trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.1,
  "eval_steps": 282,
  "global_step": 846,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007092198581560284,
      "grad_norm": 1.791174054145813,
      "learning_rate": 1e-05,
      "loss": 2.6917,
      "step": 1
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.42204609513282776,
      "learning_rate": 0.0008610687022900763,
      "loss": 0.7537,
      "step": 282
    },
    {
      "epoch": 1.1,
      "eval_loss": 0.5796585083007812,
      "eval_runtime": 102.9977,
      "eval_samples_per_second": 4.359,
      "eval_steps_per_second": 0.553,
      "step": 282
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.2676902711391449,
      "learning_rate": 0.0006458015267175574,
      "loss": 0.2638,
      "step": 564
    },
    {
      "epoch": 3.1,
      "eval_loss": 0.4017384648323059,
      "eval_runtime": 100.6276,
      "eval_samples_per_second": 4.462,
      "eval_steps_per_second": 0.566,
      "step": 564
    },
    {
      "epoch": 5.1,
      "grad_norm": 0.27857616543769836,
      "learning_rate": 0.00043053435114503817,
      "loss": 0.1532,
      "step": 846
    },
    {
      "epoch": 5.1,
      "eval_loss": 0.40539106726646423,
      "eval_runtime": 108.1949,
      "eval_samples_per_second": 4.15,
      "eval_steps_per_second": 0.527,
      "step": 846
    }
  ],
  "logging_steps": 282,
  "max_steps": 1410,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 282,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.152869930975232e+20,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}