| { |
| "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": 1.6434824466705322, |
| "learning_rate": 0.0, |
| "loss": 2.5324, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.5169517993927002, |
| "learning_rate": 4e-05, |
| "loss": 2.4298, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 2.1552116870880127, |
| "learning_rate": 8e-05, |
| "loss": 3.6751, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.7675827741622925, |
| "learning_rate": 0.00012, |
| "loss": 2.6287, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 1.9941221475601196, |
| "learning_rate": 0.00016, |
| "loss": 2.4341, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 2.577136516571045, |
| "learning_rate": 0.0002, |
| "loss": 2.3798, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 2.411424398422241, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 1.8769, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 1.9915826320648193, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 1.671, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.7537499070167542, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 1.2368, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 1.5307854413986206, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 1.2651, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 1.0386676788330078, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 1.3088, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.5621629953384399, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 1.1189, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.6583429574966431, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 1.1157, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.45013824105262756, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.9839, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.44181209802627563, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 1.4493, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.3815290033817291, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.9192, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.3356572985649109, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 1.1357, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.31392374634742737, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 1.0106, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.5165255069732666, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 1.0717, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.32307010889053345, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 1.0066, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.38696736097335815, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 1.0178, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.45919156074523926, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 1.3634, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.3402266800403595, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 1.0087, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.2613711655139923, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.8385, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.35281801223754883, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.9981, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.347657710313797, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 1.097, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.2869630455970764, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.8232, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.33703890442848206, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 1.0008, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.32335910201072693, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 1.0167, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.26683419942855835, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.788, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.32632026076316833, |
| "learning_rate": 0.00018891352549889136, |
| "loss": 0.9766, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.4012938439846039, |
| "learning_rate": 0.00018847006651884703, |
| "loss": 1.1352, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.2666340470314026, |
| "learning_rate": 0.00018802660753880268, |
| "loss": 0.7854, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.31724995374679565, |
| "learning_rate": 0.00018758314855875832, |
| "loss": 1.131, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.35468608140945435, |
| "learning_rate": 0.00018713968957871397, |
| "loss": 0.824, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.29676058888435364, |
| "learning_rate": 0.00018669623059866964, |
| "loss": 0.9068, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.3603779077529907, |
| "learning_rate": 0.00018625277161862528, |
| "loss": 1.0625, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.28585994243621826, |
| "learning_rate": 0.00018580931263858095, |
| "loss": 0.96, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.3147846758365631, |
| "learning_rate": 0.0001853658536585366, |
| "loss": 1.0241, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.365302175283432, |
| "learning_rate": 0.00018492239467849224, |
| "loss": 1.2389, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.29522451758384705, |
| "learning_rate": 0.0001844789356984479, |
| "loss": 0.7442, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.2930554449558258, |
| "learning_rate": 0.00018403547671840356, |
| "loss": 1.115, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.31714215874671936, |
| "learning_rate": 0.0001835920177383592, |
| "loss": 0.9953, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.3149819076061249, |
| "learning_rate": 0.00018314855875831487, |
| "loss": 1.0285, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.2990363836288452, |
| "learning_rate": 0.00018270509977827052, |
| "loss": 1.0126, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.3032967032967033, |
| "grad_norm": 0.2756856083869934, |
| "learning_rate": 0.00018226164079822616, |
| "loss": 0.9699, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.3098901098901099, |
| "grad_norm": 0.3523540794849396, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 1.1403, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.31648351648351647, |
| "grad_norm": 0.28931504487991333, |
| "learning_rate": 0.00018137472283813748, |
| "loss": 0.9127, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.3230769230769231, |
| "grad_norm": 0.25859928131103516, |
| "learning_rate": 0.00018093126385809312, |
| "loss": 0.827, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.32967032967032966, |
| "grad_norm": 0.30126574635505676, |
| "learning_rate": 0.0001804878048780488, |
| "loss": 0.975, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3362637362637363, |
| "grad_norm": 0.31548774242401123, |
| "learning_rate": 0.00018004434589800444, |
| "loss": 0.9585, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 0.353438138961792, |
| "learning_rate": 0.00017960088691796008, |
| "loss": 0.9411, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.34945054945054943, |
| "grad_norm": 0.30521494150161743, |
| "learning_rate": 0.00017915742793791575, |
| "loss": 0.8952, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.35604395604395606, |
| "grad_norm": 0.3431454598903656, |
| "learning_rate": 0.0001787139689578714, |
| "loss": 0.7917, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3626373626373626, |
| "grad_norm": 0.2956169545650482, |
| "learning_rate": 0.00017827050997782707, |
| "loss": 1.0781, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 0.3299672603607178, |
| "learning_rate": 0.00017782705099778271, |
| "loss": 1.0668, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3758241758241758, |
| "grad_norm": 0.2662365734577179, |
| "learning_rate": 0.00017738359201773839, |
| "loss": 0.9365, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.3824175824175824, |
| "grad_norm": 0.34422916173934937, |
| "learning_rate": 0.000176940133037694, |
| "loss": 0.9569, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.389010989010989, |
| "grad_norm": 0.3445512354373932, |
| "learning_rate": 0.00017649667405764967, |
| "loss": 0.9401, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3956043956043956, |
| "grad_norm": 0.2959913909435272, |
| "learning_rate": 0.00017605321507760532, |
| "loss": 0.9567, |
| "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": 9780607168020480.0, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
