| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9865871833084947, | |
| "eval_steps": 500, | |
| "global_step": 501, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05961251862891207, | |
| "grad_norm": 9.858894874210412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11922503725782414, | |
| "grad_norm": 3.200951587553443, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8872, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17883755588673622, | |
| "grad_norm": 0.8709047390143161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8521, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23845007451564829, | |
| "grad_norm": 0.7917099907436183, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8247, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.7435704731717787, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35767511177347244, | |
| "grad_norm": 0.6069787155672357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8091, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4172876304023845, | |
| "grad_norm": 0.7240817518375863, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7952, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47690014903129657, | |
| "grad_norm": 0.7043281338985534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7931, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5365126676602087, | |
| "grad_norm": 0.586854693193699, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7883, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.5823407135149267, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7853, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 0.6283773137272283, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7847, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7153502235469449, | |
| "grad_norm": 0.6299087806837431, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7847, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7749627421758569, | |
| "grad_norm": 0.6905339934914414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7716, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.834575260804769, | |
| "grad_norm": 0.5764098315055344, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7722, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8941877794336811, | |
| "grad_norm": 0.596630510361194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7723, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9538002980625931, | |
| "grad_norm": 0.6393363259269436, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7727, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9955290611028316, | |
| "eval_loss": 0.7674793601036072, | |
| "eval_runtime": 178.4077, | |
| "eval_samples_per_second": 25.33, | |
| "eval_steps_per_second": 0.398, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.0134128166915053, | |
| "grad_norm": 1.028243455897246, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7832, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0730253353204173, | |
| "grad_norm": 0.6463791732368608, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7342, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.1326378539493294, | |
| "grad_norm": 0.7099545246983331, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7264, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1922503725782414, | |
| "grad_norm": 0.6643420655401983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7249, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2518628912071534, | |
| "grad_norm": 0.7310409955228447, | |
| "learning_rate": 5e-06, | |
| "loss": 0.733, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 0.6511777722980082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7219, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.3710879284649775, | |
| "grad_norm": 0.7827849824805997, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7208, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.4307004470938898, | |
| "grad_norm": 0.6318650254279009, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7188, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.4903129657228018, | |
| "grad_norm": 0.6677002292570327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7192, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5499254843517138, | |
| "grad_norm": 0.564078834227423, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7245, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.6095380029806259, | |
| "grad_norm": 0.5237353037646948, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7263, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.669150521609538, | |
| "grad_norm": 0.6003861550477204, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7203, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.7287630402384502, | |
| "grad_norm": 0.7033677185903798, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7217, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.788375558867362, | |
| "grad_norm": 0.6820739163112765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7267, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.8479880774962743, | |
| "grad_norm": 0.6594996515164985, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7179, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.9076005961251863, | |
| "grad_norm": 0.6309878288237989, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7196, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.9672131147540983, | |
| "grad_norm": 0.5108818281911819, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7274, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.9970193740685542, | |
| "eval_loss": 0.7537275552749634, | |
| "eval_runtime": 178.6454, | |
| "eval_samples_per_second": 25.296, | |
| "eval_steps_per_second": 0.397, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.0268256333830106, | |
| "grad_norm": 0.919905069790943, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7213, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0864381520119224, | |
| "grad_norm": 0.5627127586056083, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6748, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.1460506706408347, | |
| "grad_norm": 0.698070822337305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6786, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.2056631892697465, | |
| "grad_norm": 0.7188866615898121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6768, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.2652757078986587, | |
| "grad_norm": 0.7308617732721838, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6779, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.3248882265275705, | |
| "grad_norm": 0.6553661010694801, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6764, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.384500745156483, | |
| "grad_norm": 0.5825389739879382, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6782, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.444113263785395, | |
| "grad_norm": 0.5934721290598023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6723, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.503725782414307, | |
| "grad_norm": 0.6213580858455807, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6771, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.563338301043219, | |
| "grad_norm": 0.5958772497068647, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6772, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 0.6075566821845071, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6771, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.682563338301043, | |
| "grad_norm": 0.6500795583419717, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6777, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.742175856929955, | |
| "grad_norm": 0.5645816490580728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6745, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.8017883755588673, | |
| "grad_norm": 0.593606888596975, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6781, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.8614008941877795, | |
| "grad_norm": 0.7862396669753284, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6794, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.9210134128166914, | |
| "grad_norm": 0.5741353341999686, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6742, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.9806259314456036, | |
| "grad_norm": 0.6882181948210808, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6854, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9865871833084947, | |
| "eval_loss": 0.7531510591506958, | |
| "eval_runtime": 177.5218, | |
| "eval_samples_per_second": 25.456, | |
| "eval_steps_per_second": 0.4, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 2.9865871833084947, | |
| "step": 501, | |
| "total_flos": 838984280309760.0, | |
| "train_loss": 0.7383992823060164, | |
| "train_runtime": 29820.4569, | |
| "train_samples_per_second": 8.636, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 501, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 838984280309760.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |