| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2967032967032967, |
| "eval_steps": 500, |
| "global_step": 45, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.0287306308746338, |
| "learning_rate": 0.0, |
| "loss": 1.084, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 0.948112428188324, |
| "learning_rate": 9.56e-05, |
| "loss": 1.0638, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.0350998640060425, |
| "learning_rate": 0.0001912, |
| "loss": 1.143, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.1360750198364258, |
| "learning_rate": 0.0002868, |
| "loss": 1.0394, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.7310333251953125, |
| "learning_rate": 0.0003824, |
| "loss": 0.8949, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.6246419548988342, |
| "learning_rate": 0.000478, |
| "loss": 0.9157, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5591331720352173, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.9064, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.411284863948822, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8349, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.30876654386520386, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.8626, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.39697328209877014, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.8347, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.3990109860897064, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.8383, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.3827734589576721, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.7593, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.5764995217323303, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.7725, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.5014582276344299, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.7577, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.4466342628002167, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.7279, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.3709656894207001, |
| "learning_rate": 0.00046740133037694015, |
| "loss": 0.7577, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.5953618288040161, |
| "learning_rate": 0.00046634146341463414, |
| "loss": 0.8038, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.43582218885421753, |
| "learning_rate": 0.0004652815964523282, |
| "loss": 0.7836, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.35281723737716675, |
| "learning_rate": 0.0004642217294900222, |
| "loss": 0.7541, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.4125503897666931, |
| "learning_rate": 0.0004631618625277162, |
| "loss": 0.7476, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.3566338121891022, |
| "learning_rate": 0.00046210199556541025, |
| "loss": 0.6958, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.3785325884819031, |
| "learning_rate": 0.00046104212860310423, |
| "loss": 0.7827, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.3147861659526825, |
| "learning_rate": 0.0004599822616407982, |
| "loss": 0.7631, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.4547198712825775, |
| "learning_rate": 0.00045892239467849226, |
| "loss": 0.7453, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.3506404459476471, |
| "learning_rate": 0.0004578625277161863, |
| "loss": 0.7397, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.35579541325569153, |
| "learning_rate": 0.0004568026607538803, |
| "loss": 0.8032, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.35984915494918823, |
| "learning_rate": 0.00045574279379157433, |
| "loss": 0.6869, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.3912736177444458, |
| "learning_rate": 0.00045468292682926826, |
| "loss": 0.7423, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.3313451111316681, |
| "learning_rate": 0.0004536230598669623, |
| "loss": 0.826, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.3460421860218048, |
| "learning_rate": 0.00045256319290465634, |
| "loss": 0.7155, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.42073190212249756, |
| "learning_rate": 0.00045150332594235033, |
| "loss": 0.7308, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.3369511067867279, |
| "learning_rate": 0.00045044345898004437, |
| "loss": 0.7529, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.3326997756958008, |
| "learning_rate": 0.0004493835920177384, |
| "loss": 0.7098, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.3323321044445038, |
| "learning_rate": 0.00044832372505543234, |
| "loss": 0.7104, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.365688294172287, |
| "learning_rate": 0.0004472638580931264, |
| "loss": 0.6777, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.4034178853034973, |
| "learning_rate": 0.0004462039911308204, |
| "loss": 0.7655, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.4079640209674835, |
| "learning_rate": 0.0004451441241685144, |
| "loss": 0.6348, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.35669246315956116, |
| "learning_rate": 0.00044408425720620845, |
| "loss": 0.7146, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.4017118513584137, |
| "learning_rate": 0.0004430243902439025, |
| "loss": 0.8002, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.37425458431243896, |
| "learning_rate": 0.0004419645232815964, |
| "loss": 0.6953, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.3201092779636383, |
| "learning_rate": 0.00044090465631929047, |
| "loss": 0.6991, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.3773852288722992, |
| "learning_rate": 0.0004398447893569845, |
| "loss": 0.7467, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.2974673807621002, |
| "learning_rate": 0.0004387849223946785, |
| "loss": 0.7288, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.30199432373046875, |
| "learning_rate": 0.00043772505543237253, |
| "loss": 0.7304, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.3696371018886566, |
| "learning_rate": 0.0004366651884700666, |
| "loss": 0.7752, |
| "step": 45 |
| } |
| ], |
| "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": 2.061041518964736e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
