last-checkpoint/trainer_state.json

{
  "best_metric": 1.0392017364501953,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.07357449417535254,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002452483139178418,
      "eval_loss": 1.4818801879882812,
      "eval_runtime": 22.764,
      "eval_samples_per_second": 7.556,
      "eval_steps_per_second": 3.778,
      "step": 1
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 1.2928500175476074,
      "learning_rate": 0.00012,
      "loss": 1.734,
      "step": 3
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 1.3787840604782104,
      "eval_runtime": 22.5045,
      "eval_samples_per_second": 7.643,
      "eval_steps_per_second": 3.821,
      "step": 5
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 1.2489778995513916,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.3838,
      "step": 6
    },
    {
      "epoch": 0.022072348252605765,
      "grad_norm": 1.3369332551956177,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.3781,
      "step": 9
    },
    {
      "epoch": 0.024524831391784182,
      "eval_loss": 1.1421102285385132,
      "eval_runtime": 22.61,
      "eval_samples_per_second": 7.607,
      "eval_steps_per_second": 3.804,
      "step": 10
    },
    {
      "epoch": 0.029429797670141016,
      "grad_norm": 1.327689290046692,
      "learning_rate": 0.000163742398974869,
      "loss": 1.1258,
      "step": 12
    },
    {
      "epoch": 0.03678724708767627,
      "grad_norm": 1.273471713066101,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9996,
      "step": 15
    },
    {
      "epoch": 0.03678724708767627,
      "eval_loss": 1.0793565511703491,
      "eval_runtime": 22.625,
      "eval_samples_per_second": 7.602,
      "eval_steps_per_second": 3.801,
      "step": 15
    },
    {
      "epoch": 0.04414469650521153,
      "grad_norm": 1.7768419981002808,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.0098,
      "step": 18
    },
    {
      "epoch": 0.049049662783568364,
      "eval_loss": 1.0603944063186646,
      "eval_runtime": 22.7228,
      "eval_samples_per_second": 7.569,
      "eval_steps_per_second": 3.785,
      "step": 20
    },
    {
      "epoch": 0.05150214592274678,
      "grad_norm": 1.286733627319336,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.8213,
      "step": 21
    },
    {
      "epoch": 0.05885959534028203,
      "grad_norm": 1.1605747938156128,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.9504,
      "step": 24
    },
    {
      "epoch": 0.061312078479460456,
      "eval_loss": 1.0429292917251587,
      "eval_runtime": 22.7352,
      "eval_samples_per_second": 7.565,
      "eval_steps_per_second": 3.783,
      "step": 25
    },
    {
      "epoch": 0.06621704475781728,
      "grad_norm": 1.3598169088363647,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.1226,
      "step": 27
    },
    {
      "epoch": 0.07357449417535254,
      "grad_norm": 1.4133316278457642,
      "learning_rate": 0.0,
      "loss": 1.0215,
      "step": 30
    },
    {
      "epoch": 0.07357449417535254,
      "eval_loss": 1.0392017364501953,
      "eval_runtime": 22.7316,
      "eval_samples_per_second": 7.567,
      "eval_steps_per_second": 3.783,
      "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": 1.0455331230449664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}