trainer_state.json

{
  "best_metric": 0.03029637224972248,
  "best_model_checkpoint": "/home/paperspace/mmdoc/outputs/Damarcode_AB_v1_20241129_qwen_v2/checkpoint-39/checkpoint-30",
  "epoch": 2.8363636363636364,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.10270193964242935,
      "learning_rate": 0.0002,
      "loss": 0.0403,
      "step": 10
    },
    {
      "epoch": 0.7272727272727273,
      "eval_loss": 0.03421077877283096,
      "eval_runtime": 21.1288,
      "eval_samples_per_second": 0.331,
      "eval_steps_per_second": 0.331,
      "step": 10
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.15500934422016144,
      "learning_rate": 0.0002,
      "loss": 0.0241,
      "step": 20
    },
    {
      "epoch": 1.4545454545454546,
      "eval_loss": 0.03104669786989689,
      "eval_runtime": 21.2862,
      "eval_samples_per_second": 0.329,
      "eval_steps_per_second": 0.329,
      "step": 20
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.0952190160751343,
      "learning_rate": 0.0002,
      "loss": 0.0441,
      "step": 30
    },
    {
      "epoch": 2.1818181818181817,
      "eval_loss": 0.03029637224972248,
      "eval_runtime": 21.3082,
      "eval_samples_per_second": 0.329,
      "eval_steps_per_second": 0.329,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.417506073386496e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}