trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012416190712689347,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008277460475126231,
      "grad_norm": 0.6720314025878906,
      "learning_rate": 0.00019448275862068965,
      "loss": 2.806,
      "step": 10
    },
    {
      "epoch": 0.0016554920950252463,
      "grad_norm": 0.7282748818397522,
      "learning_rate": 0.00018068965517241382,
      "loss": 2.4015,
      "step": 20
    },
    {
      "epoch": 0.0024832381425378696,
      "grad_norm": 0.6224257349967957,
      "learning_rate": 0.00016689655172413793,
      "loss": 2.4062,
      "step": 30
    },
    {
      "epoch": 0.0033109841900504926,
      "grad_norm": 0.6465514898300171,
      "learning_rate": 0.00015310344827586207,
      "loss": 2.3612,
      "step": 40
    },
    {
      "epoch": 0.004138730237563116,
      "grad_norm": 0.5610107183456421,
      "learning_rate": 0.0001393103448275862,
      "loss": 2.1203,
      "step": 50
    },
    {
      "epoch": 0.004966476285075739,
      "grad_norm": 0.5969945192337036,
      "learning_rate": 0.00012551724137931035,
      "loss": 2.2384,
      "step": 60
    },
    {
      "epoch": 0.005794222332588362,
      "grad_norm": 0.6113339066505432,
      "learning_rate": 0.00011172413793103449,
      "loss": 2.3128,
      "step": 70
    },
    {
      "epoch": 0.006621968380100985,
      "grad_norm": 0.8051493167877197,
      "learning_rate": 9.793103448275862e-05,
      "loss": 2.2082,
      "step": 80
    },
    {
      "epoch": 0.007449714427613608,
      "grad_norm": 0.6741610169410706,
      "learning_rate": 8.413793103448277e-05,
      "loss": 2.3156,
      "step": 90
    },
    {
      "epoch": 0.008277460475126232,
      "grad_norm": 0.5629040598869324,
      "learning_rate": 7.03448275862069e-05,
      "loss": 2.1989,
      "step": 100
    },
    {
      "epoch": 0.009105206522638855,
      "grad_norm": 0.7672610282897949,
      "learning_rate": 5.6551724137931037e-05,
      "loss": 2.1749,
      "step": 110
    },
    {
      "epoch": 0.009932952570151478,
      "grad_norm": 0.5322269201278687,
      "learning_rate": 4.275862068965518e-05,
      "loss": 2.171,
      "step": 120
    },
    {
      "epoch": 0.010760698617664101,
      "grad_norm": 0.7353241443634033,
      "learning_rate": 2.8965517241379313e-05,
      "loss": 2.1584,
      "step": 130
    },
    {
      "epoch": 0.011588444665176724,
      "grad_norm": 0.6774106025695801,
      "learning_rate": 1.5172413793103448e-05,
      "loss": 2.2079,
      "step": 140
    },
    {
      "epoch": 0.012416190712689347,
      "grad_norm": 0.5964234471321106,
      "learning_rate": 1.3793103448275862e-06,
      "loss": 2.1165,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.120470461579264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}