last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007620934707641893,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.620934707641892e-05,
      "grad_norm": 2.96830415725708,
      "learning_rate": 2e-05,
      "loss": 7.9647,
      "step": 1
    },
    {
      "epoch": 7.620934707641892e-05,
      "eval_loss": 1.8767974376678467,
      "eval_runtime": 162.5624,
      "eval_samples_per_second": 33.987,
      "eval_steps_per_second": 16.997,
      "step": 1
    },
    {
      "epoch": 0.00015241869415283783,
      "grad_norm": 3.3713619709014893,
      "learning_rate": 4e-05,
      "loss": 7.0786,
      "step": 2
    },
    {
      "epoch": 0.00022862804122925678,
      "grad_norm": 3.96400785446167,
      "learning_rate": 6e-05,
      "loss": 8.3758,
      "step": 3
    },
    {
      "epoch": 0.00022862804122925678,
      "eval_loss": 1.8678418397903442,
      "eval_runtime": 162.4757,
      "eval_samples_per_second": 34.005,
      "eval_steps_per_second": 17.006,
      "step": 3
    },
    {
      "epoch": 0.00030483738830567567,
      "grad_norm": 3.0439226627349854,
      "learning_rate": 8e-05,
      "loss": 6.9977,
      "step": 4
    },
    {
      "epoch": 0.00038104673538209464,
      "grad_norm": 4.791325092315674,
      "learning_rate": 0.0001,
      "loss": 7.0244,
      "step": 5
    },
    {
      "epoch": 0.00045725608245851356,
      "grad_norm": 4.13270378112793,
      "learning_rate": 0.00012,
      "loss": 6.8967,
      "step": 6
    },
    {
      "epoch": 0.00045725608245851356,
      "eval_loss": 1.7656927108764648,
      "eval_runtime": 162.9982,
      "eval_samples_per_second": 33.896,
      "eval_steps_per_second": 16.951,
      "step": 6
    },
    {
      "epoch": 0.0005334654295349325,
      "grad_norm": 4.542642116546631,
      "learning_rate": 0.00014,
      "loss": 6.9806,
      "step": 7
    },
    {
      "epoch": 0.0006096747766113513,
      "grad_norm": 3.3268468379974365,
      "learning_rate": 0.00016,
      "loss": 6.7394,
      "step": 8
    },
    {
      "epoch": 0.0006858841236877703,
      "grad_norm": 2.629209518432617,
      "learning_rate": 0.00018,
      "loss": 8.0235,
      "step": 9
    },
    {
      "epoch": 0.0006858841236877703,
      "eval_loss": 1.5179685354232788,
      "eval_runtime": 162.9814,
      "eval_samples_per_second": 33.9,
      "eval_steps_per_second": 16.953,
      "step": 9
    },
    {
      "epoch": 0.0007620934707641893,
      "grad_norm": 1.3314701318740845,
      "learning_rate": 0.0002,
      "loss": 5.9379,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 963851046617088.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}