| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003612325253765849, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.224650507531698e-05, | |
| "eval_loss": 11.937585830688477, | |
| "eval_runtime": 162.9739, | |
| "eval_samples_per_second": 35.766, | |
| "eval_steps_per_second": 17.886, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003612325253765849, | |
| "grad_norm": 0.09002860635519028, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9366, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007224650507531698, | |
| "grad_norm": 0.0925336480140686, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9363, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007224650507531698, | |
| "eval_loss": 11.936973571777344, | |
| "eval_runtime": 162.0736, | |
| "eval_samples_per_second": 35.965, | |
| "eval_steps_per_second": 17.986, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010836975761297548, | |
| "grad_norm": 0.08634686470031738, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014449301015063397, | |
| "grad_norm": 0.10018280148506165, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014449301015063397, | |
| "eval_loss": 11.935565948486328, | |
| "eval_runtime": 161.4049, | |
| "eval_samples_per_second": 36.114, | |
| "eval_steps_per_second": 18.06, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018061626268829245, | |
| "grad_norm": 0.1152799129486084, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9341, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0021673951522595096, | |
| "grad_norm": 0.1293969452381134, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0021673951522595096, | |
| "eval_loss": 11.934331893920898, | |
| "eval_runtime": 162.9063, | |
| "eval_samples_per_second": 35.781, | |
| "eval_steps_per_second": 17.894, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025286276776360942, | |
| "grad_norm": 0.10169284790754318, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9344, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0028898602030126793, | |
| "grad_norm": 0.11014612764120102, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9326, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0028898602030126793, | |
| "eval_loss": 11.933674812316895, | |
| "eval_runtime": 162.6736, | |
| "eval_samples_per_second": 35.832, | |
| "eval_steps_per_second": 17.919, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003251092728389264, | |
| "grad_norm": 0.08841203153133392, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9347, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003612325253765849, | |
| "grad_norm": 0.11199869960546494, | |
| "learning_rate": 0.0, | |
| "loss": 11.9338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003612325253765849, | |
| "eval_loss": 11.933558464050293, | |
| "eval_runtime": 163.0871, | |
| "eval_samples_per_second": 35.742, | |
| "eval_steps_per_second": 17.874, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 10450520506368.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |