last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015787396395211155,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001754155155023462,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 0.7932,
      "step": 1
    },
    {
      "epoch": 0.0001754155155023462,
      "eval_loss": 0.8225405812263489,
      "eval_runtime": 362.678,
      "eval_samples_per_second": 6.62,
      "eval_steps_per_second": 3.311,
      "step": 1
    },
    {
      "epoch": 0.0003508310310046924,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 0.7328,
      "step": 2
    },
    {
      "epoch": 0.0005262465465070386,
      "grad_norm": Infinity,
      "learning_rate": 6e-05,
      "loss": 0.7663,
      "step": 3
    },
    {
      "epoch": 0.0005262465465070386,
      "eval_loss": 0.8225405812263489,
      "eval_runtime": 363.1253,
      "eval_samples_per_second": 6.612,
      "eval_steps_per_second": 3.307,
      "step": 3
    },
    {
      "epoch": 0.0007016620620093847,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 0.7553,
      "step": 4
    },
    {
      "epoch": 0.0008770775775117309,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.6949,
      "step": 5
    },
    {
      "epoch": 0.0010524930930140772,
      "grad_norm": Infinity,
      "learning_rate": 0.00012,
      "loss": 0.861,
      "step": 6
    },
    {
      "epoch": 0.0010524930930140772,
      "eval_loss": 0.8225405812263489,
      "eval_runtime": 365.755,
      "eval_samples_per_second": 6.565,
      "eval_steps_per_second": 3.284,
      "step": 6
    },
    {
      "epoch": 0.0012279086085164232,
      "grad_norm": Infinity,
      "learning_rate": 0.00014,
      "loss": 0.8151,
      "step": 7
    },
    {
      "epoch": 0.0014033241240187695,
      "grad_norm": Infinity,
      "learning_rate": 0.00016,
      "loss": 0.8015,
      "step": 8
    },
    {
      "epoch": 0.0015787396395211155,
      "grad_norm": Infinity,
      "learning_rate": 0.00018,
      "loss": 0.962,
      "step": 9
    },
    {
      "epoch": 0.0015787396395211155,
      "eval_loss": 0.8225405812263489,
      "eval_runtime": 365.0236,
      "eval_samples_per_second": 6.578,
      "eval_steps_per_second": 3.29,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1852863789662208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}