trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 7474,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1337971635001338,
      "grad_norm": 1.7339763641357422,
      "learning_rate": 5e-05,
      "loss": 1.0865,
      "step": 500
    },
    {
      "epoch": 0.2675943270002676,
      "grad_norm": 1.3081908226013184,
      "learning_rate": 4.64152566676226e-05,
      "loss": 0.4781,
      "step": 1000
    },
    {
      "epoch": 0.4013914905004014,
      "grad_norm": 0.8795633316040039,
      "learning_rate": 4.2830513335245196e-05,
      "loss": 0.4536,
      "step": 1500
    },
    {
      "epoch": 0.5351886540005352,
      "grad_norm": 1.046536922454834,
      "learning_rate": 3.92457700028678e-05,
      "loss": 0.4486,
      "step": 2000
    },
    {
      "epoch": 0.668985817500669,
      "grad_norm": 0.68308424949646,
      "learning_rate": 3.566102667049039e-05,
      "loss": 0.428,
      "step": 2500
    },
    {
      "epoch": 0.8027829810008028,
      "grad_norm": 0.7812120318412781,
      "learning_rate": 3.2076283338113e-05,
      "loss": 0.4242,
      "step": 3000
    },
    {
      "epoch": 0.9365801445009366,
      "grad_norm": 0.930639922618866,
      "learning_rate": 2.8491540005735588e-05,
      "loss": 0.4259,
      "step": 3500
    },
    {
      "epoch": 1.0703773080010703,
      "grad_norm": 0.7847789525985718,
      "learning_rate": 2.490679667335819e-05,
      "loss": 0.3887,
      "step": 4000
    },
    {
      "epoch": 1.2041744715012042,
      "grad_norm": 1.0552189350128174,
      "learning_rate": 2.1322053340980785e-05,
      "loss": 0.3637,
      "step": 4500
    },
    {
      "epoch": 1.337971635001338,
      "grad_norm": 0.9732643961906433,
      "learning_rate": 1.7737310008603386e-05,
      "loss": 0.3456,
      "step": 5000
    },
    {
      "epoch": 1.4717687985014718,
      "grad_norm": 0.905820906162262,
      "learning_rate": 1.4152566676225985e-05,
      "loss": 0.3446,
      "step": 5500
    },
    {
      "epoch": 1.6055659620016056,
      "grad_norm": 0.8462561964988708,
      "learning_rate": 1.056782334384858e-05,
      "loss": 0.3476,
      "step": 6000
    },
    {
      "epoch": 1.7393631255017392,
      "grad_norm": 1.2623038291931152,
      "learning_rate": 6.983080011471179e-06,
      "loss": 0.3453,
      "step": 6500
    },
    {
      "epoch": 1.873160289001873,
      "grad_norm": 1.0751724243164062,
      "learning_rate": 3.398336679093777e-06,
      "loss": 0.3434,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 7474,
  "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": 1.3880360580415488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}