checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 19.336166381835938,
      "learning_rate": 4.999859193643945e-05,
      "loss": 2.4671,
      "step": 5
    },
    {
      "epoch": 0.1,
      "grad_norm": 10.850088119506836,
      "learning_rate": 4.9949326364020314e-05,
      "loss": 2.4246,
      "step": 10
    },
    {
      "epoch": 0.15,
      "grad_norm": 10.342315673828125,
      "learning_rate": 4.982981614472039e-05,
      "loss": 2.5563,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 11.594865798950195,
      "learning_rate": 4.9640397758692715e-05,
      "loss": 2.5333,
      "step": 20
    },
    {
      "epoch": 0.25,
      "grad_norm": 9.311284065246582,
      "learning_rate": 4.938160451202521e-05,
      "loss": 2.5209,
      "step": 25
    },
    {
      "epoch": 0.3,
      "grad_norm": 16.79537010192871,
      "learning_rate": 4.9054165035221236e-05,
      "loss": 2.8026,
      "step": 30
    },
    {
      "epoch": 0.35,
      "grad_norm": 10.748820304870605,
      "learning_rate": 4.865900123174574e-05,
      "loss": 2.8341,
      "step": 35
    },
    {
      "epoch": 0.4,
      "grad_norm": 11.450349807739258,
      "learning_rate": 4.819722568241274e-05,
      "loss": 2.7475,
      "step": 40
    },
    {
      "epoch": 0.45,
      "grad_norm": 9.321686744689941,
      "learning_rate": 4.767013851292212e-05,
      "loss": 2.7298,
      "step": 45
    },
    {
      "epoch": 0.5,
      "grad_norm": 9.671792984008789,
      "learning_rate": 4.7079223733365237e-05,
      "loss": 2.6166,
      "step": 50
    },
    {
      "epoch": 0.55,
      "grad_norm": 8.407944679260254,
      "learning_rate": 4.642614506000523e-05,
      "loss": 2.5359,
      "step": 55
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.98971939086914,
      "learning_rate": 4.571274123109606e-05,
      "loss": 2.479,
      "step": 60
    },
    {
      "epoch": 0.65,
      "grad_norm": 8.909531593322754,
      "learning_rate": 4.4941020829928245e-05,
      "loss": 2.4882,
      "step": 65
    },
    {
      "epoch": 0.7,
      "grad_norm": 7.584418296813965,
      "learning_rate": 4.4113156629677316e-05,
      "loss": 2.3675,
      "step": 70
    },
    {
      "epoch": 0.75,
      "grad_norm": 8.56999683380127,
      "learning_rate": 4.323147947597666e-05,
      "loss": 2.4285,
      "step": 75
    },
    {
      "epoch": 0.8,
      "grad_norm": 9.06714153289795,
      "learning_rate": 4.229847172443866e-05,
      "loss": 2.5075,
      "step": 80
    },
    {
      "epoch": 0.85,
      "grad_norm": 7.845032691955566,
      "learning_rate": 4.131676025160047e-05,
      "loss": 2.4794,
      "step": 85
    },
    {
      "epoch": 0.9,
      "grad_norm": 7.793240070343018,
      "learning_rate": 4.028910905897229e-05,
      "loss": 2.5271,
      "step": 90
    },
    {
      "epoch": 0.95,
      "grad_norm": 7.8635029792785645,
      "learning_rate": 3.9218411491011176e-05,
      "loss": 2.4032,
      "step": 95
    },
    {
      "epoch": 1.0,
      "grad_norm": 8.155007362365723,
      "learning_rate": 3.8107682088930794e-05,
      "loss": 2.4891,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 711215129034752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}