{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2482223658694247,
  "eval_steps": 256,
  "global_step": 768,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04137039431157078,
      "grad_norm": 95.44776916503906,
      "learning_rate": 9.773140025240866e-09,
      "loss": 16.2614,
      "step": 128
    },
    {
      "epoch": 0.08274078862314156,
      "grad_norm": 81.94233703613281,
      "learning_rate": 1.9623233908948195e-08,
      "loss": 16.1329,
      "step": 256
    },
    {
      "epoch": 0.08274078862314156,
      "eval_bleu": 0.0,
      "eval_cap_loss": 9.05574489775158,
      "eval_con_loss": 3.4572216215587797,
      "eval_loss": 15.97018808031839,
      "step": 256
    },
    {
      "epoch": 0.08274078862314156,
      "eval_bleu": 0.0,
      "eval_cap_loss": 9.05574489775158,
      "eval_con_loss": 3.4572216215587797,
      "eval_loss": 15.97018808031839,
      "eval_runtime": 170.2059,
      "eval_samples_per_second": 5.875,
      "eval_steps_per_second": 0.37,
      "step": 256
    },
    {
      "epoch": 0.12411118293471235,
      "grad_norm": 92.045166015625,
      "learning_rate": 2.9473327792655523e-08,
      "loss": 15.8603,
      "step": 384
    },
    {
      "epoch": 0.16548157724628312,
      "grad_norm": 67.55699920654297,
      "learning_rate": 3.9323421676362855e-08,
      "loss": 15.4976,
      "step": 512
    },
    {
      "epoch": 0.16548157724628312,
      "eval_bleu": 0.0,
      "eval_cap_loss": 8.317013150169736,
      "eval_con_loss": 3.4565826900421626,
      "eval_loss": 15.230178530254062,
      "step": 512
    },
    {
      "epoch": 0.16548157724628312,
      "eval_bleu": 0.0,
      "eval_cap_loss": 8.317013150169736,
      "eval_con_loss": 3.4565826900421626,
      "eval_loss": 15.230178530254062,
      "eval_runtime": 169.6131,
      "eval_samples_per_second": 5.896,
      "eval_steps_per_second": 0.371,
      "step": 512
    },
    {
      "epoch": 0.2068519715578539,
      "grad_norm": 68.02971649169922,
      "learning_rate": 4.917351556007019e-08,
      "loss": 15.0425,
      "step": 640
    },
    {
      "epoch": 0.2482223658694247,
      "grad_norm": 63.56317138671875,
      "learning_rate": 5.902360944377751e-08,
      "loss": 14.5238,
      "step": 768
    },
    {
      "epoch": 0.2482223658694247,
      "eval_bleu": 0.0009372288320443345,
      "eval_cap_loss": 7.270466600145612,
      "eval_con_loss": 3.45575193374876,
      "eval_loss": 14.181970460074288,
      "step": 768
    },
    {
      "epoch": 0.2482223658694247,
      "eval_bleu": 0.0009372288320443345,
      "eval_cap_loss": 7.270466600145612,
      "eval_con_loss": 3.45575193374876,
      "eval_loss": 14.181970460074288,
      "eval_runtime": 168.362,
      "eval_samples_per_second": 5.94,
      "eval_steps_per_second": 0.374,
      "step": 768
    }
  ],
  "logging_steps": 128,
  "max_steps": 4331600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1400,
  "save_steps": 256,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}