| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.039206076941926, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0039206076941926, | |
| "grad_norm": 2.2429609298706055, | |
| "learning_rate": 1e-05, | |
| "loss": 6.967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0039206076941926, | |
| "eval_loss": 6.999577522277832, | |
| "eval_runtime": 18.5065, | |
| "eval_samples_per_second": 23.235, | |
| "eval_steps_per_second": 11.618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0078412153883852, | |
| "grad_norm": 2.1401891708374023, | |
| "learning_rate": 2e-05, | |
| "loss": 7.2077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0117618230825778, | |
| "grad_norm": 2.1569411754608154, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9874, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0117618230825778, | |
| "eval_loss": 6.990739822387695, | |
| "eval_runtime": 1.1821, | |
| "eval_samples_per_second": 363.759, | |
| "eval_steps_per_second": 181.88, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0156824307767704, | |
| "grad_norm": 2.1621460914611816, | |
| "learning_rate": 4e-05, | |
| "loss": 7.0129, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "grad_norm": 2.02799391746521, | |
| "learning_rate": 5e-05, | |
| "loss": 7.0674, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0235236461651556, | |
| "grad_norm": 2.000995397567749, | |
| "learning_rate": 6e-05, | |
| "loss": 6.8769, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0235236461651556, | |
| "eval_loss": 6.964446544647217, | |
| "eval_runtime": 1.2523, | |
| "eval_samples_per_second": 343.358, | |
| "eval_steps_per_second": 171.679, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0274442538593482, | |
| "grad_norm": 2.0904550552368164, | |
| "learning_rate": 7e-05, | |
| "loss": 7.0724, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0313648615535408, | |
| "grad_norm": 1.8750410079956055, | |
| "learning_rate": 8e-05, | |
| "loss": 6.8382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.035285469247733396, | |
| "grad_norm": 1.808696985244751, | |
| "learning_rate": 9e-05, | |
| "loss": 6.9148, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.035285469247733396, | |
| "eval_loss": 6.91793966293335, | |
| "eval_runtime": 1.2501, | |
| "eval_samples_per_second": 343.979, | |
| "eval_steps_per_second": 171.989, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.039206076941926, | |
| "grad_norm": 1.9871147871017456, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8283, | |
| "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": 2622341775360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |