| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.05362469417166605, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005362469417166605, |
| "grad_norm": 0.050072263926267624, |
| "learning_rate": 1.4961796246648793e-05, |
| "loss": 1.0673207283020019, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01072493883433321, |
| "grad_norm": 0.06825340539216995, |
| "learning_rate": 1.4921581769436997e-05, |
| "loss": 0.9185627937316895, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.016087408251499815, |
| "grad_norm": 0.06827432662248611, |
| "learning_rate": 1.48813672922252e-05, |
| "loss": 0.7999343872070312, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.02144987766866642, |
| "grad_norm": 0.05807405710220337, |
| "learning_rate": 1.4841152815013404e-05, |
| "loss": 0.7322770595550537, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.026812347085833025, |
| "grad_norm": 0.06654328852891922, |
| "learning_rate": 1.4800938337801608e-05, |
| "loss": 0.7097890377044678, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.03217481650299963, |
| "grad_norm": 0.09104783087968826, |
| "learning_rate": 1.4760723860589812e-05, |
| "loss": 0.6513629913330078, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.03753728592016624, |
| "grad_norm": 0.10718850791454315, |
| "learning_rate": 1.4720509383378015e-05, |
| "loss": 0.678717851638794, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.04289975533733284, |
| "grad_norm": 0.09187154471874237, |
| "learning_rate": 1.4680294906166219e-05, |
| "loss": 0.647278118133545, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.04826222475449945, |
| "grad_norm": 0.07148946076631546, |
| "learning_rate": 1.4640080428954423e-05, |
| "loss": 0.6737877368927002, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.05362469417166605, |
| "grad_norm": 0.08909227699041367, |
| "learning_rate": 1.4599865951742626e-05, |
| "loss": 0.6373191356658936, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 7460, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.461979015351501e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
