laptop-tinyllama/checkpoint-350/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.56,
  "eval_steps": 500,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032,
      "grad_norm": 671614.75,
      "learning_rate": 4.9493333333333336e-05,
      "loss": 2.1669,
      "step": 20
    },
    {
      "epoch": 0.064,
      "grad_norm": 41173.5,
      "learning_rate": 4.896e-05,
      "loss": 0.5516,
      "step": 40
    },
    {
      "epoch": 0.096,
      "grad_norm": 14334.6923828125,
      "learning_rate": 4.842666666666667e-05,
      "loss": 0.2249,
      "step": 60
    },
    {
      "epoch": 0.128,
      "grad_norm": 14753.2421875,
      "learning_rate": 4.789333333333334e-05,
      "loss": 0.1644,
      "step": 80
    },
    {
      "epoch": 0.16,
      "grad_norm": 12797.7333984375,
      "learning_rate": 4.736000000000001e-05,
      "loss": 0.103,
      "step": 100
    },
    {
      "epoch": 0.192,
      "grad_norm": 12743.939453125,
      "learning_rate": 4.682666666666667e-05,
      "loss": 0.0684,
      "step": 120
    },
    {
      "epoch": 0.224,
      "grad_norm": 10378.1640625,
      "learning_rate": 4.629333333333333e-05,
      "loss": 0.0495,
      "step": 140
    },
    {
      "epoch": 0.256,
      "grad_norm": 8000.236328125,
      "learning_rate": 4.576e-05,
      "loss": 0.0404,
      "step": 160
    },
    {
      "epoch": 0.288,
      "grad_norm": 8669.037109375,
      "learning_rate": 4.5226666666666665e-05,
      "loss": 0.0356,
      "step": 180
    },
    {
      "epoch": 0.32,
      "grad_norm": 8630.375,
      "learning_rate": 4.4693333333333335e-05,
      "loss": 0.0291,
      "step": 200
    },
    {
      "epoch": 0.352,
      "grad_norm": 8318.3955078125,
      "learning_rate": 4.4160000000000004e-05,
      "loss": 0.0285,
      "step": 220
    },
    {
      "epoch": 0.384,
      "grad_norm": 7282.09619140625,
      "learning_rate": 4.3626666666666674e-05,
      "loss": 0.0282,
      "step": 240
    },
    {
      "epoch": 0.416,
      "grad_norm": 7333.845703125,
      "learning_rate": 4.3093333333333336e-05,
      "loss": 0.028,
      "step": 260
    },
    {
      "epoch": 0.448,
      "grad_norm": 8852.5693359375,
      "learning_rate": 4.256e-05,
      "loss": 0.0312,
      "step": 280
    },
    {
      "epoch": 0.48,
      "grad_norm": 6368.5595703125,
      "learning_rate": 4.202666666666667e-05,
      "loss": 0.0279,
      "step": 300
    },
    {
      "epoch": 0.512,
      "grad_norm": 7761.8134765625,
      "learning_rate": 4.149333333333333e-05,
      "loss": 0.0277,
      "step": 320
    },
    {
      "epoch": 0.544,
      "grad_norm": 6672.0615234375,
      "learning_rate": 4.096e-05,
      "loss": 0.0276,
      "step": 340
    }
  ],
  "logging_steps": 20,
  "max_steps": 1875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8908150564454400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}