{
  "best_metric": 0.8285950217539291,
  "best_model_checkpoint": "/content/temp_assamese/checkpoint-50000",
  "epoch": 1.0,
  "eval_steps": 5000,
  "global_step": 53713,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09308733453726287,
      "grad_norm": 5.457111358642578,
      "learning_rate": 4.5348425893172976e-05,
      "loss": 2.4466,
      "step": 5000
    },
    {
      "epoch": 0.09308733453726287,
      "eval_accuracy": 0.707468341537135,
      "eval_loss": 1.5004358291625977,
      "eval_runtime": 308.6127,
      "eval_samples_per_second": 146.822,
      "eval_steps_per_second": 9.177,
      "step": 5000
    },
    {
      "epoch": 0.18617466907452573,
      "grad_norm": 4.776674270629883,
      "learning_rate": 4.0694990039655205e-05,
      "loss": 1.4994,
      "step": 10000
    },
    {
      "epoch": 0.18617466907452573,
      "eval_accuracy": 0.7532453087820641,
      "eval_loss": 1.2256046533584595,
      "eval_runtime": 306.864,
      "eval_samples_per_second": 147.658,
      "eval_steps_per_second": 9.229,
      "step": 10000
    },
    {
      "epoch": 0.2792620036117886,
      "grad_norm": 3.9309194087982178,
      "learning_rate": 3.604248505948281e-05,
      "loss": 1.2888,
      "step": 15000
    },
    {
      "epoch": 0.2792620036117886,
      "eval_accuracy": 0.7765668816186476,
      "eval_loss": 1.099416732788086,
      "eval_runtime": 321.8088,
      "eval_samples_per_second": 140.801,
      "eval_steps_per_second": 8.8,
      "step": 15000
    },
    {
      "epoch": 0.37234933814905147,
      "grad_norm": 3.988945722579956,
      "learning_rate": 3.1389980079310413e-05,
      "loss": 1.1746,
      "step": 20000
    },
    {
      "epoch": 0.37234933814905147,
      "eval_accuracy": 0.791549800931217,
      "eval_loss": 1.0090231895446777,
      "eval_runtime": 316.5344,
      "eval_samples_per_second": 143.147,
      "eval_steps_per_second": 8.947,
      "step": 20000
    },
    {
      "epoch": 0.4654366726863143,
      "grad_norm": 4.230010509490967,
      "learning_rate": 2.6736544225792642e-05,
      "loss": 1.0994,
      "step": 25000
    },
    {
      "epoch": 0.4654366726863143,
      "eval_accuracy": 0.8021278468205446,
      "eval_loss": 0.9513992667198181,
      "eval_runtime": 317.1699,
      "eval_samples_per_second": 142.86,
      "eval_steps_per_second": 8.929,
      "step": 25000
    },
    {
      "epoch": 0.5585240072235772,
      "grad_norm": 4.287986755371094,
      "learning_rate": 2.2084970118965616e-05,
      "loss": 1.0379,
      "step": 30000
    },
    {
      "epoch": 0.5585240072235772,
      "eval_accuracy": 0.8115293649487124,
      "eval_loss": 0.9028974771499634,
      "eval_runtime": 316.9066,
      "eval_samples_per_second": 142.979,
      "eval_steps_per_second": 8.936,
      "step": 30000
    },
    {
      "epoch": 0.65161134176084,
      "grad_norm": 3.521850347518921,
      "learning_rate": 1.743339601213859e-05,
      "loss": 0.9956,
      "step": 35000
    },
    {
      "epoch": 0.65161134176084,
      "eval_accuracy": 0.8174002465681974,
      "eval_loss": 0.8695101737976074,
      "eval_runtime": 316.9452,
      "eval_samples_per_second": 142.962,
      "eval_steps_per_second": 8.935,
      "step": 35000
    },
    {
      "epoch": 0.7446986762981029,
      "grad_norm": 4.046538829803467,
      "learning_rate": 1.2779960158620818e-05,
      "loss": 0.9647,
      "step": 40000
    },
    {
      "epoch": 0.7446986762981029,
      "eval_accuracy": 0.8216175421669631,
      "eval_loss": 0.8461592793464661,
      "eval_runtime": 318.3007,
      "eval_samples_per_second": 142.353,
      "eval_steps_per_second": 8.897,
      "step": 40000
    },
    {
      "epoch": 0.8377860108353657,
      "grad_norm": 4.023233413696289,
      "learning_rate": 8.12745517844842e-06,
      "loss": 0.9351,
      "step": 45000
    },
    {
      "epoch": 0.8377860108353657,
      "eval_accuracy": 0.8258444821249434,
      "eval_loss": 0.8274036645889282,
      "eval_runtime": 318.395,
      "eval_samples_per_second": 142.311,
      "eval_steps_per_second": 8.895,
      "step": 45000
    },
    {
      "epoch": 0.9308733453726286,
      "grad_norm": 3.7155344486236572,
      "learning_rate": 3.4749501982760224e-06,
      "loss": 0.9194,
      "step": 50000
    },
    {
      "epoch": 0.9308733453726286,
      "eval_accuracy": 0.8285950217539291,
      "eval_loss": 0.8120360374450684,
      "eval_runtime": 309.307,
      "eval_samples_per_second": 146.492,
      "eval_steps_per_second": 9.156,
      "step": 50000
    },
    {
      "epoch": 1.0,
      "step": 53713,
      "total_flos": 1.1339138340497818e+17,
      "train_loss": 1.2134282816267128,
      "train_runtime": 14742.2291,
      "train_samples_per_second": 58.295,
      "train_steps_per_second": 3.643
    }
  ],
  "logging_steps": 5000,
  "max_steps": 53713,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1339138340497818e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}