checkpoint-308/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.0,
  "eval_steps": 500,
  "global_step": 308,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.8585774898529053,
      "learning_rate": 2.25e-06,
      "loss": 4.6803,
      "step": 10
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.6986469626426697,
      "learning_rate": 4.75e-06,
      "loss": 4.6484,
      "step": 20
    },
    {
      "epoch": 1.372093023255814,
      "grad_norm": 0.9079183340072632,
      "learning_rate": 7.25e-06,
      "loss": 4.692,
      "step": 30
    },
    {
      "epoch": 1.8372093023255816,
      "grad_norm": 0.9651162624359131,
      "learning_rate": 9.750000000000002e-06,
      "loss": 4.5727,
      "step": 40
    },
    {
      "epoch": 2.2790697674418605,
      "grad_norm": 1.0011574029922485,
      "learning_rate": 1.225e-05,
      "loss": 4.5349,
      "step": 50
    },
    {
      "epoch": 2.744186046511628,
      "grad_norm": 0.8613724708557129,
      "learning_rate": 1.475e-05,
      "loss": 4.4834,
      "step": 60
    },
    {
      "epoch": 3.186046511627907,
      "grad_norm": 0.7298063039779663,
      "learning_rate": 1.725e-05,
      "loss": 4.3632,
      "step": 70
    },
    {
      "epoch": 3.6511627906976747,
      "grad_norm": 0.9772608876228333,
      "learning_rate": 1.9750000000000002e-05,
      "loss": 4.2663,
      "step": 80
    },
    {
      "epoch": 4.093023255813954,
      "grad_norm": 0.9942960143089294,
      "learning_rate": 2.2250000000000002e-05,
      "loss": 4.0867,
      "step": 90
    },
    {
      "epoch": 4.558139534883721,
      "grad_norm": 1.3665835857391357,
      "learning_rate": 2.4750000000000002e-05,
      "loss": 3.8939,
      "step": 100
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0870517492294312,
      "learning_rate": 2.725e-05,
      "loss": 3.6812,
      "step": 110
    },
    {
      "epoch": 5.465116279069767,
      "grad_norm": 1.2463775873184204,
      "learning_rate": 2.975e-05,
      "loss": 3.4444,
      "step": 120
    },
    {
      "epoch": 5.930232558139535,
      "grad_norm": 1.569264531135559,
      "learning_rate": 3.2250000000000005e-05,
      "loss": 3.1378,
      "step": 130
    },
    {
      "epoch": 6.372093023255814,
      "grad_norm": 1.720213532447815,
      "learning_rate": 3.475e-05,
      "loss": 2.925,
      "step": 140
    },
    {
      "epoch": 6.837209302325581,
      "grad_norm": 1.5594395399093628,
      "learning_rate": 3.7250000000000004e-05,
      "loss": 2.5943,
      "step": 150
    },
    {
      "epoch": 7.27906976744186,
      "grad_norm": 1.1726150512695312,
      "learning_rate": 3.9750000000000004e-05,
      "loss": 2.4226,
      "step": 160
    },
    {
      "epoch": 7.7441860465116275,
      "grad_norm": 1.3921430110931396,
      "learning_rate": 4.2250000000000004e-05,
      "loss": 2.1763,
      "step": 170
    },
    {
      "epoch": 8.186046511627907,
      "grad_norm": 1.3491045236587524,
      "learning_rate": 4.4750000000000004e-05,
      "loss": 2.1677,
      "step": 180
    },
    {
      "epoch": 8.651162790697674,
      "grad_norm": 0.9162717461585999,
      "learning_rate": 4.7249999999999997e-05,
      "loss": 1.9753,
      "step": 190
    },
    {
      "epoch": 9.093023255813954,
      "grad_norm": 1.0425995588302612,
      "learning_rate": 4.975e-05,
      "loss": 2.1817,
      "step": 200
    },
    {
      "epoch": 9.55813953488372,
      "grad_norm": 0.9056143164634705,
      "learning_rate": 4.9411026970731805e-05,
      "loss": 1.9631,
      "step": 210
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2772588729858398,
      "learning_rate": 4.7410673432392596e-05,
      "loss": 1.8078,
      "step": 220
    },
    {
      "epoch": 10.465116279069768,
      "grad_norm": 1.1431177854537964,
      "learning_rate": 4.410789301364621e-05,
      "loss": 1.9238,
      "step": 230
    },
    {
      "epoch": 10.930232558139535,
      "grad_norm": 0.9406613707542419,
      "learning_rate": 3.9694631307311836e-05,
      "loss": 1.7594,
      "step": 240
    },
    {
      "epoch": 11.372093023255815,
      "grad_norm": 0.8469231724739075,
      "learning_rate": 3.442737104220801e-05,
      "loss": 1.9515,
      "step": 250
    },
    {
      "epoch": 11.837209302325581,
      "grad_norm": 1.383780598640442,
      "learning_rate": 2.8612226239230532e-05,
      "loss": 1.6711,
      "step": 260
    },
    {
      "epoch": 12.279069767441861,
      "grad_norm": 0.8472384214401245,
      "learning_rate": 2.2587151977137122e-05,
      "loss": 1.7611,
      "step": 270
    },
    {
      "epoch": 12.744186046511627,
      "grad_norm": 0.8573427796363831,
      "learning_rate": 1.6702303671786797e-05,
      "loss": 1.734,
      "step": 280
    },
    {
      "epoch": 13.186046511627907,
      "grad_norm": 0.9242410659790039,
      "learning_rate": 1.1299687316133256e-05,
      "loss": 1.7234,
      "step": 290
    },
    {
      "epoch": 13.651162790697674,
      "grad_norm": 0.9648193717002869,
      "learning_rate": 6.69328333505567e-06,
      "loss": 1.7062,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 664107774640128.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}