last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013691596782474755,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002738319356494951,
      "grad_norm": 0.4893011152744293,
      "learning_rate": 1e-05,
      "loss": 0.8538,
      "step": 1
    },
    {
      "epoch": 0.002738319356494951,
      "eval_loss": 0.9573982357978821,
      "eval_runtime": 157.5057,
      "eval_samples_per_second": 3.905,
      "eval_steps_per_second": 1.955,
      "step": 1
    },
    {
      "epoch": 0.005476638712989902,
      "grad_norm": 0.5565076470375061,
      "learning_rate": 2e-05,
      "loss": 0.943,
      "step": 2
    },
    {
      "epoch": 0.005476638712989902,
      "eval_loss": 0.95511794090271,
      "eval_runtime": 9.4384,
      "eval_samples_per_second": 65.159,
      "eval_steps_per_second": 32.633,
      "step": 2
    },
    {
      "epoch": 0.008214958069484853,
      "grad_norm": 0.4042225480079651,
      "learning_rate": 3e-05,
      "loss": 0.8588,
      "step": 3
    },
    {
      "epoch": 0.010953277425979804,
      "grad_norm": 0.4440908432006836,
      "learning_rate": 4e-05,
      "loss": 0.8743,
      "step": 4
    },
    {
      "epoch": 0.010953277425979804,
      "eval_loss": 0.9426833987236023,
      "eval_runtime": 9.4251,
      "eval_samples_per_second": 65.251,
      "eval_steps_per_second": 32.679,
      "step": 4
    },
    {
      "epoch": 0.013691596782474755,
      "grad_norm": 0.3984867036342621,
      "learning_rate": 5e-05,
      "loss": 0.7452,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1337760359645184.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}