| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.4180374361883152, | |
| "eval_steps": 500, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28360748723766305, | |
| "grad_norm": 4.999021530151367, | |
| "learning_rate": 1.971639251276234e-05, | |
| "loss": 6.7525, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5672149744753261, | |
| "grad_norm": 8.877035140991211, | |
| "learning_rate": 1.9432785025524678e-05, | |
| "loss": 4.8633, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8508224617129893, | |
| "grad_norm": 5.504563808441162, | |
| "learning_rate": 1.9149177538287012e-05, | |
| "loss": 4.7848, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 39.1159, | |
| "eval_samples_per_second": 5.011, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 1.1344299489506522, | |
| "grad_norm": 4.3093953132629395, | |
| "learning_rate": 1.886557005104935e-05, | |
| "loss": 4.7304, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4180374361883152, | |
| "grad_norm": 8.88564395904541, | |
| "learning_rate": 1.8581962563811688e-05, | |
| "loss": 4.7621, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 35260, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "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": 5.077711454208e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |