model/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09474407257395959,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.6188,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.9331,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3866,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.9368,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 4.1305,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.6112,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9524,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2576,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.8537,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.6216,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5815,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.7437,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4984,
      "step": 130
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.8505,
      "step": 140
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.7214,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.606,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.862,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2848,
      "step": 180
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.8269,
      "step": 190
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 4.1686,
      "step": 200
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5837,
      "step": 210
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8463,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3385,
      "step": 230
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.7516,
      "step": 240
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 4.3126,
      "step": 250
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.6452,
      "step": 260
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.8725,
      "step": 270
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.4927,
      "step": 280
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.7915,
      "step": 290
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 3.8221,
      "step": 300
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.6097,
      "step": 310
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.8211,
      "step": 320
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.433,
      "step": 330
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.7152,
      "step": 340
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 3.5142,
      "step": 350
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.644,
      "step": 360
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.929,
      "step": 370
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.3664,
      "step": 380
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.6471,
      "step": 390
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 3.725,
      "step": 400
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.6746,
      "step": 410
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.9368,
      "step": 420
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.2657,
      "step": 430
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.8564,
      "step": 440
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 3.4636,
      "step": 450
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.5803,
      "step": 460
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.9354,
      "step": 470
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.3318,
      "step": 480
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.7885,
      "step": 490
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 3.4117,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 1.481730585710592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}