last-checkpoint/trainer_state.json

{
  "best_metric": 1.3834524154663086,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0015083240634250269,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.541620317125135e-05,
      "eval_loss": 1.8153135776519775,
      "eval_runtime": 1593.9524,
      "eval_samples_per_second": 3.503,
      "eval_steps_per_second": 1.752,
      "step": 1
    },
    {
      "epoch": 0.00022624860951375402,
      "grad_norm": 2.8038218021392822,
      "learning_rate": 6e-05,
      "loss": 7.3316,
      "step": 3
    },
    {
      "epoch": 0.0003770810158562567,
      "eval_loss": 1.6777693033218384,
      "eval_runtime": 1603.5828,
      "eval_samples_per_second": 3.482,
      "eval_steps_per_second": 1.741,
      "step": 5
    },
    {
      "epoch": 0.00045249721902750805,
      "grad_norm": 2.051038980484009,
      "learning_rate": 0.00012,
      "loss": 7.0454,
      "step": 6
    },
    {
      "epoch": 0.0006787458285412621,
      "grad_norm": 4.268225193023682,
      "learning_rate": 0.00018,
      "loss": 6.7648,
      "step": 9
    },
    {
      "epoch": 0.0007541620317125134,
      "eval_loss": 1.5855581760406494,
      "eval_runtime": 1603.3237,
      "eval_samples_per_second": 3.483,
      "eval_steps_per_second": 1.741,
      "step": 10
    },
    {
      "epoch": 0.0009049944380550161,
      "grad_norm": 1.9496262073516846,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.3233,
      "step": 12
    },
    {
      "epoch": 0.0011312430475687702,
      "grad_norm": 2.13738751411438,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.0778,
      "step": 15
    },
    {
      "epoch": 0.0011312430475687702,
      "eval_loss": 1.461401104927063,
      "eval_runtime": 1602.9873,
      "eval_samples_per_second": 3.483,
      "eval_steps_per_second": 1.742,
      "step": 15
    },
    {
      "epoch": 0.0013574916570825242,
      "grad_norm": 1.280239224433899,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.633,
      "step": 18
    },
    {
      "epoch": 0.0015083240634250269,
      "eval_loss": 1.3834524154663086,
      "eval_runtime": 1603.2441,
      "eval_samples_per_second": 3.483,
      "eval_steps_per_second": 1.741,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.015315512786944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}