checkpoint-150/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.37593984962406013,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02506265664160401,
      "grad_norm": 1.0692139863967896,
      "learning_rate": 2.5e-06,
      "loss": 4.188,
      "step": 10
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 1.1046545505523682,
      "learning_rate": 5e-06,
      "loss": 4.1657,
      "step": 20
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 1.2392791509628296,
      "learning_rate": 7.500000000000001e-06,
      "loss": 4.1205,
      "step": 30
    },
    {
      "epoch": 0.10025062656641603,
      "grad_norm": 1.4656062126159668,
      "learning_rate": 1e-05,
      "loss": 4.0411,
      "step": 40
    },
    {
      "epoch": 0.12531328320802004,
      "grad_norm": 1.5381596088409424,
      "learning_rate": 9.722222222222223e-06,
      "loss": 3.8527,
      "step": 50
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 1.220762014389038,
      "learning_rate": 9.444444444444445e-06,
      "loss": 3.6254,
      "step": 60
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.0793465375900269,
      "learning_rate": 9.166666666666666e-06,
      "loss": 3.4326,
      "step": 70
    },
    {
      "epoch": 0.20050125313283207,
      "grad_norm": 0.9771835803985596,
      "learning_rate": 8.888888888888888e-06,
      "loss": 3.2486,
      "step": 80
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 0.9600415825843811,
      "learning_rate": 8.611111111111112e-06,
      "loss": 3.0867,
      "step": 90
    },
    {
      "epoch": 0.2506265664160401,
      "grad_norm": 0.789818525314331,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.9344,
      "step": 100
    },
    {
      "epoch": 0.2756892230576441,
      "grad_norm": 0.7392975091934204,
      "learning_rate": 9.365079365079366e-06,
      "loss": 2.8172,
      "step": 110
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.7141592502593994,
      "learning_rate": 9.206349206349207e-06,
      "loss": 2.6949,
      "step": 120
    },
    {
      "epoch": 0.3258145363408521,
      "grad_norm": 0.6999505162239075,
      "learning_rate": 9.047619047619049e-06,
      "loss": 2.5975,
      "step": 130
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.7100343704223633,
      "learning_rate": 8.888888888888888e-06,
      "loss": 2.4933,
      "step": 140
    },
    {
      "epoch": 0.37593984962406013,
      "grad_norm": 0.7077847719192505,
      "learning_rate": 8.730158730158731e-06,
      "loss": 2.3849,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6182662167068672e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}