| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002638174383326738, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.276348766653476e-05, | |
| "eval_loss": 0.6893571615219116, | |
| "eval_runtime": 192.3768, | |
| "eval_samples_per_second": 20.741, | |
| "eval_steps_per_second": 10.37, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005276348766653475, | |
| "grad_norm": 0.7897371053695679, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.3743, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006859253396649519, | |
| "eval_loss": 0.5820460319519043, | |
| "eval_runtime": 192.5518, | |
| "eval_samples_per_second": 20.722, | |
| "eval_steps_per_second": 10.361, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001055269753330695, | |
| "grad_norm": 0.7706471681594849, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.243, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013718506793299037, | |
| "eval_loss": 0.5365630984306335, | |
| "eval_runtime": 192.8368, | |
| "eval_samples_per_second": 20.691, | |
| "eval_steps_per_second": 10.346, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0015829046299960427, | |
| "grad_norm": 0.646447479724884, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.1103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020577760189948555, | |
| "eval_loss": 0.5264923572540283, | |
| "eval_runtime": 192.9002, | |
| "eval_samples_per_second": 20.684, | |
| "eval_steps_per_second": 10.342, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00211053950666139, | |
| "grad_norm": 0.6791512966156006, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.0986, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002638174383326738, | |
| "grad_norm": 0.6163003444671631, | |
| "learning_rate": 0.0, | |
| "loss": 1.0075, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 6534646443540480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |