trainer_state.json

{
  "best_metric": 0.8936585365853658,
  "best_model_checkpoint": "test/checkpoint-1000",
  "epoch": 13.333333333333334,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3333333333333333,
      "eval_accuracy": 0.7843813146321169,
      "eval_f1": 0.7950072011521844,
      "eval_loss": 0.6181004047393799,
      "eval_precision": 0.7691593125870878,
      "eval_recall": 0.8226527570789866,
      "eval_runtime": 5.5814,
      "eval_samples_per_second": 8.958,
      "eval_steps_per_second": 4.479,
      "step": 100
    },
    {
      "epoch": 2.6666666666666665,
      "eval_accuracy": 0.832877689290384,
      "eval_f1": 0.8479196556671449,
      "eval_loss": 0.49555855989456177,
      "eval_precision": 0.8174273858921162,
      "eval_recall": 0.8807749627421758,
      "eval_runtime": 5.1208,
      "eval_samples_per_second": 9.764,
      "eval_steps_per_second": 4.882,
      "step": 200
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8296683703791751,
      "eval_f1": 0.8698812696874243,
      "eval_loss": 0.5111286640167236,
      "eval_precision": 0.8491012298959318,
      "eval_recall": 0.8917039244908097,
      "eval_runtime": 7.2692,
      "eval_samples_per_second": 6.878,
      "eval_steps_per_second": 3.439,
      "step": 300
    },
    {
      "epoch": 5.333333333333333,
      "eval_accuracy": 0.8368001901818614,
      "eval_f1": 0.88427734375,
      "eval_loss": 0.4935102164745331,
      "eval_precision": 0.8694191070571291,
      "eval_recall": 0.899652260307998,
      "eval_runtime": 6.6204,
      "eval_samples_per_second": 7.552,
      "eval_steps_per_second": 3.776,
      "step": 400
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 11.988961219787598,
      "learning_rate": 5e-06,
      "loss": 0.5444,
      "step": 500
    },
    {
      "epoch": 6.666666666666667,
      "eval_accuracy": 0.8416736003803638,
      "eval_f1": 0.873062015503876,
      "eval_loss": 0.5145852565765381,
      "eval_precision": 0.8520094562647754,
      "eval_recall": 0.8951813214108296,
      "eval_runtime": 5.5348,
      "eval_samples_per_second": 9.034,
      "eval_steps_per_second": 4.517,
      "step": 500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8258647331510757,
      "eval_f1": 0.8856863702979971,
      "eval_loss": 0.6251217126846313,
      "eval_precision": 0.8712157616530514,
      "eval_recall": 0.9006458022851466,
      "eval_runtime": 7.3846,
      "eval_samples_per_second": 6.771,
      "eval_steps_per_second": 3.385,
      "step": 600
    },
    {
      "epoch": 9.333333333333334,
      "eval_accuracy": 0.8268156424581006,
      "eval_f1": 0.8872691933916423,
      "eval_loss": 0.6401486396789551,
      "eval_precision": 0.8682834046600095,
      "eval_recall": 0.907103825136612,
      "eval_runtime": 5.6957,
      "eval_samples_per_second": 8.779,
      "eval_steps_per_second": 4.389,
      "step": 700
    },
    {
      "epoch": 10.666666666666666,
      "eval_accuracy": 0.8297872340425532,
      "eval_f1": 0.8906211936662607,
      "eval_loss": 0.640551745891571,
      "eval_precision": 0.8738049713193117,
      "eval_recall": 0.9080973671137605,
      "eval_runtime": 5.2926,
      "eval_samples_per_second": 9.447,
      "eval_steps_per_second": 4.724,
      "step": 800
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8321645073101153,
      "eval_f1": 0.8969726562500001,
      "eval_loss": 0.6590259075164795,
      "eval_precision": 0.8819011041766682,
      "eval_recall": 0.912568306010929,
      "eval_runtime": 5.2186,
      "eval_samples_per_second": 9.581,
      "eval_steps_per_second": 4.791,
      "step": 900
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 6.434786319732666,
      "learning_rate": 0.0,
      "loss": 0.134,
      "step": 1000
    },
    {
      "epoch": 13.333333333333334,
      "eval_accuracy": 0.8316890526566029,
      "eval_f1": 0.8936585365853658,
      "eval_loss": 0.6799957752227783,
      "eval_precision": 0.877815045519885,
      "eval_recall": 0.9100844510680576,
      "eval_runtime": 5.7958,
      "eval_samples_per_second": 8.627,
      "eval_steps_per_second": 4.313,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "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": 523783817001984.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}