| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.364877161055505, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022747952684258416, | |
| "grad_norm": 18.962158203125, | |
| "learning_rate": 2.4616154873164223e-05, | |
| "loss": 2.8908, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04549590536851683, | |
| "grad_norm": 9.855137825012207, | |
| "learning_rate": 2.4198931909212282e-05, | |
| "loss": 2.5971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06824385805277525, | |
| "grad_norm": 10.13984203338623, | |
| "learning_rate": 2.3781708945260348e-05, | |
| "loss": 2.529, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09099181073703366, | |
| "grad_norm": 8.192861557006836, | |
| "learning_rate": 2.3364485981308414e-05, | |
| "loss": 2.4313, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11373976342129208, | |
| "grad_norm": 9.359848976135254, | |
| "learning_rate": 2.2947263017356476e-05, | |
| "loss": 2.4519, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1364877161055505, | |
| "grad_norm": 9.675088882446289, | |
| "learning_rate": 2.2530040053404542e-05, | |
| "loss": 2.3522, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1592356687898089, | |
| "grad_norm": 7.448574066162109, | |
| "learning_rate": 2.2112817089452604e-05, | |
| "loss": 2.2756, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18198362147406733, | |
| "grad_norm": 8.285670280456543, | |
| "learning_rate": 2.1695594125500667e-05, | |
| "loss": 2.4835, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20473157415832574, | |
| "grad_norm": 10.987030982971191, | |
| "learning_rate": 2.1278371161548733e-05, | |
| "loss": 2.4054, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.22747952684258416, | |
| "grad_norm": 9.691205978393555, | |
| "learning_rate": 2.08611481975968e-05, | |
| "loss": 2.3081, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2502274795268426, | |
| "grad_norm": 9.08532428741455, | |
| "learning_rate": 2.044392523364486e-05, | |
| "loss": 2.3223, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.272975432211101, | |
| "grad_norm": 7.425185680389404, | |
| "learning_rate": 2.0026702269692923e-05, | |
| "loss": 2.388, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29572338489535943, | |
| "grad_norm": 8.487403869628906, | |
| "learning_rate": 1.960947930574099e-05, | |
| "loss": 2.2745, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3184713375796178, | |
| "grad_norm": 11.06141471862793, | |
| "learning_rate": 1.9192256341789052e-05, | |
| "loss": 2.2413, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.34121929026387626, | |
| "grad_norm": 8.929823875427246, | |
| "learning_rate": 1.8775033377837118e-05, | |
| "loss": 2.2775, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.36396724294813465, | |
| "grad_norm": 6.374183654785156, | |
| "learning_rate": 1.8357810413885184e-05, | |
| "loss": 2.2436, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3867151956323931, | |
| "grad_norm": 9.918680191040039, | |
| "learning_rate": 1.7940587449933243e-05, | |
| "loss": 2.2926, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4094631483166515, | |
| "grad_norm": 6.771628379821777, | |
| "learning_rate": 1.752336448598131e-05, | |
| "loss": 2.2754, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4322111010009099, | |
| "grad_norm": 9.636200904846191, | |
| "learning_rate": 1.7106141522029374e-05, | |
| "loss": 2.4094, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4549590536851683, | |
| "grad_norm": 10.16539478302002, | |
| "learning_rate": 1.6688918558077437e-05, | |
| "loss": 2.3422, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4549590536851683, | |
| "eval_loss": 2.135864496231079, | |
| "eval_runtime": 18.7379, | |
| "eval_samples_per_second": 5.87, | |
| "eval_steps_per_second": 0.747, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47770700636942676, | |
| "grad_norm": 8.440470695495605, | |
| "learning_rate": 1.6271695594125503e-05, | |
| "loss": 2.3016, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5004549590536852, | |
| "grad_norm": 10.333203315734863, | |
| "learning_rate": 1.585447263017357e-05, | |
| "loss": 2.2732, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5232029117379435, | |
| "grad_norm": 8.159846305847168, | |
| "learning_rate": 1.5437249666221628e-05, | |
| "loss": 2.1742, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.545950864422202, | |
| "grad_norm": 7.440310955047607, | |
| "learning_rate": 1.5020026702269693e-05, | |
| "loss": 2.3123, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5686988171064604, | |
| "grad_norm": 7.5925374031066895, | |
| "learning_rate": 1.4602803738317758e-05, | |
| "loss": 2.262, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5914467697907189, | |
| "grad_norm": 7.50217342376709, | |
| "learning_rate": 1.4185580774365822e-05, | |
| "loss": 2.1893, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6141947224749773, | |
| "grad_norm": 7.763234615325928, | |
| "learning_rate": 1.3768357810413888e-05, | |
| "loss": 2.2997, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6369426751592356, | |
| "grad_norm": 8.378331184387207, | |
| "learning_rate": 1.3351134846461948e-05, | |
| "loss": 2.1408, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6596906278434941, | |
| "grad_norm": 9.364808082580566, | |
| "learning_rate": 1.2933911882510014e-05, | |
| "loss": 2.3418, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6824385805277525, | |
| "grad_norm": 7.610098838806152, | |
| "learning_rate": 1.2516688918558078e-05, | |
| "loss": 2.2467, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.705186533212011, | |
| "grad_norm": 7.710592746734619, | |
| "learning_rate": 1.2099465954606141e-05, | |
| "loss": 2.3844, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7279344858962693, | |
| "grad_norm": 7.574198246002197, | |
| "learning_rate": 1.1682242990654207e-05, | |
| "loss": 2.3413, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7506824385805277, | |
| "grad_norm": 10.453964233398438, | |
| "learning_rate": 1.1265020026702271e-05, | |
| "loss": 2.3048, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7734303912647862, | |
| "grad_norm": 8.253402709960938, | |
| "learning_rate": 1.0847797062750333e-05, | |
| "loss": 2.2046, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.7961783439490446, | |
| "grad_norm": 8.736198425292969, | |
| "learning_rate": 1.04305740987984e-05, | |
| "loss": 2.2299, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.818926296633303, | |
| "grad_norm": 8.582794189453125, | |
| "learning_rate": 1.0013351134846462e-05, | |
| "loss": 2.2477, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8416742493175614, | |
| "grad_norm": 8.511619567871094, | |
| "learning_rate": 9.596128170894526e-06, | |
| "loss": 2.1604, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.8644222020018199, | |
| "grad_norm": 7.394681930541992, | |
| "learning_rate": 9.178905206942592e-06, | |
| "loss": 2.2107, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.8871701546860783, | |
| "grad_norm": 9.960970878601074, | |
| "learning_rate": 8.761682242990654e-06, | |
| "loss": 2.2325, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.9099181073703366, | |
| "grad_norm": 8.213104248046875, | |
| "learning_rate": 8.344459279038718e-06, | |
| "loss": 2.3189, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9099181073703366, | |
| "eval_loss": 1.8801201581954956, | |
| "eval_runtime": 18.4977, | |
| "eval_samples_per_second": 5.947, | |
| "eval_steps_per_second": 0.757, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9326660600545951, | |
| "grad_norm": 7.146160125732422, | |
| "learning_rate": 7.927236315086784e-06, | |
| "loss": 2.2208, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9554140127388535, | |
| "grad_norm": 10.675107955932617, | |
| "learning_rate": 7.510013351134847e-06, | |
| "loss": 2.3002, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.978161965423112, | |
| "grad_norm": 7.811581611633301, | |
| "learning_rate": 7.092790387182911e-06, | |
| "loss": 2.2749, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.0009099181073704, | |
| "grad_norm": 5.786709785461426, | |
| "learning_rate": 6.675567423230974e-06, | |
| "loss": 2.1707, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0236578707916288, | |
| "grad_norm": 8.969910621643066, | |
| "learning_rate": 6.258344459279039e-06, | |
| "loss": 1.7638, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.046405823475887, | |
| "grad_norm": 7.258237361907959, | |
| "learning_rate": 5.841121495327103e-06, | |
| "loss": 1.8112, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.0691537761601455, | |
| "grad_norm": 8.390810012817383, | |
| "learning_rate": 5.423898531375167e-06, | |
| "loss": 1.7777, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.091901728844404, | |
| "grad_norm": 7.946865081787109, | |
| "learning_rate": 5.006675567423231e-06, | |
| "loss": 1.7933, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.1146496815286624, | |
| "grad_norm": 8.631255149841309, | |
| "learning_rate": 4.589452603471296e-06, | |
| "loss": 1.7064, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.1373976342129208, | |
| "grad_norm": 11.77323055267334, | |
| "learning_rate": 4.172229639519359e-06, | |
| "loss": 1.8455, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.1601455868971793, | |
| "grad_norm": 8.695523262023926, | |
| "learning_rate": 3.7550066755674234e-06, | |
| "loss": 1.7634, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.1828935395814377, | |
| "grad_norm": 8.56210708618164, | |
| "learning_rate": 3.337783711615487e-06, | |
| "loss": 1.7213, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2056414922656962, | |
| "grad_norm": 9.016804695129395, | |
| "learning_rate": 2.9205607476635517e-06, | |
| "loss": 1.7588, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.2283894449499546, | |
| "grad_norm": 10.927498817443848, | |
| "learning_rate": 2.5033377837116154e-06, | |
| "loss": 1.8489, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.251137397634213, | |
| "grad_norm": 8.833426475524902, | |
| "learning_rate": 2.0861148197596796e-06, | |
| "loss": 1.764, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.2738853503184713, | |
| "grad_norm": 7.1187262535095215, | |
| "learning_rate": 1.6688918558077436e-06, | |
| "loss": 1.8312, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.2966333030027297, | |
| "grad_norm": 13.539063453674316, | |
| "learning_rate": 1.2516688918558077e-06, | |
| "loss": 1.6446, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.3193812556869882, | |
| "grad_norm": 9.34390640258789, | |
| "learning_rate": 8.344459279038718e-07, | |
| "loss": 1.812, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.3421292083712466, | |
| "grad_norm": 11.918546676635742, | |
| "learning_rate": 4.172229639519359e-07, | |
| "loss": 1.8513, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.364877161055505, | |
| "grad_norm": 10.514022827148438, | |
| "learning_rate": 0.0, | |
| "loss": 1.7566, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.364877161055505, | |
| "eval_loss": 1.6919403076171875, | |
| "eval_runtime": 18.5198, | |
| "eval_samples_per_second": 5.94, | |
| "eval_steps_per_second": 0.756, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.316134264491213e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |