last-checkpoint/trainer_state.json

{
  "best_metric": 0.14316821098327637,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.11117287381878821,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022234574763757643,
      "eval_loss": 0.859638512134552,
      "eval_runtime": 1372.4825,
      "eval_samples_per_second": 5.519,
      "eval_steps_per_second": 1.38,
      "step": 1
    },
    {
      "epoch": 0.011117287381878822,
      "grad_norm": 5.895731449127197,
      "learning_rate": 0.000109,
      "loss": 4.9432,
      "step": 50
    },
    {
      "epoch": 0.022234574763757644,
      "grad_norm": 6.479587554931641,
      "learning_rate": 0.000218,
      "loss": 3.714,
      "step": 100
    },
    {
      "epoch": 0.033351862145636464,
      "grad_norm": 5.92208194732666,
      "learning_rate": 0.00020970286904373027,
      "loss": 2.918,
      "step": 150
    },
    {
      "epoch": 0.04446914952751529,
      "grad_norm": 6.322952747344971,
      "learning_rate": 0.00018607463914933369,
      "loss": 2.3977,
      "step": 200
    },
    {
      "epoch": 0.055586436909394105,
      "grad_norm": 13.940869331359863,
      "learning_rate": 0.0001507124941277948,
      "loss": 2.0249,
      "step": 250
    },
    {
      "epoch": 0.06670372429127293,
      "grad_norm": 6.892241477966309,
      "learning_rate": 0.000109,
      "loss": 1.7234,
      "step": 300
    },
    {
      "epoch": 0.07782101167315175,
      "grad_norm": 5.733283996582031,
      "learning_rate": 6.728750587220522e-05,
      "loss": 1.5057,
      "step": 350
    },
    {
      "epoch": 0.08893829905503058,
      "grad_norm": 5.083144664764404,
      "learning_rate": 3.192536085066633e-05,
      "loss": 1.2964,
      "step": 400
    },
    {
      "epoch": 0.1000555864369094,
      "grad_norm": 6.453845024108887,
      "learning_rate": 8.297130956269746e-06,
      "loss": 1.2532,
      "step": 450
    },
    {
      "epoch": 0.11117287381878821,
      "grad_norm": 6.496048927307129,
      "learning_rate": 0.0,
      "loss": 1.1791,
      "step": 500
    },
    {
      "epoch": 0.11117287381878821,
      "eval_loss": 0.14316821098327637,
      "eval_runtime": 1373.8924,
      "eval_samples_per_second": 5.514,
      "eval_steps_per_second": 1.379,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4161731097146163e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}