last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11782032400589101,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00235640648011782,
      "eval_loss": 1.2666594982147217,
      "eval_runtime": 181.2818,
      "eval_samples_per_second": 3.944,
      "eval_steps_per_second": 1.975,
      "step": 1
    },
    {
      "epoch": 0.023564064801178203,
      "grad_norm": 12.266291618347168,
      "learning_rate": 2e-05,
      "loss": 19.7628,
      "step": 10
    },
    {
      "epoch": 0.023564064801178203,
      "eval_loss": 1.2563062906265259,
      "eval_runtime": 181.3336,
      "eval_samples_per_second": 3.943,
      "eval_steps_per_second": 1.974,
      "step": 10
    },
    {
      "epoch": 0.047128129602356406,
      "grad_norm": 15.010481834411621,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 19.3008,
      "step": 20
    },
    {
      "epoch": 0.047128129602356406,
      "eval_loss": 1.2074867486953735,
      "eval_runtime": 182.2349,
      "eval_samples_per_second": 3.924,
      "eval_steps_per_second": 1.964,
      "step": 20
    },
    {
      "epoch": 0.07069219440353461,
      "grad_norm": 14.47107219696045,
      "learning_rate": 1e-05,
      "loss": 18.0378,
      "step": 30
    },
    {
      "epoch": 0.07069219440353461,
      "eval_loss": 1.1676819324493408,
      "eval_runtime": 182.525,
      "eval_samples_per_second": 3.917,
      "eval_steps_per_second": 1.961,
      "step": 30
    },
    {
      "epoch": 0.09425625920471281,
      "grad_norm": 21.754932403564453,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 17.9564,
      "step": 40
    },
    {
      "epoch": 0.09425625920471281,
      "eval_loss": 1.1547653675079346,
      "eval_runtime": 181.1181,
      "eval_samples_per_second": 3.948,
      "eval_steps_per_second": 1.977,
      "step": 40
    },
    {
      "epoch": 0.11782032400589101,
      "grad_norm": 13.211586952209473,
      "learning_rate": 0.0,
      "loss": 18.4396,
      "step": 50
    },
    {
      "epoch": 0.11782032400589101,
      "eval_loss": 1.1526776552200317,
      "eval_runtime": 180.9851,
      "eval_samples_per_second": 3.951,
      "eval_steps_per_second": 1.978,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "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": 4.955673819768422e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}