{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9998833002684093,
  "eval_steps": 250,
  "global_step": 2142,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 3.3468704223632812,
      "learning_rate": 8.978253703087328e-05,
      "loss": 0.2775,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.15148572623729706,
      "eval_runtime": 39.6801,
      "eval_samples_per_second": 2.193,
      "eval_steps_per_second": 2.193,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 2.920819044113159,
      "learning_rate": 5.828471682626175e-05,
      "loss": 0.1133,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.1198219284415245,
      "eval_runtime": 39.745,
      "eval_samples_per_second": 2.189,
      "eval_steps_per_second": 2.189,
      "step": 500
    },
    {
      "epoch": 0.7001983895437041,
      "grad_norm": 2.5761032104492188,
      "learning_rate": 2.2174321662025427e-05,
      "loss": 0.0984,
      "step": 750
    },
    {
      "epoch": 0.7001983895437041,
      "eval_loss": 0.10974007099866867,
      "eval_runtime": 40.532,
      "eval_samples_per_second": 2.146,
      "eval_steps_per_second": 2.146,
      "step": 750
    },
    {
      "epoch": 0.9335978527249388,
      "grad_norm": 2.041003704071045,
      "learning_rate": 1.2487983905362933e-06,
      "loss": 0.0898,
      "step": 1000
    },
    {
      "epoch": 0.9335978527249388,
      "eval_loss": 0.10598217695951462,
      "eval_runtime": 40.54,
      "eval_samples_per_second": 2.146,
      "eval_steps_per_second": 2.146,
      "step": 1000
    },
    {
      "epoch": 1.167114015637764,
      "grad_norm": 2.1208701133728027,
      "learning_rate": 3.923237709089673e-05,
      "loss": 0.8209,
      "step": 1250
    },
    {
      "epoch": 1.167114015637764,
      "eval_loss": 0.12319507449865341,
      "eval_runtime": 22.336,
      "eval_samples_per_second": 3.895,
      "eval_steps_per_second": 3.895,
      "step": 1250
    },
    {
      "epoch": 1.4005134788189988,
      "grad_norm": 1.6080504655838013,
      "learning_rate": 2.202920942606599e-05,
      "loss": 0.7162,
      "step": 1500
    },
    {
      "epoch": 1.4005134788189988,
      "eval_loss": 0.11270491033792496,
      "eval_runtime": 22.3302,
      "eval_samples_per_second": 3.896,
      "eval_steps_per_second": 3.896,
      "step": 1500
    },
    {
      "epoch": 1.6339129420002334,
      "grad_norm": 1.914191484451294,
      "learning_rate": 8.704297796564736e-06,
      "loss": 0.6787,
      "step": 1750
    },
    {
      "epoch": 1.6339129420002334,
      "eval_loss": 0.10757231712341309,
      "eval_runtime": 22.3526,
      "eval_samples_per_second": 3.892,
      "eval_steps_per_second": 3.892,
      "step": 1750
    },
    {
      "epoch": 1.867312405181468,
      "grad_norm": 0.9888834953308105,
      "learning_rate": 1.2142463090958345e-06,
      "loss": 0.6495,
      "step": 2000
    },
    {
      "epoch": 1.867312405181468,
      "eval_loss": 0.10583414882421494,
      "eval_runtime": 22.2883,
      "eval_samples_per_second": 3.903,
      "eval_steps_per_second": 3.903,
      "step": 2000
    }
  ],
  "logging_steps": 250,
  "max_steps": 2142,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.719457385256407e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}