| { |
| "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": 1.02959144115448, |
| "learning_rate": 0.0, |
| "loss": 3.3348, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.0243064165115356, |
| "learning_rate": 4e-05, |
| "loss": 3.3843, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 0.9533873796463013, |
| "learning_rate": 8e-05, |
| "loss": 3.1602, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.3778162002563477, |
| "learning_rate": 0.00012, |
| "loss": 3.8548, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 1.5720551013946533, |
| "learning_rate": 0.00016, |
| "loss": 3.334, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 2.0702953338623047, |
| "learning_rate": 0.0002, |
| "loss": 3.2436, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 1.883508563041687, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 2.4118, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 1.8991221189498901, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 1.7996, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 1.943290114402771, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 1.7992, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 1.1848249435424805, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 1.3218, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.8290153741836548, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 1.1483, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.782597541809082, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 1.1466, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 1.070041537284851, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 1.0435, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.7890101671218872, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 1.1189, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.6797720789909363, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.9294, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.6561483144760132, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.8717, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.6154541969299316, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.9475, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.6936250925064087, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 1.1112, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.4830031096935272, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 0.8719, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.4977757930755615, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 0.8456, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.4251507520675659, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 0.7946, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.5000141263008118, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 0.9003, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.5055630803108215, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 0.8483, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.5189692378044128, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.862, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.39381036162376404, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.73, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.4727248549461365, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 0.9574, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.5471789836883545, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.8291, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.4908490777015686, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 0.7855, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.5352988243103027, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 0.8019, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.4222325384616852, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.7782, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.5250545740127563, |
| "learning_rate": 0.00018891352549889136, |
| "loss": 0.827, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.5112847685813904, |
| "learning_rate": 0.00018847006651884703, |
| "loss": 0.7717, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.45085787773132324, |
| "learning_rate": 0.00018802660753880268, |
| "loss": 0.8548, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.5169785618782043, |
| "learning_rate": 0.00018758314855875832, |
| "loss": 0.8469, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.4831181466579437, |
| "learning_rate": 0.00018713968957871397, |
| "loss": 0.7138, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.4298362731933594, |
| "learning_rate": 0.00018669623059866964, |
| "loss": 0.6416, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.4677696228027344, |
| "learning_rate": 0.00018625277161862528, |
| "loss": 0.8296, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.4513629376888275, |
| "learning_rate": 0.00018580931263858095, |
| "loss": 0.6803, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.4796628952026367, |
| "learning_rate": 0.0001853658536585366, |
| "loss": 0.7778, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.4168303906917572, |
| "learning_rate": 0.00018492239467849224, |
| "loss": 0.748, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.3913823962211609, |
| "learning_rate": 0.0001844789356984479, |
| "loss": 0.8508, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.46302542090415955, |
| "learning_rate": 0.00018403547671840356, |
| "loss": 0.86, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.43823087215423584, |
| "learning_rate": 0.0001835920177383592, |
| "loss": 0.7062, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.4874539375305176, |
| "learning_rate": 0.00018314855875831487, |
| "loss": 0.7632, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.44593605399131775, |
| "learning_rate": 0.00018270509977827052, |
| "loss": 0.8815, |
| "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": 1.7922262945112064e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
