checkpoint-10/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 258.9384460449219,
      "learning_rate": 0.0003,
      "loss": 109.7683,
      "step": 1
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 307.8008117675781,
      "learning_rate": 0.0003,
      "loss": 63.592,
      "step": 2
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 68.41874694824219,
      "learning_rate": 0.0003,
      "loss": 45.0693,
      "step": 3
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 42.555973052978516,
      "learning_rate": 0.0003,
      "loss": 38.2675,
      "step": 4
    },
    {
      "epoch": 1.0,
      "grad_norm": 20.205808639526367,
      "learning_rate": 0.0003,
      "loss": 24.643,
      "step": 5
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 40.714134216308594,
      "learning_rate": 0.0003,
      "loss": 28.5208,
      "step": 6
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 28.32428741455078,
      "learning_rate": 0.0003,
      "loss": 26.8694,
      "step": 7
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 36.77808380126953,
      "learning_rate": 0.0003,
      "loss": 25.45,
      "step": 8
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 12.102893829345703,
      "learning_rate": 0.0003,
      "loss": 23.5542,
      "step": 9
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.711143493652344,
      "learning_rate": 0.0003,
      "loss": 16.8427,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}