last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.127659574468085,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010638297872340425,
      "eval_loss": 2.7702033519744873,
      "eval_runtime": 30.6604,
      "eval_samples_per_second": 48.956,
      "eval_steps_per_second": 6.132,
      "step": 1
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 5.40625,
      "learning_rate": 8e-05,
      "loss": 2.0559,
      "step": 10
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 5.25,
      "learning_rate": 0.00016,
      "loss": 2.0743,
      "step": 20
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 5.75,
      "learning_rate": 0.00019994532573409262,
      "loss": 2.4587,
      "step": 30
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 6.03125,
      "learning_rate": 0.00019950829025450114,
      "loss": 2.6661,
      "step": 40
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 6.75,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.8731,
      "step": 50
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 4.0625,
      "learning_rate": 0.0001973326597248006,
      "loss": 2.8111,
      "step": 60
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 5.59375,
      "learning_rate": 0.00019560357815343577,
      "loss": 2.8978,
      "step": 70
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 7.09375,
      "learning_rate": 0.0001934564464599461,
      "loss": 2.9503,
      "step": 80
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 10.125,
      "learning_rate": 0.00019090065350491626,
      "loss": 2.9875,
      "step": 90
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 5.34375,
      "learning_rate": 0.0001879473751206489,
      "loss": 2.1433,
      "step": 100
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 5.1875,
      "learning_rate": 0.00018460952524209355,
      "loss": 1.4928,
      "step": 110
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 4.90625,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.6588,
      "step": 120
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 4.59375,
      "learning_rate": 0.00017684011108568592,
      "loss": 1.5762,
      "step": 130
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 4.46875,
      "learning_rate": 0.00017244252047910892,
      "loss": 1.6862,
      "step": 140
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 4.59375,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.6834,
      "step": 150
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 4.46875,
      "learning_rate": 0.0001627176358473537,
      "loss": 1.6762,
      "step": 160
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 4.5625,
      "learning_rate": 0.00015743286626829437,
      "loss": 1.7259,
      "step": 170
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 4.84375,
      "learning_rate": 0.00015189695737812152,
      "loss": 1.8411,
      "step": 180
    },
    {
      "epoch": 2.021276595744681,
      "grad_norm": 3.53125,
      "learning_rate": 0.0001461341162978688,
      "loss": 1.5208,
      "step": 190
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 2.75,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.6512,
      "step": 200
    },
    {
      "epoch": 2.127659574468085,
      "eval_loss": 3.396796941757202,
      "eval_runtime": 28.9515,
      "eval_samples_per_second": 51.845,
      "eval_steps_per_second": 6.494,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4755282835996672e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}