| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0989010989010989, |
| "eval_steps": 500, |
| "global_step": 15, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 0.8822625875473022, |
| "learning_rate": 0.0, |
| "loss": 2.9966, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.1069581508636475, |
| "learning_rate": 4e-05, |
| "loss": 2.9598, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 0.8758227229118347, |
| "learning_rate": 8e-05, |
| "loss": 2.5775, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.0401133298873901, |
| "learning_rate": 0.00012, |
| "loss": 2.6196, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 1.4041666984558105, |
| "learning_rate": 0.00016, |
| "loss": 3.1798, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 1.4210084676742554, |
| "learning_rate": 0.0002, |
| "loss": 2.0834, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 2.1845953464508057, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 2.3524, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 1.3485188484191895, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 1.616, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 1.0533819198608398, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 1.2391, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 1.1041414737701416, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 1.0831, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.7204957604408264, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 0.8896, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.7176511287689209, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 0.8995, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.7679543495178223, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 0.7737, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.8583915829658508, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.8345, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5992399454116821, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.7105, |
| "step": 15 |
| } |
| ], |
| "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": 6285147048069120.0, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
