{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007797270955165692,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007797270955165692,
      "grad_norm": 0.1444627344608307,
      "learning_rate": 2e-05,
      "loss": 11.9412,
      "step": 1
    },
    {
      "epoch": 0.0007797270955165692,
      "eval_loss": 11.941343307495117,
      "eval_runtime": 1.9423,
      "eval_samples_per_second": 278.02,
      "eval_steps_per_second": 139.01,
      "step": 1
    },
    {
      "epoch": 0.0015594541910331384,
      "grad_norm": 0.14752788841724396,
      "learning_rate": 4e-05,
      "loss": 11.9407,
      "step": 2
    },
    {
      "epoch": 0.0023391812865497076,
      "grad_norm": 0.14889869093894958,
      "learning_rate": 6e-05,
      "loss": 11.9423,
      "step": 3
    },
    {
      "epoch": 0.0023391812865497076,
      "eval_loss": 11.941235542297363,
      "eval_runtime": 1.9809,
      "eval_samples_per_second": 272.6,
      "eval_steps_per_second": 136.3,
      "step": 3
    },
    {
      "epoch": 0.0031189083820662767,
      "grad_norm": 0.14497824013233185,
      "learning_rate": 8e-05,
      "loss": 11.9409,
      "step": 4
    },
    {
      "epoch": 0.003898635477582846,
      "grad_norm": 0.12068742513656616,
      "learning_rate": 0.0001,
      "loss": 11.9412,
      "step": 5
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 0.1221635490655899,
      "learning_rate": 0.00012,
      "loss": 11.9422,
      "step": 6
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 11.94079875946045,
      "eval_runtime": 2.0524,
      "eval_samples_per_second": 263.107,
      "eval_steps_per_second": 131.554,
      "step": 6
    },
    {
      "epoch": 0.005458089668615985,
      "grad_norm": 0.13349322974681854,
      "learning_rate": 0.00014,
      "loss": 11.9413,
      "step": 7
    },
    {
      "epoch": 0.006237816764132553,
      "grad_norm": 0.153638556599617,
      "learning_rate": 0.00016,
      "loss": 11.9406,
      "step": 8
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 0.13560660183429718,
      "learning_rate": 0.00018,
      "loss": 11.9413,
      "step": 9
    },
    {
      "epoch": 0.007017543859649123,
      "eval_loss": 11.939946174621582,
      "eval_runtime": 2.0576,
      "eval_samples_per_second": 262.442,
      "eval_steps_per_second": 131.221,
      "step": 9
    },
    {
      "epoch": 0.007797270955165692,
      "grad_norm": 0.14415445923805237,
      "learning_rate": 0.0002,
      "loss": 11.9402,
      "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": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}