last-checkpoint/trainer_state.json

{
  "best_metric": 2.4615635871887207,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00030026648650677474,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0026648650677475e-05,
      "grad_norm": 2.444312810897827,
      "learning_rate": 2e-05,
      "loss": 3.318,
      "step": 1
    },
    {
      "epoch": 3.0026648650677475e-05,
      "eval_loss": 4.371880054473877,
      "eval_runtime": 2983.3634,
      "eval_samples_per_second": 4.7,
      "eval_steps_per_second": 2.35,
      "step": 1
    },
    {
      "epoch": 6.005329730135495e-05,
      "grad_norm": 2.6870970726013184,
      "learning_rate": 4e-05,
      "loss": 4.8858,
      "step": 2
    },
    {
      "epoch": 9.007994595203243e-05,
      "grad_norm": 3.0285346508026123,
      "learning_rate": 6e-05,
      "loss": 4.4867,
      "step": 3
    },
    {
      "epoch": 0.0001201065946027099,
      "grad_norm": 3.162102460861206,
      "learning_rate": 8e-05,
      "loss": 4.0637,
      "step": 4
    },
    {
      "epoch": 0.00015013324325338737,
      "grad_norm": 3.520521402359009,
      "learning_rate": 0.0001,
      "loss": 4.9885,
      "step": 5
    },
    {
      "epoch": 0.00015013324325338737,
      "eval_loss": 4.278146266937256,
      "eval_runtime": 3013.5635,
      "eval_samples_per_second": 4.653,
      "eval_steps_per_second": 2.327,
      "step": 5
    },
    {
      "epoch": 0.00018015989190406487,
      "grad_norm": 3.8060147762298584,
      "learning_rate": 0.00012,
      "loss": 4.7423,
      "step": 6
    },
    {
      "epoch": 0.00021018654055474234,
      "grad_norm": 4.787139892578125,
      "learning_rate": 0.00014,
      "loss": 3.4616,
      "step": 7
    },
    {
      "epoch": 0.0002402131892054198,
      "grad_norm": 4.9317450523376465,
      "learning_rate": 0.00016,
      "loss": 3.7389,
      "step": 8
    },
    {
      "epoch": 0.0002702398378560973,
      "grad_norm": 6.266666412353516,
      "learning_rate": 0.00018,
      "loss": 3.8855,
      "step": 9
    },
    {
      "epoch": 0.00030026648650677474,
      "grad_norm": 4.693113327026367,
      "learning_rate": 0.0002,
      "loss": 2.5356,
      "step": 10
    },
    {
      "epoch": 0.00030026648650677474,
      "eval_loss": 2.4615635871887207,
      "eval_runtime": 2990.7511,
      "eval_samples_per_second": 4.689,
      "eval_steps_per_second": 2.345,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 4353530737459200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}