trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.9890895485877991,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.709,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.568547248840332,
      "learning_rate": 4.951963201008076e-05,
      "loss": 0.1543,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.757222056388855,
      "learning_rate": 4.721114089947181e-05,
      "loss": 0.1166,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0231865644454956,
      "learning_rate": 4.316650805085068e-05,
      "loss": 0.1208,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6902381777763367,
      "learning_rate": 3.770188363116324e-05,
      "loss": 0.092,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7536186575889587,
      "learning_rate": 3.1244411954180676e-05,
      "loss": 0.0878,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.343789279460907,
      "learning_rate": 2.429884359310328e-05,
      "loss": 0.0798,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.6155710816383362,
      "learning_rate": 1.7408081372259632e-05,
      "loss": 0.093,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4667530655860901,
      "learning_rate": 1.1110744174509952e-05,
      "loss": 0.0705,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.176645278930664,
      "learning_rate": 5.899065604459814e-06,
      "loss": 0.0577,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.32808709144592285,
      "learning_rate": 2.1804183734670277e-06,
      "loss": 0.058,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.5392273664474487,
      "learning_rate": 2.454718665888589e-07,
      "loss": 0.0863,
      "step": 120
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 3934658943516672.0,
      "train_loss": 0.13944334506988526,
      "train_runtime": 795.412,
      "train_samples_per_second": 1.257,
      "train_steps_per_second": 0.157
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3934658943516672.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}