last-checkpoint/trainer_state.json

{
  "best_metric": 0.4652339220046997,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.012795905310300703,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042653017701002344,
      "eval_loss": 0.56065833568573,
      "eval_runtime": 263.2979,
      "eval_samples_per_second": 3.752,
      "eval_steps_per_second": 1.876,
      "step": 1
    },
    {
      "epoch": 0.0012795905310300703,
      "grad_norm": 0.6046045422554016,
      "learning_rate": 6e-05,
      "loss": 2.1147,
      "step": 3
    },
    {
      "epoch": 0.0021326508850501172,
      "eval_loss": 0.5460861325263977,
      "eval_runtime": 262.8719,
      "eval_samples_per_second": 3.758,
      "eval_steps_per_second": 1.879,
      "step": 5
    },
    {
      "epoch": 0.0025591810620601407,
      "grad_norm": 0.8303176164627075,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.2154,
      "step": 6
    },
    {
      "epoch": 0.003838771593090211,
      "grad_norm": 0.6104483604431152,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.0916,
      "step": 9
    },
    {
      "epoch": 0.0042653017701002344,
      "eval_loss": 0.5023233890533447,
      "eval_runtime": 262.8886,
      "eval_samples_per_second": 3.758,
      "eval_steps_per_second": 1.879,
      "step": 10
    },
    {
      "epoch": 0.005118362124120281,
      "grad_norm": 0.5042480826377869,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.0858,
      "step": 12
    },
    {
      "epoch": 0.006397952655150352,
      "grad_norm": 0.5379993319511414,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.8691,
      "step": 15
    },
    {
      "epoch": 0.006397952655150352,
      "eval_loss": 0.48632144927978516,
      "eval_runtime": 262.8336,
      "eval_samples_per_second": 3.759,
      "eval_steps_per_second": 1.88,
      "step": 15
    },
    {
      "epoch": 0.007677543186180422,
      "grad_norm": 0.5686798691749573,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.8122,
      "step": 18
    },
    {
      "epoch": 0.008530603540200469,
      "eval_loss": 0.4728478491306305,
      "eval_runtime": 262.8181,
      "eval_samples_per_second": 3.759,
      "eval_steps_per_second": 1.88,
      "step": 20
    },
    {
      "epoch": 0.008957133717210493,
      "grad_norm": 0.5234971046447754,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.8444,
      "step": 21
    },
    {
      "epoch": 0.010236724248240563,
      "grad_norm": 0.5886001586914062,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.0016,
      "step": 24
    },
    {
      "epoch": 0.010663254425250587,
      "eval_loss": 0.46638426184654236,
      "eval_runtime": 263.2899,
      "eval_samples_per_second": 3.753,
      "eval_steps_per_second": 1.876,
      "step": 25
    },
    {
      "epoch": 0.011516314779270634,
      "grad_norm": 0.45593273639678955,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.7822,
      "step": 27
    },
    {
      "epoch": 0.012795905310300703,
      "grad_norm": 0.4886685907840729,
      "learning_rate": 0.0,
      "loss": 1.7605,
      "step": 30
    },
    {
      "epoch": 0.012795905310300703,
      "eval_loss": 0.4652339220046997,
      "eval_runtime": 263.4922,
      "eval_samples_per_second": 3.75,
      "eval_steps_per_second": 1.875,
      "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": 1.105254905020416e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}