checkpoint-339/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 339,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17718715393134,
      "grad_norm": 0.17973445355892181,
      "learning_rate": 0.0001887905604719764,
      "loss": 0.7903,
      "step": 20
    },
    {
      "epoch": 0.35437430786268,
      "grad_norm": 0.1280462145805359,
      "learning_rate": 0.0001769911504424779,
      "loss": 0.3812,
      "step": 40
    },
    {
      "epoch": 0.53156146179402,
      "grad_norm": 0.12361812591552734,
      "learning_rate": 0.00016519174041297935,
      "loss": 0.2641,
      "step": 60
    },
    {
      "epoch": 0.70874861572536,
      "grad_norm": 0.12793277204036713,
      "learning_rate": 0.00015339233038348085,
      "loss": 0.2592,
      "step": 80
    },
    {
      "epoch": 0.8859357696566998,
      "grad_norm": 0.1262834519147873,
      "learning_rate": 0.0001415929203539823,
      "loss": 0.2863,
      "step": 100
    },
    {
      "epoch": 1.062015503875969,
      "grad_norm": 0.11208096146583557,
      "learning_rate": 0.0001297935103244838,
      "loss": 0.2562,
      "step": 120
    },
    {
      "epoch": 1.239202657807309,
      "grad_norm": 0.11791215091943741,
      "learning_rate": 0.00011799410029498526,
      "loss": 0.2169,
      "step": 140
    },
    {
      "epoch": 1.4163898117386489,
      "grad_norm": 0.15054354071617126,
      "learning_rate": 0.00010619469026548674,
      "loss": 0.2106,
      "step": 160
    },
    {
      "epoch": 1.593576965669989,
      "grad_norm": 0.12777256965637207,
      "learning_rate": 9.43952802359882e-05,
      "loss": 0.1961,
      "step": 180
    },
    {
      "epoch": 1.770764119601329,
      "grad_norm": 0.11737984418869019,
      "learning_rate": 8.259587020648968e-05,
      "loss": 0.1973,
      "step": 200
    },
    {
      "epoch": 1.9479512735326687,
      "grad_norm": 0.13406690955162048,
      "learning_rate": 7.079646017699115e-05,
      "loss": 0.2155,
      "step": 220
    },
    {
      "epoch": 2.124031007751938,
      "grad_norm": 0.18812713027000427,
      "learning_rate": 5.899705014749263e-05,
      "loss": 0.1805,
      "step": 240
    },
    {
      "epoch": 2.301218161683278,
      "grad_norm": 0.17461156845092773,
      "learning_rate": 4.71976401179941e-05,
      "loss": 0.2135,
      "step": 260
    },
    {
      "epoch": 2.478405315614618,
      "grad_norm": 0.13407497107982635,
      "learning_rate": 3.5398230088495574e-05,
      "loss": 0.1425,
      "step": 280
    },
    {
      "epoch": 2.655592469545958,
      "grad_norm": 0.15132130682468414,
      "learning_rate": 2.359882005899705e-05,
      "loss": 0.216,
      "step": 300
    },
    {
      "epoch": 2.8327796234772977,
      "grad_norm": 0.12531444430351257,
      "learning_rate": 1.1799410029498525e-05,
      "loss": 0.1654,
      "step": 320
    }
  ],
  "logging_steps": 20,
  "max_steps": 339,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9936954298404454e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}