last-checkpoint/trainer_state.json

{
  "best_metric": 0.04173528403043747,
  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-7000",
  "epoch": 3.4516765285996054,
  "eval_steps": 1000,
  "global_step": 7000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2465483234714004,
      "grad_norm": 0.3881610631942749,
      "learning_rate": 1.9950690335305722e-05,
      "loss": 0.1669,
      "step": 500
    },
    {
      "epoch": 0.4930966469428008,
      "grad_norm": 0.3564796447753906,
      "learning_rate": 1.9901380670611442e-05,
      "loss": 0.0935,
      "step": 1000
    },
    {
      "epoch": 0.4930966469428008,
      "eval_accuracy": 0.9814660487265615,
      "eval_f1": 0.0,
      "eval_loss": 0.08951831609010696,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 12.2339,
      "eval_samples_per_second": 662.913,
      "eval_steps_per_second": 2.616,
      "step": 1000
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.4097365140914917,
      "learning_rate": 1.9852071005917162e-05,
      "loss": 0.0869,
      "step": 1500
    },
    {
      "epoch": 0.9861932938856016,
      "grad_norm": 0.3858756422996521,
      "learning_rate": 1.980276134122288e-05,
      "loss": 0.0764,
      "step": 2000
    },
    {
      "epoch": 0.9861932938856016,
      "eval_accuracy": 0.9814660487265615,
      "eval_f1": 0.0,
      "eval_loss": 0.07000521570444107,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 12.0785,
      "eval_samples_per_second": 671.442,
      "eval_steps_per_second": 2.649,
      "step": 2000
    },
    {
      "epoch": 1.232741617357002,
      "grad_norm": 0.3765203356742859,
      "learning_rate": 1.9753451676528602e-05,
      "loss": 0.068,
      "step": 2500
    },
    {
      "epoch": 1.4792899408284024,
      "grad_norm": 0.3380969762802124,
      "learning_rate": 1.9704142011834322e-05,
      "loss": 0.0621,
      "step": 3000
    },
    {
      "epoch": 1.4792899408284024,
      "eval_accuracy": 0.982086823419363,
      "eval_f1": 0.07304730473047305,
      "eval_loss": 0.05673361197113991,
      "eval_precision": 0.8924731182795699,
      "eval_recall": 0.03808212892865336,
      "eval_runtime": 14.4231,
      "eval_samples_per_second": 562.293,
      "eval_steps_per_second": 2.219,
      "step": 3000
    },
    {
      "epoch": 1.725838264299803,
      "grad_norm": 0.3490855395793915,
      "learning_rate": 1.965483234714004e-05,
      "loss": 0.056,
      "step": 3500
    },
    {
      "epoch": 1.972386587771203,
      "grad_norm": 0.4068734347820282,
      "learning_rate": 1.9605522682445763e-05,
      "loss": 0.0542,
      "step": 4000
    },
    {
      "epoch": 1.972386587771203,
      "eval_accuracy": 0.9840823731167708,
      "eval_f1": 0.2891322235584531,
      "eval_loss": 0.04972199350595474,
      "eval_precision": 0.8390889052167524,
      "eval_recall": 0.174657796130611,
      "eval_runtime": 14.6604,
      "eval_samples_per_second": 553.191,
      "eval_steps_per_second": 2.183,
      "step": 4000
    },
    {
      "epoch": 2.2189349112426036,
      "grad_norm": 0.39391544461250305,
      "learning_rate": 1.9556213017751483e-05,
      "loss": 0.0488,
      "step": 4500
    },
    {
      "epoch": 2.465483234714004,
      "grad_norm": 0.2698710858821869,
      "learning_rate": 1.95069033530572e-05,
      "loss": 0.0468,
      "step": 5000
    },
    {
      "epoch": 2.465483234714004,
      "eval_accuracy": 0.9852672307496066,
      "eval_f1": 0.42163244867300953,
      "eval_loss": 0.046487729996442795,
      "eval_precision": 0.7738970588235294,
      "eval_recall": 0.28974535443909155,
      "eval_runtime": 14.5194,
      "eval_samples_per_second": 558.563,
      "eval_steps_per_second": 2.204,
      "step": 5000
    },
    {
      "epoch": 2.712031558185404,
      "grad_norm": 0.39123860001564026,
      "learning_rate": 1.9457593688362923e-05,
      "loss": 0.0456,
      "step": 5500
    },
    {
      "epoch": 2.9585798816568047,
      "grad_norm": 0.4525609016418457,
      "learning_rate": 1.940828402366864e-05,
      "loss": 0.0441,
      "step": 6000
    },
    {
      "epoch": 2.9585798816568047,
      "eval_accuracy": 0.9860793401079978,
      "eval_f1": 0.48790406673618353,
      "eval_loss": 0.04352094233036041,
      "eval_precision": 0.7666721284614124,
      "eval_recall": 0.3578037776248375,
      "eval_runtime": 14.4967,
      "eval_samples_per_second": 559.439,
      "eval_steps_per_second": 2.207,
      "step": 6000
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 0.47004055976867676,
      "learning_rate": 1.935897435897436e-05,
      "loss": 0.0409,
      "step": 6500
    },
    {
      "epoch": 3.4516765285996054,
      "grad_norm": 0.3331545293331146,
      "learning_rate": 1.930966469428008e-05,
      "loss": 0.0395,
      "step": 7000
    },
    {
      "epoch": 3.4516765285996054,
      "eval_accuracy": 0.9862437461910228,
      "eval_f1": 0.5321958743011375,
      "eval_loss": 0.04173528403043747,
      "eval_precision": 0.7197236344674749,
      "eval_recall": 0.42219163416685784,
      "eval_runtime": 14.6186,
      "eval_samples_per_second": 554.772,
      "eval_steps_per_second": 2.189,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 202800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 157815991349820.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}