checkpoint-220/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 220,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 8.667610168457031,
      "learning_rate": 1.9181818181818183e-05,
      "loss": 0.5911,
      "step": 10
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 6.615207672119141,
      "learning_rate": 1.8272727272727275e-05,
      "loss": 0.464,
      "step": 20
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 13.182315826416016,
      "learning_rate": 1.7363636363636363e-05,
      "loss": 0.3223,
      "step": 30
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 8.283531188964844,
      "learning_rate": 1.6454545454545455e-05,
      "loss": 0.2932,
      "step": 40
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 2.350064277648926,
      "learning_rate": 1.5545454545454547e-05,
      "loss": 0.3104,
      "step": 50
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.3099472522735596,
      "learning_rate": 1.4636363636363637e-05,
      "loss": 0.2794,
      "step": 60
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.701838493347168,
      "learning_rate": 1.3727272727272729e-05,
      "loss": 0.1536,
      "step": 70
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.7129743695259094,
      "learning_rate": 1.281818181818182e-05,
      "loss": 0.2083,
      "step": 80
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 5.099246025085449,
      "learning_rate": 1.190909090909091e-05,
      "loss": 0.1498,
      "step": 90
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 25.056194305419922,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.2337,
      "step": 100
    },
    {
      "epoch": 2.5,
      "grad_norm": 27.893611907958984,
      "learning_rate": 1.0090909090909092e-05,
      "loss": 0.1566,
      "step": 110
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.9230498671531677,
      "learning_rate": 9.181818181818184e-06,
      "loss": 0.1208,
      "step": 120
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.20559445023536682,
      "learning_rate": 8.272727272727274e-06,
      "loss": 0.2526,
      "step": 130
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 8.288787841796875,
      "learning_rate": 7.363636363636364e-06,
      "loss": 0.1241,
      "step": 140
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 0.2578887343406677,
      "learning_rate": 6.454545454545456e-06,
      "loss": 0.1863,
      "step": 150
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.26157981157302856,
      "learning_rate": 5.545454545454546e-06,
      "loss": 0.1131,
      "step": 160
    },
    {
      "epoch": 3.8636363636363638,
      "grad_norm": 10.041345596313477,
      "learning_rate": 4.636363636363636e-06,
      "loss": 0.1458,
      "step": 170
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 0.2509705126285553,
      "learning_rate": 3.727272727272728e-06,
      "loss": 0.0781,
      "step": 180
    },
    {
      "epoch": 4.318181818181818,
      "grad_norm": 0.141200453042984,
      "learning_rate": 2.818181818181818e-06,
      "loss": 0.1208,
      "step": 190
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.3103751242160797,
      "learning_rate": 1.9090909090909095e-06,
      "loss": 0.0898,
      "step": 200
    },
    {
      "epoch": 4.7727272727272725,
      "grad_norm": 0.1590297371149063,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1013,
      "step": 210
    },
    {
      "epoch": 5.0,
      "grad_norm": 67.25486755371094,
      "learning_rate": 9.090909090909091e-08,
      "loss": 0.2334,
      "step": 220
    }
  ],
  "logging_steps": 10,
  "max_steps": 220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 124877726925996.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}