checkpoint-3000/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.47679593134138587,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01589319771137953,
      "grad_norm": 0.9081700444221497,
      "learning_rate": 0.0002,
      "loss": 2.3142,
      "step": 100
    },
    {
      "epoch": 0.03178639542275906,
      "grad_norm": 0.8463758826255798,
      "learning_rate": 0.0002,
      "loss": 2.0015,
      "step": 200
    },
    {
      "epoch": 0.04767959313413859,
      "grad_norm": 1.0305041074752808,
      "learning_rate": 0.0002,
      "loss": 1.9429,
      "step": 300
    },
    {
      "epoch": 0.06357279084551812,
      "grad_norm": 0.48407527804374695,
      "learning_rate": 0.0002,
      "loss": 1.9406,
      "step": 400
    },
    {
      "epoch": 0.07946598855689765,
      "grad_norm": 0.9855284690856934,
      "learning_rate": 0.0002,
      "loss": 1.79,
      "step": 500
    },
    {
      "epoch": 0.09535918626827718,
      "grad_norm": 0.8263546228408813,
      "learning_rate": 0.0002,
      "loss": 1.7586,
      "step": 600
    },
    {
      "epoch": 0.11125238397965671,
      "grad_norm": 1.258915901184082,
      "learning_rate": 0.0002,
      "loss": 1.628,
      "step": 700
    },
    {
      "epoch": 0.12714558169103624,
      "grad_norm": 0.7160557508468628,
      "learning_rate": 0.0002,
      "loss": 1.4786,
      "step": 800
    },
    {
      "epoch": 0.14303877940241577,
      "grad_norm": 2.1789512634277344,
      "learning_rate": 0.0002,
      "loss": 1.4301,
      "step": 900
    },
    {
      "epoch": 0.1589319771137953,
      "grad_norm": 0.34466424584388733,
      "learning_rate": 0.0002,
      "loss": 1.5137,
      "step": 1000
    },
    {
      "epoch": 0.17482517482517482,
      "grad_norm": 1.9239227771759033,
      "learning_rate": 0.0002,
      "loss": 1.4945,
      "step": 1100
    },
    {
      "epoch": 0.19071837253655435,
      "grad_norm": 1.7776683568954468,
      "learning_rate": 0.0002,
      "loss": 1.3702,
      "step": 1200
    },
    {
      "epoch": 0.2066115702479339,
      "grad_norm": 1.5118937492370605,
      "learning_rate": 0.0002,
      "loss": 1.4384,
      "step": 1300
    },
    {
      "epoch": 0.22250476795931343,
      "grad_norm": 1.504011869430542,
      "learning_rate": 0.0002,
      "loss": 1.3728,
      "step": 1400
    },
    {
      "epoch": 0.23839796567069294,
      "grad_norm": 0.8850716352462769,
      "learning_rate": 0.0002,
      "loss": 1.4082,
      "step": 1500
    },
    {
      "epoch": 0.25429116338207247,
      "grad_norm": 0.7327104210853577,
      "learning_rate": 0.0002,
      "loss": 1.3342,
      "step": 1600
    },
    {
      "epoch": 0.270184361093452,
      "grad_norm": 0.9595212936401367,
      "learning_rate": 0.0002,
      "loss": 1.3882,
      "step": 1700
    },
    {
      "epoch": 0.28607755880483154,
      "grad_norm": 2.5830607414245605,
      "learning_rate": 0.0002,
      "loss": 1.2326,
      "step": 1800
    },
    {
      "epoch": 0.3019707565162111,
      "grad_norm": 1.852844476699829,
      "learning_rate": 0.0002,
      "loss": 1.3595,
      "step": 1900
    },
    {
      "epoch": 0.3178639542275906,
      "grad_norm": 1.6929068565368652,
      "learning_rate": 0.0002,
      "loss": 1.0967,
      "step": 2000
    },
    {
      "epoch": 0.3337571519389701,
      "grad_norm": 1.2370538711547852,
      "learning_rate": 0.0002,
      "loss": 1.3132,
      "step": 2100
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 1.0512717962265015,
      "learning_rate": 0.0002,
      "loss": 1.2205,
      "step": 2200
    },
    {
      "epoch": 0.36554354736172917,
      "grad_norm": 2.0815775394439697,
      "learning_rate": 0.0002,
      "loss": 1.2684,
      "step": 2300
    },
    {
      "epoch": 0.3814367450731087,
      "grad_norm": 1.7328189611434937,
      "learning_rate": 0.0002,
      "loss": 1.0058,
      "step": 2400
    },
    {
      "epoch": 0.39732994278448824,
      "grad_norm": 1.8121742010116577,
      "learning_rate": 0.0002,
      "loss": 1.1701,
      "step": 2500
    },
    {
      "epoch": 0.4132231404958678,
      "grad_norm": 1.3292349576950073,
      "learning_rate": 0.0002,
      "loss": 1.1467,
      "step": 2600
    },
    {
      "epoch": 0.4291163382072473,
      "grad_norm": 1.1031920909881592,
      "learning_rate": 0.0002,
      "loss": 1.2143,
      "step": 2700
    },
    {
      "epoch": 0.44500953591862685,
      "grad_norm": 1.3371531963348389,
      "learning_rate": 0.0002,
      "loss": 0.996,
      "step": 2800
    },
    {
      "epoch": 0.46090273363000633,
      "grad_norm": 0.6710326671600342,
      "learning_rate": 0.0002,
      "loss": 0.9845,
      "step": 2900
    },
    {
      "epoch": 0.47679593134138587,
      "grad_norm": 0.930266797542572,
      "learning_rate": 0.0002,
      "loss": 1.0894,
      "step": 3000
    }
  ],
  "logging_steps": 100,
  "max_steps": 6292,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5300629102592e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}