| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03524229074889868, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003524229074889868, | |
| "grad_norm": 32.06682205200195, | |
| "learning_rate": 2e-05, | |
| "loss": 10.1682, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003524229074889868, | |
| "eval_loss": 10.107810020446777, | |
| "eval_runtime": 4.3614, | |
| "eval_samples_per_second": 27.514, | |
| "eval_steps_per_second": 13.757, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007048458149779736, | |
| "grad_norm": 28.340951919555664, | |
| "learning_rate": 4e-05, | |
| "loss": 10.2809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010572687224669603, | |
| "grad_norm": 26.849491119384766, | |
| "learning_rate": 6e-05, | |
| "loss": 9.5855, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010572687224669603, | |
| "eval_loss": 9.586976051330566, | |
| "eval_runtime": 3.6708, | |
| "eval_samples_per_second": 32.691, | |
| "eval_steps_per_second": 16.345, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014096916299559472, | |
| "grad_norm": 29.646787643432617, | |
| "learning_rate": 8e-05, | |
| "loss": 10.0704, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01762114537444934, | |
| "grad_norm": 32.25894546508789, | |
| "learning_rate": 0.0001, | |
| "loss": 7.8373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021145374449339206, | |
| "grad_norm": 26.04344367980957, | |
| "learning_rate": 0.00012, | |
| "loss": 5.4309, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021145374449339206, | |
| "eval_loss": 3.7627370357513428, | |
| "eval_runtime": 3.7381, | |
| "eval_samples_per_second": 32.102, | |
| "eval_steps_per_second": 16.051, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024669603524229075, | |
| "grad_norm": 20.36292839050293, | |
| "learning_rate": 0.00014, | |
| "loss": 3.3894, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.028193832599118944, | |
| "grad_norm": 21.608123779296875, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8491, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03171806167400881, | |
| "grad_norm": 10.76959228515625, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8269, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03171806167400881, | |
| "eval_loss": 0.6693419814109802, | |
| "eval_runtime": 3.7065, | |
| "eval_samples_per_second": 32.376, | |
| "eval_steps_per_second": 16.188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03524229074889868, | |
| "grad_norm": 12.470585823059082, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7803, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |