{
  "best_global_step": 1100,
  "best_metric": 0.07910037785768509,
  "best_model_checkpoint": "OpenAHA-Calvin-2p-3b/checkpoint-1100",
  "epoch": 2.9121644017235666,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2651640702684786,
      "eval_loss": 0.1917700171470642,
      "eval_runtime": 35.1714,
      "eval_samples_per_second": 5.772,
      "eval_steps_per_second": 0.739,
      "step": 100
    },
    {
      "epoch": 0.5303281405369572,
      "eval_loss": 0.13455702364444733,
      "eval_runtime": 33.0746,
      "eval_samples_per_second": 6.138,
      "eval_steps_per_second": 0.786,
      "step": 200
    },
    {
      "epoch": 0.7954922108054359,
      "eval_loss": 0.1287507265806198,
      "eval_runtime": 36.6447,
      "eval_samples_per_second": 5.54,
      "eval_steps_per_second": 0.71,
      "step": 300
    },
    {
      "epoch": 1.0583360954590653,
      "eval_loss": 0.10800737142562866,
      "eval_runtime": 33.0659,
      "eval_samples_per_second": 6.139,
      "eval_steps_per_second": 0.786,
      "step": 400
    },
    {
      "epoch": 1.3235001657275438,
      "grad_norm": 2.1960959434509277,
      "learning_rate": 1.2450980392156864e-05,
      "loss": 0.4408,
      "step": 500
    },
    {
      "epoch": 1.3235001657275438,
      "eval_loss": 0.10127653181552887,
      "eval_runtime": 32.9484,
      "eval_samples_per_second": 6.161,
      "eval_steps_per_second": 0.789,
      "step": 500
    },
    {
      "epoch": 1.5886642359960226,
      "eval_loss": 0.10220777243375778,
      "eval_runtime": 33.1253,
      "eval_samples_per_second": 6.128,
      "eval_steps_per_second": 0.785,
      "step": 600
    },
    {
      "epoch": 1.8538283062645011,
      "eval_loss": 0.09732703119516373,
      "eval_runtime": 32.9224,
      "eval_samples_per_second": 6.166,
      "eval_steps_per_second": 0.79,
      "step": 700
    },
    {
      "epoch": 2.1166721909181305,
      "eval_loss": 0.08920517563819885,
      "eval_runtime": 35.8547,
      "eval_samples_per_second": 5.662,
      "eval_steps_per_second": 0.725,
      "step": 800
    },
    {
      "epoch": 2.381836261186609,
      "eval_loss": 0.0842105895280838,
      "eval_runtime": 33.201,
      "eval_samples_per_second": 6.114,
      "eval_steps_per_second": 0.783,
      "step": 900
    },
    {
      "epoch": 2.6470003314550876,
      "grad_norm": 1.400881290435791,
      "learning_rate": 2.647058823529412e-06,
      "loss": 0.0631,
      "step": 1000
    },
    {
      "epoch": 2.6470003314550876,
      "eval_loss": 0.08373343199491501,
      "eval_runtime": 33.2639,
      "eval_samples_per_second": 6.103,
      "eval_steps_per_second": 0.782,
      "step": 1000
    },
    {
      "epoch": 2.9121644017235666,
      "eval_loss": 0.07910037785768509,
      "eval_runtime": 33.3862,
      "eval_samples_per_second": 6.08,
      "eval_steps_per_second": 0.779,
      "step": 1100
    }
  ],
  "logging_steps": 500,
  "max_steps": 1134,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0716799705164969e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}