last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10179597178797353,
  "eval_steps": 500,
  "global_step": 7000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00727114084199811,
      "grad_norm": 25.571533203125,
      "learning_rate": 1.9951525727720014e-05,
      "loss": 7.7581,
      "step": 500
    },
    {
      "epoch": 0.01454228168399622,
      "grad_norm": 12.20069694519043,
      "learning_rate": 1.990305145544003e-05,
      "loss": 6.872,
      "step": 1000
    },
    {
      "epoch": 0.021813422525994327,
      "grad_norm": 11.402491569519043,
      "learning_rate": 1.985457718316004e-05,
      "loss": 6.6344,
      "step": 1500
    },
    {
      "epoch": 0.02908456336799244,
      "grad_norm": 16.95390510559082,
      "learning_rate": 1.9806102910880053e-05,
      "loss": 6.4979,
      "step": 2000
    },
    {
      "epoch": 0.03635570420999055,
      "grad_norm": 13.161620140075684,
      "learning_rate": 1.9757628638600062e-05,
      "loss": 6.4306,
      "step": 2500
    },
    {
      "epoch": 0.043626845051988654,
      "grad_norm": 13.924323081970215,
      "learning_rate": 1.9709154366320078e-05,
      "loss": 6.3061,
      "step": 3000
    },
    {
      "epoch": 0.050897985893986766,
      "grad_norm": 20.163259506225586,
      "learning_rate": 1.966068009404009e-05,
      "loss": 6.2785,
      "step": 3500
    },
    {
      "epoch": 0.05816912673598488,
      "grad_norm": 13.455365180969238,
      "learning_rate": 1.9612205821760102e-05,
      "loss": 6.126,
      "step": 4000
    },
    {
      "epoch": 0.06544026757798299,
      "grad_norm": 14.471346855163574,
      "learning_rate": 1.9563731549480117e-05,
      "loss": 6.0571,
      "step": 4500
    },
    {
      "epoch": 0.0727114084199811,
      "grad_norm": 15.127618789672852,
      "learning_rate": 1.951525727720013e-05,
      "loss": 6.1144,
      "step": 5000
    },
    {
      "epoch": 0.0799825492619792,
      "grad_norm": 12.843366622924805,
      "learning_rate": 1.946678300492014e-05,
      "loss": 5.9973,
      "step": 5500
    },
    {
      "epoch": 0.08725369010397731,
      "grad_norm": 23.14200782775879,
      "learning_rate": 1.9418308732640154e-05,
      "loss": 5.9721,
      "step": 6000
    },
    {
      "epoch": 0.09452483094597543,
      "grad_norm": 24.403915405273438,
      "learning_rate": 1.9369834460360166e-05,
      "loss": 5.9525,
      "step": 6500
    },
    {
      "epoch": 0.10179597178797353,
      "grad_norm": 14.797924041748047,
      "learning_rate": 1.9321360188080178e-05,
      "loss": 5.8114,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 206295,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1513105308502176.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}