| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4945054945054945, |
| "eval_steps": 500, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.0638142824172974, |
| "learning_rate": 0.0, |
| "loss": 1.0777, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 0.9542151689529419, |
| "learning_rate": 9.56e-05, |
| "loss": 1.1025, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.0668847560882568, |
| "learning_rate": 0.0001912, |
| "loss": 1.0405, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.0646922588348389, |
| "learning_rate": 0.0002868, |
| "loss": 0.9056, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.6475369334220886, |
| "learning_rate": 0.0003824, |
| "loss": 0.8513, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.653504490852356, |
| "learning_rate": 0.000478, |
| "loss": 0.9432, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5652804374694824, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.8951, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.38114824891090393, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8546, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.3202402591705322, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.9013, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.3632391095161438, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.7981, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.38180795311927795, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.8034, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.44034814834594727, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.8194, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.5649089217185974, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.7964, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.4905894994735718, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.7767, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5945530533790588, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.7485, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.47223448753356934, |
| "learning_rate": 0.00046740133037694015, |
| "loss": 0.7412, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.4855833053588867, |
| "learning_rate": 0.00046634146341463414, |
| "loss": 0.7992, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.420284628868103, |
| "learning_rate": 0.0004652815964523282, |
| "loss": 0.7427, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.517633855342865, |
| "learning_rate": 0.0004642217294900222, |
| "loss": 0.7918, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.434706449508667, |
| "learning_rate": 0.0004631618625277162, |
| "loss": 0.7891, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.3698730766773224, |
| "learning_rate": 0.00046210199556541025, |
| "loss": 0.7076, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.3561922609806061, |
| "learning_rate": 0.00046104212860310423, |
| "loss": 0.7893, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.3815233111381531, |
| "learning_rate": 0.0004599822616407982, |
| "loss": 0.7999, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.38611900806427, |
| "learning_rate": 0.00045892239467849226, |
| "loss": 0.7928, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.29186370968818665, |
| "learning_rate": 0.0004578625277161863, |
| "loss": 0.724, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.3245350420475006, |
| "learning_rate": 0.0004568026607538803, |
| "loss": 0.7503, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.3803184926509857, |
| "learning_rate": 0.00045574279379157433, |
| "loss": 0.7455, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.3178353011608124, |
| "learning_rate": 0.00045468292682926826, |
| "loss": 0.7207, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.4353942573070526, |
| "learning_rate": 0.0004536230598669623, |
| "loss": 0.8268, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.3097940981388092, |
| "learning_rate": 0.00045256319290465634, |
| "loss": 0.6621, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.3318345546722412, |
| "learning_rate": 0.00045150332594235033, |
| "loss": 0.7092, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.31531524658203125, |
| "learning_rate": 0.00045044345898004437, |
| "loss": 0.7668, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.3566637933254242, |
| "learning_rate": 0.0004493835920177384, |
| "loss": 0.7545, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.36444291472435, |
| "learning_rate": 0.00044832372505543234, |
| "loss": 0.8064, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.3560720980167389, |
| "learning_rate": 0.0004472638580931264, |
| "loss": 0.7774, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.3715183734893799, |
| "learning_rate": 0.0004462039911308204, |
| "loss": 0.7131, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.2921788692474365, |
| "learning_rate": 0.0004451441241685144, |
| "loss": 0.8009, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.29083380103111267, |
| "learning_rate": 0.00044408425720620845, |
| "loss": 0.7223, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.3140243887901306, |
| "learning_rate": 0.0004430243902439025, |
| "loss": 0.7196, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.3676493465900421, |
| "learning_rate": 0.0004419645232815964, |
| "loss": 0.7143, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.3598462641239166, |
| "learning_rate": 0.00044090465631929047, |
| "loss": 0.7474, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.3195889890193939, |
| "learning_rate": 0.0004398447893569845, |
| "loss": 0.7229, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.30827897787094116, |
| "learning_rate": 0.0004387849223946785, |
| "loss": 0.7428, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.38703453540802, |
| "learning_rate": 0.00043772505543237253, |
| "loss": 0.7169, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.28942254185676575, |
| "learning_rate": 0.0004366651884700666, |
| "loss": 0.7456, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.35373979806900024, |
| "learning_rate": 0.0004356053215077605, |
| "loss": 0.7703, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.3619854748249054, |
| "learning_rate": 0.00043454545454545455, |
| "loss": 0.6991, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.3936954438686371, |
| "learning_rate": 0.0004334855875831486, |
| "loss": 0.7505, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.31419533491134644, |
| "learning_rate": 0.0004324257206208426, |
| "loss": 0.7218, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.31622064113616943, |
| "learning_rate": 0.0004313658536585366, |
| "loss": 0.7133, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.31881847977638245, |
| "learning_rate": 0.00043030598669623066, |
| "loss": 0.7015, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.29825660586357117, |
| "learning_rate": 0.0004292461197339246, |
| "loss": 0.7513, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.28996437788009644, |
| "learning_rate": 0.00042818625277161863, |
| "loss": 0.7417, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.317898690700531, |
| "learning_rate": 0.00042712638580931267, |
| "loss": 0.7547, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.35207676887512207, |
| "learning_rate": 0.00042606651884700666, |
| "loss": 0.8215, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.2996538579463959, |
| "learning_rate": 0.0004250066518847007, |
| "loss": 0.7897, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.35331282019615173, |
| "learning_rate": 0.00042394678492239474, |
| "loss": 0.7466, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.30339422821998596, |
| "learning_rate": 0.00042288691796008867, |
| "loss": 0.7079, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.35229793190956116, |
| "learning_rate": 0.0004218270509977827, |
| "loss": 0.7322, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.3471188545227051, |
| "learning_rate": 0.00042076718403547675, |
| "loss": 0.6908, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4021978021978022, |
| "grad_norm": 0.384351521730423, |
| "learning_rate": 0.00041970731707317074, |
| "loss": 0.6937, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.4087912087912088, |
| "grad_norm": 0.34261906147003174, |
| "learning_rate": 0.0004186474501108648, |
| "loss": 0.694, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.4153846153846154, |
| "grad_norm": 0.36659127473831177, |
| "learning_rate": 0.0004175875831485588, |
| "loss": 0.7186, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.421978021978022, |
| "grad_norm": 0.3876580595970154, |
| "learning_rate": 0.00041652771618625275, |
| "loss": 0.7474, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.3435872495174408, |
| "learning_rate": 0.0004154678492239468, |
| "loss": 0.7313, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.4351648351648352, |
| "grad_norm": 0.2954373061656952, |
| "learning_rate": 0.00041440798226164083, |
| "loss": 0.6693, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.44175824175824174, |
| "grad_norm": 0.2931239604949951, |
| "learning_rate": 0.0004133481152993348, |
| "loss": 0.7175, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.44835164835164837, |
| "grad_norm": 0.37997666001319885, |
| "learning_rate": 0.00041228824833702886, |
| "loss": 0.704, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.45494505494505494, |
| "grad_norm": 0.3305527865886688, |
| "learning_rate": 0.00041122838137472285, |
| "loss": 0.7234, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.33284375071525574, |
| "learning_rate": 0.00041016851441241683, |
| "loss": 0.6931, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.46813186813186813, |
| "grad_norm": 0.32701659202575684, |
| "learning_rate": 0.00040910864745011087, |
| "loss": 0.7191, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4747252747252747, |
| "grad_norm": 0.32257601618766785, |
| "learning_rate": 0.00040804878048780486, |
| "loss": 0.6495, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.48131868131868133, |
| "grad_norm": 0.34117209911346436, |
| "learning_rate": 0.0004069889135254989, |
| "loss": 0.7386, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4879120879120879, |
| "grad_norm": 0.41902703046798706, |
| "learning_rate": 0.00040592904656319294, |
| "loss": 0.7807, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4945054945054945, |
| "grad_norm": 0.3014705181121826, |
| "learning_rate": 0.0004048691796008869, |
| "loss": 0.6529, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.4296404785606656e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
