last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00028650216667263544,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8650216667263546e-05,
      "grad_norm": 1.1023699045181274,
      "learning_rate": 2e-05,
      "loss": 0.9984,
      "step": 1
    },
    {
      "epoch": 2.8650216667263546e-05,
      "eval_loss": 1.0276609659194946,
      "eval_runtime": 201.42,
      "eval_samples_per_second": 72.967,
      "eval_steps_per_second": 36.486,
      "step": 1
    },
    {
      "epoch": 5.730043333452709e-05,
      "grad_norm": 1.086967945098877,
      "learning_rate": 4e-05,
      "loss": 0.8721,
      "step": 2
    },
    {
      "epoch": 8.595065000179063e-05,
      "grad_norm": 1.4901301860809326,
      "learning_rate": 6e-05,
      "loss": 1.0657,
      "step": 3
    },
    {
      "epoch": 8.595065000179063e-05,
      "eval_loss": 1.0250277519226074,
      "eval_runtime": 201.3296,
      "eval_samples_per_second": 73.0,
      "eval_steps_per_second": 36.502,
      "step": 3
    },
    {
      "epoch": 0.00011460086666905418,
      "grad_norm": 1.1688634157180786,
      "learning_rate": 8e-05,
      "loss": 0.865,
      "step": 4
    },
    {
      "epoch": 0.00014325108333631772,
      "grad_norm": 1.052207589149475,
      "learning_rate": 0.0001,
      "loss": 0.9949,
      "step": 5
    },
    {
      "epoch": 0.00017190130000358127,
      "grad_norm": 0.9874056577682495,
      "learning_rate": 0.00012,
      "loss": 0.8694,
      "step": 6
    },
    {
      "epoch": 0.00017190130000358127,
      "eval_loss": 0.9844986200332642,
      "eval_runtime": 201.5424,
      "eval_samples_per_second": 72.923,
      "eval_steps_per_second": 36.464,
      "step": 6
    },
    {
      "epoch": 0.00020055151667084482,
      "grad_norm": 1.2436754703521729,
      "learning_rate": 0.00014,
      "loss": 0.7273,
      "step": 7
    },
    {
      "epoch": 0.00022920173333810837,
      "grad_norm": 0.8379012942314148,
      "learning_rate": 0.00016,
      "loss": 0.9509,
      "step": 8
    },
    {
      "epoch": 0.0002578519500053719,
      "grad_norm": 0.9932730197906494,
      "learning_rate": 0.00018,
      "loss": 0.8936,
      "step": 9
    },
    {
      "epoch": 0.0002578519500053719,
      "eval_loss": 0.9006158113479614,
      "eval_runtime": 213.2771,
      "eval_samples_per_second": 68.91,
      "eval_steps_per_second": 34.458,
      "step": 9
    },
    {
      "epoch": 0.00028650216667263544,
      "grad_norm": 0.7014549374580383,
      "learning_rate": 0.0002,
      "loss": 0.9925,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 68585300951040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}