checkpoint-46/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9826435246995995,
  "eval_steps": 3,
  "global_step": 46,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06408544726301736,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.9207,
      "step": 3
    },
    {
      "epoch": 0.12817089452603472,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.9249,
      "step": 6
    },
    {
      "epoch": 0.19225634178905207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.9354,
      "step": 9
    },
    {
      "epoch": 0.25634178905206945,
      "grad_norm": 0.20225562155246735,
      "learning_rate": 0.002,
      "loss": 0.9184,
      "step": 12
    },
    {
      "epoch": 0.3204272363150868,
      "grad_norm": 0.18608325719833374,
      "learning_rate": 0.0011547005383792518,
      "loss": 0.8359,
      "step": 15
    },
    {
      "epoch": 0.38451268357810414,
      "grad_norm": 1.095795750617981,
      "learning_rate": 0.0008944271909999159,
      "loss": 0.843,
      "step": 18
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 2.1086606979370117,
      "learning_rate": 0.0008164965809277262,
      "loss": 0.7406,
      "step": 21
    },
    {
      "epoch": 0.5126835781041389,
      "grad_norm": 0.3816397786140442,
      "learning_rate": 0.0007071067811865475,
      "loss": 0.717,
      "step": 24
    },
    {
      "epoch": 0.5767690253671562,
      "grad_norm": 0.23568345606327057,
      "learning_rate": 0.0006030226891555273,
      "loss": 0.6573,
      "step": 27
    },
    {
      "epoch": 0.6408544726301736,
      "grad_norm": 0.1751287281513214,
      "learning_rate": 0.0005345224838248488,
      "loss": 0.6366,
      "step": 30
    },
    {
      "epoch": 0.7049399198931909,
      "grad_norm": 0.19176988303661346,
      "learning_rate": 0.0004850712500726659,
      "loss": 0.6498,
      "step": 33
    },
    {
      "epoch": 0.7690253671562083,
      "grad_norm": 0.17194005846977234,
      "learning_rate": 0.00044721359549995795,
      "loss": 0.6296,
      "step": 36
    },
    {
      "epoch": 0.8331108144192256,
      "grad_norm": 0.25768938660621643,
      "learning_rate": 0.0004170288281141495,
      "loss": 0.6209,
      "step": 39
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.1806868016719818,
      "learning_rate": 0.0003922322702763681,
      "loss": 0.6021,
      "step": 42
    },
    {
      "epoch": 0.9612817089452603,
      "grad_norm": 0.21339942514896393,
      "learning_rate": 0.0003713906763541037,
      "loss": 0.5855,
      "step": 45
    }
  ],
  "logging_steps": 3,
  "max_steps": 46,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.671973340489974e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}