trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 4.9967756271362305,
      "learning_rate": 9.999104613348688e-05,
      "loss": 1.1058,
      "step": 10
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.8961405754089355,
      "learning_rate": 9.892045704727864e-05,
      "loss": 0.3453,
      "step": 20
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1.2652360200881958,
      "learning_rate": 9.610293015188067e-05,
      "loss": 0.2044,
      "step": 30
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.8738003373146057,
      "learning_rate": 9.163907865818806e-05,
      "loss": 0.165,
      "step": 40
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.8198190927505493,
      "learning_rate": 8.568830563435694e-05,
      "loss": 0.132,
      "step": 50
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.7635666728019714,
      "learning_rate": 7.846311176040331e-05,
      "loss": 0.1211,
      "step": 60
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8185427784919739,
      "learning_rate": 7.022150697979384e-05,
      "loss": 0.1161,
      "step": 70
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.6302494406700134,
      "learning_rate": 6.125779702613471e-05,
      "loss": 0.1109,
      "step": 80
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.5293920040130615,
      "learning_rate": 5.1892073835883524e-05,
      "loss": 0.0961,
      "step": 90
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.5659812092781067,
      "learning_rate": 4.2458785141931314e-05,
      "loss": 0.0822,
      "step": 100
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 0.4485885202884674,
      "learning_rate": 3.329479142513051e-05,
      "loss": 0.0927,
      "step": 110
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.5655118227005005,
      "learning_rate": 2.4727336707170973e-05,
      "loss": 0.0805,
      "step": 120
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 0.46993887424468994,
      "learning_rate": 1.7062362744910322e-05,
      "loss": 0.0737,
      "step": 130
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4176179766654968,
      "learning_rate": 1.0573583923481711e-05,
      "loss": 0.078,
      "step": 140
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3602999448776245,
      "learning_rate": 5.4927129811301715e-06,
      "loss": 0.0776,
      "step": 150
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.43983834981918335,
      "learning_rate": 2.0011866028038617e-06,
      "loss": 0.0799,
      "step": 160
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 0.36634841561317444,
      "learning_rate": 2.2368635957205618e-07,
      "loss": 0.0728,
      "step": 170
    },
    {
      "epoch": 1.0,
      "step": 175,
      "total_flos": 2.4449910045876e+16,
      "train_loss": 0.17537879467010498,
      "train_runtime": 249.8042,
      "train_samples_per_second": 44.655,
      "train_steps_per_second": 0.701
    }
  ],
  "logging_steps": 10,
  "max_steps": 175,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4449910045876e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}