maviutkarsh12/jigsaw_partA_binary_classification_head

1{2  "best_metric": 0.7239819004524887,3  "best_model_checkpoint": "/content/drive/MyDrive/Applied LLM Assignment 4/0_Models/Assignment_4_Part_A/gemma_lora_imb/checkpoint-50",4  "epoch": 0.9852216748768473,5  "eval_steps": 500,6  "global_step": 50,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.49261083743842365,13      "grad_norm": 173.0,14      "learning_rate": 7.500000000000001e-06,15      "loss": 1.9939,16      "step": 2517    },18    {19      "epoch": 0.9852216748768473,20      "grad_norm": 290.0,21      "learning_rate": 5e-06,22      "loss": 0.7057,23      "step": 5024    },25    {26      "epoch": 0.9852216748768473,27      "eval_accuracy": 0.6995073891625616,28      "eval_f1": 0.7239819004524887,29      "eval_loss": 0.6276153922080994,30      "eval_precision": 0.6666666666666666,31      "eval_recall": 0.7920792079207921,32      "eval_runtime": 4.6826,33      "eval_samples_per_second": 43.352,34      "eval_steps_per_second": 5.552,35      "step": 5036    }37  ],38  "logging_steps": 25,39  "max_steps": 100,40  "num_input_tokens_seen": 0,41  "num_train_epochs": 2,42  "save_steps": 500,43  "stateful_callbacks": {44    "TrainerControl": {45      "args": {46        "should_epoch_stop": false,47        "should_evaluate": false,48        "should_log": false,49        "should_save": true,50        "should_training_stop": false51      },52      "attributes": {}53    }54  },55  "total_flos": 5742874412158464.0,56  "train_batch_size": 8,57  "trial_name": null,58  "trial_params": null59}60