| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7001983895437041, | |
| "eval_steps": 250, | |
| "global_step": 750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 3.2987656593322754, | |
| "learning_rate": 8.978253703087328e-05, | |
| "loss": 0.2749, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.15301218628883362, | |
| "eval_runtime": 38.0307, | |
| "eval_samples_per_second": 2.288, | |
| "eval_steps_per_second": 2.288, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 3.038522958755493, | |
| "learning_rate": 5.813544178200335e-05, | |
| "loss": 0.115, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.12411840260028839, | |
| "eval_runtime": 37.9989, | |
| "eval_samples_per_second": 2.29, | |
| "eval_steps_per_second": 2.29, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 2.7000675201416016, | |
| "learning_rate": 2.2048719230965166e-05, | |
| "loss": 0.1008, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.11009757965803146, | |
| "eval_runtime": 38.0347, | |
| "eval_samples_per_second": 2.287, | |
| "eval_steps_per_second": 2.287, | |
| "step": 750 | |
| } | |
| ], | |
| "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": 6.078735274352026e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |