last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1052631578947367,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 2.373548746109009,
      "eval_runtime": 30.8211,
      "eval_samples_per_second": 48.7,
      "eval_steps_per_second": 6.1,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 4.1875,
      "learning_rate": 8e-05,
      "loss": 1.916,
      "step": 10
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 3.21875,
      "learning_rate": 0.00016,
      "loss": 1.8779,
      "step": 20
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 2.515625,
      "learning_rate": 0.00019994532573409262,
      "loss": 2.1362,
      "step": 30
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 2.296875,
      "learning_rate": 0.00019950829025450114,
      "loss": 2.3736,
      "step": 40
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 3.15625,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.4914,
      "step": 50
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 2.46875,
      "learning_rate": 0.0001973326597248006,
      "loss": 2.5562,
      "step": 60
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 3.953125,
      "learning_rate": 0.00019560357815343577,
      "loss": 2.7778,
      "step": 70
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 4.5625,
      "learning_rate": 0.0001934564464599461,
      "loss": 2.6995,
      "step": 80
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 17.0,
      "learning_rate": 0.00019090065350491626,
      "loss": 2.619,
      "step": 90
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 2.65625,
      "learning_rate": 0.0001879473751206489,
      "loss": 1.9637,
      "step": 100
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 2.15625,
      "learning_rate": 0.00018460952524209355,
      "loss": 1.1648,
      "step": 110
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 1.8125,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.2698,
      "step": 120
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 2.265625,
      "learning_rate": 0.00017684011108568592,
      "loss": 1.2703,
      "step": 130
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 2.1875,
      "learning_rate": 0.00017244252047910892,
      "loss": 1.3674,
      "step": 140
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 2.0625,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.3329,
      "step": 150
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 2.90625,
      "learning_rate": 0.0001627176358473537,
      "loss": 1.3702,
      "step": 160
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 2.078125,
      "learning_rate": 0.00015743286626829437,
      "loss": 1.3481,
      "step": 170
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 2.1875,
      "learning_rate": 0.00015189695737812152,
      "loss": 1.4838,
      "step": 180
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.046875,
      "learning_rate": 0.0001461341162978688,
      "loss": 1.3654,
      "step": 190
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.517,
      "step": 200
    },
    {
      "epoch": 2.1052631578947367,
      "eval_loss": 3.045600652694702,
      "eval_runtime": 29.0213,
      "eval_samples_per_second": 51.721,
      "eval_steps_per_second": 6.478,
      "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": 1.3898457261539328e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}