| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014082027812004929, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014082027812004929, | |
| "grad_norm": 0.14066897332668304, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014082027812004929, | |
| "eval_loss": 10.834281921386719, | |
| "eval_runtime": 9.2658, | |
| "eval_samples_per_second": 322.693, | |
| "eval_steps_per_second": 161.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028164055624009857, | |
| "grad_norm": 0.1249518170952797, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8414, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042246083436014786, | |
| "grad_norm": 0.09757815301418304, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8309, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00042246083436014786, | |
| "eval_loss": 10.834235191345215, | |
| "eval_runtime": 8.4562, | |
| "eval_samples_per_second": 353.588, | |
| "eval_steps_per_second": 176.794, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005632811124801971, | |
| "grad_norm": 0.11606577038764954, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8325, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007041013906002464, | |
| "grad_norm": 0.09170947968959808, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008449216687202957, | |
| "grad_norm": 0.11384788155555725, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8325, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008449216687202957, | |
| "eval_loss": 10.83386516571045, | |
| "eval_runtime": 8.6078, | |
| "eval_samples_per_second": 347.359, | |
| "eval_steps_per_second": 173.68, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009857419468403451, | |
| "grad_norm": 0.09094872325658798, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011265622249603943, | |
| "grad_norm": 0.15334953367710114, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8373, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012673825030804437, | |
| "grad_norm": 0.19216717779636383, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012673825030804437, | |
| "eval_loss": 10.833248138427734, | |
| "eval_runtime": 8.5606, | |
| "eval_samples_per_second": 349.275, | |
| "eval_steps_per_second": 174.638, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014082027812004929, | |
| "grad_norm": 0.1223614290356636, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8299, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1066384490496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |