last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008642855599490072,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8809518664966907e-05,
      "eval_loss": 11.131224632263184,
      "eval_runtime": 86.9571,
      "eval_samples_per_second": 168.071,
      "eval_steps_per_second": 84.041,
      "step": 1
    },
    {
      "epoch": 8.642855599490072e-05,
      "grad_norm": 1.3858121633529663,
      "learning_rate": 6e-05,
      "loss": 44.5363,
      "step": 3
    },
    {
      "epoch": 0.00014404759332483453,
      "eval_loss": 11.12358570098877,
      "eval_runtime": 88.8936,
      "eval_samples_per_second": 164.41,
      "eval_steps_per_second": 82.211,
      "step": 5
    },
    {
      "epoch": 0.00017285711198980144,
      "grad_norm": 1.541732668876648,
      "learning_rate": 0.00012,
      "loss": 44.4982,
      "step": 6
    },
    {
      "epoch": 0.00025928566798470216,
      "grad_norm": 1.2338385581970215,
      "learning_rate": 0.00018,
      "loss": 44.4534,
      "step": 9
    },
    {
      "epoch": 0.00028809518664966907,
      "eval_loss": 11.095381736755371,
      "eval_runtime": 88.0006,
      "eval_samples_per_second": 166.078,
      "eval_steps_per_second": 83.045,
      "step": 10
    },
    {
      "epoch": 0.0003457142239796029,
      "grad_norm": 1.6294808387756348,
      "learning_rate": 0.00019510565162951537,
      "loss": 44.3679,
      "step": 12
    },
    {
      "epoch": 0.0004321427799745036,
      "grad_norm": 1.6171613931655884,
      "learning_rate": 0.00017071067811865476,
      "loss": 44.2701,
      "step": 15
    },
    {
      "epoch": 0.0004321427799745036,
      "eval_loss": 11.05040168762207,
      "eval_runtime": 86.3803,
      "eval_samples_per_second": 169.194,
      "eval_steps_per_second": 84.603,
      "step": 15
    },
    {
      "epoch": 0.0005185713359694043,
      "grad_norm": 1.7718915939331055,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.1553,
      "step": 18
    },
    {
      "epoch": 0.0005761903732993381,
      "eval_loss": 11.011659622192383,
      "eval_runtime": 86.1634,
      "eval_samples_per_second": 169.62,
      "eval_steps_per_second": 84.816,
      "step": 20
    },
    {
      "epoch": 0.000604999891964305,
      "grad_norm": 2.065645456314087,
      "learning_rate": 8.435655349597689e-05,
      "loss": 44.0329,
      "step": 21
    },
    {
      "epoch": 0.0006914284479592058,
      "grad_norm": 1.887290358543396,
      "learning_rate": 4.12214747707527e-05,
      "loss": 44.0418,
      "step": 24
    },
    {
      "epoch": 0.0007202379666241726,
      "eval_loss": 10.990808486938477,
      "eval_runtime": 125.4459,
      "eval_samples_per_second": 116.504,
      "eval_steps_per_second": 58.256,
      "step": 25
    },
    {
      "epoch": 0.0007778570039541064,
      "grad_norm": 1.8186299800872803,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 43.9797,
      "step": 27
    },
    {
      "epoch": 0.0008642855599490072,
      "grad_norm": 2.0618233680725098,
      "learning_rate": 0.0,
      "loss": 43.9699,
      "step": 30
    },
    {
      "epoch": 0.0008642855599490072,
      "eval_loss": 10.986906051635742,
      "eval_runtime": 208.9452,
      "eval_samples_per_second": 69.947,
      "eval_steps_per_second": 34.976,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1128375779328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}