checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3250711093051605,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016253555465258026,
      "grad_norm": 2.077186346054077,
      "learning_rate": 4.9998691031433496e-05,
      "loss": 2.8778,
      "step": 5
    },
    {
      "epoch": 0.03250711093051605,
      "grad_norm": 2.073504686355591,
      "learning_rate": 4.999476426280588e-05,
      "loss": 2.6432,
      "step": 10
    },
    {
      "epoch": 0.048760666395774074,
      "grad_norm": 2.1281931400299072,
      "learning_rate": 4.998822010531848e-05,
      "loss": 2.3167,
      "step": 15
    },
    {
      "epoch": 0.0650142218610321,
      "grad_norm": 1.090219497680664,
      "learning_rate": 4.997905924425903e-05,
      "loss": 2.1533,
      "step": 20
    },
    {
      "epoch": 0.08126777732629012,
      "grad_norm": 1.007896900177002,
      "learning_rate": 4.996728263892985e-05,
      "loss": 2.0267,
      "step": 25
    },
    {
      "epoch": 0.09752133279154815,
      "grad_norm": 0.9982665777206421,
      "learning_rate": 4.995289152254744e-05,
      "loss": 1.9352,
      "step": 30
    },
    {
      "epoch": 0.11377488825680618,
      "grad_norm": 0.8844298720359802,
      "learning_rate": 4.9935887402113315e-05,
      "loss": 1.9486,
      "step": 35
    },
    {
      "epoch": 0.1300284437220642,
      "grad_norm": 0.9337536692619324,
      "learning_rate": 4.991627205825621e-05,
      "loss": 1.9228,
      "step": 40
    },
    {
      "epoch": 0.14628199918732224,
      "grad_norm": 0.9377800822257996,
      "learning_rate": 4.9894047545045605e-05,
      "loss": 1.835,
      "step": 45
    },
    {
      "epoch": 0.16253555465258024,
      "grad_norm": 0.8525241017341614,
      "learning_rate": 4.986921618977664e-05,
      "loss": 1.8157,
      "step": 50
    },
    {
      "epoch": 0.17878911011783827,
      "grad_norm": 0.872871458530426,
      "learning_rate": 4.984178059272638e-05,
      "loss": 1.8811,
      "step": 55
    },
    {
      "epoch": 0.1950426655830963,
      "grad_norm": 0.9125804305076599,
      "learning_rate": 4.981174362688158e-05,
      "loss": 1.8242,
      "step": 60
    },
    {
      "epoch": 0.21129622104835433,
      "grad_norm": 0.7474733591079712,
      "learning_rate": 4.977910843763777e-05,
      "loss": 1.7808,
      "step": 65
    },
    {
      "epoch": 0.22754977651361236,
      "grad_norm": 1.0248199701309204,
      "learning_rate": 4.974387844246987e-05,
      "loss": 1.8512,
      "step": 70
    },
    {
      "epoch": 0.24380333197887039,
      "grad_norm": 0.9032835960388184,
      "learning_rate": 4.970605733057441e-05,
      "loss": 1.8172,
      "step": 75
    },
    {
      "epoch": 0.2600568874441284,
      "grad_norm": 0.8550340533256531,
      "learning_rate": 4.9665649062483115e-05,
      "loss": 1.7418,
      "step": 80
    },
    {
      "epoch": 0.27631044290938644,
      "grad_norm": 0.9429016709327698,
      "learning_rate": 4.96226578696482e-05,
      "loss": 1.8265,
      "step": 85
    },
    {
      "epoch": 0.2925639983746445,
      "grad_norm": 0.975885272026062,
      "learning_rate": 4.957708825399927e-05,
      "loss": 1.7943,
      "step": 90
    },
    {
      "epoch": 0.3088175538399025,
      "grad_norm": 0.827629804611206,
      "learning_rate": 4.9528944987471884e-05,
      "loss": 1.8067,
      "step": 95
    },
    {
      "epoch": 0.3250711093051605,
      "grad_norm": 1.0019093751907349,
      "learning_rate": 4.9478233111507856e-05,
      "loss": 1.7874,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 1535,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.205535116204442e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}