last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0035420171787833173,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003542017178783317,
      "grad_norm": 0.781147837638855,
      "learning_rate": 2e-05,
      "loss": 2.0013,
      "step": 1
    },
    {
      "epoch": 0.0007084034357566634,
      "grad_norm": 0.5571944713592529,
      "learning_rate": 4e-05,
      "loss": 1.3801,
      "step": 2
    },
    {
      "epoch": 0.0010626051536349952,
      "grad_norm": 1.1020081043243408,
      "learning_rate": 6e-05,
      "loss": 2.4536,
      "step": 3
    },
    {
      "epoch": 0.0010626051536349952,
      "eval_loss": 2.3868155479431152,
      "eval_runtime": 89.3763,
      "eval_samples_per_second": 13.303,
      "eval_steps_per_second": 6.657,
      "step": 3
    },
    {
      "epoch": 0.0014168068715133268,
      "grad_norm": 0.7416192293167114,
      "learning_rate": 8e-05,
      "loss": 1.7618,
      "step": 4
    },
    {
      "epoch": 0.0017710085893916587,
      "grad_norm": 1.3207190036773682,
      "learning_rate": 0.0001,
      "loss": 2.6044,
      "step": 5
    },
    {
      "epoch": 0.0021252103072699905,
      "grad_norm": 1.1416175365447998,
      "learning_rate": 0.00012,
      "loss": 2.1539,
      "step": 6
    },
    {
      "epoch": 0.0021252103072699905,
      "eval_loss": 2.316065788269043,
      "eval_runtime": 84.663,
      "eval_samples_per_second": 14.044,
      "eval_steps_per_second": 7.028,
      "step": 6
    },
    {
      "epoch": 0.002479412025148322,
      "grad_norm": 1.0700939893722534,
      "learning_rate": 0.00014,
      "loss": 1.9569,
      "step": 7
    },
    {
      "epoch": 0.0028336137430266537,
      "grad_norm": 0.8500562906265259,
      "learning_rate": 0.00016,
      "loss": 1.7184,
      "step": 8
    },
    {
      "epoch": 0.0031878154609049853,
      "grad_norm": 1.1840053796768188,
      "learning_rate": 0.00018,
      "loss": 1.9608,
      "step": 9
    },
    {
      "epoch": 0.0031878154609049853,
      "eval_loss": 2.069765329360962,
      "eval_runtime": 83.9491,
      "eval_samples_per_second": 14.163,
      "eval_steps_per_second": 7.088,
      "step": 9
    },
    {
      "epoch": 0.0035420171787833173,
      "grad_norm": 0.544064998626709,
      "learning_rate": 0.0002,
      "loss": 1.2178,
      "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": 1988281566756864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}