| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1631321370309951, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "grad_norm": 0.774185299873352, | |
| "learning_rate": 5e-06, | |
| "loss": 44.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "eval_loss": 11.076703071594238, | |
| "eval_runtime": 1.2109, | |
| "eval_samples_per_second": 107.361, | |
| "eval_steps_per_second": 53.68, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 0.8545265793800354, | |
| "learning_rate": 1e-05, | |
| "loss": 44.2985, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009787928221859706, | |
| "grad_norm": 0.8348920941352844, | |
| "learning_rate": 1.5e-05, | |
| "loss": 44.289, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 0.7924385070800781, | |
| "learning_rate": 2e-05, | |
| "loss": 44.308, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01631321370309951, | |
| "grad_norm": 0.8149838447570801, | |
| "learning_rate": 2.5e-05, | |
| "loss": 44.2981, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01957585644371941, | |
| "grad_norm": 0.8136796951293945, | |
| "learning_rate": 3e-05, | |
| "loss": 44.2935, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022838499184339316, | |
| "grad_norm": 0.8278170824050903, | |
| "learning_rate": 3.5e-05, | |
| "loss": 44.3029, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "grad_norm": 0.8501989245414734, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3039, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02936378466557912, | |
| "grad_norm": 0.8882483243942261, | |
| "learning_rate": 4.5e-05, | |
| "loss": 44.2868, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03262642740619902, | |
| "grad_norm": 0.8116857409477234, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03588907014681892, | |
| "grad_norm": 0.8323069214820862, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 44.2835, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03915171288743882, | |
| "grad_norm": 0.8103060722351074, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 44.2985, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04241435562805873, | |
| "grad_norm": 0.8131699562072754, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 44.2883, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04241435562805873, | |
| "eval_loss": 11.075307846069336, | |
| "eval_runtime": 0.3243, | |
| "eval_samples_per_second": 400.855, | |
| "eval_steps_per_second": 200.428, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04567699836867863, | |
| "grad_norm": 0.8031054139137268, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 44.2919, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048939641109298535, | |
| "grad_norm": 0.7678930163383484, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 44.3113, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "grad_norm": 0.8228908777236938, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 44.2994, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05546492659053834, | |
| "grad_norm": 0.8377927541732788, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 44.2779, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05872756933115824, | |
| "grad_norm": 0.8467262387275696, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 44.2685, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06199021207177814, | |
| "grad_norm": 0.8959646821022034, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 44.2928, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "grad_norm": 0.7665279507637024, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 44.3061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06851549755301795, | |
| "grad_norm": 0.8404932618141174, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 44.2792, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07177814029363784, | |
| "grad_norm": 0.7906339168548584, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 44.2955, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07504078303425775, | |
| "grad_norm": 0.8726968169212341, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 44.2876, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "grad_norm": 0.830900251865387, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 44.2961, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08156606851549755, | |
| "grad_norm": 0.8512407541275024, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 44.2854, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08482871125611746, | |
| "grad_norm": 0.8591986298561096, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 44.2909, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08482871125611746, | |
| "eval_loss": 11.072349548339844, | |
| "eval_runtime": 0.3215, | |
| "eval_samples_per_second": 404.336, | |
| "eval_steps_per_second": 202.168, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08809135399673736, | |
| "grad_norm": 0.7887829542160034, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 44.2948, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09135399673735727, | |
| "grad_norm": 0.8105373978614807, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 44.2921, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09461663947797716, | |
| "grad_norm": 0.8155120015144348, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 44.2903, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09787928221859707, | |
| "grad_norm": 0.8712279796600342, | |
| "learning_rate": 2.5e-05, | |
| "loss": 44.2978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10114192495921696, | |
| "grad_norm": 0.8829441070556641, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 44.2782, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10440456769983687, | |
| "grad_norm": 0.8893045783042908, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 44.295, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10766721044045677, | |
| "grad_norm": 0.7750392556190491, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 44.2962, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11092985318107668, | |
| "grad_norm": 0.8300427794456482, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 44.2627, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11419249592169657, | |
| "grad_norm": 0.8020292520523071, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 44.291, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11745513866231648, | |
| "grad_norm": 0.7964890003204346, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 44.2862, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12071778140293637, | |
| "grad_norm": 0.8006289601325989, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 44.2753, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12398042414355628, | |
| "grad_norm": 0.8699887990951538, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 44.2691, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1272430668841762, | |
| "grad_norm": 0.84561687707901, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 44.2795, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1272430668841762, | |
| "eval_loss": 11.0687837600708, | |
| "eval_runtime": 0.3224, | |
| "eval_samples_per_second": 403.278, | |
| "eval_steps_per_second": 201.639, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13050570962479607, | |
| "grad_norm": 0.9297838807106018, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 44.2678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13376835236541598, | |
| "grad_norm": 0.8666333556175232, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 44.2706, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1370309951060359, | |
| "grad_norm": 0.8372588753700256, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 44.2717, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1402936378466558, | |
| "grad_norm": 0.8530192971229553, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 44.2512, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14355628058727568, | |
| "grad_norm": 0.8691236972808838, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 44.2779, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1468189233278956, | |
| "grad_norm": 0.8216147422790527, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 44.2793, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1500815660685155, | |
| "grad_norm": 0.8256657123565674, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 44.2719, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1533442088091354, | |
| "grad_norm": 0.8734961152076721, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 44.2613, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1566068515497553, | |
| "grad_norm": 0.7690317034721375, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 44.2756, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1598694942903752, | |
| "grad_norm": 0.851801335811615, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 44.2664, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1631321370309951, | |
| "grad_norm": 0.8386527895927429, | |
| "learning_rate": 0.0, | |
| "loss": 44.2724, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 42958848000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |