last-checkpoint/trainer_state.json

{
  "best_metric": 1.768334150314331,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.01974658548625967,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006582195162086556,
      "eval_loss": 2.139127731323242,
      "eval_runtime": 113.5237,
      "eval_samples_per_second": 5.638,
      "eval_steps_per_second": 2.819,
      "step": 1
    },
    {
      "epoch": 0.001974658548625967,
      "grad_norm": 1.1616520881652832,
      "learning_rate": 6e-05,
      "loss": 2.0603,
      "step": 3
    },
    {
      "epoch": 0.003291097581043278,
      "eval_loss": 2.061668872833252,
      "eval_runtime": 115.0199,
      "eval_samples_per_second": 5.564,
      "eval_steps_per_second": 2.782,
      "step": 5
    },
    {
      "epoch": 0.003949317097251934,
      "grad_norm": 1.4159042835235596,
      "learning_rate": 0.00012,
      "loss": 2.0058,
      "step": 6
    },
    {
      "epoch": 0.0059239756458779,
      "grad_norm": 1.1785248517990112,
      "learning_rate": 0.00018,
      "loss": 2.0132,
      "step": 9
    },
    {
      "epoch": 0.006582195162086556,
      "eval_loss": 1.9116626977920532,
      "eval_runtime": 115.1914,
      "eval_samples_per_second": 5.556,
      "eval_steps_per_second": 2.778,
      "step": 10
    },
    {
      "epoch": 0.007898634194503868,
      "grad_norm": 0.9806345105171204,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.8867,
      "step": 12
    },
    {
      "epoch": 0.009873292743129834,
      "grad_norm": 0.7483391165733337,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.7436,
      "step": 15
    },
    {
      "epoch": 0.009873292743129834,
      "eval_loss": 1.8191039562225342,
      "eval_runtime": 115.3176,
      "eval_samples_per_second": 5.55,
      "eval_steps_per_second": 2.775,
      "step": 15
    },
    {
      "epoch": 0.0118479512917558,
      "grad_norm": 0.8663469552993774,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7865,
      "step": 18
    },
    {
      "epoch": 0.013164390324173112,
      "eval_loss": 1.7831417322158813,
      "eval_runtime": 115.2706,
      "eval_samples_per_second": 5.552,
      "eval_steps_per_second": 2.776,
      "step": 20
    },
    {
      "epoch": 0.013822609840381767,
      "grad_norm": 1.1832069158554077,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.7964,
      "step": 21
    },
    {
      "epoch": 0.015797268389007735,
      "grad_norm": 1.099212884902954,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.7596,
      "step": 24
    },
    {
      "epoch": 0.01645548790521639,
      "eval_loss": 1.7728391885757446,
      "eval_runtime": 115.3063,
      "eval_samples_per_second": 5.55,
      "eval_steps_per_second": 2.775,
      "step": 25
    },
    {
      "epoch": 0.0177719269376337,
      "grad_norm": 0.9602068662643433,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.8017,
      "step": 27
    },
    {
      "epoch": 0.01974658548625967,
      "grad_norm": 0.9222397208213806,
      "learning_rate": 0.0,
      "loss": 1.8021,
      "step": 30
    },
    {
      "epoch": 0.01974658548625967,
      "eval_loss": 1.768334150314331,
      "eval_runtime": 115.4324,
      "eval_samples_per_second": 5.544,
      "eval_steps_per_second": 2.772,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5023225645826048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}