trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 3.0137152671813965,
      "learning_rate": 4.975e-05,
      "loss": 1.5611,
      "step": 200
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.7309519052505493,
      "learning_rate": 4.3580645161290324e-05,
      "loss": 0.7047,
      "step": 400
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.1510002613067627,
      "learning_rate": 3.7129032258064516e-05,
      "loss": 0.6898,
      "step": 600
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.406550407409668,
      "learning_rate": 3.067741935483871e-05,
      "loss": 0.6786,
      "step": 800
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.0540295839309692,
      "learning_rate": 2.4225806451612903e-05,
      "loss": 0.654,
      "step": 1000
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.9512343406677246,
      "learning_rate": 1.7774193548387098e-05,
      "loss": 0.66,
      "step": 1200
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.16969895362854,
      "learning_rate": 1.132258064516129e-05,
      "loss": 0.6414,
      "step": 1400
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.0737848281860352,
      "learning_rate": 4.870967741935484e-06,
      "loss": 0.6501,
      "step": 1600
    }
  ],
  "logging_steps": 200,
  "max_steps": 1750,
  "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": 6500904861696000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}