checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06364562118126273,
  "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": 1.3744,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.4719,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.8097,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.868,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0557,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.4231,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3828,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.7284,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.14,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3983,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8301,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.2601,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4198,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8985,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.7728,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.1191,
      "step": 160
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3876,
      "step": 170
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.528,
      "step": 180
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.067,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8507,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4472,
      "step": 210
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.5308,
      "step": 220
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2405,
      "step": 230
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8404,
      "step": 240
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0961,
      "step": 250
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.1615,
      "step": 260
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.1319,
      "step": 270
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.3976,
      "step": 280
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8732,
      "step": 290
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1415,
      "step": 300
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7423,
      "step": 310
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5519,
      "step": 320
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.4975,
      "step": 330
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2549,
      "step": 340
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3298,
      "step": 350
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.1939,
      "step": 360
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.7077,
      "step": 370
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9593,
      "step": 380
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9703,
      "step": 390
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.958,
      "step": 400
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.3889,
      "step": 410
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.4975,
      "step": 420
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9328,
      "step": 430
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.1274,
      "step": 440
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.0546,
      "step": 450
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.2364,
      "step": 460
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3099,
      "step": 470
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.2687,
      "step": 480
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.8152,
      "step": 490
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.1546,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1971890728980480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}