ckpts/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0183299389002036,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6531,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.4496,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.5821,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.895,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.9526,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.4505,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4075,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.472,
      "step": 80
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.8758,
      "step": 90
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.9509,
      "step": 100
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.4616,
      "step": 110
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.4365,
      "step": 120
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.5214,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.8216,
      "step": 140
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.9155,
      "step": 150
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4898,
      "step": 160
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.3915,
      "step": 170
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.5799,
      "step": 180
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 2.0476,
      "step": 190
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.9179,
      "step": 200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.4597,
      "step": 210
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.4114,
      "step": 220
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.5009,
      "step": 230
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.8596,
      "step": 240
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.851,
      "step": 250
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.3758,
      "step": 260
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.3879,
      "step": 270
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.6088,
      "step": 280
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.8558,
      "step": 290
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.8685,
      "step": 300
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.3584,
      "step": 310
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.3976,
      "step": 320
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.5402,
      "step": 330
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.8134,
      "step": 340
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.9623,
      "step": 350
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.3733,
      "step": 360
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.276,
      "step": 370
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.5179,
      "step": 380
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.7899,
      "step": 390
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.8778,
      "step": 400
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.4008,
      "step": 410
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.402,
      "step": 420
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.5183,
      "step": 430
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.8471,
      "step": 440
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.9354,
      "step": 450
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.4035,
      "step": 460
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.4147,
      "step": 470
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.639,
      "step": 480
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.9683,
      "step": 490
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.417,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 2.4365101134336e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}