trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.957983193277311,
  "eval_steps": 500,
  "global_step": 177,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 1.64210754465846,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.8834,
      "step": 10
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 1.6216633128454179,
      "learning_rate": 9.99609654676786e-06,
      "loss": 0.832,
      "step": 20
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 1.0890026008565015,
      "learning_rate": 9.860114570402055e-06,
      "loss": 0.7929,
      "step": 30
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.9852931548778409,
      "learning_rate": 9.535012074008688e-06,
      "loss": 0.7613,
      "step": 40
    },
    {
      "epoch": 0.8403361344537815,
      "grad_norm": 1.0010829198190254,
      "learning_rate": 9.033439696227966e-06,
      "loss": 0.7369,
      "step": 50
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9912119135873784,
      "learning_rate": 8.374915007591053e-06,
      "loss": 0.6853,
      "step": 60
    },
    {
      "epoch": 1.1680672268907564,
      "grad_norm": 0.9598316653212201,
      "learning_rate": 7.58506302778873e-06,
      "loss": 0.6288,
      "step": 70
    },
    {
      "epoch": 1.3361344537815127,
      "grad_norm": 0.9969526888332303,
      "learning_rate": 6.694619085176159e-06,
      "loss": 0.5971,
      "step": 80
    },
    {
      "epoch": 1.504201680672269,
      "grad_norm": 5.712426354685314,
      "learning_rate": 5.738232820012407e-06,
      "loss": 0.5633,
      "step": 90
    },
    {
      "epoch": 1.6722689075630253,
      "grad_norm": 0.8053877541293872,
      "learning_rate": 4.753119870981486e-06,
      "loss": 0.5586,
      "step": 100
    },
    {
      "epoch": 1.8403361344537816,
      "grad_norm": 0.9085557253419428,
      "learning_rate": 3.777613711607087e-06,
      "loss": 0.5633,
      "step": 110
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9125623622985397,
      "learning_rate": 2.8496739886173994e-06,
      "loss": 0.5249,
      "step": 120
    },
    {
      "epoch": 2.168067226890756,
      "grad_norm": 0.9796403145730364,
      "learning_rate": 2.005409406946e-06,
      "loss": 0.4774,
      "step": 130
    },
    {
      "epoch": 2.3361344537815127,
      "grad_norm": 0.8379009664030831,
      "learning_rate": 1.277672640004936e-06,
      "loss": 0.4569,
      "step": 140
    },
    {
      "epoch": 2.504201680672269,
      "grad_norm": 0.912579146579012,
      "learning_rate": 6.947819411632223e-07,
      "loss": 0.4598,
      "step": 150
    },
    {
      "epoch": 2.6722689075630255,
      "grad_norm": 0.8570497984949336,
      "learning_rate": 2.7941920206915443e-07,
      "loss": 0.4533,
      "step": 160
    },
    {
      "epoch": 2.8403361344537816,
      "grad_norm": 0.913025927962694,
      "learning_rate": 4.774733741942206e-08,
      "loss": 0.4608,
      "step": 170
    },
    {
      "epoch": 2.957983193277311,
      "step": 177,
      "total_flos": 92447203917824.0,
      "train_loss": 0.6085002004763501,
      "train_runtime": 1135.371,
      "train_samples_per_second": 20.124,
      "train_steps_per_second": 0.156
    }
  ],
  "logging_steps": 10,
  "max_steps": 177,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 92447203917824.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}