| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9335978527249388, | |
| "eval_steps": 250, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 0.8913317918777466, | |
| "learning_rate": 8.959847237666421e-05, | |
| "loss": 0.453, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.23909452557563782, | |
| "eval_runtime": 15.8602, | |
| "eval_samples_per_second": 5.485, | |
| "eval_steps_per_second": 5.485, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 0.5381897687911987, | |
| "learning_rate": 5.783666949486448e-05, | |
| "loss": 0.1536, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.13772033154964447, | |
| "eval_runtime": 15.7869, | |
| "eval_samples_per_second": 5.511, | |
| "eval_steps_per_second": 5.511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 0.4797663390636444, | |
| "learning_rate": 2.179828363456768e-05, | |
| "loss": 0.1063, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.10924059897661209, | |
| "eval_runtime": 15.8188, | |
| "eval_samples_per_second": 5.5, | |
| "eval_steps_per_second": 5.5, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "grad_norm": 0.39953428506851196, | |
| "learning_rate": 1.149979013737007e-06, | |
| "loss": 0.0908, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "eval_loss": 0.10349918156862259, | |
| "eval_runtime": 15.8518, | |
| "eval_samples_per_second": 5.488, | |
| "eval_steps_per_second": 5.488, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1071, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.311086281607168e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |