trainer_state.json

{
  "best_metric": 0.5666028954056137,
  "best_model_checkpoint": "./models/brx_TrA50_MR/checkpoint-2214",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 2214,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.997289972899729,
      "grad_norm": 3.5397324562072754,
      "learning_rate": 4.168925022583559e-05,
      "loss": 0.8438,
      "step": 368
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.44267854576807014,
      "eval_loss": 0.5134469270706177,
      "eval_precision": 0.4302273615999106,
      "eval_recall": 0.4558719071859832,
      "eval_runtime": 71.5939,
      "eval_samples_per_second": 330.321,
      "eval_steps_per_second": 5.168,
      "step": 369
    },
    {
      "epoch": 1.994579945799458,
      "grad_norm": 2.107616901397705,
      "learning_rate": 3.3378500451671184e-05,
      "loss": 0.4624,
      "step": 736
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.5124409543580949,
      "eval_loss": 0.4316766858100891,
      "eval_precision": 0.5210793611943951,
      "eval_recall": 0.504084290280573,
      "eval_runtime": 71.7509,
      "eval_samples_per_second": 329.599,
      "eval_steps_per_second": 5.157,
      "step": 738
    },
    {
      "epoch": 2.991869918699187,
      "grad_norm": 3.3447747230529785,
      "learning_rate": 2.5067750677506774e-05,
      "loss": 0.3523,
      "step": 1104
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.5369874838152783,
      "eval_loss": 0.4135218858718872,
      "eval_precision": 0.5224511505514808,
      "eval_recall": 0.5523558659879247,
      "eval_runtime": 71.9772,
      "eval_samples_per_second": 328.562,
      "eval_steps_per_second": 5.141,
      "step": 1107
    },
    {
      "epoch": 3.989159891598916,
      "grad_norm": 2.4756720066070557,
      "learning_rate": 1.675700090334237e-05,
      "loss": 0.275,
      "step": 1472
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.550384120140627,
      "eval_loss": 0.4026535451412201,
      "eval_precision": 0.5383657411338485,
      "eval_recall": 0.5629513436723097,
      "eval_runtime": 71.9543,
      "eval_samples_per_second": 328.667,
      "eval_steps_per_second": 5.142,
      "step": 1476
    },
    {
      "epoch": 4.9864498644986455,
      "grad_norm": 1.6352941989898682,
      "learning_rate": 8.446251129177959e-06,
      "loss": 0.219,
      "step": 1840
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.5614785049658729,
      "eval_loss": 0.4078289270401001,
      "eval_precision": 0.5413975983072737,
      "eval_recall": 0.583106428317746,
      "eval_runtime": 71.8827,
      "eval_samples_per_second": 328.994,
      "eval_steps_per_second": 5.147,
      "step": 1845
    },
    {
      "epoch": 5.983739837398374,
      "grad_norm": 1.7785389423370361,
      "learning_rate": 1.3550135501355015e-07,
      "loss": 0.1772,
      "step": 2208
    },
    {
      "epoch": 6.0,
      "eval_f1": 0.5666028954056137,
      "eval_loss": 0.41467106342315674,
      "eval_precision": 0.5473327081149666,
      "eval_recall": 0.5872795075174618,
      "eval_runtime": 71.6677,
      "eval_samples_per_second": 329.981,
      "eval_steps_per_second": 5.163,
      "step": 2214
    }
  ],
  "logging_steps": 368,
  "max_steps": 2214,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 2.9681397967022096e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}