trainer_state.json

{
  "best_metric": 0.55,
  "best_model_checkpoint": "test\\checkpoint-1000",
  "epoch": 500.0,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 50.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.55,
      "eval_loss": 1.2207863330841064,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.8902,
      "eval_samples_per_second": 0.409,
      "eval_steps_per_second": 0.204,
      "step": 100
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 0.9717425107955933,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.525,
      "eval_samples_per_second": 0.442,
      "eval_steps_per_second": 0.221,
      "step": 200
    },
    {
      "epoch": 150.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.0064021348953247,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.277,
      "eval_samples_per_second": 0.468,
      "eval_steps_per_second": 0.234,
      "step": 300
    },
    {
      "epoch": 200.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.0413910150527954,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.4579,
      "eval_samples_per_second": 0.449,
      "eval_steps_per_second": 0.224,
      "step": 400
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.17069780826568604,
      "learning_rate": 5e-06,
      "loss": 0.326,
      "step": 500
    },
    {
      "epoch": 250.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.4878048780487805,
      "eval_loss": 1.0729484558105469,
      "eval_precision": 0.47619047619047616,
      "eval_recall": 0.5,
      "eval_runtime": 4.4009,
      "eval_samples_per_second": 0.454,
      "eval_steps_per_second": 0.227,
      "step": 500
    },
    {
      "epoch": 300.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.066214919090271,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.6788,
      "eval_samples_per_second": 0.427,
      "eval_steps_per_second": 0.214,
      "step": 600
    },
    {
      "epoch": 350.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.075073480606079,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.6425,
      "eval_samples_per_second": 0.431,
      "eval_steps_per_second": 0.215,
      "step": 700
    },
    {
      "epoch": 400.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.0892070531845093,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.3673,
      "eval_samples_per_second": 0.458,
      "eval_steps_per_second": 0.229,
      "step": 800
    },
    {
      "epoch": 450.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.0904639959335327,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.3499,
      "eval_samples_per_second": 0.46,
      "eval_steps_per_second": 0.23,
      "step": 900
    },
    {
      "epoch": 500.0,
      "grad_norm": 0.07940377295017242,
      "learning_rate": 0.0,
      "loss": 0.0113,
      "step": 1000
    },
    {
      "epoch": 500.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.093883991241455,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.4538,
      "eval_samples_per_second": 0.449,
      "eval_steps_per_second": 0.225,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 500,
  "save_steps": 500,
  "total_flos": 398157811200000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}