trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8421052631578947,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 668.1707763671875,
      "learning_rate": 2.7653631284916204e-06,
      "loss": 76.9764,
      "step": 100
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 334.9554138183594,
      "learning_rate": 4.995154405440528e-06,
      "loss": 20.7828,
      "step": 200
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 412.4559326171875,
      "learning_rate": 4.827522757879159e-06,
      "loss": 15.08,
      "step": 300
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 237.86691284179688,
      "learning_rate": 4.436070529523132e-06,
      "loss": 13.2074,
      "step": 400
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 524.6715087890625,
      "learning_rate": 3.858440774476823e-06,
      "loss": 12.3694,
      "step": 500
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": 355.589599609375,
      "eval_runtime": 177.1704,
      "eval_samples_per_second": 2.822,
      "eval_steps_per_second": 2.822,
      "step": 500
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 240.74716186523438,
      "learning_rate": 3.1501798571403568e-06,
      "loss": 11.8955,
      "step": 600
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 245.36228942871094,
      "learning_rate": 2.3793959708002526e-06,
      "loss": 11.3556,
      "step": 700
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 240.87294006347656,
      "learning_rate": 1.6202096784128967e-06,
      "loss": 10.9534,
      "step": 800
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 256.82452392578125,
      "learning_rate": 9.456262884412293e-07,
      "loss": 11.0009,
      "step": 900
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 246.02391052246094,
      "learning_rate": 4.205154764348304e-07,
      "loss": 10.8251,
      "step": 1000
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": 300.8138732910156,
      "eval_runtime": 178.7981,
      "eval_samples_per_second": 2.796,
      "eval_steps_per_second": 2.796,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 1188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}