| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9835189309576835, | |
| "eval_steps": 500, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07126948775055679, | |
| "grad_norm": 3.7971609533442936, | |
| "learning_rate": 4.761904761904762e-06, | |
| "loss": 0.8475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14253897550111358, | |
| "grad_norm": 0.9295260271504954, | |
| "learning_rate": 9.523809523809525e-06, | |
| "loss": 0.5121, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21380846325167038, | |
| "grad_norm": 0.7378111786994856, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.4342, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28507795100222716, | |
| "grad_norm": 0.706728951221838, | |
| "learning_rate": 1.904761904761905e-05, | |
| "loss": 0.3944, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35634743875278396, | |
| "grad_norm": 0.8090312873781099, | |
| "learning_rate": 1.997790438338385e-05, | |
| "loss": 0.3626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42761692650334077, | |
| "grad_norm": 0.6955054433411858, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.3474, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49888641425389757, | |
| "grad_norm": 0.6161974091570769, | |
| "learning_rate": 1.973044870579824e-05, | |
| "loss": 0.3277, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5701559020044543, | |
| "grad_norm": 0.6402632736940507, | |
| "learning_rate": 1.9505415489478293e-05, | |
| "loss": 0.3141, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6414253897550112, | |
| "grad_norm": 0.6353304250627707, | |
| "learning_rate": 1.921476211870408e-05, | |
| "loss": 0.2979, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7126948775055679, | |
| "grad_norm": 0.6366565830233913, | |
| "learning_rate": 1.8860495104301346e-05, | |
| "loss": 0.2871, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7839643652561247, | |
| "grad_norm": 0.6354146476657556, | |
| "learning_rate": 1.844506011066308e-05, | |
| "loss": 0.2723, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8552338530066815, | |
| "grad_norm": 0.5882708445945315, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.2681, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9265033407572383, | |
| "grad_norm": 0.5762368078327551, | |
| "learning_rate": 1.7442560394846518e-05, | |
| "loss": 0.2559, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9977728285077951, | |
| "grad_norm": 0.5958357402554844, | |
| "learning_rate": 1.686241637868734e-05, | |
| "loss": 0.2437, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.064142538975501, | |
| "grad_norm": 0.6936917056904216, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 0.1816, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.135412026726058, | |
| "grad_norm": 0.5744999045875022, | |
| "learning_rate": 1.5564337355766412e-05, | |
| "loss": 0.1727, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2066815144766148, | |
| "grad_norm": 0.5316452824085909, | |
| "learning_rate": 1.4855363571801523e-05, | |
| "loss": 0.1644, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2779510022271716, | |
| "grad_norm": 0.4952795924197091, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.1631, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3492204899777283, | |
| "grad_norm": 0.4880859442135627, | |
| "learning_rate": 1.3341985493931877e-05, | |
| "loss": 0.1615, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4204899777282851, | |
| "grad_norm": 0.4845969774780985, | |
| "learning_rate": 1.2548028728946548e-05, | |
| "loss": 0.1601, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4917594654788418, | |
| "grad_norm": 0.5021044989896025, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.1583, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5630289532293986, | |
| "grad_norm": 0.44605081296525473, | |
| "learning_rate": 1.0912947110386484e-05, | |
| "loss": 0.1541, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6342984409799555, | |
| "grad_norm": 0.46635765009201846, | |
| "learning_rate": 1.0083109959960974e-05, | |
| "loss": 0.154, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.7055679287305123, | |
| "grad_norm": 0.45234389725218227, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.1536, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7768374164810692, | |
| "grad_norm": 0.47812323330213485, | |
| "learning_rate": 8.427447122476148e-06, | |
| "loss": 0.1509, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8481069042316258, | |
| "grad_norm": 0.4452592705770747, | |
| "learning_rate": 7.613051219968624e-06, | |
| "loss": 0.1475, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.9193763919821827, | |
| "grad_norm": 0.447493408892927, | |
| "learning_rate": 6.815133497483157e-06, | |
| "loss": 0.1478, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.9906458797327393, | |
| "grad_norm": 0.4643827774343368, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.1469, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.057015590200445, | |
| "grad_norm": 0.5296378146178365, | |
| "learning_rate": 5.290614347797802e-06, | |
| "loss": 0.0958, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.128285077951002, | |
| "grad_norm": 0.4045550908197575, | |
| "learning_rate": 4.5745373613424075e-06, | |
| "loss": 0.0776, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.199554565701559, | |
| "grad_norm": 0.4040354519811954, | |
| "learning_rate": 3.89591478145437e-06, | |
| "loss": 0.0776, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.270824053452116, | |
| "grad_norm": 0.42857601545200796, | |
| "learning_rate": 3.2594314447468457e-06, | |
| "loss": 0.0754, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.3420935412026727, | |
| "grad_norm": 0.3670300653980398, | |
| "learning_rate": 2.669481281701739e-06, | |
| "loss": 0.0748, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.4133630289532295, | |
| "grad_norm": 0.3902364845802205, | |
| "learning_rate": 2.130136983393112e-06, | |
| "loss": 0.0704, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.4846325167037864, | |
| "grad_norm": 0.377128443473291, | |
| "learning_rate": 1.6451218858706374e-06, | |
| "loss": 0.0742, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.5559020044543432, | |
| "grad_norm": 0.3930553430015275, | |
| "learning_rate": 1.2177842662977136e-06, | |
| "loss": 0.0733, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.6271714922048996, | |
| "grad_norm": 0.3590982366224671, | |
| "learning_rate": 8.510742282896545e-07, | |
| "loss": 0.0717, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.6984409799554565, | |
| "grad_norm": 0.3746976787822436, | |
| "learning_rate": 5.475233360227516e-07, | |
| "loss": 0.0709, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.7697104677060134, | |
| "grad_norm": 0.36100542307641714, | |
| "learning_rate": 3.0922713770922155e-07, | |
| "loss": 0.0723, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.8409799554565702, | |
| "grad_norm": 0.3896273158596708, | |
| "learning_rate": 1.3783069908621772e-07, | |
| "loss": 0.0727, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.912249443207127, | |
| "grad_norm": 0.385255671671692, | |
| "learning_rate": 3.451724678784518e-08, | |
| "loss": 0.0727, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.9835189309576835, | |
| "grad_norm": 0.38370569586805797, | |
| "learning_rate": 0.0, | |
| "loss": 0.072, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.9835189309576835, | |
| "step": 420, | |
| "total_flos": 234603226333184.0, | |
| "train_loss": 0.20078422256878445, | |
| "train_runtime": 13460.8563, | |
| "train_samples_per_second": 16.011, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 420, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 234603226333184.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |