last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7003720726636026,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035018603633180127,
      "eval_loss": NaN,
      "eval_runtime": 95.4561,
      "eval_samples_per_second": 5.039,
      "eval_steps_per_second": 2.525,
      "step": 1
    },
    {
      "epoch": 0.14007441453272051,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.14007441453272051,
      "eval_loss": NaN,
      "eval_runtime": 94.0732,
      "eval_samples_per_second": 5.113,
      "eval_steps_per_second": 2.562,
      "step": 40
    },
    {
      "epoch": 0.28014882906544103,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.28014882906544103,
      "eval_loss": NaN,
      "eval_runtime": 94.0054,
      "eval_samples_per_second": 5.117,
      "eval_steps_per_second": 2.564,
      "step": 80
    },
    {
      "epoch": 0.42022324359816154,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.42022324359816154,
      "eval_loss": NaN,
      "eval_runtime": 94.067,
      "eval_samples_per_second": 5.113,
      "eval_steps_per_second": 2.562,
      "step": 120
    },
    {
      "epoch": 0.5602976581308821,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.5602976581308821,
      "eval_loss": NaN,
      "eval_runtime": 94.0318,
      "eval_samples_per_second": 5.115,
      "eval_steps_per_second": 2.563,
      "step": 160
    },
    {
      "epoch": 0.7003720726636026,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.7003720726636026,
      "eval_loss": NaN,
      "eval_runtime": 94.0957,
      "eval_samples_per_second": 5.112,
      "eval_steps_per_second": 2.561,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.0224916726494e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}