| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1978021978021978, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.2240082025527954, |
| "learning_rate": 0.0, |
| "loss": 3.2004, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.1817413568496704, |
| "learning_rate": 4e-05, |
| "loss": 2.9195, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.089200496673584, |
| "learning_rate": 8e-05, |
| "loss": 2.9322, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.23591947555542, |
| "learning_rate": 0.00012, |
| "loss": 2.493, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 1.2914438247680664, |
| "learning_rate": 0.00016, |
| "loss": 2.6719, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 1.425159215927124, |
| "learning_rate": 0.0002, |
| "loss": 2.0729, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 1.8763092756271362, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 2.063, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 1.2933986186981201, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 1.4339, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 1.5251818895339966, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 1.5351, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.9210705161094666, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 1.1847, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.8823724389076233, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 0.9696, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.8065115809440613, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 1.0103, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.8599637150764465, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 0.7631, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.7091007232666016, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.774, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5932487845420837, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.7102, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.5805957317352295, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.8034, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.5351698398590088, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.7074, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.5085647106170654, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 0.7856, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.4852818250656128, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 0.6869, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.4774964451789856, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 0.5578, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.4320865273475647, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 0.6558, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.5121509432792664, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 0.7886, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.43891361355781555, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 0.6733, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.4488874077796936, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.6966, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.42902886867523193, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.75, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.42811888456344604, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 0.5749, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.38084888458251953, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.6558, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.39865079522132874, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 0.6655, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.29908454418182373, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 0.5844, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.38320380449295044, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.6285, |
| "step": 30 |
| } |
| ], |
| "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": 1.1832737003974656e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
