checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.373134328358209,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018656716417910446,
      "grad_norm": 2.403158187866211,
      "learning_rate": 4.9998282347929784e-05,
      "loss": 3.3875,
      "step": 5
    },
    {
      "epoch": 0.03731343283582089,
      "grad_norm": 2.301710367202759,
      "learning_rate": 4.99931296277454e-05,
      "loss": 2.9015,
      "step": 10
    },
    {
      "epoch": 0.055970149253731345,
      "grad_norm": 1.271048665046692,
      "learning_rate": 4.998454254749331e-05,
      "loss": 2.6229,
      "step": 15
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 1.069893717765808,
      "learning_rate": 4.997252228714279e-05,
      "loss": 2.3704,
      "step": 20
    },
    {
      "epoch": 0.09328358208955224,
      "grad_norm": 0.9044906497001648,
      "learning_rate": 4.9957070498423854e-05,
      "loss": 2.3782,
      "step": 25
    },
    {
      "epoch": 0.11194029850746269,
      "grad_norm": 0.9635376334190369,
      "learning_rate": 4.993818930460026e-05,
      "loss": 2.3576,
      "step": 30
    },
    {
      "epoch": 0.13059701492537312,
      "grad_norm": 0.8513979315757751,
      "learning_rate": 4.9915881300177725e-05,
      "loss": 2.4603,
      "step": 35
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.845267117023468,
      "learning_rate": 4.9890149550547454e-05,
      "loss": 2.2033,
      "step": 40
    },
    {
      "epoch": 0.16791044776119404,
      "grad_norm": 0.6632418036460876,
      "learning_rate": 4.98609975915649e-05,
      "loss": 2.1851,
      "step": 45
    },
    {
      "epoch": 0.1865671641791045,
      "grad_norm": 0.6857479810714722,
      "learning_rate": 4.982842942906386e-05,
      "loss": 2.3592,
      "step": 50
    },
    {
      "epoch": 0.20522388059701493,
      "grad_norm": 0.7204287648200989,
      "learning_rate": 4.979244953830608e-05,
      "loss": 2.1323,
      "step": 55
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 0.6864420175552368,
      "learning_rate": 4.9753062863366276e-05,
      "loss": 2.2138,
      "step": 60
    },
    {
      "epoch": 0.24253731343283583,
      "grad_norm": 0.7536088228225708,
      "learning_rate": 4.971027481645274e-05,
      "loss": 2.2584,
      "step": 65
    },
    {
      "epoch": 0.26119402985074625,
      "grad_norm": 0.9708526134490967,
      "learning_rate": 4.966409127716367e-05,
      "loss": 2.2669,
      "step": 70
    },
    {
      "epoch": 0.2798507462686567,
      "grad_norm": 0.7516190409660339,
      "learning_rate": 4.96145185916792e-05,
      "loss": 2.2133,
      "step": 75
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.7864778637886047,
      "learning_rate": 4.95615635718894e-05,
      "loss": 2.1683,
      "step": 80
    },
    {
      "epoch": 0.31716417910447764,
      "grad_norm": 0.7846741080284119,
      "learning_rate": 4.950523349445824e-05,
      "loss": 2.1274,
      "step": 85
    },
    {
      "epoch": 0.3358208955223881,
      "grad_norm": 0.816838800907135,
      "learning_rate": 4.944553609982363e-05,
      "loss": 2.2033,
      "step": 90
    },
    {
      "epoch": 0.35447761194029853,
      "grad_norm": 0.7661916017532349,
      "learning_rate": 4.938247959113386e-05,
      "loss": 2.1492,
      "step": 95
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 0.8964986205101013,
      "learning_rate": 4.931607263312032e-05,
      "loss": 2.0862,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 1340,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.0457337537390182e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}