last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002022346933616462,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002022346933616462,
      "grad_norm": 0.3922646641731262,
      "learning_rate": 2e-05,
      "loss": 2.245,
      "step": 1
    },
    {
      "epoch": 0.0002022346933616462,
      "eval_loss": 2.176133394241333,
      "eval_runtime": 131.4289,
      "eval_samples_per_second": 7.921,
      "eval_steps_per_second": 7.921,
      "step": 1
    },
    {
      "epoch": 0.0004044693867232924,
      "grad_norm": 0.6289243698120117,
      "learning_rate": 4e-05,
      "loss": 2.22,
      "step": 2
    },
    {
      "epoch": 0.0004044693867232924,
      "eval_loss": 2.17583966255188,
      "eval_runtime": 131.5098,
      "eval_samples_per_second": 7.916,
      "eval_steps_per_second": 7.916,
      "step": 2
    },
    {
      "epoch": 0.0006067040800849386,
      "grad_norm": 0.3943503201007843,
      "learning_rate": 6e-05,
      "loss": 2.071,
      "step": 3
    },
    {
      "epoch": 0.0008089387734465848,
      "grad_norm": 0.7399203777313232,
      "learning_rate": 8e-05,
      "loss": 1.9578,
      "step": 4
    },
    {
      "epoch": 0.0008089387734465848,
      "eval_loss": 2.170461654663086,
      "eval_runtime": 131.7128,
      "eval_samples_per_second": 7.904,
      "eval_steps_per_second": 7.904,
      "step": 4
    },
    {
      "epoch": 0.001011173466808231,
      "grad_norm": 0.3636244535446167,
      "learning_rate": 0.0001,
      "loss": 2.1186,
      "step": 5
    },
    {
      "epoch": 0.0012134081601698772,
      "grad_norm": 0.4586368799209595,
      "learning_rate": 0.00012,
      "loss": 1.9298,
      "step": 6
    },
    {
      "epoch": 0.0012134081601698772,
      "eval_loss": 2.1426615715026855,
      "eval_runtime": 131.861,
      "eval_samples_per_second": 7.895,
      "eval_steps_per_second": 7.895,
      "step": 6
    },
    {
      "epoch": 0.0014156428535315234,
      "grad_norm": 0.4819552004337311,
      "learning_rate": 0.00014,
      "loss": 2.2254,
      "step": 7
    },
    {
      "epoch": 0.0016178775468931696,
      "grad_norm": 0.34892919659614563,
      "learning_rate": 0.00016,
      "loss": 2.3499,
      "step": 8
    },
    {
      "epoch": 0.0016178775468931696,
      "eval_loss": 2.0889296531677246,
      "eval_runtime": 131.8555,
      "eval_samples_per_second": 7.895,
      "eval_steps_per_second": 7.895,
      "step": 8
    },
    {
      "epoch": 0.0018201122402548156,
      "grad_norm": 1.2191482782363892,
      "learning_rate": 0.00018,
      "loss": 1.9804,
      "step": 9
    },
    {
      "epoch": 0.002022346933616462,
      "grad_norm": 0.34325483441352844,
      "learning_rate": 0.0002,
      "loss": 2.0201,
      "step": 10
    },
    {
      "epoch": 0.002022346933616462,
      "eval_loss": 2.0338456630706787,
      "eval_runtime": 131.8006,
      "eval_samples_per_second": 7.898,
      "eval_steps_per_second": 7.898,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "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": 2794842929233920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}