| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 30, |
| "global_step": 113, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08849557522123894, |
| "grad_norm": 0.5378276109695435, |
| "learning_rate": 9.808007740920646e-05, |
| "loss": 0.4426, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.17699115044247787, |
| "grad_norm": 0.08370009064674377, |
| "learning_rate": 9.246775374701139e-05, |
| "loss": 0.0061, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.26548672566371684, |
| "grad_norm": 0.010601534508168697, |
| "learning_rate": 8.359403809285053e-05, |
| "loss": 0.004, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.26548672566371684, |
| "eval_loss": 0.0038232754450291395, |
| "eval_runtime": 56.0996, |
| "eval_samples_per_second": 8.913, |
| "eval_steps_per_second": 0.232, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.35398230088495575, |
| "grad_norm": 0.03688598424196243, |
| "learning_rate": 7.214040433267198e-05, |
| "loss": 0.0038, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.4424778761061947, |
| "grad_norm": 0.013299869373440742, |
| "learning_rate": 5.8986456074589404e-05, |
| "loss": 0.0038, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5309734513274337, |
| "grad_norm": 0.08473875373601913, |
| "learning_rate": 4.5142375815355706e-05, |
| "loss": 0.0037, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5309734513274337, |
| "eval_loss": 0.0035941482055932283, |
| "eval_runtime": 56.1024, |
| "eval_samples_per_second": 8.912, |
| "eval_steps_per_second": 0.232, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.6194690265486725, |
| "grad_norm": 0.008843529969453812, |
| "learning_rate": 3.167134605250938e-05, |
| "loss": 0.0037, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.7079646017699115, |
| "grad_norm": 0.006533902138471603, |
| "learning_rate": 1.960790016056801e-05, |
| "loss": 0.0036, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7964601769911505, |
| "grad_norm": 0.06442264467477798, |
| "learning_rate": 9.878473431161767e-06, |
| "loss": 0.0035, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7964601769911505, |
| "eval_loss": 0.003458332037553191, |
| "eval_runtime": 56.0617, |
| "eval_samples_per_second": 8.919, |
| "eval_steps_per_second": 0.232, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8849557522123894, |
| "grad_norm": 0.06732333451509476, |
| "learning_rate": 3.230255711220992e-06, |
| "loss": 0.0034, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9734513274336283, |
| "grad_norm": 0.01167540717869997, |
| "learning_rate": 1.7380953630678488e-07, |
| "loss": 0.0035, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 113, |
| "total_flos": 4.179655240942879e+17, |
| "train_loss": 0.042722021724072703, |
| "train_runtime": 1759.0892, |
| "train_samples_per_second": 2.558, |
| "train_steps_per_second": 0.064 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 113, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.179655240942879e+17, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
