trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 6250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032,
      "grad_norm": 1.37652587890625,
      "learning_rate": 4.987503346465644e-05,
      "loss": 0.8855,
      "num_input_tokens_seen": 3800352,
      "step": 200
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.057775855064392,
      "learning_rate": 4.949888284448093e-05,
      "loss": 0.6955,
      "num_input_tokens_seen": 7570416,
      "step": 400
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.108160138130188,
      "learning_rate": 4.887534333738762e-05,
      "loss": 0.6572,
      "num_input_tokens_seen": 11350176,
      "step": 600
    },
    {
      "epoch": 0.128,
      "grad_norm": 1.080184817314148,
      "learning_rate": 4.801071142414212e-05,
      "loss": 0.6316,
      "num_input_tokens_seen": 15126720,
      "step": 800
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.1620898246765137,
      "learning_rate": 4.6913718128439225e-05,
      "loss": 0.6156,
      "num_input_tokens_seen": 18885984,
      "step": 1000
    },
    {
      "epoch": 0.192,
      "grad_norm": 1.1564254760742188,
      "learning_rate": 4.5595440851322203e-05,
      "loss": 0.5979,
      "num_input_tokens_seen": 22670352,
      "step": 1200
    },
    {
      "epoch": 0.224,
      "grad_norm": 1.20219886302948,
      "learning_rate": 4.406919151196325e-05,
      "loss": 0.5885,
      "num_input_tokens_seen": 26463696,
      "step": 1400
    },
    {
      "epoch": 0.256,
      "grad_norm": 1.1860393285751343,
      "learning_rate": 4.2350382124355825e-05,
      "loss": 0.576,
      "num_input_tokens_seen": 30249072,
      "step": 1600
    },
    {
      "epoch": 0.288,
      "grad_norm": 1.3443669080734253,
      "learning_rate": 4.045636916732074e-05,
      "loss": 0.5667,
      "num_input_tokens_seen": 34045728,
      "step": 1800
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.2317980527877808,
      "learning_rate": 3.8406278319372545e-05,
      "loss": 0.5555,
      "num_input_tokens_seen": 37831872,
      "step": 2000
    },
    {
      "epoch": 0.352,
      "grad_norm": 2.2530808448791504,
      "learning_rate": 3.622081132826741e-05,
      "loss": 0.5558,
      "num_input_tokens_seen": 41580912,
      "step": 2200
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.2599478960037231,
      "learning_rate": 3.3922036965457345e-05,
      "loss": 0.547,
      "num_input_tokens_seen": 45352320,
      "step": 2400
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.4325836896896362,
      "learning_rate": 3.153316817638568e-05,
      "loss": 0.5374,
      "num_input_tokens_seen": 49126704,
      "step": 2600
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.758897066116333,
      "learning_rate": 2.9078327676952238e-05,
      "loss": 0.5335,
      "num_input_tokens_seen": 52900272,
      "step": 2800
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.498462200164795,
      "learning_rate": 2.6582304363147553e-05,
      "loss": 0.5214,
      "num_input_tokens_seen": 56678352,
      "step": 3000
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.6429013013839722,
      "learning_rate": 2.4070302993622974e-05,
      "loss": 0.5214,
      "num_input_tokens_seen": 60485520,
      "step": 3200
    },
    {
      "epoch": 0.544,
      "grad_norm": 1.6480096578598022,
      "learning_rate": 2.156768967289386e-05,
      "loss": 0.5171,
      "num_input_tokens_seen": 64270992,
      "step": 3400
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.460195779800415,
      "learning_rate": 1.9099735705277676e-05,
      "loss": 0.5115,
      "num_input_tokens_seen": 68075232,
      "step": 3600
    },
    {
      "epoch": 0.608,
      "grad_norm": 1.6105644702911377,
      "learning_rate": 1.6691362406121283e-05,
      "loss": 0.5134,
      "num_input_tokens_seen": 71833152,
      "step": 3800
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.3940142393112183,
      "learning_rate": 1.4366889447204949e-05,
      "loss": 0.5054,
      "num_input_tokens_seen": 75605328,
      "step": 4000
    },
    {
      "epoch": 0.672,
      "grad_norm": 1.560068964958191,
      "learning_rate": 1.2149789277522649e-05,
      "loss": 0.4985,
      "num_input_tokens_seen": 79401840,
      "step": 4200
    },
    {
      "epoch": 0.704,
      "grad_norm": 1.9104267358779907,
      "learning_rate": 1.0062450099289355e-05,
      "loss": 0.4989,
      "num_input_tokens_seen": 83179872,
      "step": 4400
    },
    {
      "epoch": 0.736,
      "grad_norm": 1.612361192703247,
      "learning_rate": 8.125949792635392e-06,
      "loss": 0.4923,
      "num_input_tokens_seen": 86971776,
      "step": 4600
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.815528154373169,
      "learning_rate": 6.3598430718887905e-06,
      "loss": 0.4923,
      "num_input_tokens_seen": 90738480,
      "step": 4800
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.8656563758850098,
      "learning_rate": 4.7819640227340475e-06,
      "loss": 0.4957,
      "num_input_tokens_seen": 94484544,
      "step": 5000
    },
    {
      "epoch": 0.832,
      "grad_norm": 1.6296930313110352,
      "learning_rate": 3.4082460142206534e-06,
      "loss": 0.4846,
      "num_input_tokens_seen": 98243760,
      "step": 5200
    },
    {
      "epoch": 0.864,
      "grad_norm": 1.6372461318969727,
      "learning_rate": 2.252560804143558e-06,
      "loss": 0.4826,
      "num_input_tokens_seen": 102027312,
      "step": 5400
    },
    {
      "epoch": 0.896,
      "grad_norm": 1.949239730834961,
      "learning_rate": 1.3265784625040383e-06,
      "loss": 0.4865,
      "num_input_tokens_seen": 105815568,
      "step": 5600
    },
    {
      "epoch": 0.928,
      "grad_norm": 1.8905956745147705,
      "learning_rate": 6.396495275391906e-07,
      "loss": 0.4888,
      "num_input_tokens_seen": 109570512,
      "step": 5800
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.188307523727417,
      "learning_rate": 1.987105843044096e-07,
      "loss": 0.4823,
      "num_input_tokens_seen": 113341200,
      "step": 6000
    },
    {
      "epoch": 0.992,
      "grad_norm": 1.7114368677139282,
      "learning_rate": 8.214219273042222e-09,
      "loss": 0.4817,
      "num_input_tokens_seen": 117119856,
      "step": 6200
    }
  ],
  "logging_steps": 200,
  "max_steps": 6250,
  "num_input_tokens_seen": 118066224,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2705070144713916e+19,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}