| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8089030981063843, | |
| "eval_runtime": 3.1842, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.6632791757583618, | |
| "eval_runtime": 3.1852, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.4630075693130493, | |
| "eval_runtime": 3.1841, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.410213589668274, | |
| "eval_runtime": 3.1835, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.348659634590149, | |
| "eval_runtime": 3.1836, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.2120503187179565, | |
| "eval_runtime": 3.184, | |
| "eval_samples_per_second": 0.942, | |
| "eval_steps_per_second": 0.942, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 60, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1853128131477504.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |