last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009550642280693377,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.550642280693377e-05,
      "grad_norm": 0.00904960185289383,
      "learning_rate": 2e-05,
      "loss": 12.46,
      "step": 1
    },
    {
      "epoch": 9.550642280693377e-05,
      "eval_loss": 12.458211898803711,
      "eval_runtime": 146.1943,
      "eval_samples_per_second": 15.083,
      "eval_steps_per_second": 15.083,
      "step": 1
    },
    {
      "epoch": 0.00019101284561386754,
      "grad_norm": 0.005639010574668646,
      "learning_rate": 4e-05,
      "loss": 12.4556,
      "step": 2
    },
    {
      "epoch": 0.0002865192684208013,
      "grad_norm": 0.006802282761782408,
      "learning_rate": 6e-05,
      "loss": 12.4572,
      "step": 3
    },
    {
      "epoch": 0.0002865192684208013,
      "eval_loss": 12.458206176757812,
      "eval_runtime": 147.1124,
      "eval_samples_per_second": 14.989,
      "eval_steps_per_second": 14.989,
      "step": 3
    },
    {
      "epoch": 0.0003820256912277351,
      "grad_norm": 0.00783372763544321,
      "learning_rate": 8e-05,
      "loss": 12.4541,
      "step": 4
    },
    {
      "epoch": 0.00047753211403466883,
      "grad_norm": 0.009479026310145855,
      "learning_rate": 0.0001,
      "loss": 12.4588,
      "step": 5
    },
    {
      "epoch": 0.0005730385368416026,
      "grad_norm": 0.009167061187326908,
      "learning_rate": 0.00012,
      "loss": 12.4607,
      "step": 6
    },
    {
      "epoch": 0.0005730385368416026,
      "eval_loss": 12.458182334899902,
      "eval_runtime": 146.2073,
      "eval_samples_per_second": 15.081,
      "eval_steps_per_second": 15.081,
      "step": 6
    },
    {
      "epoch": 0.0006685449596485364,
      "grad_norm": 0.006962459534406662,
      "learning_rate": 0.00014,
      "loss": 12.4595,
      "step": 7
    },
    {
      "epoch": 0.0007640513824554701,
      "grad_norm": 0.006850624922662973,
      "learning_rate": 0.00016,
      "loss": 12.4649,
      "step": 8
    },
    {
      "epoch": 0.0008595578052624039,
      "grad_norm": 0.005379276815801859,
      "learning_rate": 0.00018,
      "loss": 12.4595,
      "step": 9
    },
    {
      "epoch": 0.0008595578052624039,
      "eval_loss": 12.45814037322998,
      "eval_runtime": 146.2048,
      "eval_samples_per_second": 15.082,
      "eval_steps_per_second": 15.082,
      "step": 9
    },
    {
      "epoch": 0.0009550642280693377,
      "grad_norm": 0.006671583745628595,
      "learning_rate": 0.0002,
      "loss": 12.4563,
      "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": 6165626880.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}