checkpoint-400/trainer_state.json

{
  "best_global_step": 400,
  "best_metric": 1.2062289714813232,
  "best_model_checkpoint": "Qwen-3-0.6B-it-Medical-LoRA/checkpoint-400",
  "epoch": 0.9060022650056625,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11325028312570781,
      "grad_norm": 0.3080866038799286,
      "learning_rate": 0.00019075425790754258,
      "loss": 1.8711,
      "step": 50
    },
    {
      "epoch": 0.22650056625141562,
      "grad_norm": 0.28974413871765137,
      "learning_rate": 0.0001664233576642336,
      "loss": 1.338,
      "step": 100
    },
    {
      "epoch": 0.22650056625141562,
      "eval_loss": 1.3033037185668945,
      "eval_runtime": 217.1489,
      "eval_samples_per_second": 7.225,
      "eval_steps_per_second": 0.907,
      "step": 100
    },
    {
      "epoch": 0.33975084937712347,
      "grad_norm": 0.3371483385562897,
      "learning_rate": 0.0001420924574209246,
      "loss": 1.2923,
      "step": 150
    },
    {
      "epoch": 0.45300113250283125,
      "grad_norm": 0.35730767250061035,
      "learning_rate": 0.00011776155717761557,
      "loss": 1.2703,
      "step": 200
    },
    {
      "epoch": 0.45300113250283125,
      "eval_loss": 1.2490053176879883,
      "eval_runtime": 217.4793,
      "eval_samples_per_second": 7.214,
      "eval_steps_per_second": 0.906,
      "step": 200
    },
    {
      "epoch": 0.5662514156285391,
      "grad_norm": 0.35110780596733093,
      "learning_rate": 9.343065693430657e-05,
      "loss": 1.2397,
      "step": 250
    },
    {
      "epoch": 0.6795016987542469,
      "grad_norm": 0.35077276825904846,
      "learning_rate": 6.909975669099758e-05,
      "loss": 1.232,
      "step": 300
    },
    {
      "epoch": 0.6795016987542469,
      "eval_loss": 1.2211977243423462,
      "eval_runtime": 217.5364,
      "eval_samples_per_second": 7.213,
      "eval_steps_per_second": 0.906,
      "step": 300
    },
    {
      "epoch": 0.7927519818799547,
      "grad_norm": 0.3939191699028015,
      "learning_rate": 4.476885644768857e-05,
      "loss": 1.2241,
      "step": 350
    },
    {
      "epoch": 0.9060022650056625,
      "grad_norm": 0.366871178150177,
      "learning_rate": 2.0437956204379563e-05,
      "loss": 1.2078,
      "step": 400
    },
    {
      "epoch": 0.9060022650056625,
      "eval_loss": 1.2062289714813232,
      "eval_runtime": 217.4838,
      "eval_samples_per_second": 7.214,
      "eval_steps_per_second": 0.906,
      "step": 400
    }
  ],
  "logging_steps": 50,
  "max_steps": 441,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.024051048448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}