eval_samples_per_second": 58.128, |
| "eval_steps_per_second": 7.297, |
| "step": 43000 |
| }, |
| { |
| "epoch": 2452.3470839260312, |
| "grad_norm": 0.231778085231781, |
| "learning_rate": 1.6956521739130435e-06, |
| "loss": 2.5848, |
| "step": 43100 |
| }, |
| { |
| "epoch": 2452.3470839260312, |
| "eval_loss": 2.609499454498291, |
| "eval_runtime": 23.9762, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 43100 |
| }, |
| { |
| "epoch": 2458.0369843527737, |
| "grad_norm": 0.2319919317960739, |
| "learning_rate": 1.6856187290969898e-06, |
| "loss": 2.5854, |
| "step": 43200 |
| }, |
| { |
| "epoch": 2458.0369843527737, |
| "eval_loss": 2.6097819805145264, |
| "eval_runtime": 23.9664, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.302, |
| "step": 43200 |
| }, |
| { |
| "epoch": 2463.7268847795162, |
| "grad_norm": 0.212693452835083, |
| "learning_rate": 1.6755852842809363e-06, |
| "loss": 2.5846, |
| "step": 43300 |
| }, |
| { |
| "epoch": 2463.7268847795162, |
| "eval_loss": 2.6089398860931396, |
| "eval_runtime": 23.9713, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 43300 |
| }, |
| { |
| "epoch": 2469.4167852062587, |
| "grad_norm": 0.2074272632598877, |
| "learning_rate": 1.665551839464883e-06, |
| "loss": 2.5852, |
| "step": 43400 |
| }, |
| { |
| "epoch": 2469.4167852062587, |
| "eval_loss": 2.6096198558807373, |
| "eval_runtime": 23.9727, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 43400 |
| }, |
| { |
| "epoch": 2475.1066856330012, |
| "grad_norm": 0.23323705792427063, |
| "learning_rate": 1.6555183946488294e-06, |
| "loss": 2.5847, |
| "step": 43500 |
| }, |
| { |
| "epoch": 2475.1066856330012, |
| "eval_loss": 2.607158899307251, |
| "eval_runtime": 23.8136, |
| "eval_samples_per_second": 58.538, |
| "eval_steps_per_second": 7.349, |
| "step": 43500 |
| }, |
| { |
| "epoch": 2480.7965860597437, |
| "grad_norm": 0.24258296191692352, |
| "learning_rate": 1.6454849498327758e-06, |
| "loss": 2.585, |
| "step": 43600 |
| }, |
| { |
| "epoch": 2480.7965860597437, |
| "eval_loss": 2.6117851734161377, |
| "eval_runtime": 23.8061, |
| "eval_samples_per_second": 58.556, |
| "eval_steps_per_second": 7.351, |
| "step": 43600 |
| }, |
| { |
| "epoch": 2486.4864864864867, |
| "grad_norm": 0.23719272017478943, |
| "learning_rate": 1.6354515050167223e-06, |
| "loss": 2.585, |
| "step": 43700 |
| }, |
| { |
| "epoch": 2486.4864864864867, |
| "eval_loss": 2.610424518585205, |
| "eval_runtime": 23.9999, |
| "eval_samples_per_second": 58.083, |
| "eval_steps_per_second": 7.292, |
| "step": 43700 |
| }, |
| { |
| "epoch": 2492.176386913229, |
| "grad_norm": 0.2383095622062683, |
| "learning_rate": 1.6254180602006689e-06, |
| "loss": 2.5847, |
| "step": 43800 |
| }, |
| { |
| "epoch": 2492.176386913229, |
| "eval_loss": 2.6086204051971436, |
| "eval_runtime": 23.9767, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 43800 |
| }, |
| { |
| "epoch": 2497.8662873399717, |
| "grad_norm": 0.23796670138835907, |
| "learning_rate": 1.6153846153846154e-06, |
| "loss": 2.5843, |
| "step": 43900 |
| }, |
| { |
| "epoch": 2497.8662873399717, |
| "eval_loss": 2.607516050338745, |
| "eval_runtime": 23.9736, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 43900 |
| }, |
| { |
| "epoch": 2503.556187766714, |
| "grad_norm": 0.2234671711921692, |
| "learning_rate": 1.6053511705685618e-06, |
| "loss": 2.5846, |
| "step": 44000 |
| }, |
| { |
| "epoch": 2503.556187766714, |
| "eval_loss": 2.6071882247924805, |
| "eval_runtime": 23.9746, |
| "eval_samples_per_second": 58.145, |
| "eval_steps_per_second": 7.299, |
| "step": 44000 |
| }, |
| { |
| "epoch": 2509.2460881934567, |
| "grad_norm": 0.2136596143245697, |
| "learning_rate": 1.5953177257525083e-06, |
| "loss": 2.5847, |
| "step": 44100 |
| }, |
| { |
| "epoch": 2509.2460881934567, |
| "eval_loss": 2.6061131954193115, |
| "eval_runtime": 23.6146, |
| "eval_samples_per_second": 59.031, |
| "eval_steps_per_second": 7.411, |
| "step": 44100 |
| }, |
| { |
| "epoch": 2514.935988620199, |
| "grad_norm": 0.21045100688934326, |
| "learning_rate": 1.5852842809364549e-06, |
| "loss": 2.5841, |
| "step": 44200 |
| }, |
| { |
| "epoch": 2514.935988620199, |
| "eval_loss": 2.6131772994995117, |
| "eval_runtime": 23.9763, |
| "eval_samples_per_second": 58.141, |
| "eval_steps_per_second": 7.299, |
| "step": 44200 |
| }, |
| { |
| "epoch": 2520.6258890469417, |
| "grad_norm": 0.2306642085313797, |
| "learning_rate": 1.5752508361204012e-06, |
| "loss": 2.5843, |
| "step": 44300 |
| }, |
| { |
| "epoch": 2520.6258890469417, |
| "eval_loss": 2.613348960876465, |
| "eval_runtime": 23.6254, |
| "eval_samples_per_second": 59.004, |
| "eval_steps_per_second": 7.407, |
| "step": 44300 |
| }, |
| { |
| "epoch": 2526.315789473684, |
| "grad_norm": 0.22865846753120422, |
| "learning_rate": 1.5652173913043478e-06, |
| "loss": 2.5839, |
| "step": 44400 |
| }, |
| { |
| "epoch": 2526.315789473684, |
| "eval_loss": 2.608555793762207, |
| "eval_runtime": 23.9869, |
| "eval_samples_per_second": 58.115, |
| "eval_steps_per_second": 7.296, |
| "step": 44400 |
| }, |
| { |
| "epoch": 2532.0056899004267, |
| "grad_norm": 0.23196746408939362, |
| "learning_rate": 1.5551839464882943e-06, |
| "loss": 2.5837, |
| "step": 44500 |
| }, |
| { |
| "epoch": 2532.0056899004267, |
| "eval_loss": 2.6074063777923584, |
| "eval_runtime": 23.9961, |
| "eval_samples_per_second": 58.093, |
| "eval_steps_per_second": 7.293, |
| "step": 44500 |
| }, |
| { |
| "epoch": 2537.695590327169, |
| "grad_norm": 0.22961702942848206, |
| "learning_rate": 1.5451505016722409e-06, |
| "loss": 2.5843, |
| "step": 44600 |
| }, |
| { |
| "epoch": 2537.695590327169, |
| "eval_loss": 2.6085050106048584, |
| "eval_runtime": 23.6299, |
| "eval_samples_per_second": 58.993, |
| "eval_steps_per_second": 7.406, |
| "step": 44600 |
| }, |
| { |
| "epoch": 2543.3854907539117, |
| "grad_norm": 0.23799484968185425, |
| "learning_rate": 1.5351170568561872e-06, |
| "loss": 2.584, |
| "step": 44700 |
| }, |
| { |
| "epoch": 2543.3854907539117, |
| "eval_loss": 2.610715866088867, |
| "eval_runtime": 23.9802, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 44700 |
| }, |
| { |
| "epoch": 2549.075391180654, |
| "grad_norm": 0.21905191242694855, |
| "learning_rate": 1.5250836120401338e-06, |
| "loss": 2.5835, |
| "step": 44800 |
| }, |
| { |
| "epoch": 2549.075391180654, |
| "eval_loss": 2.6101200580596924, |
| "eval_runtime": 23.9821, |
| "eval_samples_per_second": 58.127, |
| "eval_steps_per_second": 7.297, |
| "step": 44800 |
| }, |
| { |
| "epoch": 2554.7652916073966, |
| "grad_norm": 0.21092022955417633, |
| "learning_rate": 1.5150501672240803e-06, |
| "loss": 2.5836, |
| "step": 44900 |
| }, |
| { |
| "epoch": 2554.7652916073966, |
| "eval_loss": 2.6060028076171875, |
| "eval_runtime": 23.9759, |
| "eval_samples_per_second": 58.142, |
| "eval_steps_per_second": 7.299, |
| "step": 44900 |
| }, |
| { |
| "epoch": 2560.4551920341396, |
| "grad_norm": 0.25125664472579956, |
| "learning_rate": 1.5050167224080269e-06, |
| "loss": 2.5832, |
| "step": 45000 |
| }, |
| { |
| "epoch": 2560.4551920341396, |
| "eval_loss": 2.612673759460449, |
| "eval_runtime": 23.9727, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 45000 |
| }, |
| { |
| "epoch": 2566.145092460882, |
| "grad_norm": 0.23938561975955963, |
| "learning_rate": 1.4949832775919732e-06, |
| "loss": 2.5833, |
| "step": 45100 |
| }, |
| { |
| "epoch": 2566.145092460882, |
| "eval_loss": 2.61169171333313, |
| "eval_runtime": 23.9657, |
| "eval_samples_per_second": 58.167, |
| "eval_steps_per_second": 7.302, |
| "step": 45100 |
| }, |
| { |
| "epoch": 2571.8349928876246, |
| "grad_norm": 0.23332080245018005, |
| "learning_rate": 1.4849498327759198e-06, |
| "loss": 2.5836, |
| "step": 45200 |
| }, |
| { |
| "epoch": 2571.8349928876246, |
| "eval_loss": 2.6075634956359863, |
| "eval_runtime": 23.9719, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 45200 |
| }, |
| { |
| "epoch": 2577.524893314367, |
| "grad_norm": 0.2493467926979065, |
| "learning_rate": 1.4749163879598663e-06, |
| "loss": 2.5833, |
| "step": 45300 |
| }, |
| { |
| "epoch": 2577.524893314367, |
| "eval_loss": 2.6123712062835693, |
| "eval_runtime": 23.9809, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.297, |
| "step": 45300 |
| }, |
| { |
| "epoch": 2583.2147937411096, |
| "grad_norm": 0.23774316906929016, |
| "learning_rate": 1.4648829431438129e-06, |
| "loss": 2.5832, |
| "step": 45400 |
| }, |
| { |
| "epoch": 2583.2147937411096, |
| "eval_loss": 2.6104633808135986, |
| "eval_runtime": 23.6171, |
| "eval_samples_per_second": 59.025, |
| "eval_steps_per_second": 7.41, |
| "step": 45400 |
| }, |
| { |
| "epoch": 2588.904694167852, |
| "grad_norm": 0.2435203492641449, |
| "learning_rate": 1.4548494983277592e-06, |
| "loss": 2.5829, |
| "step": 45500 |
| }, |
| { |
| "epoch": 2588.904694167852, |
| "eval_loss": 2.6109774112701416, |
| "eval_runtime": 23.9777, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 45500 |
| }, |
| { |
| "epoch": 2594.5945945945946, |
| "grad_norm": 0.22922101616859436, |
| "learning_rate": 1.4448160535117058e-06, |
| "loss": 2.5835, |
| "step": 45600 |
| }, |
| { |
| "epoch": 2594.5945945945946, |
| "eval_loss": 2.6112453937530518, |
| "eval_runtime": 23.972, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 45600 |
| }, |
| { |
| "epoch": 2600.284495021337, |
| "grad_norm": 0.23543110489845276, |
| "learning_rate": 1.4347826086956523e-06, |
| "loss": 2.5828, |
| "step": 45700 |
| }, |
| { |
| "epoch": 2600.284495021337, |
| "eval_loss": 2.6099853515625, |
| "eval_runtime": 23.9851, |
| "eval_samples_per_second": 58.119, |
| "eval_steps_per_second": 7.296, |
| "step": 45700 |
| }, |
| { |
| "epoch": 2605.9743954480796, |
| "grad_norm": 0.2309664934873581, |
| "learning_rate": 1.4247491638795989e-06, |
| "loss": 2.5826, |
| "step": 45800 |
| }, |
| { |
| "epoch": 2605.9743954480796, |
| "eval_loss": 2.6090052127838135, |
| "eval_runtime": 23.9855, |
| "eval_samples_per_second": 58.119, |
| "eval_steps_per_second": 7.296, |
| "step": 45800 |
| }, |
| { |
| "epoch": 2611.664295874822, |
| "grad_norm": 0.22243796288967133, |
| "learning_rate": 1.4147157190635452e-06, |
| "loss": 2.5829, |
| "step": 45900 |
| }, |
| { |
| "epoch": 2611.664295874822, |
| "eval_loss": 2.610006809234619, |
| "eval_runtime": 23.6294, |
| "eval_samples_per_second": 58.994, |
| "eval_steps_per_second": 7.406, |
| "step": 45900 |
| }, |
| { |
| "epoch": 2617.3541963015646, |
| "grad_norm": 0.23384037613868713, |
| "learning_rate": 1.4046822742474917e-06, |
| "loss": 2.5823, |
| "step": 46000 |
| }, |
| { |
| "epoch": 2617.3541963015646, |
| "eval_loss": 2.6132850646972656, |
| "eval_runtime": 23.9678, |
| "eval_samples_per_second": 58.161, |
| "eval_steps_per_second": 7.301, |
| "step": 46000 |
| }, |
| { |
| "epoch": 2623.044096728307, |
| "grad_norm": 0.23333188891410828, |
| "learning_rate": 1.3946488294314383e-06, |
| "loss": 2.5827, |
| "step": 46100 |
| }, |
| { |
| "epoch": 2623.044096728307, |
| "eval_loss": 2.612513780593872, |
| "eval_runtime": 23.6358, |
| "eval_samples_per_second": 58.978, |
| "eval_steps_per_second": 7.404, |
| "step": 46100 |
| }, |
| { |
| "epoch": 2628.7339971550496, |
| "grad_norm": 0.23102706670761108, |
| "learning_rate": 1.3846153846153846e-06, |
| "loss": 2.5824, |
| "step": 46200 |
| }, |
| { |
| "epoch": 2628.7339971550496, |
| "eval_loss": 2.610734701156616, |
| "eval_runtime": 23.9924, |
| "eval_samples_per_second": 58.102, |
| "eval_steps_per_second": 7.294, |
| "step": 46200 |
| }, |
| { |
| "epoch": 2634.4238975817925, |
| "grad_norm": 0.2388777732849121, |
| "learning_rate": 1.374581939799331e-06, |
| "loss": 2.5828, |
| "step": 46300 |
| }, |
| { |
| "epoch": 2634.4238975817925, |
| "eval_loss": 2.6136250495910645, |
| "eval_runtime": 23.6235, |
| "eval_samples_per_second": 59.009, |
| "eval_steps_per_second": 7.408, |
| "step": 46300 |
| }, |
| { |
| "epoch": 2640.113798008535, |
| "grad_norm": 0.24917742609977722, |
| "learning_rate": 1.3645484949832775e-06, |
| "loss": 2.5827, |
| "step": 46400 |
| }, |
| { |
| "epoch": 2640.113798008535, |
| "eval_loss": 2.6128790378570557, |
| "eval_runtime": 23.9692, |
| "eval_samples_per_second": 58.158, |
| "eval_steps_per_second": 7.301, |
| "step": 46400 |
| }, |
| { |
| "epoch": 2645.8036984352775, |
| "grad_norm": 0.2471284121274948, |
| "learning_rate": 1.354515050167224e-06, |
| "loss": 2.5821, |
| "step": 46500 |
| }, |
| { |
| "epoch": 2645.8036984352775, |
| "eval_loss": 2.612271785736084, |
| "eval_runtime": 23.9748, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 46500 |
| }, |
| { |
| "epoch": 2651.49359886202, |
| "grad_norm": 0.24588705599308014, |
| "learning_rate": 1.3444816053511706e-06, |
| "loss": 2.5824, |
| "step": 46600 |
| }, |
| { |
| "epoch": 2651.49359886202, |
| "eval_loss": 2.6146724224090576, |
| "eval_runtime": 23.9734, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 46600 |
| }, |
| { |
| "epoch": 2657.1834992887625, |
| "grad_norm": 0.22074657678604126, |
| "learning_rate": 1.334448160535117e-06, |
| "loss": 2.5821, |
| "step": 46700 |
| }, |
| { |
| "epoch": 2657.1834992887625, |
| "eval_loss": 2.612962484359741, |
| "eval_runtime": 23.6303, |
| "eval_samples_per_second": 58.992, |
| "eval_steps_per_second": 7.406, |
| "step": 46700 |
| }, |
| { |
| "epoch": 2662.873399715505, |
| "grad_norm": 0.23231124877929688, |
| "learning_rate": 1.3244147157190635e-06, |
| "loss": 2.5826, |
| "step": 46800 |
| }, |
| { |
| "epoch": 2662.873399715505, |
| "eval_loss": 2.6139097213745117, |
| "eval_runtime": 23.9752, |
| "eval_samples_per_second": 58.143, |
| "eval_steps_per_second": 7.299, |
| "step": 46800 |
| }, |
| { |
| "epoch": 2668.5633001422475, |
| "grad_norm": 0.24543775618076324, |
| "learning_rate": 1.31438127090301e-06, |
| "loss": 2.5814, |
| "step": 46900 |
| }, |
| { |
| "epoch": 2668.5633001422475, |
| "eval_loss": 2.6093571186065674, |
| "eval_runtime": 23.9769, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 46900 |
| }, |
| { |
| "epoch": 2674.25320056899, |
| "grad_norm": 0.24010956287384033, |
| "learning_rate": 1.3043478260869566e-06, |
| "loss": 2.5825, |
| "step": 47000 |
| }, |
| { |
| "epoch": 2674.25320056899, |
| "eval_loss": 2.610830307006836, |
| "eval_runtime": 23.973, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 47000 |
| }, |
| { |
| "epoch": 2679.9431009957325, |
| "grad_norm": 0.25266411900520325, |
| "learning_rate": 1.294314381270903e-06, |
| "loss": 2.5823, |
| "step": 47100 |
| }, |
| { |
| "epoch": 2679.9431009957325, |
| "eval_loss": 2.613356113433838, |
| "eval_runtime": 24.8418, |
| "eval_samples_per_second": 56.115, |
| "eval_steps_per_second": 7.045, |
| "step": 47100 |
| }, |
| { |
| "epoch": 2685.633001422475, |
| "grad_norm": 0.2359105348587036, |
| "learning_rate": 1.2842809364548495e-06, |
| "loss": 2.5815, |
| "step": 47200 |
| }, |
| { |
| "epoch": 2685.633001422475, |
| "eval_loss": 2.6079251766204834, |
| "eval_runtime": 23.9697, |
| "eval_samples_per_second": 58.157, |
| "eval_steps_per_second": 7.301, |
| "step": 47200 |
| }, |
| { |
| "epoch": 2691.3229018492175, |
| "grad_norm": 0.23083586990833282, |
| "learning_rate": 1.274247491638796e-06, |
| "loss": 2.5813, |
| "step": 47300 |
| }, |
| { |
| "epoch": 2691.3229018492175, |
| "eval_loss": 2.6135170459747314, |
| "eval_runtime": 23.6299, |
| "eval_samples_per_second": 58.993, |
| "eval_steps_per_second": 7.406, |
| "step": 47300 |
| }, |
| { |
| "epoch": 2697.01280227596, |
| "grad_norm": 0.2380247265100479, |
| "learning_rate": 1.2642140468227424e-06, |
| "loss": 2.5818, |
| "step": 47400 |
| }, |
| { |
| "epoch": 2697.01280227596, |
| "eval_loss": 2.6122384071350098, |
| "eval_runtime": 23.9739, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 47400 |
| }, |
| { |
| "epoch": 2702.7027027027025, |
| "grad_norm": 0.24715080857276917, |
| "learning_rate": 1.254180602006689e-06, |
| "loss": 2.5817, |
| "step": 47500 |
| }, |
| { |
| "epoch": 2702.7027027027025, |
| "eval_loss": 2.6100640296936035, |
| "eval_runtime": 23.6355, |
| "eval_samples_per_second": 58.979, |
| "eval_steps_per_second": 7.404, |
| "step": 47500 |
| }, |
| { |
| "epoch": 2708.3926031294454, |
| "grad_norm": 0.24939079582691193, |
| "learning_rate": 1.2441471571906355e-06, |
| "loss": 2.5819, |
| "step": 47600 |
| }, |
| { |
| "epoch": 2708.3926031294454, |
| "eval_loss": 2.611419439315796, |
| "eval_runtime": 23.9748, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 47600 |
| }, |
| { |
| "epoch": 2714.082503556188, |
| "grad_norm": 0.22941380739212036, |
| "learning_rate": 1.234113712374582e-06, |
| "loss": 2.5809, |
| "step": 47700 |
| }, |
| { |
| "epoch": 2714.082503556188, |
| "eval_loss": 2.612551689147949, |
| "eval_runtime": 23.9661, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.302, |
| "step": 47700 |
| }, |
| { |
| "epoch": 2719.7724039829304, |
| "grad_norm": 0.25405701994895935, |
| "learning_rate": 1.2240802675585284e-06, |
| "loss": 2.5817, |
| "step": 47800 |
| }, |
| { |
| "epoch": 2719.7724039829304, |
| "eval_loss": 2.6119425296783447, |
| "eval_runtime": 23.9765, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 47800 |
| }, |
| { |
| "epoch": 2725.462304409673, |
| "grad_norm": 0.22298355400562286, |
| "learning_rate": 1.214046822742475e-06, |
| "loss": 2.581, |
| "step": 47900 |
| }, |
| { |
| "epoch": 2725.462304409673, |
| "eval_loss": 2.6139628887176514, |
| "eval_runtime": 23.9951, |
| "eval_samples_per_second": 58.095, |
| "eval_steps_per_second": 7.293, |
| "step": 47900 |
| }, |
| { |
| "epoch": 2731.1522048364154, |
| "grad_norm": 0.2541176676750183, |
| "learning_rate": 1.2040133779264215e-06, |
| "loss": 2.5816, |
| "step": 48000 |
| }, |
| { |
| "epoch": 2731.1522048364154, |
| "eval_loss": 2.611189365386963, |
| "eval_runtime": 23.9729, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 48000 |
| }, |
| { |
| "epoch": 2736.842105263158, |
| "grad_norm": 0.2229371964931488, |
| "learning_rate": 1.193979933110368e-06, |
| "loss": 2.5807, |
| "step": 48100 |
| }, |
| { |
| "epoch": 2736.842105263158, |
| "eval_loss": 2.611900568008423, |
| "eval_runtime": 23.9711, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 48100 |
| }, |
| { |
| "epoch": 2742.5320056899004, |
| "grad_norm": 0.23724424839019775, |
| "learning_rate": 1.1839464882943144e-06, |
| "loss": 2.5813, |
| "step": 48200 |
| }, |
| { |
| "epoch": 2742.5320056899004, |
| "eval_loss": 2.612854242324829, |
| "eval_runtime": 23.9618, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 48200 |
| }, |
| { |
| "epoch": 2748.221906116643, |
| "grad_norm": 0.2304125279188156, |
| "learning_rate": 1.173913043478261e-06, |
| "loss": 2.5809, |
| "step": 48300 |
| }, |
| { |
| "epoch": 2748.221906116643, |
| "eval_loss": 2.6128289699554443, |
| "eval_runtime": 23.6362, |
| "eval_samples_per_second": 58.977, |
| "eval_steps_per_second": 7.404, |
| "step": 48300 |
| }, |
| { |
| "epoch": 2753.9118065433854, |
| "grad_norm": 0.23649877309799194, |
| "learning_rate": 1.1638795986622075e-06, |
| "loss": 2.5809, |
| "step": 48400 |
| }, |
| { |
| "epoch": 2753.9118065433854, |
| "eval_loss": 2.610621929168701, |
| "eval_runtime": 23.9852, |
| "eval_samples_per_second": 58.119, |
| "eval_steps_per_second": 7.296, |
| "step": 48400 |
| }, |
| { |
| "epoch": 2759.601706970128, |
| "grad_norm": 0.22622932493686676, |
| "learning_rate": 1.153846153846154e-06, |
| "loss": 2.5812, |
| "step": 48500 |
| }, |
| { |
| "epoch": 2759.601706970128, |
| "eval_loss": 2.6125988960266113, |
| "eval_runtime": 23.9907, |
| "eval_samples_per_second": 58.106, |
| "eval_steps_per_second": 7.294, |
| "step": 48500 |
| }, |
| { |
| "epoch": 2765.2916073968704, |
| "grad_norm": 0.22394676506519318, |
| "learning_rate": 1.1438127090301004e-06, |
| "loss": 2.5811, |
| "step": 48600 |
| }, |
| { |
| "epoch": 2765.2916073968704, |
| "eval_loss": 2.6074447631835938, |
| "eval_runtime": 23.9898, |
| "eval_samples_per_second": 58.108, |
| "eval_steps_per_second": 7.295, |
| "step": 48600 |
| }, |
| { |
| "epoch": 2770.981507823613, |
| "grad_norm": 0.22825615108013153, |
| "learning_rate": 1.133779264214047e-06, |
| "loss": 2.5807, |
| "step": 48700 |
| }, |
| { |
| "epoch": 2770.981507823613, |
| "eval_loss": 2.611135721206665, |
| "eval_runtime": 23.9665, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 48700 |
| }, |
| { |
| "epoch": 2776.6714082503554, |
| "grad_norm": 0.21429681777954102, |
| "learning_rate": 1.1237458193979933e-06, |
| "loss": 2.5806, |
| "step": 48800 |
| }, |
| { |
| "epoch": 2776.6714082503554, |
| "eval_loss": 2.6128909587860107, |
| "eval_runtime": 23.9654, |
| "eval_samples_per_second": 58.167, |
| "eval_steps_per_second": 7.302, |
| "step": 48800 |
| }, |
| { |
| "epoch": 2782.3613086770984, |
| "grad_norm": 0.24192963540554047, |
| "learning_rate": 1.1137123745819398e-06, |
| "loss": 2.5808, |
| "step": 48900 |
| }, |
| { |
| "epoch": 2782.3613086770984, |
| "eval_loss": 2.6103410720825195, |
| "eval_runtime": 23.9656, |
| "eval_samples_per_second": 58.167, |
| "eval_steps_per_second": 7.302, |
| "step": 48900 |
| }, |
| { |
| "epoch": 2788.051209103841, |
| "grad_norm": 0.23475612699985504, |
| "learning_rate": 1.1036789297658862e-06, |
| "loss": 2.5808, |
| "step": 49000 |
| }, |
| { |
| "epoch": 2788.051209103841, |
| "eval_loss": 2.6121463775634766, |
| "eval_runtime": 23.9729, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 49000 |
| }, |
| { |
| "epoch": 2793.7411095305833, |
| "grad_norm": 0.2512466609477997, |
| "learning_rate": 1.0936454849498327e-06, |
| "loss": 2.5807, |
| "step": 49100 |
| }, |
| { |
| "epoch": 2793.7411095305833, |
| "eval_loss": 2.6137309074401855, |
| "eval_runtime": 23.6272, |
| "eval_samples_per_second": 59.0, |
| "eval_steps_per_second": 7.407, |
| "step": 49100 |
| }, |
| { |
| "epoch": 2799.431009957326, |
| "grad_norm": 0.23058511316776276, |
| "learning_rate": 1.0836120401337793e-06, |
| "loss": 2.5804, |
| "step": 49200 |
| }, |
| { |
| "epoch": 2799.431009957326, |
| "eval_loss": 2.6124165058135986, |
| "eval_runtime": 23.9709, |
| "eval_samples_per_second": 58.154, |
| "eval_steps_per_second": 7.301, |
| "step": 49200 |
| }, |
| { |
| "epoch": 2805.1209103840683, |
| "grad_norm": 0.22364000976085663, |
| "learning_rate": 1.0735785953177258e-06, |
| "loss": 2.5806, |
| "step": 49300 |
| }, |
| { |
| "epoch": 2805.1209103840683, |
| "eval_loss": 2.6106984615325928, |
| "eval_runtime": 23.9772, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 49300 |
| }, |
| { |
| "epoch": 2810.810810810811, |
| "grad_norm": 0.2526606321334839, |
| "learning_rate": 1.0635451505016722e-06, |
| "loss": 2.5804, |
| "step": 49400 |
| }, |
| { |
| "epoch": 2810.810810810811, |
| "eval_loss": 2.610975742340088, |
| "eval_runtime": 23.9837, |
| "eval_samples_per_second": 58.123, |
| "eval_steps_per_second": 7.297, |
| "step": 49400 |
| }, |
| { |
| "epoch": 2816.5007112375533, |
| "grad_norm": 0.2499561458826065, |
| "learning_rate": 1.0535117056856187e-06, |
| "loss": 2.58, |
| "step": 49500 |
| }, |
| { |
| "epoch": 2816.5007112375533, |
| "eval_loss": 2.6134748458862305, |
| "eval_runtime": 23.9785, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 49500 |
| }, |
| { |
| "epoch": 2822.190611664296, |
| "grad_norm": 0.24504046142101288, |
| "learning_rate": 1.0434782608695653e-06, |
| "loss": 2.5807, |
| "step": 49600 |
| }, |
| { |
| "epoch": 2822.190611664296, |
| "eval_loss": 2.612489700317383, |
| "eval_runtime": 23.9682, |
| "eval_samples_per_second": 58.16, |
| "eval_steps_per_second": 7.301, |
| "step": 49600 |
| }, |
| { |
| "epoch": 2827.8805120910383, |
| "grad_norm": 0.271673321723938, |
| "learning_rate": 1.0334448160535118e-06, |
| "loss": 2.5806, |
| "step": 49700 |
| }, |
| { |
| "epoch": 2827.8805120910383, |
| "eval_loss": 2.609774112701416, |
| "eval_runtime": 23.9659, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 49700 |
| }, |
| { |
| "epoch": 2833.570412517781, |
| "grad_norm": 0.2435864955186844, |
| "learning_rate": 1.0234113712374581e-06, |
| "loss": 2.58, |
| "step": 49800 |
| }, |
| { |
| "epoch": 2833.570412517781, |
| "eval_loss": 2.6116602420806885, |
| "eval_runtime": 23.9611, |
| "eval_samples_per_second": 58.178, |
| "eval_steps_per_second": 7.304, |
| "step": 49800 |
| }, |
| { |
| "epoch": 2839.2603129445233, |
| "grad_norm": 0.24582748115062714, |
| "learning_rate": 1.0133779264214047e-06, |
| "loss": 2.5801, |
| "step": 49900 |
| }, |
| { |
| "epoch": 2839.2603129445233, |
| "eval_loss": 2.605586528778076, |
| "eval_runtime": 23.6223, |
| "eval_samples_per_second": 59.012, |
| "eval_steps_per_second": 7.408, |
| "step": 49900 |
| }, |
| { |
| "epoch": 2844.950213371266, |
| "grad_norm": 0.24231892824172974, |
| "learning_rate": 1.0033444816053512e-06, |
| "loss": 2.5797, |
| "step": 50000 |
| }, |
| { |
| "epoch": 2844.950213371266, |
| "eval_loss": 2.6107475757598877, |
| "eval_runtime": 23.9738, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 50000 |
| }, |
| { |
| "epoch": 2850.6401137980083, |
| "grad_norm": 0.23913002014160156, |
| "learning_rate": 9.933110367892976e-07, |
| "loss": 2.5803, |
| "step": 50100 |
| }, |
| { |
| "epoch": 2850.6401137980083, |
| "eval_loss": 2.611083745956421, |
| "eval_runtime": 23.9703, |
| "eval_samples_per_second": 58.155, |
| "eval_steps_per_second": 7.301, |
| "step": 50100 |
| }, |
| { |
| "epoch": 2856.3300142247513, |
| "grad_norm": 0.23877963423728943, |
| "learning_rate": 9.832775919732441e-07, |
| "loss": 2.5797, |
| "step": 50200 |
| }, |
| { |
| "epoch": 2856.3300142247513, |
| "eval_loss": 2.6153957843780518, |
| "eval_runtime": 23.9825, |
| "eval_samples_per_second": 58.126, |
| "eval_steps_per_second": 7.297, |
| "step": 50200 |
| }, |
| { |
| "epoch": 2862.0199146514938, |
| "grad_norm": 0.23219284415245056, |
| "learning_rate": 9.732441471571907e-07, |
| "loss": 2.5798, |
| "step": 50300 |
| }, |
| { |
| "epoch": 2862.0199146514938, |
| "eval_loss": 2.6109278202056885, |
| "eval_runtime": 23.9766, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 50300 |
| }, |
| { |
| "epoch": 2867.7098150782363, |
| "grad_norm": 0.23990660905838013, |
| "learning_rate": 9.632107023411372e-07, |
| "loss": 2.5797, |
| "step": 50400 |
| }, |
| { |
| "epoch": 2867.7098150782363, |
| "eval_loss": 2.6120529174804688, |
| "eval_runtime": 23.9635, |
| "eval_samples_per_second": 58.172, |
| "eval_steps_per_second": 7.303, |
| "step": 50400 |
| }, |
| { |
| "epoch": 2873.3997155049788, |
| "grad_norm": 0.22840148210525513, |
| "learning_rate": 9.531772575250837e-07, |
| "loss": 2.5799, |
| "step": 50500 |
| }, |
| { |
| "epoch": 2873.3997155049788, |
| "eval_loss": 2.6159815788269043, |
| "eval_runtime": 23.9613, |
| "eval_samples_per_second": 58.177, |
| "eval_steps_per_second": 7.303, |
| "step": 50500 |
| }, |
| { |
| "epoch": 2879.0896159317213, |
| "grad_norm": 0.24212676286697388, |
| "learning_rate": 9.431438127090301e-07, |
| "loss": 2.5798, |
| "step": 50600 |
| }, |
| { |
| "epoch": 2879.0896159317213, |
| "eval_loss": 2.609698534011841, |
| "eval_runtime": 23.966, |
| "eval_samples_per_second": 58.166, |
| "eval_steps_per_second": 7.302, |
| "step": 50600 |
| }, |
| { |
| "epoch": 2884.7795163584638, |
| "grad_norm": 0.2604888081550598, |
| "learning_rate": 9.331103678929767e-07, |
| "loss": 2.5795, |
| "step": 50700 |
| }, |
| { |
| "epoch": 2884.7795163584638, |
| "eval_loss": 2.6143059730529785, |
| "eval_runtime": 23.616, |
| "eval_samples_per_second": 59.028, |
| "eval_steps_per_second": 7.41, |
| "step": 50700 |
| }, |
| { |
| "epoch": 2890.4694167852062, |
| "grad_norm": 0.2513519823551178, |
| "learning_rate": 9.230769230769231e-07, |
| "loss": 2.5798, |
| "step": 50800 |
| }, |
| { |
| "epoch": 2890.4694167852062, |
| "eval_loss": 2.6114535331726074, |
| "eval_runtime": 23.9617, |
| "eval_samples_per_second": 58.176, |
| "eval_steps_per_second": 7.303, |
| "step": 50800 |
| }, |
| { |
| "epoch": 2896.1593172119487, |
| "grad_norm": 0.262923926115036, |
| "learning_rate": 9.130434782608697e-07, |
| "loss": 2.5795, |
| "step": 50900 |
| }, |
| { |
| "epoch": 2896.1593172119487, |
| "eval_loss": 2.613948106765747, |
| "eval_runtime": 23.9726, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 50900 |
| }, |
| { |
| "epoch": 2901.8492176386912, |
| "grad_norm": 0.2399134784936905, |
| "learning_rate": 9.030100334448161e-07, |
| "loss": 2.5796, |
| "step": 51000 |
| }, |
| { |
| "epoch": 2901.8492176386912, |
| "eval_loss": 2.612149477005005, |
| "eval_runtime": 23.9766, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 51000 |
| }, |
| { |
| "epoch": 2907.5391180654337, |
| "grad_norm": 0.23589570820331573, |
| "learning_rate": 8.929765886287627e-07, |
| "loss": 2.5803, |
| "step": 51100 |
| }, |
| { |
| "epoch": 2907.5391180654337, |
| "eval_loss": 2.612802743911743, |
| "eval_runtime": 23.9879, |
| "eval_samples_per_second": 58.113, |
| "eval_steps_per_second": 7.295, |
| "step": 51100 |
| }, |
| { |
| "epoch": 2913.2290184921762, |
| "grad_norm": 0.24552448093891144, |
| "learning_rate": 8.829431438127091e-07, |
| "loss": 2.5795, |
| "step": 51200 |
| }, |
| { |
| "epoch": 2913.2290184921762, |
| "eval_loss": 2.61102294921875, |
| "eval_runtime": 23.9819, |
| "eval_samples_per_second": 58.127, |
| "eval_steps_per_second": 7.297, |
| "step": 51200 |
| }, |
| { |
| "epoch": 2918.9189189189187, |
| "grad_norm": 0.23780512809753418, |
| "learning_rate": 8.729096989966555e-07, |
| "loss": 2.5793, |
| "step": 51300 |
| }, |
| { |
| "epoch": 2918.9189189189187, |
| "eval_loss": 2.6139285564422607, |
| "eval_runtime": 23.9687, |
| "eval_samples_per_second": 58.159, |
| "eval_steps_per_second": 7.301, |
| "step": 51300 |
| }, |
| { |
| "epoch": 2924.6088193456612, |
| "grad_norm": 0.25004133582115173, |
| "learning_rate": 8.628762541806019e-07, |
| "loss": 2.5791, |
| "step": 51400 |
| }, |
| { |
| "epoch": 2924.6088193456612, |
| "eval_loss": 2.6126387119293213, |
| "eval_runtime": 24.012, |
| "eval_samples_per_second": 58.054, |
| "eval_steps_per_second": 7.288, |
| "step": 51400 |
| }, |
| { |
| "epoch": 2930.298719772404, |
| "grad_norm": 0.24633045494556427, |
| "learning_rate": 8.528428093645485e-07, |
| "loss": 2.5793, |
| "step": 51500 |
| }, |
| { |
| "epoch": 2930.298719772404, |
| "eval_loss": 2.6124863624572754, |
| "eval_runtime": 23.9703, |
| "eval_samples_per_second": 58.155, |
| "eval_steps_per_second": 7.301, |
| "step": 51500 |
| }, |
| { |
| "epoch": 2935.9886201991467, |
| "grad_norm": 0.22113491594791412, |
| "learning_rate": 8.428093645484949e-07, |
| "loss": 2.5787, |
| "step": 51600 |
| }, |
| { |
| "epoch": 2935.9886201991467, |
| "eval_loss": 2.611276626586914, |
| "eval_runtime": 23.6181, |
| "eval_samples_per_second": 59.023, |
| "eval_steps_per_second": 7.41, |
| "step": 51600 |
| }, |
| { |
| "epoch": 2941.678520625889, |
| "grad_norm": 0.23446623980998993, |
| "learning_rate": 8.327759197324414e-07, |
| "loss": 2.5789, |
| "step": 51700 |
| }, |
| { |
| "epoch": 2941.678520625889, |
| "eval_loss": 2.6144800186157227, |
| "eval_runtime": 23.9766, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 51700 |
| }, |
| { |
| "epoch": 2947.3684210526317, |
| "grad_norm": 0.24706819653511047, |
| "learning_rate": 8.227424749163879e-07, |
| "loss": 2.5792, |
| "step": 51800 |
| }, |
| { |
| "epoch": 2947.3684210526317, |
| "eval_loss": 2.613771915435791, |
| "eval_runtime": 23.9663, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.302, |
| "step": 51800 |
| }, |
| { |
| "epoch": 2953.058321479374, |
| "grad_norm": 0.2382979393005371, |
| "learning_rate": 8.127090301003344e-07, |
| "loss": 2.5792, |
| "step": 51900 |
| }, |
| { |
| "epoch": 2953.058321479374, |
| "eval_loss": 2.61126446723938, |
| "eval_runtime": 23.9672, |
| "eval_samples_per_second": 58.163, |
| "eval_steps_per_second": 7.302, |
| "step": 51900 |
| }, |
| { |
| "epoch": 2958.7482219061167, |
| "grad_norm": 0.22167593240737915, |
| "learning_rate": 8.026755852842809e-07, |
| "loss": 2.5789, |
| "step": 52000 |
| }, |
| { |
| "epoch": 2958.7482219061167, |
| "eval_loss": 2.612398147583008, |
| "eval_runtime": 23.9669, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 52000 |
| }, |
| { |
| "epoch": 2964.438122332859, |
| "grad_norm": 0.24954278767108917, |
| "learning_rate": 7.926421404682274e-07, |
| "loss": 2.5789, |
| "step": 52100 |
| }, |
| { |
| "epoch": 2964.438122332859, |
| "eval_loss": 2.6127331256866455, |
| "eval_runtime": 23.9665, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 52100 |
| }, |
| { |
| "epoch": 2970.1280227596017, |
| "grad_norm": 0.25174450874328613, |
| "learning_rate": 7.826086956521739e-07, |
| "loss": 2.5787, |
| "step": 52200 |
| }, |
| { |
| "epoch": 2970.1280227596017, |
| "eval_loss": 2.612732410430908, |
| "eval_runtime": 23.6271, |
| "eval_samples_per_second": 59.0, |
| "eval_steps_per_second": 7.407, |
| "step": 52200 |
| }, |
| { |
| "epoch": 2975.817923186344, |
| "grad_norm": 0.2445630580186844, |
| "learning_rate": 7.725752508361204e-07, |
| "loss": 2.579, |
| "step": 52300 |
| }, |
| { |
| "epoch": 2975.817923186344, |
| "eval_loss": 2.613999366760254, |
| "eval_runtime": 23.9666, |
| "eval_samples_per_second": 58.164, |
| "eval_steps_per_second": 7.302, |
| "step": 52300 |
| }, |
| { |
| "epoch": 2981.5078236130867, |
| "grad_norm": 0.23932389914989471, |
| "learning_rate": 7.625418060200669e-07, |
| "loss": 2.5786, |
| "step": 52400 |
| }, |
| { |
| "epoch": 2981.5078236130867, |
| "eval_loss": 2.6142683029174805, |
| "eval_runtime": 23.9605, |
| "eval_samples_per_second": 58.179, |
| "eval_steps_per_second": 7.304, |
| "step": 52400 |
| }, |
| { |
| "epoch": 2987.197724039829, |
| "grad_norm": 0.23177169263362885, |
| "learning_rate": 7.525083612040134e-07, |
| "loss": 2.5787, |
| "step": 52500 |
| }, |
| { |
| "epoch": 2987.197724039829, |
| "eval_loss": 2.6153082847595215, |
| "eval_runtime": 23.9736, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 52500 |
| }, |
| { |
| "epoch": 2992.8876244665717, |
| "grad_norm": 0.23721282184123993, |
| "learning_rate": 7.424749163879599e-07, |
| "loss": 2.5785, |
| "step": 52600 |
| }, |
| { |
| "epoch": 2992.8876244665717, |
| "eval_loss": 2.6143527030944824, |
| "eval_runtime": 23.9808, |
| "eval_samples_per_second": 58.13, |
| "eval_steps_per_second": 7.297, |
| "step": 52600 |
| }, |
| { |
| "epoch": 2998.577524893314, |
| "grad_norm": 0.2384282797574997, |
| "learning_rate": 7.324414715719064e-07, |
| "loss": 2.5785, |
| "step": 52700 |
| }, |
| { |
| "epoch": 2998.577524893314, |
| "eval_loss": 2.611684560775757, |
| "eval_runtime": 23.9684, |
| "eval_samples_per_second": 58.16, |
| "eval_steps_per_second": 7.301, |
| "step": 52700 |
| }, |
| { |
| "epoch": 3004.267425320057, |
| "grad_norm": 0.21971900761127472, |
| "learning_rate": 7.224080267558529e-07, |
| "loss": 2.5786, |
| "step": 52800 |
| }, |
| { |
| "epoch": 3004.267425320057, |
| "eval_loss": 2.6113009452819824, |
| "eval_runtime": 23.9803, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 52800 |
| }, |
| { |
| "epoch": 3009.9573257467996, |
| "grad_norm": 0.2397443652153015, |
| "learning_rate": 7.123745819397994e-07, |
| "loss": 2.5787, |
| "step": 52900 |
| }, |
| { |
| "epoch": 3009.9573257467996, |
| "eval_loss": 2.6127891540527344, |
| "eval_runtime": 23.9984, |
| "eval_samples_per_second": 58.087, |
| "eval_steps_per_second": 7.292, |
| "step": 52900 |
| }, |
| { |
| "epoch": 3015.647226173542, |
| "grad_norm": 0.2291790097951889, |
| "learning_rate": 7.023411371237459e-07, |
| "loss": 2.5782, |
| "step": 53000 |
| }, |
| { |
| "epoch": 3015.647226173542, |
| "eval_loss": 2.615396499633789, |
| "eval_runtime": 23.9773, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 53000 |
| }, |
| { |
| "epoch": 3021.3371266002846, |
| "grad_norm": 0.22614707052707672, |
| "learning_rate": 6.923076923076923e-07, |
| "loss": 2.5786, |
| "step": 53100 |
| }, |
| { |
| "epoch": 3021.3371266002846, |
| "eval_loss": 2.6115903854370117, |
| "eval_runtime": 23.6261, |
| "eval_samples_per_second": 59.003, |
| "eval_steps_per_second": 7.407, |
| "step": 53100 |
| }, |
| { |
| "epoch": 3027.027027027027, |
| "grad_norm": 0.25179383158683777, |
| "learning_rate": 6.822742474916388e-07, |
| "loss": 2.5789, |
| "step": 53200 |
| }, |
| { |
| "epoch": 3027.027027027027, |
| "eval_loss": 2.6113967895507812, |
| "eval_runtime": 23.9771, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 53200 |
| }, |
| { |
| "epoch": 3032.7169274537696, |
| "grad_norm": 0.24571330845355988, |
| "learning_rate": 6.722408026755853e-07, |
| "loss": 2.579, |
| "step": 53300 |
| }, |
| { |
| "epoch": 3032.7169274537696, |
| "eval_loss": 2.6136531829833984, |
| "eval_runtime": 23.6309, |
| "eval_samples_per_second": 58.991, |
| "eval_steps_per_second": 7.406, |
| "step": 53300 |
| }, |
| { |
| "epoch": 3038.406827880512, |
| "grad_norm": 0.22767402231693268, |
| "learning_rate": 6.622073578595318e-07, |
| "loss": 2.5783, |
| "step": 53400 |
| }, |
| { |
| "epoch": 3038.406827880512, |
| "eval_loss": 2.6177024841308594, |
| "eval_runtime": 23.9884, |
| "eval_samples_per_second": 58.111, |
| "eval_steps_per_second": 7.295, |
| "step": 53400 |
| }, |
| { |
| "epoch": 3044.0967283072546, |
| "grad_norm": 0.23231668770313263, |
| "learning_rate": 6.521739130434783e-07, |
| "loss": 2.5787, |
| "step": 53500 |
| }, |
| { |
| "epoch": 3044.0967283072546, |
| "eval_loss": 2.611980438232422, |
| "eval_runtime": 23.6137, |
| "eval_samples_per_second": 59.033, |
| "eval_steps_per_second": 7.411, |
| "step": 53500 |
| }, |
| { |
| "epoch": 3049.786628733997, |
| "grad_norm": 0.23049120604991913, |
| "learning_rate": 6.421404682274248e-07, |
| "loss": 2.5779, |
| "step": 53600 |
| }, |
| { |
| "epoch": 3049.786628733997, |
| "eval_loss": 2.61087965965271, |
| "eval_runtime": 23.9786, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 53600 |
| }, |
| { |
| "epoch": 3055.4765291607396, |
| "grad_norm": 0.23373426496982574, |
| "learning_rate": 6.321070234113712e-07, |
| "loss": 2.5782, |
| "step": 53700 |
| }, |
| { |
| "epoch": 3055.4765291607396, |
| "eval_loss": 2.612997531890869, |
| "eval_runtime": 23.6252, |
| "eval_samples_per_second": 59.005, |
| "eval_steps_per_second": 7.407, |
| "step": 53700 |
| }, |
| { |
| "epoch": 3061.166429587482, |
| "grad_norm": 0.25036904215812683, |
| "learning_rate": 6.220735785953178e-07, |
| "loss": 2.5782, |
| "step": 53800 |
| }, |
| { |
| "epoch": 3061.166429587482, |
| "eval_loss": 2.614743709564209, |
| "eval_runtime": 23.9821, |
| "eval_samples_per_second": 58.127, |
| "eval_steps_per_second": 7.297, |
| "step": 53800 |
| }, |
| { |
| "epoch": 3066.8563300142246, |
| "grad_norm": 0.2329493761062622, |
| "learning_rate": 6.120401337792642e-07, |
| "loss": 2.5777, |
| "step": 53900 |
| }, |
| { |
| "epoch": 3066.8563300142246, |
| "eval_loss": 2.60845947265625, |
| "eval_runtime": 23.6181, |
| "eval_samples_per_second": 59.023, |
| "eval_steps_per_second": 7.41, |
| "step": 53900 |
| }, |
| { |
| "epoch": 3072.546230440967, |
| "grad_norm": 0.24762089550495148, |
| "learning_rate": 6.020066889632107e-07, |
| "loss": 2.5781, |
| "step": 54000 |
| }, |
| { |
| "epoch": 3072.546230440967, |
| "eval_loss": 2.6142795085906982, |
| "eval_runtime": 23.9734, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 54000 |
| }, |
| { |
| "epoch": 3078.23613086771, |
| "grad_norm": 0.26611801981925964, |
| "learning_rate": 5.919732441471572e-07, |
| "loss": 2.5779, |
| "step": 54100 |
| }, |
| { |
| "epoch": 3078.23613086771, |
| "eval_loss": 2.6147961616516113, |
| "eval_runtime": 23.9768, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 54100 |
| }, |
| { |
| "epoch": 3083.9260312944525, |
| "grad_norm": 0.23262718319892883, |
| "learning_rate": 5.819397993311037e-07, |
| "loss": 2.5779, |
| "step": 54200 |
| }, |
| { |
| "epoch": 3083.9260312944525, |
| "eval_loss": 2.6128289699554443, |
| "eval_runtime": 23.9893, |
| "eval_samples_per_second": 58.109, |
| "eval_steps_per_second": 7.295, |
| "step": 54200 |
| }, |
| { |
| "epoch": 3089.615931721195, |
| "grad_norm": 0.23977543413639069, |
| "learning_rate": 5.719063545150502e-07, |
| "loss": 2.5781, |
| "step": 54300 |
| }, |
| { |
| "epoch": 3089.615931721195, |
| "eval_loss": 2.6133010387420654, |
| "eval_runtime": 23.9739, |
| "eval_samples_per_second": 58.147, |
| "eval_steps_per_second": 7.3, |
| "step": 54300 |
| }, |
| { |
| "epoch": 3095.3058321479375, |
| "grad_norm": 0.24166710674762726, |
| "learning_rate": 5.618729096989966e-07, |
| "loss": 2.5779, |
| "step": 54400 |
| }, |
| { |
| "epoch": 3095.3058321479375, |
| "eval_loss": 2.6149790287017822, |
| "eval_runtime": 23.96, |
| "eval_samples_per_second": 58.18, |
| "eval_steps_per_second": 7.304, |
| "step": 54400 |
| }, |
| { |
| "epoch": 3100.99573257468, |
| "grad_norm": 0.23214000463485718, |
| "learning_rate": 5.518394648829431e-07, |
| "loss": 2.5779, |
| "step": 54500 |
| }, |
| { |
| "epoch": 3100.99573257468, |
| "eval_loss": 2.612640142440796, |
| "eval_runtime": 23.9716, |
| "eval_samples_per_second": 58.152, |
| "eval_steps_per_second": 7.3, |
| "step": 54500 |
| }, |
| { |
| "epoch": 3106.6856330014225, |
| "grad_norm": 0.23323415219783783, |
| "learning_rate": 5.418060200668896e-07, |
| "loss": 2.5775, |
| "step": 54600 |
| }, |
| { |
| "epoch": 3106.6856330014225, |
| "eval_loss": 2.61309552192688, |
| "eval_runtime": 23.9769, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 54600 |
| }, |
| { |
| "epoch": 3112.375533428165, |
| "grad_norm": 0.255034863948822, |
| "learning_rate": 5.317725752508361e-07, |
| "loss": 2.5782, |
| "step": 54700 |
| }, |
| { |
| "epoch": 3112.375533428165, |
| "eval_loss": 2.6171648502349854, |
| "eval_runtime": 23.9725, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.3, |
| "step": 54700 |
| }, |
| { |
| "epoch": 3118.0654338549075, |
| "grad_norm": 0.239244744181633, |
| "learning_rate": 5.217391304347826e-07, |
| "loss": 2.5779, |
| "step": 54800 |
| }, |
| { |
| "epoch": 3118.0654338549075, |
| "eval_loss": 2.612152576446533, |
| "eval_runtime": 23.6301, |
| "eval_samples_per_second": 58.993, |
| "eval_steps_per_second": 7.406, |
| "step": 54800 |
| }, |
| { |
| "epoch": 3123.75533428165, |
| "grad_norm": 0.22807510197162628, |
| "learning_rate": 5.117056856187291e-07, |
| "loss": 2.5778, |
| "step": 54900 |
| }, |
| { |
| "epoch": 3123.75533428165, |
| "eval_loss": 2.615468978881836, |
| "eval_runtime": 23.9816, |
| "eval_samples_per_second": 58.128, |
| "eval_steps_per_second": 7.297, |
| "step": 54900 |
| }, |
| { |
| "epoch": 3129.4452347083925, |
| "grad_norm": 0.23386307060718536, |
| "learning_rate": 5.016722408026756e-07, |
| "loss": 2.5774, |
| "step": 55000 |
| }, |
| { |
| "epoch": 3129.4452347083925, |
| "eval_loss": 2.6134111881256104, |
| "eval_runtime": 23.9585, |
| "eval_samples_per_second": 58.184, |
| "eval_steps_per_second": 7.304, |
| "step": 55000 |
| }, |
| { |
| "epoch": 3135.135135135135, |
| "grad_norm": 0.23969079554080963, |
| "learning_rate": 4.916387959866221e-07, |
| "loss": 2.5776, |
| "step": 55100 |
| }, |
| { |
| "epoch": 3135.135135135135, |
| "eval_loss": 2.6106112003326416, |
| "eval_runtime": 23.9709, |
| "eval_samples_per_second": 58.154, |
| "eval_steps_per_second": 7.301, |
| "step": 55100 |
| }, |
| { |
| "epoch": 3140.8250355618775, |
| "grad_norm": 0.24286451935768127, |
| "learning_rate": 4.816053511705686e-07, |
| "loss": 2.5779, |
| "step": 55200 |
| }, |
| { |
| "epoch": 3140.8250355618775, |
| "eval_loss": 2.6160521507263184, |
| "eval_runtime": 23.9565, |
| "eval_samples_per_second": 58.189, |
| "eval_steps_per_second": 7.305, |
| "step": 55200 |
| }, |
| { |
| "epoch": 3146.51493598862, |
| "grad_norm": 0.24260209500789642, |
| "learning_rate": 4.7157190635451506e-07, |
| "loss": 2.5778, |
| "step": 55300 |
| }, |
| { |
| "epoch": 3146.51493598862, |
| "eval_loss": 2.615705728530884, |
| "eval_runtime": 23.9728, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.3, |
| "step": 55300 |
| }, |
| { |
| "epoch": 3152.204836415363, |
| "grad_norm": 0.2503577768802643, |
| "learning_rate": 4.6153846153846156e-07, |
| "loss": 2.5775, |
| "step": 55400 |
| }, |
| { |
| "epoch": 3152.204836415363, |
| "eval_loss": 2.6147685050964355, |
| "eval_runtime": 23.9704, |
| "eval_samples_per_second": 58.155, |
| "eval_steps_per_second": 7.301, |
| "step": 55400 |
| }, |
| { |
| "epoch": 3157.8947368421054, |
| "grad_norm": 0.23583941161632538, |
| "learning_rate": 4.5150501672240806e-07, |
| "loss": 2.5775, |
| "step": 55500 |
| }, |
| { |
| "epoch": 3157.8947368421054, |
| "eval_loss": 2.6131534576416016, |
| "eval_runtime": 23.9699, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 55500 |
| }, |
| { |
| "epoch": 3163.584637268848, |
| "grad_norm": 0.23154014348983765, |
| "learning_rate": 4.4147157190635456e-07, |
| "loss": 2.5769, |
| "step": 55600 |
| }, |
| { |
| "epoch": 3163.584637268848, |
| "eval_loss": 2.612272024154663, |
| "eval_runtime": 23.9775, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 55600 |
| }, |
| { |
| "epoch": 3169.2745376955904, |
| "grad_norm": 0.2477724254131317, |
| "learning_rate": 4.3143812709030095e-07, |
| "loss": 2.5778, |
| "step": 55700 |
| }, |
| { |
| "epoch": 3169.2745376955904, |
| "eval_loss": 2.613452196121216, |
| "eval_runtime": 23.6176, |
| "eval_samples_per_second": 59.024, |
| "eval_steps_per_second": 7.41, |
| "step": 55700 |
| }, |
| { |
| "epoch": 3174.964438122333, |
| "grad_norm": 0.23132053017616272, |
| "learning_rate": 4.2140468227424745e-07, |
| "loss": 2.5776, |
| "step": 55800 |
| }, |
| { |
| "epoch": 3174.964438122333, |
| "eval_loss": 2.6152663230895996, |
| "eval_runtime": 23.978, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 55800 |
| }, |
| { |
| "epoch": 3180.6543385490754, |
| "grad_norm": 0.2514456510543823, |
| "learning_rate": 4.1137123745819395e-07, |
| "loss": 2.5773, |
| "step": 55900 |
| }, |
| { |
| "epoch": 3180.6543385490754, |
| "eval_loss": 2.6148664951324463, |
| "eval_runtime": 23.969, |
| "eval_samples_per_second": 58.158, |
| "eval_steps_per_second": 7.301, |
| "step": 55900 |
| }, |
| { |
| "epoch": 3186.344238975818, |
| "grad_norm": 0.2294733226299286, |
| "learning_rate": 4.0133779264214045e-07, |
| "loss": 2.5773, |
| "step": 56000 |
| }, |
| { |
| "epoch": 3186.344238975818, |
| "eval_loss": 2.6135528087615967, |
| "eval_runtime": 23.9804, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 56000 |
| }, |
| { |
| "epoch": 3192.0341394025604, |
| "grad_norm": 0.23970623314380646, |
| "learning_rate": 3.9130434782608694e-07, |
| "loss": 2.5773, |
| "step": 56100 |
| }, |
| { |
| "epoch": 3192.0341394025604, |
| "eval_loss": 2.61356258392334, |
| "eval_runtime": 23.9871, |
| "eval_samples_per_second": 58.115, |
| "eval_steps_per_second": 7.296, |
| "step": 56100 |
| }, |
| { |
| "epoch": 3197.724039829303, |
| "grad_norm": 0.23367737233638763, |
| "learning_rate": 3.8127090301003344e-07, |
| "loss": 2.5772, |
| "step": 56200 |
| }, |
| { |
| "epoch": 3197.724039829303, |
| "eval_loss": 2.614643096923828, |
| "eval_runtime": 23.9787, |
| "eval_samples_per_second": 58.135, |
| "eval_steps_per_second": 7.298, |
| "step": 56200 |
| }, |
| { |
| "epoch": 3203.4139402560454, |
| "grad_norm": 0.23269738256931305, |
| "learning_rate": 3.7123745819397994e-07, |
| "loss": 2.577, |
| "step": 56300 |
| }, |
| { |
| "epoch": 3203.4139402560454, |
| "eval_loss": 2.6141436100006104, |
| "eval_runtime": 23.9773, |
| "eval_samples_per_second": 58.138, |
| "eval_steps_per_second": 7.299, |
| "step": 56300 |
| }, |
| { |
| "epoch": 3209.103840682788, |
| "grad_norm": 0.2536345422267914, |
| "learning_rate": 3.6120401337792644e-07, |
| "loss": 2.5768, |
| "step": 56400 |
| }, |
| { |
| "epoch": 3209.103840682788, |
| "eval_loss": 2.612579345703125, |
| "eval_runtime": 24.012, |
| "eval_samples_per_second": 58.054, |
| "eval_steps_per_second": 7.288, |
| "step": 56400 |
| }, |
| { |
| "epoch": 3214.7937411095304, |
| "grad_norm": 0.23528337478637695, |
| "learning_rate": 3.5117056856187294e-07, |
| "loss": 2.5769, |
| "step": 56500 |
| }, |
| { |
| "epoch": 3214.7937411095304, |
| "eval_loss": 2.6140823364257812, |
| "eval_runtime": 23.6308, |
| "eval_samples_per_second": 58.991, |
| "eval_steps_per_second": 7.406, |
| "step": 56500 |
| }, |
| { |
| "epoch": 3220.483641536273, |
| "grad_norm": 0.22182530164718628, |
| "learning_rate": 3.411371237458194e-07, |
| "loss": 2.5777, |
| "step": 56600 |
| }, |
| { |
| "epoch": 3220.483641536273, |
| "eval_loss": 2.60969614982605, |
| "eval_runtime": 23.9743, |
| "eval_samples_per_second": 58.146, |
| "eval_steps_per_second": 7.299, |
| "step": 56600 |
| }, |
| { |
| "epoch": 3226.173541963016, |
| "grad_norm": 0.23210017383098602, |
| "learning_rate": 3.311036789297659e-07, |
| "loss": 2.5778, |
| "step": 56700 |
| }, |
| { |
| "epoch": 3226.173541963016, |
| "eval_loss": 2.614919900894165, |
| "eval_runtime": 23.9777, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 56700 |
| }, |
| { |
| "epoch": 3231.8634423897583, |
| "grad_norm": 0.2339479774236679, |
| "learning_rate": 3.210702341137124e-07, |
| "loss": 2.5773, |
| "step": 56800 |
| }, |
| { |
| "epoch": 3231.8634423897583, |
| "eval_loss": 2.615126848220825, |
| "eval_runtime": 23.9735, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 56800 |
| }, |
| { |
| "epoch": 3237.553342816501, |
| "grad_norm": 0.2549735903739929, |
| "learning_rate": 3.110367892976589e-07, |
| "loss": 2.5771, |
| "step": 56900 |
| }, |
| { |
| "epoch": 3237.553342816501, |
| "eval_loss": 2.6175296306610107, |
| "eval_runtime": 23.9758, |
| "eval_samples_per_second": 58.142, |
| "eval_steps_per_second": 7.299, |
| "step": 56900 |
| }, |
| { |
| "epoch": 3243.2432432432433, |
| "grad_norm": 0.2367645800113678, |
| "learning_rate": 3.010033444816054e-07, |
| "loss": 2.5775, |
| "step": 57000 |
| }, |
| { |
| "epoch": 3243.2432432432433, |
| "eval_loss": 2.6152868270874023, |
| "eval_runtime": 23.6141, |
| "eval_samples_per_second": 59.033, |
| "eval_steps_per_second": 7.411, |
| "step": 57000 |
| }, |
| { |
| "epoch": 3248.933143669986, |
| "grad_norm": 0.24510601162910461, |
| "learning_rate": 2.9096989966555187e-07, |
| "loss": 2.5769, |
| "step": 57100 |
| }, |
| { |
| "epoch": 3248.933143669986, |
| "eval_loss": 2.6133997440338135, |
| "eval_runtime": 23.9936, |
| "eval_samples_per_second": 58.099, |
| "eval_steps_per_second": 7.294, |
| "step": 57100 |
| }, |
| { |
| "epoch": 3254.6230440967283, |
| "grad_norm": 0.2624337673187256, |
| "learning_rate": 2.809364548494983e-07, |
| "loss": 2.5772, |
| "step": 57200 |
| }, |
| { |
| "epoch": 3254.6230440967283, |
| "eval_loss": 2.611377716064453, |
| "eval_runtime": 23.9805, |
| "eval_samples_per_second": 58.131, |
| "eval_steps_per_second": 7.298, |
| "step": 57200 |
| }, |
| { |
| "epoch": 3260.312944523471, |
| "grad_norm": 0.23755531013011932, |
| "learning_rate": 2.709030100334448e-07, |
| "loss": 2.5768, |
| "step": 57300 |
| }, |
| { |
| "epoch": 3260.312944523471, |
| "eval_loss": 2.6142404079437256, |
| "eval_runtime": 23.989, |
| "eval_samples_per_second": 58.11, |
| "eval_steps_per_second": 7.295, |
| "step": 57300 |
| }, |
| { |
| "epoch": 3266.0028449502133, |
| "grad_norm": 0.22622860968112946, |
| "learning_rate": 2.608695652173913e-07, |
| "loss": 2.5774, |
| "step": 57400 |
| }, |
| { |
| "epoch": 3266.0028449502133, |
| "eval_loss": 2.6112027168273926, |
| "eval_runtime": 23.9649, |
| "eval_samples_per_second": 58.168, |
| "eval_steps_per_second": 7.302, |
| "step": 57400 |
| }, |
| { |
| "epoch": 3271.692745376956, |
| "grad_norm": 0.26149579882621765, |
| "learning_rate": 2.508361204013378e-07, |
| "loss": 2.5769, |
| "step": 57500 |
| }, |
| { |
| "epoch": 3271.692745376956, |
| "eval_loss": 2.6112406253814697, |
| "eval_runtime": 23.975, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 57500 |
| }, |
| { |
| "epoch": 3277.3826458036983, |
| "grad_norm": 0.22187606990337372, |
| "learning_rate": 2.408026755852843e-07, |
| "loss": 2.5772, |
| "step": 57600 |
| }, |
| { |
| "epoch": 3277.3826458036983, |
| "eval_loss": 2.6137592792510986, |
| "eval_runtime": 23.6148, |
| "eval_samples_per_second": 59.031, |
| "eval_steps_per_second": 7.411, |
| "step": 57600 |
| }, |
| { |
| "epoch": 3283.072546230441, |
| "grad_norm": 0.22784946858882904, |
| "learning_rate": 2.3076923076923078e-07, |
| "loss": 2.5763, |
| "step": 57700 |
| }, |
| { |
| "epoch": 3283.072546230441, |
| "eval_loss": 2.6143863201141357, |
| "eval_runtime": 23.975, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 57700 |
| }, |
| { |
| "epoch": 3288.7624466571833, |
| "grad_norm": 0.23659248650074005, |
| "learning_rate": 2.2073578595317728e-07, |
| "loss": 2.5768, |
| "step": 57800 |
| }, |
| { |
| "epoch": 3288.7624466571833, |
| "eval_loss": 2.6137397289276123, |
| "eval_runtime": 23.9772, |
| "eval_samples_per_second": 58.139, |
| "eval_steps_per_second": 7.299, |
| "step": 57800 |
| }, |
| { |
| "epoch": 3294.452347083926, |
| "grad_norm": 0.2437194287776947, |
| "learning_rate": 2.1070234113712372e-07, |
| "loss": 2.5764, |
| "step": 57900 |
| }, |
| { |
| "epoch": 3294.452347083926, |
| "eval_loss": 2.6149351596832275, |
| "eval_runtime": 23.9751, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.299, |
| "step": 57900 |
| }, |
| { |
| "epoch": 3300.1422475106688, |
| "grad_norm": 0.22918538749217987, |
| "learning_rate": 2.0066889632107022e-07, |
| "loss": 2.5768, |
| "step": 58000 |
| }, |
| { |
| "epoch": 3300.1422475106688, |
| "eval_loss": 2.6140780448913574, |
| "eval_runtime": 23.9791, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.298, |
| "step": 58000 |
| }, |
| { |
| "epoch": 3305.8321479374113, |
| "grad_norm": 0.2346070110797882, |
| "learning_rate": 1.9063545150501672e-07, |
| "loss": 2.5773, |
| "step": 58100 |
| }, |
| { |
| "epoch": 3305.8321479374113, |
| "eval_loss": 2.616719961166382, |
| "eval_runtime": 23.9911, |
| "eval_samples_per_second": 58.105, |
| "eval_steps_per_second": 7.294, |
| "step": 58100 |
| }, |
| { |
| "epoch": 3311.5220483641538, |
| "grad_norm": 0.23859845101833344, |
| "learning_rate": 1.8060200668896322e-07, |
| "loss": 2.5774, |
| "step": 58200 |
| }, |
| { |
| "epoch": 3311.5220483641538, |
| "eval_loss": 2.618227481842041, |
| "eval_runtime": 23.6148, |
| "eval_samples_per_second": 59.031, |
| "eval_steps_per_second": 7.411, |
| "step": 58200 |
| }, |
| { |
| "epoch": 3317.2119487908963, |
| "grad_norm": 0.2350337654352188, |
| "learning_rate": 1.705685618729097e-07, |
| "loss": 2.5776, |
| "step": 58300 |
| }, |
| { |
| "epoch": 3317.2119487908963, |
| "eval_loss": 2.611265182495117, |
| "eval_runtime": 23.9884, |
| "eval_samples_per_second": 58.111, |
| "eval_steps_per_second": 7.295, |
| "step": 58300 |
| }, |
| { |
| "epoch": 3322.9018492176388, |
| "grad_norm": 0.24340157210826874, |
| "learning_rate": 1.605351170568562e-07, |
| "loss": 2.5765, |
| "step": 58400 |
| }, |
| { |
| "epoch": 3322.9018492176388, |
| "eval_loss": 2.6160683631896973, |
| "eval_runtime": 23.9833, |
| "eval_samples_per_second": 58.124, |
| "eval_steps_per_second": 7.297, |
| "step": 58400 |
| }, |
| { |
| "epoch": 3328.5917496443813, |
| "grad_norm": 0.23944565653800964, |
| "learning_rate": 1.505016722408027e-07, |
| "loss": 2.577, |
| "step": 58500 |
| }, |
| { |
| "epoch": 3328.5917496443813, |
| "eval_loss": 2.6151676177978516, |
| "eval_runtime": 23.9765, |
| "eval_samples_per_second": 58.14, |
| "eval_steps_per_second": 7.299, |
| "step": 58500 |
| }, |
| { |
| "epoch": 3334.2816500711237, |
| "grad_norm": 0.2317434698343277, |
| "learning_rate": 1.4046822742474916e-07, |
| "loss": 2.5769, |
| "step": 58600 |
| }, |
| { |
| "epoch": 3334.2816500711237, |
| "eval_loss": 2.612539768218994, |
| "eval_runtime": 23.9857, |
| "eval_samples_per_second": 58.118, |
| "eval_steps_per_second": 7.296, |
| "step": 58600 |
| }, |
| { |
| "epoch": 3339.9715504978662, |
| "grad_norm": 0.2317090928554535, |
| "learning_rate": 1.3043478260869566e-07, |
| "loss": 2.5766, |
| "step": 58700 |
| }, |
| { |
| "epoch": 3339.9715504978662, |
| "eval_loss": 2.614988088607788, |
| "eval_runtime": 23.9839, |
| "eval_samples_per_second": 58.122, |
| "eval_steps_per_second": 7.297, |
| "step": 58700 |
| }, |
| { |
| "epoch": 3345.6614509246087, |
| "grad_norm": 0.2286725789308548, |
| "learning_rate": 1.2040133779264215e-07, |
| "loss": 2.5771, |
| "step": 58800 |
| }, |
| { |
| "epoch": 3345.6614509246087, |
| "eval_loss": 2.610363245010376, |
| "eval_runtime": 23.9703, |
| "eval_samples_per_second": 58.155, |
| "eval_steps_per_second": 7.301, |
| "step": 58800 |
| }, |
| { |
| "epoch": 3351.3513513513512, |
| "grad_norm": 0.23261764645576477, |
| "learning_rate": 1.1036789297658864e-07, |
| "loss": 2.5773, |
| "step": 58900 |
| }, |
| { |
| "epoch": 3351.3513513513512, |
| "eval_loss": 2.612881660461426, |
| "eval_runtime": 23.9746, |
| "eval_samples_per_second": 58.145, |
| "eval_steps_per_second": 7.299, |
| "step": 58900 |
| }, |
| { |
| "epoch": 3357.0412517780937, |
| "grad_norm": 0.24025121331214905, |
| "learning_rate": 1.0033444816053511e-07, |
| "loss": 2.5771, |
| "step": 59000 |
| }, |
| { |
| "epoch": 3357.0412517780937, |
| "eval_loss": 2.616802453994751, |
| "eval_runtime": 23.9791, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.298, |
| "step": 59000 |
| }, |
| { |
| "epoch": 3362.7311522048362, |
| "grad_norm": 0.22746782004833221, |
| "learning_rate": 9.030100334448161e-08, |
| "loss": 2.5771, |
| "step": 59100 |
| }, |
| { |
| "epoch": 3362.7311522048362, |
| "eval_loss": 2.6187052726745605, |
| "eval_runtime": 23.6285, |
| "eval_samples_per_second": 58.996, |
| "eval_steps_per_second": 7.406, |
| "step": 59100 |
| }, |
| { |
| "epoch": 3368.4210526315787, |
| "grad_norm": 0.22770369052886963, |
| "learning_rate": 8.02675585284281e-08, |
| "loss": 2.5765, |
| "step": 59200 |
| }, |
| { |
| "epoch": 3368.4210526315787, |
| "eval_loss": 2.6143691539764404, |
| "eval_runtime": 23.9914, |
| "eval_samples_per_second": 58.104, |
| "eval_steps_per_second": 7.294, |
| "step": 59200 |
| }, |
| { |
| "epoch": 3374.1109530583217, |
| "grad_norm": 0.2320239543914795, |
| "learning_rate": 7.023411371237458e-08, |
| "loss": 2.5766, |
| "step": 59300 |
| }, |
| { |
| "epoch": 3374.1109530583217, |
| "eval_loss": 2.610212802886963, |
| "eval_runtime": 23.971, |
| "eval_samples_per_second": 58.153, |
| "eval_steps_per_second": 7.3, |
| "step": 59300 |
| }, |
| { |
| "epoch": 3379.800853485064, |
| "grad_norm": 0.24047939479351044, |
| "learning_rate": 6.020066889632108e-08, |
| "loss": 2.5766, |
| "step": 59400 |
| }, |
| { |
| "epoch": 3379.800853485064, |
| "eval_loss": 2.6162428855895996, |
| "eval_runtime": 23.9874, |
| "eval_samples_per_second": 58.114, |
| "eval_steps_per_second": 7.296, |
| "step": 59400 |
| }, |
| { |
| "epoch": 3385.4907539118067, |
| "grad_norm": 0.2457292228937149, |
| "learning_rate": 5.0167224080267556e-08, |
| "loss": 2.5767, |
| "step": 59500 |
| }, |
| { |
| "epoch": 3385.4907539118067, |
| "eval_loss": 2.612614870071411, |
| "eval_runtime": 23.9722, |
| "eval_samples_per_second": 58.151, |
| "eval_steps_per_second": 7.3, |
| "step": 59500 |
| }, |
| { |
| "epoch": 3391.180654338549, |
| "grad_norm": 0.24467065930366516, |
| "learning_rate": 4.013377926421405e-08, |
| "loss": 2.5765, |
| "step": 59600 |
| }, |
| { |
| "epoch": 3391.180654338549, |
| "eval_loss": 2.616481065750122, |
| "eval_runtime": 23.9732, |
| "eval_samples_per_second": 58.148, |
| "eval_steps_per_second": 7.3, |
| "step": 59600 |
| }, |
| { |
| "epoch": 3396.8705547652917, |
| "grad_norm": 0.2387106865644455, |
| "learning_rate": 3.010033444816054e-08, |
| "loss": 2.5763, |
| "step": 59700 |
| }, |
| { |
| "epoch": 3396.8705547652917, |
| "eval_loss": 2.6150505542755127, |
| "eval_runtime": 23.97, |
| "eval_samples_per_second": 58.156, |
| "eval_steps_per_second": 7.301, |
| "step": 59700 |
| }, |
| { |
| "epoch": 3402.560455192034, |
| "grad_norm": 0.24101048707962036, |
| "learning_rate": 2.0066889632107024e-08, |
| "loss": 2.5769, |
| "step": 59800 |
| }, |
| { |
| "epoch": 3402.560455192034, |
| "eval_loss": 2.6154425144195557, |
| "eval_runtime": 23.9679, |
| "eval_samples_per_second": 58.161, |
| "eval_steps_per_second": 7.301, |
| "step": 59800 |
| }, |
| { |
| "epoch": 3408.2503556187767, |
| "grad_norm": 0.25155118107795715, |
| "learning_rate": 1.0033444816053512e-08, |
| "loss": 2.5763, |
| "step": 59900 |
| }, |
| { |
| "epoch": 3408.2503556187767, |
| "eval_loss": 2.6153502464294434, |
| "eval_runtime": 23.9778, |
| "eval_samples_per_second": 58.137, |
| "eval_steps_per_second": 7.298, |
| "step": 59900 |
| }, |
| { |
| "epoch": 3413.940256045519, |
| "grad_norm": 0.23192672431468964, |
| "learning_rate": 0.0, |
| "loss": 2.5765, |
| "step": 60000 |
| }, |
| { |
| "epoch": 3413.940256045519, |
| "eval_loss": 2.6164731979370117, |
| "eval_runtime": 23.6169, |
| "eval_samples_per_second": 59.026, |
| "eval_steps_per_second": 7.41, |
| "step": 60000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 60000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3530, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.1572336017408e+19, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
