| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02478157267672756, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006354249404289118, | |
| "eval_loss": 1.934020757675171, | |
| "eval_runtime": 43.8595, | |
| "eval_samples_per_second": 15.116, | |
| "eval_steps_per_second": 7.57, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003177124702144559, | |
| "grad_norm": 1.8095368146896362, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006354249404289118, | |
| "grad_norm": 1.734501838684082, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6715, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006354249404289118, | |
| "eval_loss": 1.458052158355713, | |
| "eval_runtime": 44.1277, | |
| "eval_samples_per_second": 15.025, | |
| "eval_steps_per_second": 7.524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009531374106433678, | |
| "grad_norm": 1.461950421333313, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2896, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012708498808578236, | |
| "grad_norm": 1.1727732419967651, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1019, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012708498808578236, | |
| "eval_loss": 1.1347953081130981, | |
| "eval_runtime": 44.1236, | |
| "eval_samples_per_second": 15.026, | |
| "eval_steps_per_second": 7.524, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015885623510722795, | |
| "grad_norm": 1.0558323860168457, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9476, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019062748212867357, | |
| "grad_norm": 1.0646625757217407, | |
| "learning_rate": 5e-05, | |
| "loss": 1.015, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019062748212867357, | |
| "eval_loss": 1.0179016590118408, | |
| "eval_runtime": 44.1296, | |
| "eval_samples_per_second": 15.024, | |
| "eval_steps_per_second": 7.523, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022239872915011914, | |
| "grad_norm": 1.02644681930542, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8815, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3768979009044480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |