last-checkpoint/trainer_state.json

{
  "best_metric": 3.0686392784118652,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.004515182300485382,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.5151823004853824e-05,
      "eval_loss": 4.564711093902588,
      "eval_runtime": 183.5644,
      "eval_samples_per_second": 50.805,
      "eval_steps_per_second": 12.704,
      "step": 1
    },
    {
      "epoch": 0.0004515182300485382,
      "grad_norm": 4.505808353424072,
      "learning_rate": 4.1e-05,
      "loss": 3.6345,
      "step": 10
    },
    {
      "epoch": 0.0009030364600970764,
      "grad_norm": 4.865635395050049,
      "learning_rate": 8.2e-05,
      "loss": 3.4077,
      "step": 20
    },
    {
      "epoch": 0.0013545546901456147,
      "grad_norm": 5.399093151092529,
      "learning_rate": 0.00012299999999999998,
      "loss": 3.212,
      "step": 30
    },
    {
      "epoch": 0.0018060729201941528,
      "grad_norm": 6.037168502807617,
      "learning_rate": 0.000164,
      "loss": 3.2546,
      "step": 40
    },
    {
      "epoch": 0.002257591150242691,
      "grad_norm": 8.842162132263184,
      "learning_rate": 0.000205,
      "loss": 3.2376,
      "step": 50
    },
    {
      "epoch": 0.002257591150242691,
      "eval_loss": 3.3135757446289062,
      "eval_runtime": 185.7849,
      "eval_samples_per_second": 50.198,
      "eval_steps_per_second": 12.552,
      "step": 50
    },
    {
      "epoch": 0.0027091093802912294,
      "grad_norm": 4.627725601196289,
      "learning_rate": 0.00020475031515163197,
      "loss": 3.1244,
      "step": 60
    },
    {
      "epoch": 0.0031606276103397675,
      "grad_norm": 4.629662990570068,
      "learning_rate": 0.00020400247704601096,
      "loss": 3.0593,
      "step": 70
    },
    {
      "epoch": 0.0036121458403883056,
      "grad_norm": 4.690089225769043,
      "learning_rate": 0.00020276012907521508,
      "loss": 2.9041,
      "step": 80
    },
    {
      "epoch": 0.004063664070436844,
      "grad_norm": 5.650446891784668,
      "learning_rate": 0.00020102932383367768,
      "loss": 2.7957,
      "step": 90
    },
    {
      "epoch": 0.004515182300485382,
      "grad_norm": 6.984936237335205,
      "learning_rate": 0.00019881849363055561,
      "loss": 3.173,
      "step": 100
    },
    {
      "epoch": 0.004515182300485382,
      "eval_loss": 3.0686392784118652,
      "eval_runtime": 185.0562,
      "eval_samples_per_second": 50.395,
      "eval_steps_per_second": 12.602,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 905698840412160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}