checkpoint_500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8125126955108674,
  "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": 1.8707,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7918,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.741,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.6859,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.7982,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.7449,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.735,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.6497,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.7169,
      "step": 90
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.7922,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.7233,
      "step": 110
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.6464,
      "step": 120
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.7568,
      "step": 130
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.7124,
      "step": 140
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.7768,
      "step": 150
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.7485,
      "step": 160
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.6739,
      "step": 170
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.6386,
      "step": 180
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.7529,
      "step": 190
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.7624,
      "step": 200
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.7303,
      "step": 210
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.6326,
      "step": 220
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.6637,
      "step": 230
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.6883,
      "step": 240
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.7608,
      "step": 250
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.6986,
      "step": 260
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.6054,
      "step": 270
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.6785,
      "step": 280
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.6308,
      "step": 290
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.884,
      "step": 300
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.6899,
      "step": 310
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.7043,
      "step": 320
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.6413,
      "step": 330
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.7365,
      "step": 340
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.676,
      "step": 350
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.6738,
      "step": 360
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.7175,
      "step": 370
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.6143,
      "step": 380
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.6481,
      "step": 390
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.8566,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.741,
      "step": 410
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.6964,
      "step": 420
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.6211,
      "step": 430
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.6425,
      "step": 440
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.7595,
      "step": 450
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.6,
      "step": 460
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.606,
      "step": 470
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.6649,
      "step": 480
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.6447,
      "step": 490
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.7634,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 3.293667738832896e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}