trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2467532467532467,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16233766233766234,
      "grad_norm": 0.4960825741291046,
      "learning_rate": 5e-06,
      "loss": 2.0091,
      "step": 50
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 0.612104058265686,
      "learning_rate": 1e-05,
      "loss": 1.9859,
      "step": 100
    },
    {
      "epoch": 0.487012987012987,
      "grad_norm": 0.972963273525238,
      "learning_rate": 1.5e-05,
      "loss": 1.8634,
      "step": 150
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 1.1691817045211792,
      "learning_rate": 2e-05,
      "loss": 1.6265,
      "step": 200
    },
    {
      "epoch": 0.8116883116883117,
      "grad_norm": 0.9815682768821716,
      "learning_rate": 2.5e-05,
      "loss": 1.3582,
      "step": 250
    },
    {
      "epoch": 0.974025974025974,
      "grad_norm": 0.9641402959823608,
      "learning_rate": 3e-05,
      "loss": 1.2325,
      "step": 300
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 1.0225356817245483,
      "learning_rate": 3.5e-05,
      "loss": 1.1779,
      "step": 350
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 1.0966838598251343,
      "learning_rate": 4e-05,
      "loss": 1.1259,
      "step": 400
    },
    {
      "epoch": 1.4610389610389611,
      "grad_norm": 1.287178874015808,
      "learning_rate": 4.5e-05,
      "loss": 1.1133,
      "step": 450
    },
    {
      "epoch": 1.6233766233766234,
      "grad_norm": 1.6265290975570679,
      "learning_rate": 5e-05,
      "loss": 1.092,
      "step": 500
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.639063835144043,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.0809,
      "step": 550
    },
    {
      "epoch": 1.948051948051948,
      "grad_norm": 1.2419629096984863,
      "learning_rate": 4.522542485937369e-05,
      "loss": 1.0611,
      "step": 600
    },
    {
      "epoch": 2.1103896103896105,
      "grad_norm": 1.6913366317749023,
      "learning_rate": 3.969463130731183e-05,
      "loss": 1.0453,
      "step": 650
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 1.5554989576339722,
      "learning_rate": 3.272542485937369e-05,
      "loss": 1.0318,
      "step": 700
    },
    {
      "epoch": 2.435064935064935,
      "grad_norm": 1.399939775466919,
      "learning_rate": 2.5e-05,
      "loss": 1.0313,
      "step": 750
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 1.5082526206970215,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 1.0219,
      "step": 800
    },
    {
      "epoch": 2.75974025974026,
      "grad_norm": 1.4758871793746948,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 1.0223,
      "step": 850
    },
    {
      "epoch": 2.9220779220779223,
      "grad_norm": 1.4590177536010742,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 1.0271,
      "step": 900
    },
    {
      "epoch": 3.0844155844155843,
      "grad_norm": 1.366603136062622,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 1.0161,
      "step": 950
    },
    {
      "epoch": 3.2467532467532467,
      "grad_norm": 1.26113760471344,
      "learning_rate": 0.0,
      "loss": 1.0168,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.378177990475776e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}