trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 7466,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1339405304045004,
      "grad_norm": 9.218611717224121,
      "learning_rate": 1.878641737807314e-05,
      "loss": 0.5203,
      "step": 500
    },
    {
      "epoch": 0.2678810608090008,
      "grad_norm": 6.3912835121154785,
      "learning_rate": 1.9249888376246466e-05,
      "loss": 0.4005,
      "step": 1000
    },
    {
      "epoch": 0.4018215912135012,
      "grad_norm": 9.956713676452637,
      "learning_rate": 1.776157166244977e-05,
      "loss": 0.3351,
      "step": 1500
    },
    {
      "epoch": 0.5357621216180016,
      "grad_norm": 7.163393974304199,
      "learning_rate": 1.6273254948653075e-05,
      "loss": 0.3351,
      "step": 2000
    },
    {
      "epoch": 0.669702652022502,
      "grad_norm": 9.230996131896973,
      "learning_rate": 1.4784938234856378e-05,
      "loss": 0.3012,
      "step": 2500
    },
    {
      "epoch": 0.8036431824270024,
      "grad_norm": 5.652143955230713,
      "learning_rate": 1.3296621521059683e-05,
      "loss": 0.3005,
      "step": 3000
    },
    {
      "epoch": 0.9375837128315028,
      "grad_norm": 5.993182182312012,
      "learning_rate": 1.1808304807262986e-05,
      "loss": 0.2899,
      "step": 3500
    },
    {
      "epoch": 1.0715242432360033,
      "grad_norm": 7.842578411102295,
      "learning_rate": 1.0319988093466291e-05,
      "loss": 0.2625,
      "step": 4000
    },
    {
      "epoch": 1.2054647736405035,
      "grad_norm": 8.451859474182129,
      "learning_rate": 8.834648013097187e-06,
      "loss": 0.2381,
      "step": 4500
    },
    {
      "epoch": 1.339405304045004,
      "grad_norm": 5.78533935546875,
      "learning_rate": 7.346331299300492e-06,
      "loss": 0.2359,
      "step": 5000
    },
    {
      "epoch": 1.4733458344495043,
      "grad_norm": 3.672053098678589,
      "learning_rate": 5.8609912189313885e-06,
      "loss": 0.224,
      "step": 5500
    },
    {
      "epoch": 1.6072863648540048,
      "grad_norm": 7.369091987609863,
      "learning_rate": 4.372674505134693e-06,
      "loss": 0.2324,
      "step": 6000
    },
    {
      "epoch": 1.7412268952585053,
      "grad_norm": 5.801908016204834,
      "learning_rate": 2.890311058193184e-06,
      "loss": 0.2193,
      "step": 6500
    },
    {
      "epoch": 1.8751674256630055,
      "grad_norm": 7.236237525939941,
      "learning_rate": 1.4019943443964876e-06,
      "loss": 0.2281,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 7466,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}