checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.047372597321079624,
  "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": 2.0335,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.9474,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.3621,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.9279,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.7582,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8428,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.96,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4034,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.9758,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.8103,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8384,
      "step": 110
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8968,
      "step": 120
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1994,
      "step": 130
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.7571,
      "step": 140
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.8214,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8611,
      "step": 160
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.9232,
      "step": 170
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3179,
      "step": 180
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.8625,
      "step": 190
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.8472,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.843,
      "step": 210
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.7495,
      "step": 220
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3479,
      "step": 230
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.8036,
      "step": 240
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.3126,
      "step": 250
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.792,
      "step": 260
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7901,
      "step": 270
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.6648,
      "step": 280
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.8238,
      "step": 290
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 4.212,
      "step": 300
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9653,
      "step": 310
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8117,
      "step": 320
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3608,
      "step": 330
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.8914,
      "step": 340
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.9938,
      "step": 350
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8292,
      "step": 360
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7838,
      "step": 370
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1457,
      "step": 380
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.7957,
      "step": 390
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 4.1624,
      "step": 400
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.83,
      "step": 410
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8524,
      "step": 420
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4817,
      "step": 430
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.7078,
      "step": 440
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.602,
      "step": 450
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8429,
      "step": 460
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.794,
      "step": 470
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.2423,
      "step": 480
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.7302,
      "step": 490
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 5.2095,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 4960090339338240.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}