last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011120378092855158,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011120378092855157,
      "grad_norm": 0.6098203063011169,
      "learning_rate": 2e-05,
      "loss": 2.1223,
      "step": 1
    },
    {
      "epoch": 0.0011120378092855157,
      "eval_loss": 2.1083438396453857,
      "eval_runtime": 14.8464,
      "eval_samples_per_second": 25.528,
      "eval_steps_per_second": 12.798,
      "step": 1
    },
    {
      "epoch": 0.0022240756185710315,
      "grad_norm": 0.5889340043067932,
      "learning_rate": 4e-05,
      "loss": 2.1546,
      "step": 2
    },
    {
      "epoch": 0.003336113427856547,
      "grad_norm": 0.5553275346755981,
      "learning_rate": 6e-05,
      "loss": 2.1102,
      "step": 3
    },
    {
      "epoch": 0.003336113427856547,
      "eval_loss": 2.105567693710327,
      "eval_runtime": 14.8196,
      "eval_samples_per_second": 25.574,
      "eval_steps_per_second": 12.821,
      "step": 3
    },
    {
      "epoch": 0.004448151237142063,
      "grad_norm": 0.5620283484458923,
      "learning_rate": 8e-05,
      "loss": 2.1262,
      "step": 4
    },
    {
      "epoch": 0.005560189046427579,
      "grad_norm": 0.557763934135437,
      "learning_rate": 0.0001,
      "loss": 2.0273,
      "step": 5
    },
    {
      "epoch": 0.006672226855713094,
      "grad_norm": 0.5848349332809448,
      "learning_rate": 0.00012,
      "loss": 2.0709,
      "step": 6
    },
    {
      "epoch": 0.006672226855713094,
      "eval_loss": 2.0706539154052734,
      "eval_runtime": 14.8395,
      "eval_samples_per_second": 25.54,
      "eval_steps_per_second": 12.804,
      "step": 6
    },
    {
      "epoch": 0.00778426466499861,
      "grad_norm": 0.5398402810096741,
      "learning_rate": 0.00014,
      "loss": 1.9948,
      "step": 7
    },
    {
      "epoch": 0.008896302474284126,
      "grad_norm": 0.6420794129371643,
      "learning_rate": 0.00016,
      "loss": 2.0044,
      "step": 8
    },
    {
      "epoch": 0.010008340283569641,
      "grad_norm": 0.6951910853385925,
      "learning_rate": 0.00018,
      "loss": 1.9863,
      "step": 9
    },
    {
      "epoch": 0.010008340283569641,
      "eval_loss": 2.0390636920928955,
      "eval_runtime": 14.8686,
      "eval_samples_per_second": 25.49,
      "eval_steps_per_second": 12.779,
      "step": 9
    },
    {
      "epoch": 0.011120378092855158,
      "grad_norm": 0.6663931012153625,
      "learning_rate": 0.0002,
      "loss": 2.0286,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1000194661416960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}