| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06480881399870382, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012961762799740765, | |
| "grad_norm": 6.410052299499512, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002592352559948153, | |
| "grad_norm": 5.500060081481934, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038885288399222295, | |
| "grad_norm": 4.095714569091797, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.988, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005184705119896306, | |
| "grad_norm": 2.0647408962249756, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.4445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0064808813998703824, | |
| "grad_norm": 1.4352781772613525, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.2778, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007777057679844459, | |
| "grad_norm": 2.030522108078003, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.1893, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009073233959818535, | |
| "grad_norm": 1.0315437316894531, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.0831, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010369410239792612, | |
| "grad_norm": 1.5501576662063599, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0533, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011665586519766688, | |
| "grad_norm": 0.883230984210968, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0376, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012961762799740765, | |
| "grad_norm": 1.0092142820358276, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0378, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014257939079714841, | |
| "grad_norm": 1.1502794027328491, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0822, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015554115359688918, | |
| "grad_norm": 0.4328291714191437, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0046, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016850291639662993, | |
| "grad_norm": 0.6591416001319885, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0069, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01814646791963707, | |
| "grad_norm": 0.8374271392822266, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0054, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019442644199611146, | |
| "grad_norm": 0.335828959941864, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0071, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020738820479585224, | |
| "grad_norm": 0.4225008189678192, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0046, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0220349967595593, | |
| "grad_norm": 0.8661593198776245, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0469, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023331173039533377, | |
| "grad_norm": 0.4766126871109009, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0093, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02462734931950745, | |
| "grad_norm": 0.6881564855575562, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0135, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02592352559948153, | |
| "grad_norm": 0.6868959665298462, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027219701879455604, | |
| "grad_norm": 0.38503697514533997, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0097, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028515878159429683, | |
| "grad_norm": 1.0754024982452393, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0203, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029812054439403757, | |
| "grad_norm": 0.6338533163070679, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0152, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031108230719377836, | |
| "grad_norm": 0.6074821352958679, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0099, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03240440699935191, | |
| "grad_norm": 0.687092125415802, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.016, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033700583279325985, | |
| "grad_norm": 0.2556341290473938, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03499675955930007, | |
| "grad_norm": 0.6813236474990845, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0188, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03629293583927414, | |
| "grad_norm": 0.08286161720752716, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0007, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.037589112119248216, | |
| "grad_norm": 0.7052176594734192, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0111, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03888528839922229, | |
| "grad_norm": 0.5274888277053833, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0241, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04018146467919637, | |
| "grad_norm": 0.08222157508134842, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0008, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04147764095917045, | |
| "grad_norm": 0.2739109992980957, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0114, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04277381723914452, | |
| "grad_norm": 0.8266695737838745, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0359, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0440699935191186, | |
| "grad_norm": 0.05991604924201965, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0006, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04536616979909268, | |
| "grad_norm": 0.7909983396530151, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0127, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.046662346079066754, | |
| "grad_norm": 0.01229810994118452, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0002, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04795852235904083, | |
| "grad_norm": 0.0124417245388031, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0002, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0492546986390149, | |
| "grad_norm": 0.27802836894989014, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0061, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.050550874918988985, | |
| "grad_norm": 0.2801899313926697, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0025, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05184705119896306, | |
| "grad_norm": 0.4654271602630615, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053143227478937134, | |
| "grad_norm": 2.02001690864563, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0504, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05443940375891121, | |
| "grad_norm": 0.3809402883052826, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.024, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05573558003888529, | |
| "grad_norm": 0.174382284283638, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0018, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.057031756318859365, | |
| "grad_norm": 0.7362247705459595, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0051, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05832793259883344, | |
| "grad_norm": 0.7474696040153503, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0234, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.059624108878807515, | |
| "grad_norm": 0.5843119621276855, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.01, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0609202851587816, | |
| "grad_norm": 0.575708270072937, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0195, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06221646143875567, | |
| "grad_norm": 0.33101776242256165, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0036, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06351263771872975, | |
| "grad_norm": 0.9009850025177002, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06480881399870382, | |
| "grad_norm": 0.6479219198226929, | |
| "learning_rate": 0.0, | |
| "loss": 0.0065, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.66894361542656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |