last-checkpoint/trainer_state.json

{
  "best_metric": 1.0949171781539917,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.023575638506876228,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007858546168958742,
      "eval_loss": 1.663979172706604,
      "eval_runtime": 157.1494,
      "eval_samples_per_second": 6.822,
      "eval_steps_per_second": 1.705,
      "step": 1
    },
    {
      "epoch": 0.002357563850687623,
      "grad_norm": 0.17747168242931366,
      "learning_rate": 0.00012,
      "loss": 1.0488,
      "step": 3
    },
    {
      "epoch": 0.003929273084479371,
      "eval_loss": 1.572213888168335,
      "eval_runtime": 157.6681,
      "eval_samples_per_second": 6.799,
      "eval_steps_per_second": 1.7,
      "step": 5
    },
    {
      "epoch": 0.004715127701375246,
      "grad_norm": 0.2620897889137268,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.1636,
      "step": 6
    },
    {
      "epoch": 0.007072691552062868,
      "grad_norm": 0.3071367144584656,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.1098,
      "step": 9
    },
    {
      "epoch": 0.007858546168958742,
      "eval_loss": 1.309302568435669,
      "eval_runtime": 157.6055,
      "eval_samples_per_second": 6.802,
      "eval_steps_per_second": 1.7,
      "step": 10
    },
    {
      "epoch": 0.009430255402750491,
      "grad_norm": 0.33739161491394043,
      "learning_rate": 0.000163742398974869,
      "loss": 1.0907,
      "step": 12
    },
    {
      "epoch": 0.011787819253438114,
      "grad_norm": 0.41818809509277344,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0458,
      "step": 15
    },
    {
      "epoch": 0.011787819253438114,
      "eval_loss": 1.1936386823654175,
      "eval_runtime": 158.2706,
      "eval_samples_per_second": 6.773,
      "eval_steps_per_second": 1.693,
      "step": 15
    },
    {
      "epoch": 0.014145383104125737,
      "grad_norm": 0.6013544797897339,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.1146,
      "step": 18
    },
    {
      "epoch": 0.015717092337917484,
      "eval_loss": 1.1339696645736694,
      "eval_runtime": 157.1575,
      "eval_samples_per_second": 6.821,
      "eval_steps_per_second": 1.705,
      "step": 20
    },
    {
      "epoch": 0.016502946954813358,
      "grad_norm": 0.6046103239059448,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.0452,
      "step": 21
    },
    {
      "epoch": 0.018860510805500982,
      "grad_norm": 0.5752077698707581,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.112,
      "step": 24
    },
    {
      "epoch": 0.019646365422396856,
      "eval_loss": 1.1043939590454102,
      "eval_runtime": 158.6594,
      "eval_samples_per_second": 6.757,
      "eval_steps_per_second": 1.689,
      "step": 25
    },
    {
      "epoch": 0.021218074656188603,
      "grad_norm": 0.6900656223297119,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.0785,
      "step": 27
    },
    {
      "epoch": 0.023575638506876228,
      "grad_norm": 0.8871800303459167,
      "learning_rate": 0.0,
      "loss": 1.0869,
      "step": 30
    },
    {
      "epoch": 0.023575638506876228,
      "eval_loss": 1.0949171781539917,
      "eval_runtime": 157.1684,
      "eval_samples_per_second": 6.821,
      "eval_steps_per_second": 1.705,
      "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": 2.949001952152781e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}