| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3956043956043956, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 0.9970224499702454, |
| "learning_rate": 0.0, |
| "loss": 1.0991, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.144827127456665, |
| "learning_rate": 9.56e-05, |
| "loss": 1.1545, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.1169440746307373, |
| "learning_rate": 0.0001912, |
| "loss": 1.123, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.0855385065078735, |
| "learning_rate": 0.0002868, |
| "loss": 0.9259, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.8469429016113281, |
| "learning_rate": 0.0003824, |
| "loss": 0.8556, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.7604000568389893, |
| "learning_rate": 0.000478, |
| "loss": 0.9009, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5317047834396362, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.9281, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.47205209732055664, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8713, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.2961072027683258, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.8788, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.38304176926612854, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.816, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.5212758779525757, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.8274, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.543552577495575, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.8489, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.4572776257991791, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.8166, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.44755756855010986, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.7803, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5597015023231506, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.801, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.39118215441703796, |
| "learning_rate": 0.00046740133037694015, |
| "loss": 0.7196, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.4890790581703186, |
| "learning_rate": 0.00046634146341463414, |
| "loss": 0.7744, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.5199437737464905, |
| "learning_rate": 0.0004652815964523282, |
| "loss": 0.7521, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.4048418402671814, |
| "learning_rate": 0.0004642217294900222, |
| "loss": 0.7232, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.4759422242641449, |
| "learning_rate": 0.0004631618625277162, |
| "loss": 0.7887, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.373710572719574, |
| "learning_rate": 0.00046210199556541025, |
| "loss": 0.7673, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.3180016577243805, |
| "learning_rate": 0.00046104212860310423, |
| "loss": 0.7553, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.43041887879371643, |
| "learning_rate": 0.0004599822616407982, |
| "loss": 0.7573, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.4632937014102936, |
| "learning_rate": 0.00045892239467849226, |
| "loss": 0.7318, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.3658117651939392, |
| "learning_rate": 0.0004578625277161863, |
| "loss": 0.7129, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.39879968762397766, |
| "learning_rate": 0.0004568026607538803, |
| "loss": 0.7212, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.4226565659046173, |
| "learning_rate": 0.00045574279379157433, |
| "loss": 0.7441, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.3761254549026489, |
| "learning_rate": 0.00045468292682926826, |
| "loss": 0.7351, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.3735473155975342, |
| "learning_rate": 0.0004536230598669623, |
| "loss": 0.7274, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.3605045676231384, |
| "learning_rate": 0.00045256319290465634, |
| "loss": 0.7511, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.49938589334487915, |
| "learning_rate": 0.00045150332594235033, |
| "loss": 0.733, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.3388383090496063, |
| "learning_rate": 0.00045044345898004437, |
| "loss": 0.7086, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.6535608768463135, |
| "learning_rate": 0.0004493835920177384, |
| "loss": 0.7686, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.36676231026649475, |
| "learning_rate": 0.00044832372505543234, |
| "loss": 0.6831, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.3847268521785736, |
| "learning_rate": 0.0004472638580931264, |
| "loss": 0.7375, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.37475308775901794, |
| "learning_rate": 0.0004462039911308204, |
| "loss": 0.7084, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.3576759696006775, |
| "learning_rate": 0.0004451441241685144, |
| "loss": 0.7693, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.33207494020462036, |
| "learning_rate": 0.00044408425720620845, |
| "loss": 0.7844, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.4797557592391968, |
| "learning_rate": 0.0004430243902439025, |
| "loss": 0.6863, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.3291913866996765, |
| "learning_rate": 0.0004419645232815964, |
| "loss": 0.6941, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.3354625701904297, |
| "learning_rate": 0.00044090465631929047, |
| "loss": 0.7254, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.3200039267539978, |
| "learning_rate": 0.0004398447893569845, |
| "loss": 0.6928, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.377468079328537, |
| "learning_rate": 0.0004387849223946785, |
| "loss": 0.7907, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.35265693068504333, |
| "learning_rate": 0.00043772505543237253, |
| "loss": 0.6916, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.4030437171459198, |
| "learning_rate": 0.0004366651884700666, |
| "loss": 0.721, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.3848680853843689, |
| "learning_rate": 0.0004356053215077605, |
| "loss": 0.7261, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.3052960932254791, |
| "learning_rate": 0.00043454545454545455, |
| "loss": 0.7063, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.3832049071788788, |
| "learning_rate": 0.0004334855875831486, |
| "loss": 0.7652, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.3644565939903259, |
| "learning_rate": 0.0004324257206208426, |
| "loss": 0.8106, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.3032757639884949, |
| "learning_rate": 0.0004313658536585366, |
| "loss": 0.7162, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.3071494996547699, |
| "learning_rate": 0.00043030598669623066, |
| "loss": 0.7907, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.32176244258880615, |
| "learning_rate": 0.0004292461197339246, |
| "loss": 0.7865, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.3945949375629425, |
| "learning_rate": 0.00042818625277161863, |
| "loss": 0.8038, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.2989363968372345, |
| "learning_rate": 0.00042712638580931267, |
| "loss": 0.7172, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.317256361246109, |
| "learning_rate": 0.00042606651884700666, |
| "loss": 0.7325, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.27640077471733093, |
| "learning_rate": 0.0004250066518847007, |
| "loss": 0.765, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.3094281256198883, |
| "learning_rate": 0.00042394678492239474, |
| "loss": 0.7391, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.30334004759788513, |
| "learning_rate": 0.00042288691796008867, |
| "loss": 0.7486, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.3377019166946411, |
| "learning_rate": 0.0004218270509977827, |
| "loss": 0.7444, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.34436339139938354, |
| "learning_rate": 0.00042076718403547675, |
| "loss": 0.7041, |
| "step": 60 |
| } |
| ], |
| "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": 2.750769718476595e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
