last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21079258010118043,
  "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": 4.1470233384070705e-06,
      "loss": 1.4705,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.4552635448851985e-06,
      "loss": 1.5012,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.289174995846284e-06,
      "loss": 1.385,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.865549773769684e-06,
      "loss": 1.2729,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.306472495116047e-06,
      "loss": 1.2978,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.663646266610644e-06,
      "loss": 1.4354,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.963863644365277e-06,
      "loss": 1.4443,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.222815896602431e-06,
      "loss": 1.5108,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.450488154497406e-06,
      "loss": 1.3964,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.653629372258186e-06,
      "loss": 1.2203,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.837015420566862e-06,
      "loss": 1.3174,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.004150364012388e-06,
      "loss": 1.1764,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.157681445346895e-06,
      "loss": 1.1009,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.299657503090295e-06,
      "loss": 1.0422,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.43169675964485e-06,
      "loss": 1.0693,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.555099634066188e-06,
      "loss": 0.9296,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.670926871527948e-06,
      "loss": 1.0445,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.780055047302923e-06,
      "loss": 1.008,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.883216879176116e-06,
      "loss": 0.9062,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.98103107994822e-06,
      "loss": 1.0707,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 1e-05,
      "loss": 1.0204,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 1e-05,
      "loss": 0.8036,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 0.9934,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 0.9144,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 0.8351,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 0.8797,
      "step": 260
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 0.7679,
      "step": 270
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 0.9388,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 0.9333,
      "step": 290
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 0.8698,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 0.7842,
      "step": 310
    },
    {
      "epoch": 0.13,
      "learning_rate": 1e-05,
      "loss": 0.8371,
      "step": 320
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 0.7694,
      "step": 330
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 0.8426,
      "step": 340
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 0.7972,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 1e-05,
      "loss": 0.8183,
      "step": 360
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 0.7462,
      "step": 370
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 0.7919,
      "step": 380
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 0.8173,
      "step": 390
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 0.7654,
      "step": 400
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 0.7601,
      "step": 410
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 0.788,
      "step": 420
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 0.7488,
      "step": 430
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 0.7721,
      "step": 440
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 0.8289,
      "step": 450
    },
    {
      "epoch": 0.19,
      "learning_rate": 1e-05,
      "loss": 0.7367,
      "step": 460
    },
    {
      "epoch": 0.2,
      "learning_rate": 1e-05,
      "loss": 0.8422,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 1e-05,
      "loss": 0.7383,
      "step": 480
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 0.7729,
      "step": 490
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 0.7537,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 125136682352640.0,
  "trial_name": null,
  "trial_params": null
}