last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008230113987078721,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.23011398707872e-05,
      "grad_norm": 0.6557537913322449,
      "learning_rate": 2e-05,
      "loss": 1.5917,
      "step": 1
    },
    {
      "epoch": 8.23011398707872e-05,
      "eval_loss": 1.959477186203003,
      "eval_runtime": 135.3765,
      "eval_samples_per_second": 18.895,
      "eval_steps_per_second": 18.895,
      "step": 1
    },
    {
      "epoch": 0.0001646022797415744,
      "grad_norm": 0.7621749639511108,
      "learning_rate": 4e-05,
      "loss": 1.8288,
      "step": 2
    },
    {
      "epoch": 0.00024690341961236165,
      "grad_norm": 0.5589603781700134,
      "learning_rate": 6e-05,
      "loss": 1.0263,
      "step": 3
    },
    {
      "epoch": 0.00024690341961236165,
      "eval_loss": 1.957216739654541,
      "eval_runtime": 161.0963,
      "eval_samples_per_second": 15.879,
      "eval_steps_per_second": 15.879,
      "step": 3
    },
    {
      "epoch": 0.0003292045594831488,
      "grad_norm": 0.858914315700531,
      "learning_rate": 8e-05,
      "loss": 1.6087,
      "step": 4
    },
    {
      "epoch": 0.00041150569935393603,
      "grad_norm": 0.7685796618461609,
      "learning_rate": 0.0001,
      "loss": 1.3328,
      "step": 5
    },
    {
      "epoch": 0.0004938068392247233,
      "grad_norm": 0.6958107948303223,
      "learning_rate": 0.00012,
      "loss": 1.2796,
      "step": 6
    },
    {
      "epoch": 0.0004938068392247233,
      "eval_loss": 1.9416530132293701,
      "eval_runtime": 172.4872,
      "eval_samples_per_second": 14.83,
      "eval_steps_per_second": 14.83,
      "step": 6
    },
    {
      "epoch": 0.0005761079790955105,
      "grad_norm": 0.6250211000442505,
      "learning_rate": 0.00014,
      "loss": 1.3284,
      "step": 7
    },
    {
      "epoch": 0.0006584091189662976,
      "grad_norm": 0.9062594175338745,
      "learning_rate": 0.00016,
      "loss": 1.6334,
      "step": 8
    },
    {
      "epoch": 0.0007407102588370849,
      "grad_norm": 0.7678062319755554,
      "learning_rate": 0.00018,
      "loss": 1.4155,
      "step": 9
    },
    {
      "epoch": 0.0007407102588370849,
      "eval_loss": 1.9064750671386719,
      "eval_runtime": 170.6778,
      "eval_samples_per_second": 14.987,
      "eval_steps_per_second": 14.987,
      "step": 9
    },
    {
      "epoch": 0.0008230113987078721,
      "grad_norm": 1.5290422439575195,
      "learning_rate": 0.0002,
      "loss": 1.6838,
      "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": 240545515438080.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}