| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8, | |
| "eval_steps": 5, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.6533, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.9424, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.2103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2343, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.7824, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 3.6731483936309814, | |
| "eval_runtime": 55.7597, | |
| "eval_samples_per_second": 4.484, | |
| "eval_steps_per_second": 0.574, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3199, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000125, | |
| "loss": 3.096, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.4714, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000175, | |
| "loss": 1.8879, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.3280744552612305, | |
| "eval_runtime": 57.8978, | |
| "eval_samples_per_second": 4.318, | |
| "eval_steps_per_second": 0.553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019917355371900828, | |
| "loss": 1.3964, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019834710743801655, | |
| "loss": 0.9918, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019752066115702482, | |
| "loss": 1.0949, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001966942148760331, | |
| "loss": 0.9735, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019586776859504133, | |
| "loss": 1.0488, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.9700968861579895, | |
| "eval_runtime": 58.1991, | |
| "eval_samples_per_second": 4.296, | |
| "eval_steps_per_second": 0.55, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001950413223140496, | |
| "loss": 0.9574, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019421487603305787, | |
| "loss": 1.0327, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001933884297520661, | |
| "loss": 0.9662, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019256198347107438, | |
| "loss": 0.9054, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019173553719008265, | |
| "loss": 0.8758, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.8345032930374146, | |
| "eval_runtime": 58.0971, | |
| "eval_samples_per_second": 4.303, | |
| "eval_steps_per_second": 0.551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 0.8895, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001900826446280992, | |
| "loss": 0.8132, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018925619834710743, | |
| "loss": 0.8083, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001884297520661157, | |
| "loss": 0.74, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018760330578512397, | |
| "loss": 0.8129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.7498296499252319, | |
| "eval_runtime": 57.9009, | |
| "eval_samples_per_second": 4.318, | |
| "eval_steps_per_second": 0.553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018677685950413224, | |
| "loss": 0.7322, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001859504132231405, | |
| "loss": 0.7408, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00018512396694214878, | |
| "loss": 0.7624, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018429752066115705, | |
| "loss": 0.737, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018347107438016532, | |
| "loss": 0.6782, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.716300904750824, | |
| "eval_runtime": 58.0078, | |
| "eval_samples_per_second": 4.31, | |
| "eval_steps_per_second": 0.552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00018264462809917356, | |
| "loss": 0.7201, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.6426, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018099173553719008, | |
| "loss": 0.695, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00018016528925619835, | |
| "loss": 0.6364, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00017933884297520662, | |
| "loss": 0.5778, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.6839221715927124, | |
| "eval_runtime": 58.2032, | |
| "eval_samples_per_second": 4.295, | |
| "eval_steps_per_second": 0.55, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00017851239669421489, | |
| "loss": 0.74, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00017768595041322316, | |
| "loss": 0.5662, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00017685950413223143, | |
| "loss": 0.6046, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00017603305785123967, | |
| "loss": 0.6705, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00017520661157024794, | |
| "loss": 0.6315, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.6694893836975098, | |
| "eval_runtime": 57.899, | |
| "eval_samples_per_second": 4.318, | |
| "eval_steps_per_second": 0.553, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001743801652892562, | |
| "loss": 0.5753, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00017355371900826448, | |
| "loss": 0.4392, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00017272727272727275, | |
| "loss": 0.5003, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00017190082644628102, | |
| "loss": 0.4317, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00017107438016528926, | |
| "loss": 0.4277, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.6936589479446411, | |
| "eval_runtime": 58.1678, | |
| "eval_samples_per_second": 4.298, | |
| "eval_steps_per_second": 0.55, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00017024793388429753, | |
| "loss": 0.5912, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00016942148760330577, | |
| "loss": 0.4614, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00016859504132231404, | |
| "loss": 0.3647, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001677685950413223, | |
| "loss": 0.381, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00016694214876033058, | |
| "loss": 0.6096, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.7051330804824829, | |
| "eval_runtime": 57.8438, | |
| "eval_samples_per_second": 4.322, | |
| "eval_steps_per_second": 0.553, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00016611570247933885, | |
| "loss": 1.1622, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00016528925619834712, | |
| "loss": 0.9989, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001644628099173554, | |
| "loss": 1.1117, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.9089, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001628099173553719, | |
| "loss": 0.7292, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.6689890027046204, | |
| "eval_runtime": 57.8661, | |
| "eval_samples_per_second": 4.32, | |
| "eval_steps_per_second": 0.553, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00016198347107438017, | |
| "loss": 0.784, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00016115702479338844, | |
| "loss": 0.803, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001603305785123967, | |
| "loss": 0.7427, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00015950413223140498, | |
| "loss": 0.8347, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00015867768595041322, | |
| "loss": 0.8003, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.6277408003807068, | |
| "eval_runtime": 57.8174, | |
| "eval_samples_per_second": 4.324, | |
| "eval_steps_per_second": 0.553, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001578512396694215, | |
| "loss": 0.7497, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00015702479338842976, | |
| "loss": 0.7575, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000156198347107438, | |
| "loss": 0.6312, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00015537190082644627, | |
| "loss": 0.7552, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00015454545454545454, | |
| "loss": 0.6101, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.6085646748542786, | |
| "eval_runtime": 58.0155, | |
| "eval_samples_per_second": 4.309, | |
| "eval_steps_per_second": 0.552, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00015371900826446281, | |
| "loss": 0.6897, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00015289256198347108, | |
| "loss": 0.5665, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00015206611570247935, | |
| "loss": 0.7022, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00015123966942148762, | |
| "loss": 0.7871, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001504132231404959, | |
| "loss": 0.6128, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.6062941551208496, | |
| "eval_runtime": 57.9481, | |
| "eval_samples_per_second": 4.314, | |
| "eval_steps_per_second": 0.552, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00014958677685950414, | |
| "loss": 0.6889, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001487603305785124, | |
| "loss": 0.5652, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014793388429752067, | |
| "loss": 0.6203, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00014710743801652894, | |
| "loss": 0.6553, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001462809917355372, | |
| "loss": 0.57, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.61387038230896, | |
| "eval_runtime": 57.9724, | |
| "eval_samples_per_second": 4.312, | |
| "eval_steps_per_second": 0.552, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 0.5595, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00014462809917355373, | |
| "loss": 0.6794, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.000143801652892562, | |
| "loss": 0.5683, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00014297520661157024, | |
| "loss": 0.5436, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001421487603305785, | |
| "loss": 0.6996, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.6077276468276978, | |
| "eval_runtime": 58.1658, | |
| "eval_samples_per_second": 4.298, | |
| "eval_steps_per_second": 0.55, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00014132231404958678, | |
| "loss": 0.4647, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00014049586776859505, | |
| "loss": 0.5812, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00013966942148760332, | |
| "loss": 0.625, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001388429752066116, | |
| "loss": 0.717, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00013801652892561986, | |
| "loss": 0.5178, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.6118555665016174, | |
| "eval_runtime": 57.8518, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.553, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00013719008264462813, | |
| "loss": 0.4657, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00013636363636363637, | |
| "loss": 0.5238, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00013553719008264464, | |
| "loss": 0.4704, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00013471074380165288, | |
| "loss": 0.4564, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00013388429752066115, | |
| "loss": 0.3964, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.6064205169677734, | |
| "eval_runtime": 57.9504, | |
| "eval_samples_per_second": 4.314, | |
| "eval_steps_per_second": 0.552, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00013305785123966942, | |
| "loss": 0.4646, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001322314049586777, | |
| "loss": 0.4212, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00013140495867768596, | |
| "loss": 0.3841, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00013057851239669423, | |
| "loss": 0.6348, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00012975206611570247, | |
| "loss": 0.563, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.6179620623588562, | |
| "eval_runtime": 57.8595, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.553, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00012892561983471074, | |
| "loss": 0.6287, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.000128099173553719, | |
| "loss": 0.4541, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 0.5001, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 0.418, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00012644628099173555, | |
| "loss": 0.3845, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.6233624815940857, | |
| "eval_runtime": 58.1243, | |
| "eval_samples_per_second": 4.301, | |
| "eval_steps_per_second": 0.551, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00012561983471074382, | |
| "loss": 0.8978, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001247933884297521, | |
| "loss": 0.8395, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00012396694214876033, | |
| "loss": 0.9166, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001231404958677686, | |
| "loss": 0.719, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012231404958677685, | |
| "loss": 0.6933, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.6230288147926331, | |
| "eval_runtime": 57.9123, | |
| "eval_samples_per_second": 4.317, | |
| "eval_steps_per_second": 0.553, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00012148760330578513, | |
| "loss": 0.6997, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001206611570247934, | |
| "loss": 0.6827, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00011983471074380165, | |
| "loss": 0.9173, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00011900826446280992, | |
| "loss": 0.6493, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001181818181818182, | |
| "loss": 0.537, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.6039621829986572, | |
| "eval_runtime": 58.0963, | |
| "eval_samples_per_second": 4.303, | |
| "eval_steps_per_second": 0.551, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00011735537190082646, | |
| "loss": 0.6706, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001165289256198347, | |
| "loss": 0.5669, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00011570247933884298, | |
| "loss": 0.6952, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011487603305785125, | |
| "loss": 0.6874, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001140495867768595, | |
| "loss": 0.6718, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.5879318118095398, | |
| "eval_runtime": 57.8905, | |
| "eval_samples_per_second": 4.319, | |
| "eval_steps_per_second": 0.553, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00011322314049586777, | |
| "loss": 0.7431, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011239669421487604, | |
| "loss": 0.8516, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00011157024793388431, | |
| "loss": 0.5923, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011074380165289258, | |
| "loss": 0.5841, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010991735537190082, | |
| "loss": 0.5717, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.5779567956924438, | |
| "eval_runtime": 57.8881, | |
| "eval_samples_per_second": 4.319, | |
| "eval_steps_per_second": 0.553, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.4524, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010826446280991735, | |
| "loss": 0.5259, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00010743801652892562, | |
| "loss": 0.6316, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010661157024793389, | |
| "loss": 0.4857, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010578512396694216, | |
| "loss": 0.5092, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.5742751955986023, | |
| "eval_runtime": 57.8734, | |
| "eval_samples_per_second": 4.32, | |
| "eval_steps_per_second": 0.553, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010495867768595043, | |
| "loss": 0.5744, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001041322314049587, | |
| "loss": 0.7194, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00010330578512396694, | |
| "loss": 0.5746, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00010247933884297521, | |
| "loss": 0.5654, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00010165289256198347, | |
| "loss": 0.6142, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.5754650831222534, | |
| "eval_runtime": 57.8524, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.553, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00010082644628099174, | |
| "loss": 0.4129, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5766, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.917355371900827e-05, | |
| "loss": 0.5391, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.834710743801654e-05, | |
| "loss": 0.3944, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.75206611570248e-05, | |
| "loss": 0.5665, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.5827150940895081, | |
| "eval_runtime": 57.9089, | |
| "eval_samples_per_second": 4.317, | |
| "eval_steps_per_second": 0.553, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.669421487603306e-05, | |
| "loss": 0.4864, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.586776859504133e-05, | |
| "loss": 0.5534, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.50413223140496e-05, | |
| "loss": 0.5339, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.421487603305785e-05, | |
| "loss": 0.4784, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.338842975206612e-05, | |
| "loss": 0.5378, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.5869958996772766, | |
| "eval_runtime": 58.1247, | |
| "eval_samples_per_second": 4.301, | |
| "eval_steps_per_second": 0.551, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.256198347107439e-05, | |
| "loss": 0.5092, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.173553719008266e-05, | |
| "loss": 0.3735, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.4498, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.008264462809917e-05, | |
| "loss": 0.3738, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.925619834710744e-05, | |
| "loss": 0.4061, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.5876795649528503, | |
| "eval_runtime": 57.9113, | |
| "eval_samples_per_second": 4.317, | |
| "eval_steps_per_second": 0.553, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.842975206611571e-05, | |
| "loss": 0.3713, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.760330578512397e-05, | |
| "loss": 0.3532, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.677685950413224e-05, | |
| "loss": 0.3981, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.595041322314051e-05, | |
| "loss": 0.4389, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.512396694214876e-05, | |
| "loss": 0.3934, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.6049365401268005, | |
| "eval_runtime": 57.8527, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.553, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.429752066115702e-05, | |
| "loss": 0.766, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.347107438016529e-05, | |
| "loss": 0.6959, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.264462809917356e-05, | |
| "loss": 0.7616, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.181818181818183e-05, | |
| "loss": 0.8095, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.099173553719009e-05, | |
| "loss": 0.6343, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.5834559202194214, | |
| "eval_runtime": 58.0814, | |
| "eval_samples_per_second": 4.304, | |
| "eval_steps_per_second": 0.551, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.016528925619836e-05, | |
| "loss": 0.7482, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.933884297520661e-05, | |
| "loss": 0.6632, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.851239669421488e-05, | |
| "loss": 0.5817, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.768595041322314e-05, | |
| "loss": 0.6256, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.685950413223141e-05, | |
| "loss": 0.6727, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.5801185369491577, | |
| "eval_runtime": 57.9954, | |
| "eval_samples_per_second": 4.311, | |
| "eval_steps_per_second": 0.552, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.603305785123968e-05, | |
| "loss": 0.7253, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.520661157024795e-05, | |
| "loss": 0.6021, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.43801652892562e-05, | |
| "loss": 0.5942, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.355371900826447e-05, | |
| "loss": 0.5942, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.602, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.5663142800331116, | |
| "eval_runtime": 57.8541, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.553, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.1900826446281e-05, | |
| "loss": 0.6503, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.107438016528925e-05, | |
| "loss": 0.6197, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.024793388429752e-05, | |
| "loss": 0.4577, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.94214876033058e-05, | |
| "loss": 0.6804, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.859504132231406e-05, | |
| "loss": 0.7056, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.5660744309425354, | |
| "eval_runtime": 57.981, | |
| "eval_samples_per_second": 4.312, | |
| "eval_steps_per_second": 0.552, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.776859504132232e-05, | |
| "loss": 0.6003, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.694214876033058e-05, | |
| "loss": 0.6349, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.611570247933885e-05, | |
| "loss": 0.6308, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.528925619834711e-05, | |
| "loss": 0.5713, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.446280991735537e-05, | |
| "loss": 0.4743, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.5626071691513062, | |
| "eval_runtime": 58.0516, | |
| "eval_samples_per_second": 4.307, | |
| "eval_steps_per_second": 0.551, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.363636363636364e-05, | |
| "loss": 0.4835, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.280991735537191e-05, | |
| "loss": 0.4553, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.198347107438017e-05, | |
| "loss": 0.6067, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.115702479338842e-05, | |
| "loss": 0.5319, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.03305785123967e-05, | |
| "loss": 0.5656, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.5597254633903503, | |
| "eval_runtime": 58.0733, | |
| "eval_samples_per_second": 4.305, | |
| "eval_steps_per_second": 0.551, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.950413223140496e-05, | |
| "loss": 0.3764, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.867768595041323e-05, | |
| "loss": 0.3883, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.785123966942149e-05, | |
| "loss": 0.4815, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.702479338842975e-05, | |
| "loss": 0.4923, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.619834710743802e-05, | |
| "loss": 0.5248, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.5612524151802063, | |
| "eval_runtime": 58.039, | |
| "eval_samples_per_second": 4.307, | |
| "eval_steps_per_second": 0.551, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.537190082644629e-05, | |
| "loss": 0.4291, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.4774, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.371900826446281e-05, | |
| "loss": 0.4568, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.289256198347108e-05, | |
| "loss": 0.4394, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.206611570247935e-05, | |
| "loss": 0.4516, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.5654726624488831, | |
| "eval_runtime": 58.1592, | |
| "eval_samples_per_second": 4.299, | |
| "eval_steps_per_second": 0.55, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.1239669421487605e-05, | |
| "loss": 0.5396, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.041322314049587e-05, | |
| "loss": 0.4024, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.958677685950414e-05, | |
| "loss": 0.4171, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.87603305785124e-05, | |
| "loss": 0.5578, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.793388429752066e-05, | |
| "loss": 0.4754, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.5674455761909485, | |
| "eval_runtime": 57.9022, | |
| "eval_samples_per_second": 4.318, | |
| "eval_steps_per_second": 0.553, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.7107438016528926e-05, | |
| "loss": 0.4136, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.6280991735537196e-05, | |
| "loss": 0.4266, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3173, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.462809917355372e-05, | |
| "loss": 0.3905, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.3801652892561984e-05, | |
| "loss": 0.6875, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.567625105381012, | |
| "eval_runtime": 57.8625, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.553, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 250, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "total_flos": 4563123475120128.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |