trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9969945902624725,
  "eval_steps": 16,
  "global_step": 311,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05129232618713685,
      "grad_norm": 0.5048500299453735,
      "learning_rate": 0.0015,
      "loss": 1.1504,
      "step": 16
    },
    {
      "epoch": 0.1025846523742737,
      "grad_norm": 0.389893114566803,
      "learning_rate": 0.0011094003924504584,
      "loss": 3.0392,
      "step": 32
    },
    {
      "epoch": 0.15387697856141053,
      "grad_norm": 0.2868100106716156,
      "learning_rate": 0.0007427813527082075,
      "loss": 0.8441,
      "step": 48
    },
    {
      "epoch": 0.2051693047485474,
      "grad_norm": 0.2573494613170624,
      "learning_rate": 0.0005962847939999439,
      "loss": 0.783,
      "step": 64
    },
    {
      "epoch": 0.25646163093568425,
      "grad_norm": 0.31569787859916687,
      "learning_rate": 0.000512147519731584,
      "loss": 0.7637,
      "step": 80
    },
    {
      "epoch": 0.30775395712282105,
      "grad_norm": 0.2564464211463928,
      "learning_rate": 0.0004558423058385518,
      "loss": 0.719,
      "step": 96
    },
    {
      "epoch": 0.3590462833099579,
      "grad_norm": 0.32603177428245544,
      "learning_rate": 0.0004147806778921701,
      "loss": 0.7037,
      "step": 112
    },
    {
      "epoch": 0.4103386094970948,
      "grad_norm": 0.2662847340106964,
      "learning_rate": 0.0003831305140884606,
      "loss": 0.6794,
      "step": 128
    },
    {
      "epoch": 0.46163093568423164,
      "grad_norm": 0.3353310525417328,
      "learning_rate": 0.00035777087639996636,
      "loss": 0.6737,
      "step": 144
    },
    {
      "epoch": 0.5129232618713685,
      "grad_norm": 0.26287367939949036,
      "learning_rate": 0.00033686076842660763,
      "loss": 0.6561,
      "step": 160
    },
    {
      "epoch": 0.5642155880585054,
      "grad_norm": 0.3288561999797821,
      "learning_rate": 0.00031923475378704884,
      "loss": 0.6359,
      "step": 176
    },
    {
      "epoch": 0.6155079142456421,
      "grad_norm": 0.35450485348701477,
      "learning_rate": 0.0003041143685078822,
      "loss": 0.612,
      "step": 192
    },
    {
      "epoch": 0.666800240432779,
      "grad_norm": 0.29516109824180603,
      "learning_rate": 0.00029095718698132317,
      "loss": 0.6057,
      "step": 208
    },
    {
      "epoch": 0.7180925666199158,
      "grad_norm": 0.38677069544792175,
      "learning_rate": 0.00027937211830783126,
      "loss": 0.5943,
      "step": 224
    },
    {
      "epoch": 0.7693848928070527,
      "grad_norm": 0.3125530481338501,
      "learning_rate": 0.000269069117598525,
      "loss": 0.5635,
      "step": 240
    },
    {
      "epoch": 0.8206772189941896,
      "grad_norm": 0.3307824730873108,
      "learning_rate": 0.00025982792098465233,
      "loss": 0.5629,
      "step": 256
    },
    {
      "epoch": 0.8719695451813264,
      "grad_norm": 0.31122493743896484,
      "learning_rate": 0.0002514778453847726,
      "loss": 0.5582,
      "step": 272
    },
    {
      "epoch": 0.9232618713684633,
      "grad_norm": 0.3087589144706726,
      "learning_rate": 0.00024388430433987693,
      "loss": 0.5364,
      "step": 288
    },
    {
      "epoch": 0.9745541975556001,
      "grad_norm": 0.3315638601779938,
      "learning_rate": 0.00023693955110363693,
      "loss": 0.5412,
      "step": 304
    },
    {
      "epoch": 0.9969945902624725,
      "step": 311,
      "total_flos": 3.158660236722569e+18,
      "train_loss": 0.7963475859050199,
      "train_runtime": 2372.2052,
      "train_samples_per_second": 16.831,
      "train_steps_per_second": 0.131
    }
  ],
  "logging_steps": 16,
  "max_steps": 311,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.158660236722569e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}