checkpoints/checkpoint-225/trainer_state.json

{
  "best_global_step": 225,
  "best_metric": 2.3704192638397217,
  "best_model_checkpoint": "./output/checkpoint-225",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.1648311614990234,
      "learning_rate": 4.5e-06,
      "loss": 2.466257667541504,
      "step": 10
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 4.898372650146484,
      "learning_rate": 9.5e-06,
      "loss": 2.397753143310547,
      "step": 20
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 2.4088022708892822,
      "learning_rate": 1.45e-05,
      "loss": 2.3467193603515626,
      "step": 30
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.3660852909088135,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 2.3866750717163088,
      "step": 40
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.8886386156082153,
      "learning_rate": 2.45e-05,
      "loss": 2.4110111236572265,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.3049066066741943,
      "learning_rate": 2.95e-05,
      "loss": 2.3524829864501955,
      "step": 60
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 2.200075387954712,
      "learning_rate": 3.45e-05,
      "loss": 2.45643310546875,
      "step": 70
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.166034460067749,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 2.4559621810913086,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.8101855516433716,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 2.372382926940918,
      "step": 90
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.296342134475708,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 2.4228847503662108,
      "step": 100
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 2.5206782817840576,
      "learning_rate": 4.9217391304347824e-05,
      "loss": 2.4426870346069336,
      "step": 110
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.3830366134643555,
      "learning_rate": 4.834782608695652e-05,
      "loss": 2.379886817932129,
      "step": 120
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 2.637955665588379,
      "learning_rate": 4.747826086956522e-05,
      "loss": 2.3728614807128907,
      "step": 130
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.458829879760742,
      "learning_rate": 4.660869565217392e-05,
      "loss": 2.462764358520508,
      "step": 140
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.68799090385437,
      "learning_rate": 4.5739130434782614e-05,
      "loss": 2.323098373413086,
      "step": 150
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.776823043823242,
      "learning_rate": 4.486956521739131e-05,
      "loss": 2.330042839050293,
      "step": 160
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 2.658755302429199,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.3432085037231447,
      "step": 170
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.509666681289673,
      "learning_rate": 4.3130434782608695e-05,
      "loss": 2.353105163574219,
      "step": 180
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 2.1432905197143555,
      "learning_rate": 4.226086956521739e-05,
      "loss": 2.4502593994140627,
      "step": 190
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.2782559394836426,
      "learning_rate": 4.1391304347826086e-05,
      "loss": 2.399493408203125,
      "step": 200
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 2.4559714794158936,
      "learning_rate": 4.052173913043478e-05,
      "loss": 2.4100601196289064,
      "step": 210
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 2.3984427452087402,
      "learning_rate": 3.965217391304348e-05,
      "loss": 2.3846929550170897,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.3704192638397217,
      "eval_runtime": 2.7149,
      "eval_samples_per_second": 73.667,
      "eval_steps_per_second": 9.208,
      "step": 225
    }
  ],
  "logging_steps": 10,
  "max_steps": 675,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 20741291827200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}