trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2244039270687237,
  "eval_steps": 500,
  "global_step": 480,
  "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": 3.8098,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.3734,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.4228,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.5075,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.5348,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.2127,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.1331,
      "step": 70
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.3015,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.3916,
      "step": 90
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 3.2022,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 3.1666,
      "step": 110
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 3.1852,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 3.3735,
      "step": 130
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 3.4446,
      "step": 140
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 3.2336,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 3.1014,
      "step": 160
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 3.2876,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 3.4007,
      "step": 180
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 3.4232,
      "step": 190
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 3.1296,
      "step": 200
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 3.0279,
      "step": 210
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 3.1056,
      "step": 220
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 3.2392,
      "step": 230
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 3.3685,
      "step": 240
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 3.1524,
      "step": 250
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 3.096,
      "step": 260
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 3.1069,
      "step": 270
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 3.2493,
      "step": 280
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 3.4734,
      "step": 290
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 3.0148,
      "step": 300
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 3.0526,
      "step": 310
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 3.2258,
      "step": 320
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 3.2428,
      "step": 330
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 3.4101,
      "step": 340
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 3.3459,
      "step": 350
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.9403,
      "step": 360
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 3.1751,
      "step": 370
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 3.3037,
      "step": 380
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 3.384,
      "step": 390
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 3.1564,
      "step": 400
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 3.0212,
      "step": 410
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 3.1779,
      "step": 420
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 3.2376,
      "step": 430
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 3.3929,
      "step": 440
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 3.0818,
      "step": 450
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 3.0314,
      "step": 460
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 3.0675,
      "step": 470
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 3.2193,
      "step": 480
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 3153546910897920.0,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}