last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10790396547073106,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002158079309414621,
      "eval_loss": 0.23150818049907684,
      "eval_runtime": 159.2285,
      "eval_samples_per_second": 4.905,
      "eval_steps_per_second": 2.456,
      "step": 1
    },
    {
      "epoch": 0.02158079309414621,
      "grad_norm": 4.403369426727295,
      "learning_rate": 2e-05,
      "loss": 3.5073,
      "step": 10
    },
    {
      "epoch": 0.02158079309414621,
      "eval_loss": 0.2252948135137558,
      "eval_runtime": 160.0077,
      "eval_samples_per_second": 4.881,
      "eval_steps_per_second": 2.444,
      "step": 10
    },
    {
      "epoch": 0.04316158618829242,
      "grad_norm": 5.183837890625,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 3.0088,
      "step": 20
    },
    {
      "epoch": 0.04316158618829242,
      "eval_loss": 0.1603516936302185,
      "eval_runtime": 159.1028,
      "eval_samples_per_second": 4.909,
      "eval_steps_per_second": 2.458,
      "step": 20
    },
    {
      "epoch": 0.06474237928243863,
      "grad_norm": 2.9469869136810303,
      "learning_rate": 1e-05,
      "loss": 2.6216,
      "step": 30
    },
    {
      "epoch": 0.06474237928243863,
      "eval_loss": 0.1086607277393341,
      "eval_runtime": 156.6982,
      "eval_samples_per_second": 4.984,
      "eval_steps_per_second": 2.495,
      "step": 30
    },
    {
      "epoch": 0.08632317237658484,
      "grad_norm": 4.422735691070557,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 1.9042,
      "step": 40
    },
    {
      "epoch": 0.08632317237658484,
      "eval_loss": 0.09215810149908066,
      "eval_runtime": 158.3154,
      "eval_samples_per_second": 4.933,
      "eval_steps_per_second": 2.47,
      "step": 40
    },
    {
      "epoch": 0.10790396547073106,
      "grad_norm": 2.5692081451416016,
      "learning_rate": 0.0,
      "loss": 1.7143,
      "step": 50
    },
    {
      "epoch": 0.10790396547073106,
      "eval_loss": 0.08992834389209747,
      "eval_runtime": 161.6511,
      "eval_samples_per_second": 4.831,
      "eval_steps_per_second": 2.419,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.15297574469632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}