last-checkpoint/trainer_state.json

{
  "best_metric": 1.9577324390411377,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0025854825156744875,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.618275052248293e-05,
      "eval_loss": 2.57096529006958,
      "eval_runtime": 724.3902,
      "eval_samples_per_second": 6.745,
      "eval_steps_per_second": 3.372,
      "step": 1
    },
    {
      "epoch": 0.0002585482515674488,
      "grad_norm": 1.1678370237350464,
      "learning_rate": 3e-05,
      "loss": 2.5973,
      "step": 3
    },
    {
      "epoch": 0.0004309137526124146,
      "eval_loss": 2.531855344772339,
      "eval_runtime": 727.2568,
      "eval_samples_per_second": 6.718,
      "eval_steps_per_second": 3.359,
      "step": 5
    },
    {
      "epoch": 0.0005170965031348976,
      "grad_norm": 0.9036294221878052,
      "learning_rate": 6e-05,
      "loss": 2.6077,
      "step": 6
    },
    {
      "epoch": 0.0007756447547023463,
      "grad_norm": 0.9021340608596802,
      "learning_rate": 9e-05,
      "loss": 2.5392,
      "step": 9
    },
    {
      "epoch": 0.0008618275052248292,
      "eval_loss": 2.293621778488159,
      "eval_runtime": 727.6181,
      "eval_samples_per_second": 6.715,
      "eval_steps_per_second": 3.358,
      "step": 10
    },
    {
      "epoch": 0.001034193006269795,
      "grad_norm": 1.4376518726348877,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1546,
      "step": 12
    },
    {
      "epoch": 0.0012927412578372438,
      "grad_norm": 0.8561299443244934,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.0008,
      "step": 15
    },
    {
      "epoch": 0.0012927412578372438,
      "eval_loss": 2.138024091720581,
      "eval_runtime": 726.3131,
      "eval_samples_per_second": 6.727,
      "eval_steps_per_second": 3.364,
      "step": 15
    },
    {
      "epoch": 0.0015512895094046927,
      "grad_norm": 0.7144878506660461,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1058,
      "step": 18
    },
    {
      "epoch": 0.0017236550104496584,
      "eval_loss": 2.027435064315796,
      "eval_runtime": 726.536,
      "eval_samples_per_second": 6.725,
      "eval_steps_per_second": 3.363,
      "step": 20
    },
    {
      "epoch": 0.0018098377609721413,
      "grad_norm": 0.6979389190673828,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.098,
      "step": 21
    },
    {
      "epoch": 0.00206838601253959,
      "grad_norm": 0.6137436032295227,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.9768,
      "step": 24
    },
    {
      "epoch": 0.002154568763062073,
      "eval_loss": 1.970348596572876,
      "eval_runtime": 727.1195,
      "eval_samples_per_second": 6.72,
      "eval_steps_per_second": 3.36,
      "step": 25
    },
    {
      "epoch": 0.002326934264107039,
      "grad_norm": 0.5752513408660889,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.9468,
      "step": 27
    },
    {
      "epoch": 0.0025854825156744875,
      "grad_norm": 0.9238215088844299,
      "learning_rate": 0.0,
      "loss": 2.0248,
      "step": 30
    },
    {
      "epoch": 0.0025854825156744875,
      "eval_loss": 1.9577324390411377,
      "eval_runtime": 727.8641,
      "eval_samples_per_second": 6.713,
      "eval_steps_per_second": 3.356,
      "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": 5597576413839360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}