last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001134286974604575,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000126031886067175,
      "grad_norm": 0.7470651865005493,
      "learning_rate": 2e-05,
      "loss": 0.9771,
      "step": 1
    },
    {
      "epoch": 0.000126031886067175,
      "eval_loss": 1.1003992557525635,
      "eval_runtime": 65.535,
      "eval_samples_per_second": 50.98,
      "eval_steps_per_second": 25.498,
      "step": 1
    },
    {
      "epoch": 0.00025206377213435,
      "grad_norm": 0.8964004516601562,
      "learning_rate": 4e-05,
      "loss": 1.0398,
      "step": 2
    },
    {
      "epoch": 0.00037809565820152497,
      "grad_norm": 0.7652208209037781,
      "learning_rate": 6e-05,
      "loss": 1.0015,
      "step": 3
    },
    {
      "epoch": 0.00037809565820152497,
      "eval_loss": 1.0993669033050537,
      "eval_runtime": 65.4757,
      "eval_samples_per_second": 51.027,
      "eval_steps_per_second": 25.521,
      "step": 3
    },
    {
      "epoch": 0.0005041275442687,
      "grad_norm": 0.8987447023391724,
      "learning_rate": 8e-05,
      "loss": 1.0111,
      "step": 4
    },
    {
      "epoch": 0.0006301594303358749,
      "grad_norm": 0.7501655220985413,
      "learning_rate": 0.0001,
      "loss": 1.0644,
      "step": 5
    },
    {
      "epoch": 0.0007561913164030499,
      "grad_norm": 0.6338196992874146,
      "learning_rate": 0.00012,
      "loss": 0.9401,
      "step": 6
    },
    {
      "epoch": 0.0007561913164030499,
      "eval_loss": 1.0883917808532715,
      "eval_runtime": 66.1456,
      "eval_samples_per_second": 50.51,
      "eval_steps_per_second": 25.262,
      "step": 6
    },
    {
      "epoch": 0.000882223202470225,
      "grad_norm": 0.6224209070205688,
      "learning_rate": 0.00014,
      "loss": 0.9561,
      "step": 7
    },
    {
      "epoch": 0.0010082550885374,
      "grad_norm": 0.620303213596344,
      "learning_rate": 0.00016,
      "loss": 0.9573,
      "step": 8
    },
    {
      "epoch": 0.001134286974604575,
      "grad_norm": 0.907393217086792,
      "learning_rate": 0.00018,
      "loss": 1.1493,
      "step": 9
    },
    {
      "epoch": 0.001134286974604575,
      "eval_loss": 1.0724258422851562,
      "eval_runtime": 65.794,
      "eval_samples_per_second": 50.78,
      "eval_steps_per_second": 25.397,
      "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": 133557245706240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}