{
  "best_global_step": 2000,
  "best_metric": 0.17954599857330322,
  "best_model_checkpoint": "D:\\BrainBug\\brainbug-backend\\Ml\\ml_models/codet5-error-analyzer\\checkpoint-2000",
  "epoch": 7.9710289710289715,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3996003996003996,
      "grad_norm": 1.8659660816192627,
      "learning_rate": 5.940000000000001e-06,
      "loss": 1.8891,
      "step": 100
    },
    {
      "epoch": 0.7992007992007992,
      "grad_norm": 0.5347102284431458,
      "learning_rate": 1.1940000000000001e-05,
      "loss": 0.3603,
      "step": 200
    },
    {
      "epoch": 1.1958041958041958,
      "grad_norm": 0.5820861458778381,
      "learning_rate": 1.794e-05,
      "loss": 0.2662,
      "step": 300
    },
    {
      "epoch": 1.5954045954045954,
      "grad_norm": 0.7345849275588989,
      "learning_rate": 2.394e-05,
      "loss": 0.2539,
      "step": 400
    },
    {
      "epoch": 1.995004995004995,
      "grad_norm": 0.40858349204063416,
      "learning_rate": 2.994e-05,
      "loss": 0.2227,
      "step": 500
    },
    {
      "epoch": 1.995004995004995,
      "eval_loss": 0.2152772843837738,
      "eval_runtime": 21.0116,
      "eval_samples_per_second": 23.844,
      "eval_steps_per_second": 23.844,
      "step": 500
    },
    {
      "epoch": 2.3916083916083917,
      "grad_norm": 0.36830630898475647,
      "learning_rate": 2.852238805970149e-05,
      "loss": 0.2012,
      "step": 600
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.3250398337841034,
      "learning_rate": 2.7029850746268658e-05,
      "loss": 0.2067,
      "step": 700
    },
    {
      "epoch": 3.1878121878121877,
      "grad_norm": 0.260728120803833,
      "learning_rate": 2.553731343283582e-05,
      "loss": 0.1818,
      "step": 800
    },
    {
      "epoch": 3.5874125874125875,
      "grad_norm": 0.4586130976676941,
      "learning_rate": 2.4044776119402987e-05,
      "loss": 0.1758,
      "step": 900
    },
    {
      "epoch": 3.987012987012987,
      "grad_norm": 0.44490137696266174,
      "learning_rate": 2.255223880597015e-05,
      "loss": 0.18,
      "step": 1000
    },
    {
      "epoch": 3.987012987012987,
      "eval_loss": 0.1895027756690979,
      "eval_runtime": 26.0522,
      "eval_samples_per_second": 19.231,
      "eval_steps_per_second": 19.231,
      "step": 1000
    },
    {
      "epoch": 4.383616383616384,
      "grad_norm": 0.3791581988334656,
      "learning_rate": 2.1059701492537313e-05,
      "loss": 0.1594,
      "step": 1100
    },
    {
      "epoch": 4.783216783216783,
      "grad_norm": 0.26640045642852783,
      "learning_rate": 1.956716417910448e-05,
      "loss": 0.169,
      "step": 1200
    },
    {
      "epoch": 5.1798201798201795,
      "grad_norm": 0.45615479350090027,
      "learning_rate": 1.8074626865671642e-05,
      "loss": 0.1558,
      "step": 1300
    },
    {
      "epoch": 5.57942057942058,
      "grad_norm": 0.37295207381248474,
      "learning_rate": 1.658208955223881e-05,
      "loss": 0.1586,
      "step": 1400
    },
    {
      "epoch": 5.979020979020979,
      "grad_norm": 0.37807774543762207,
      "learning_rate": 1.5089552238805971e-05,
      "loss": 0.1477,
      "step": 1500
    },
    {
      "epoch": 5.979020979020979,
      "eval_loss": 0.18257541954517365,
      "eval_runtime": 20.4853,
      "eval_samples_per_second": 24.457,
      "eval_steps_per_second": 24.457,
      "step": 1500
    },
    {
      "epoch": 6.375624375624375,
      "grad_norm": 0.34316518902778625,
      "learning_rate": 1.3597014925373134e-05,
      "loss": 0.1394,
      "step": 1600
    },
    {
      "epoch": 6.775224775224775,
      "grad_norm": 0.3410404920578003,
      "learning_rate": 1.2104477611940299e-05,
      "loss": 0.1473,
      "step": 1700
    },
    {
      "epoch": 7.171828171828172,
      "grad_norm": 0.24783101677894592,
      "learning_rate": 1.0611940298507462e-05,
      "loss": 0.1367,
      "step": 1800
    },
    {
      "epoch": 7.571428571428571,
      "grad_norm": 0.3025240898132324,
      "learning_rate": 9.119402985074627e-06,
      "loss": 0.1388,
      "step": 1900
    },
    {
      "epoch": 7.9710289710289715,
      "grad_norm": 0.19492867588996887,
      "learning_rate": 7.626865671641791e-06,
      "loss": 0.1344,
      "step": 2000
    },
    {
      "epoch": 7.9710289710289715,
      "eval_loss": 0.17954599857330322,
      "eval_runtime": 19.7902,
      "eval_samples_per_second": 25.316,
      "eval_steps_per_second": 25.316,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.457662502633472e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}