trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.993006993006993,
  "eval_steps": 500,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06993006993006994,
      "grad_norm": 4.480388164520264,
      "learning_rate": 1.9989008914857115e-05,
      "loss": 1.4426,
      "step": 5
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 2.3457789421081543,
      "learning_rate": 1.9606851875768404e-05,
      "loss": 1.2301,
      "step": 10
    },
    {
      "epoch": 0.2097902097902098,
      "grad_norm": 0.6594367027282715,
      "learning_rate": 1.8699063724087905e-05,
      "loss": 1.0951,
      "step": 15
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 0.509782612323761,
      "learning_rate": 1.731531335263669e-05,
      "loss": 1.0442,
      "step": 20
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 0.45541152358055115,
      "learning_rate": 1.5531311541251995e-05,
      "loss": 1.0289,
      "step": 25
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 0.39447295665740967,
      "learning_rate": 1.344466850284333e-05,
      "loss": 1.0119,
      "step": 30
    },
    {
      "epoch": 0.48951048951048953,
      "grad_norm": 0.35773131251335144,
      "learning_rate": 1.1169553219720828e-05,
      "loss": 1.0016,
      "step": 35
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.33480194211006165,
      "learning_rate": 8.830446780279175e-06,
      "loss": 0.9878,
      "step": 40
    },
    {
      "epoch": 0.6293706293706294,
      "grad_norm": 0.3191274404525757,
      "learning_rate": 6.555331497156671e-06,
      "loss": 0.9799,
      "step": 45
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 0.29347702860832214,
      "learning_rate": 4.468688458748006e-06,
      "loss": 0.9727,
      "step": 50
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.3030100166797638,
      "learning_rate": 2.6846866473633126e-06,
      "loss": 0.9769,
      "step": 55
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 0.2904769778251648,
      "learning_rate": 1.300936275912098e-06,
      "loss": 0.9739,
      "step": 60
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.2873133718967438,
      "learning_rate": 3.931481242315993e-07,
      "loss": 0.9724,
      "step": 65
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 0.29529905319213867,
      "learning_rate": 1.099108514288627e-08,
      "loss": 0.9735,
      "step": 70
    },
    {
      "epoch": 0.993006993006993,
      "step": 71,
      "total_flos": 1.6814365427000934e+17,
      "train_loss": 1.0495624525446288,
      "train_runtime": 12091.2309,
      "train_samples_per_second": 4.529,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 5,
  "max_steps": 71,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.6814365427000934e+17,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}