checkpoint-1500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04595517838268409,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003063678558845606,
      "grad_norm": 2.5270798206329346,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.1564,
      "step": 100
    },
    {
      "epoch": 0.006127357117691212,
      "grad_norm": 2.604092597961426,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.1166,
      "step": 200
    },
    {
      "epoch": 0.009191035676536818,
      "grad_norm": 2.5005924701690674,
      "learning_rate": 3e-06,
      "loss": 3.0905,
      "step": 300
    },
    {
      "epoch": 0.012254714235382424,
      "grad_norm": 2.7525177001953125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.0652,
      "step": 400
    },
    {
      "epoch": 0.015318392794228029,
      "grad_norm": 2.5251283645629883,
      "learning_rate": 5e-06,
      "loss": 3.0351,
      "step": 500
    },
    {
      "epoch": 0.018382071353073636,
      "grad_norm": 2.6771860122680664,
      "learning_rate": 6e-06,
      "loss": 3.0028,
      "step": 600
    },
    {
      "epoch": 0.02144574991191924,
      "grad_norm": 2.4799458980560303,
      "learning_rate": 7e-06,
      "loss": 3.0007,
      "step": 700
    },
    {
      "epoch": 0.024509428470764847,
      "grad_norm": 2.8402369022369385,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.9753,
      "step": 800
    },
    {
      "epoch": 0.027573107029610452,
      "grad_norm": 2.446842908859253,
      "learning_rate": 9e-06,
      "loss": 2.9737,
      "step": 900
    },
    {
      "epoch": 0.030636785588456058,
      "grad_norm": 2.3989391326904297,
      "learning_rate": 1e-05,
      "loss": 2.9618,
      "step": 1000
    },
    {
      "epoch": 0.03370046414730166,
      "grad_norm": 2.469160795211792,
      "learning_rate": 9.99695413509548e-06,
      "loss": 2.928,
      "step": 1100
    },
    {
      "epoch": 0.03676414270614727,
      "grad_norm": 2.4107494354248047,
      "learning_rate": 9.987820251299121e-06,
      "loss": 2.9214,
      "step": 1200
    },
    {
      "epoch": 0.039827821264992874,
      "grad_norm": 2.540278911590576,
      "learning_rate": 9.972609476841368e-06,
      "loss": 2.9198,
      "step": 1300
    },
    {
      "epoch": 0.04289149982383848,
      "grad_norm": 2.4398670196533203,
      "learning_rate": 9.951340343707852e-06,
      "loss": 2.9182,
      "step": 1400
    },
    {
      "epoch": 0.04595517838268409,
      "grad_norm": 2.49687123298645,
      "learning_rate": 9.924038765061042e-06,
      "loss": 2.8994,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 10000,
  "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": 1.43496233091072e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}