checkpoint-2500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24210070784194454,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009684028313677782,
      "grad_norm": 1.3304239511489868,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6269,
      "step": 100
    },
    {
      "epoch": 0.019368056627355565,
      "grad_norm": 1.3456004858016968,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.3907,
      "step": 200
    },
    {
      "epoch": 0.029052084941033347,
      "grad_norm": 1.288303256034851,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 0.3566,
      "step": 300
    },
    {
      "epoch": 0.03873611325471113,
      "grad_norm": 1.231126308441162,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.3428,
      "step": 400
    },
    {
      "epoch": 0.04842014156838891,
      "grad_norm": 1.1136806011199951,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.3361,
      "step": 500
    },
    {
      "epoch": 0.058104169882066695,
      "grad_norm": 1.1187803745269775,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.3305,
      "step": 600
    },
    {
      "epoch": 0.06778819819574447,
      "grad_norm": 1.0419028997421265,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.329,
      "step": 700
    },
    {
      "epoch": 0.07747222650942226,
      "grad_norm": 1.0367131233215332,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.3222,
      "step": 800
    },
    {
      "epoch": 0.08715625482310004,
      "grad_norm": 1.1226321458816528,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.3219,
      "step": 900
    },
    {
      "epoch": 0.09684028313677782,
      "grad_norm": 0.9624041318893433,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.3173,
      "step": 1000
    },
    {
      "epoch": 0.1065243114504556,
      "grad_norm": 1.0128655433654785,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 0.3103,
      "step": 1100
    },
    {
      "epoch": 0.11620833976413339,
      "grad_norm": 0.9672228693962097,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 0.3138,
      "step": 1200
    },
    {
      "epoch": 0.12589236807781118,
      "grad_norm": 0.9582985639572144,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.3095,
      "step": 1300
    },
    {
      "epoch": 0.13557639639148894,
      "grad_norm": 1.0016893148422241,
      "learning_rate": 9.651005032974994e-06,
      "loss": 0.3019,
      "step": 1400
    },
    {
      "epoch": 0.14526042470516673,
      "grad_norm": 0.9507680535316467,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.2964,
      "step": 1500
    },
    {
      "epoch": 0.15494445301884452,
      "grad_norm": 0.9306615591049194,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.2942,
      "step": 1600
    },
    {
      "epoch": 0.1646284813325223,
      "grad_norm": 0.9242100715637207,
      "learning_rate": 5.616288532109225e-06,
      "loss": 0.2936,
      "step": 1700
    },
    {
      "epoch": 0.17431250964620007,
      "grad_norm": 1.1241374015808105,
      "learning_rate": 4.408070965292534e-06,
      "loss": 0.2919,
      "step": 1800
    },
    {
      "epoch": 0.18399653795987786,
      "grad_norm": 1.051304817199707,
      "learning_rate": 3.308693936411421e-06,
      "loss": 0.2889,
      "step": 1900
    },
    {
      "epoch": 0.19368056627355565,
      "grad_norm": 0.9818484783172607,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.2854,
      "step": 2000
    },
    {
      "epoch": 0.20336459458723344,
      "grad_norm": 0.9617915749549866,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 0.2792,
      "step": 2100
    },
    {
      "epoch": 0.2130486229009112,
      "grad_norm": 1.021549940109253,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.2843,
      "step": 2200
    },
    {
      "epoch": 0.222732651214589,
      "grad_norm": 0.9170396327972412,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 0.2855,
      "step": 2300
    },
    {
      "epoch": 0.23241667952826678,
      "grad_norm": 0.9328998923301697,
      "learning_rate": 9.731931258429638e-08,
      "loss": 0.2844,
      "step": 2400
    },
    {
      "epoch": 0.24210070784194454,
      "grad_norm": 0.9335331320762634,
      "learning_rate": 0.0,
      "loss": 0.2819,
      "step": 2500
    }
  ],
  "logging_steps": 100,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3916038848512e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}