{
  "best_global_step": 30,
  "best_metric": 1.3498777151107788,
  "best_model_checkpoint": "outputs\\gaialab-naija-adapter-v0.4\\checkpoint-30",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 16.430423736572266,
      "learning_rate": 0.0,
      "loss": 4.572,
      "step": 1
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 15.095035552978516,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.4529,
      "step": 2
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 8.647032737731934,
      "learning_rate": 0.00013333333333333334,
      "loss": 4.1566,
      "step": 3
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 6.524106979370117,
      "learning_rate": 0.0002,
      "loss": 3.2851,
      "step": 4
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 5.279809474945068,
      "learning_rate": 0.0001925925925925926,
      "loss": 3.0107,
      "step": 5
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.055668354034424,
      "learning_rate": 0.0001851851851851852,
      "loss": 2.2786,
      "step": 6
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4303853511810303,
      "eval_runtime": 3.2399,
      "eval_samples_per_second": 1.543,
      "eval_steps_per_second": 1.543,
      "step": 6
    },
    {
      "epoch": 1.1777777777777778,
      "grad_norm": 3.808993101119995,
      "learning_rate": 0.00017777777777777779,
      "loss": 2.1329,
      "step": 7
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 5.183055400848389,
      "learning_rate": 0.00017037037037037037,
      "loss": 1.9554,
      "step": 8
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 4.297043323516846,
      "learning_rate": 0.00016296296296296295,
      "loss": 1.5536,
      "step": 9
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 6.999485969543457,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.4798,
      "step": 10
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 2.94558048248291,
      "learning_rate": 0.00014814814814814815,
      "loss": 1.2903,
      "step": 11
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.834883689880371,
      "learning_rate": 0.00014074074074074076,
      "loss": 1.4292,
      "step": 12
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.6124086380004883,
      "eval_runtime": 2.189,
      "eval_samples_per_second": 2.284,
      "eval_steps_per_second": 2.284,
      "step": 12
    },
    {
      "epoch": 2.1777777777777776,
      "grad_norm": 1.9701344966888428,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.2039,
      "step": 13
    },
    {
      "epoch": 2.3555555555555556,
      "grad_norm": 1.6061532497406006,
      "learning_rate": 0.00012592592592592592,
      "loss": 1.1494,
      "step": 14
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 2.38248348236084,
      "learning_rate": 0.00011851851851851852,
      "loss": 1.3483,
      "step": 15
    },
    {
      "epoch": 2.7111111111111112,
      "grad_norm": 1.7200688123703003,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.9927,
      "step": 16
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 1.625122308731079,
      "learning_rate": 0.0001037037037037037,
      "loss": 1.1136,
      "step": 17
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7844679355621338,
      "learning_rate": 9.62962962962963e-05,
      "loss": 0.9103,
      "step": 18
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.4323580265045166,
      "eval_runtime": 3.0258,
      "eval_samples_per_second": 1.652,
      "eval_steps_per_second": 1.652,
      "step": 18
    },
    {
      "epoch": 3.1777777777777776,
      "grad_norm": 1.5016974210739136,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.8749,
      "step": 19
    },
    {
      "epoch": 3.3555555555555556,
      "grad_norm": 1.3555611371994019,
      "learning_rate": 8.148148148148148e-05,
      "loss": 0.9289,
      "step": 20
    },
    {
      "epoch": 3.533333333333333,
      "grad_norm": 1.7811331748962402,
      "learning_rate": 7.407407407407407e-05,
      "loss": 1.099,
      "step": 21
    },
    {
      "epoch": 3.7111111111111112,
      "grad_norm": 1.5052400827407837,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8184,
      "step": 22
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 1.7020034790039062,
      "learning_rate": 5.925925925925926e-05,
      "loss": 0.9686,
      "step": 23
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.030837297439575,
      "learning_rate": 5.185185185185185e-05,
      "loss": 0.8103,
      "step": 24
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3614479303359985,
      "eval_runtime": 2.2939,
      "eval_samples_per_second": 2.18,
      "eval_steps_per_second": 2.18,
      "step": 24
    },
    {
      "epoch": 4.177777777777778,
      "grad_norm": 1.6491711139678955,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.7975,
      "step": 25
    },
    {
      "epoch": 4.355555555555555,
      "grad_norm": 1.469295859336853,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.8944,
      "step": 26
    },
    {
      "epoch": 4.533333333333333,
      "grad_norm": 1.6997331380844116,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.7977,
      "step": 27
    },
    {
      "epoch": 4.711111111111111,
      "grad_norm": 1.5283434391021729,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.7814,
      "step": 28
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 1.6913104057312012,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.7772,
      "step": 29
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.0519070625305176,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.7568,
      "step": 30
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.3498777151107788,
      "eval_runtime": 2.3264,
      "eval_samples_per_second": 2.149,
      "eval_steps_per_second": 2.149,
      "step": 30
    },
    {
      "epoch": 5.0,
      "step": 30,
      "total_flos": 45576685612800.0,
      "train_loss": 1.6206799745559692,
      "train_runtime": 362.9377,
      "train_samples_per_second": 0.62,
      "train_steps_per_second": 0.083
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 45576685612800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}