checkpoint-110/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2146341463414634,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01951219512195122,
      "grad_norm": 0.6663638353347778,
      "learning_rate": 0.00019934683213585893,
      "loss": 0.5255,
      "step": 10
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": 0.7442628741264343,
      "learning_rate": 0.00019804049640757677,
      "loss": 0.3367,
      "step": 20
    },
    {
      "epoch": 0.05853658536585366,
      "grad_norm": 0.504467785358429,
      "learning_rate": 0.0001967341606792946,
      "loss": 0.3368,
      "step": 30
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 0.339693546295166,
      "learning_rate": 0.00019542782495101242,
      "loss": 0.3064,
      "step": 40
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.267976313829422,
      "learning_rate": 0.00019412148922273026,
      "loss": 0.3108,
      "step": 50
    },
    {
      "epoch": 0.11707317073170732,
      "grad_norm": 0.48640233278274536,
      "learning_rate": 0.00019281515349444807,
      "loss": 0.3069,
      "step": 60
    },
    {
      "epoch": 0.13658536585365855,
      "grad_norm": 0.7269986867904663,
      "learning_rate": 0.0001915088177661659,
      "loss": 0.3134,
      "step": 70
    },
    {
      "epoch": 0.15609756097560976,
      "grad_norm": 0.31376832723617554,
      "learning_rate": 0.00019020248203788375,
      "loss": 0.2915,
      "step": 80
    },
    {
      "epoch": 0.17560975609756097,
      "grad_norm": 0.6166387796401978,
      "learning_rate": 0.00018889614630960156,
      "loss": 0.2862,
      "step": 90
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.6621638536453247,
      "learning_rate": 0.0001875898105813194,
      "loss": 0.263,
      "step": 100
    },
    {
      "epoch": 0.2146341463414634,
      "grad_norm": 0.2815336287021637,
      "learning_rate": 0.00018628347485303724,
      "loss": 0.2747,
      "step": 110
    }
  ],
  "logging_steps": 10,
  "max_steps": 1536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.070001597690061e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}