trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24780076818238136,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004956015363647627,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 4.2107,
      "step": 1
    },
    {
      "epoch": 0.04956015363647627,
      "grad_norm": 3.2077109813690186,
      "learning_rate": 4.887124782932275e-05,
      "loss": 1.4837,
      "step": 100
    },
    {
      "epoch": 0.09912030727295254,
      "grad_norm": 2.276442766189575,
      "learning_rate": 4.7630860828578514e-05,
      "loss": 1.1293,
      "step": 200
    },
    {
      "epoch": 0.14868046090942882,
      "grad_norm": 2.232943058013916,
      "learning_rate": 4.639047382783428e-05,
      "loss": 1.0766,
      "step": 300
    },
    {
      "epoch": 0.19824061454590508,
      "grad_norm": 2.2297351360321045,
      "learning_rate": 4.515008682709005e-05,
      "loss": 1.031,
      "step": 400
    },
    {
      "epoch": 0.24780076818238136,
      "grad_norm": 2.1566355228424072,
      "learning_rate": 4.390969982634582e-05,
      "loss": 1.0002,
      "step": 500
    },
    {
      "epoch": 0.24780076818238136,
      "eval_loss": 1.442247986793518,
      "eval_runtime": 413.7022,
      "eval_samples_per_second": 5.857,
      "eval_steps_per_second": 2.93,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4036,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6454383779512320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}