| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 23148, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 0.00018, | |
| "loss": 0.505, | |
| "step": 7716 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.46735596656799316, | |
| "eval_runtime": 342.3396, | |
| "eval_samples_per_second": 40.068, | |
| "eval_steps_per_second": 2.506, | |
| "step": 7716 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4262, | |
| "step": 15432 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4464378356933594, | |
| "eval_runtime": 342.3086, | |
| "eval_samples_per_second": 40.072, | |
| "eval_steps_per_second": 2.507, | |
| "step": 15432 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 0.00014, | |
| "loss": 0.3778, | |
| "step": 23148 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.438097208738327, | |
| "eval_runtime": 342.3093, | |
| "eval_samples_per_second": 40.072, | |
| "eval_steps_per_second": 2.507, | |
| "step": 23148 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 77160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 2.3185328802459156e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |