last-checkpoint/trainer_state.json

{
  "best_metric": 2.7641873359680176,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.001203091946301996,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.01030648767332e-05,
      "eval_loss": 2.840841054916382,
      "eval_runtime": 170.0839,
      "eval_samples_per_second": 61.734,
      "eval_steps_per_second": 30.867,
      "step": 1
    },
    {
      "epoch": 0.00012030919463019961,
      "grad_norm": 0.7718831896781921,
      "learning_rate": 3e-05,
      "loss": 11.0529,
      "step": 3
    },
    {
      "epoch": 0.00020051532438366602,
      "eval_loss": 2.840318441390991,
      "eval_runtime": 169.4803,
      "eval_samples_per_second": 61.954,
      "eval_steps_per_second": 30.977,
      "step": 5
    },
    {
      "epoch": 0.00024061838926039923,
      "grad_norm": 0.8364648222923279,
      "learning_rate": 6e-05,
      "loss": 10.4353,
      "step": 6
    },
    {
      "epoch": 0.00036092758389059883,
      "grad_norm": 0.810796856880188,
      "learning_rate": 9e-05,
      "loss": 11.7993,
      "step": 9
    },
    {
      "epoch": 0.00040103064876733204,
      "eval_loss": 2.8312199115753174,
      "eval_runtime": 167.9488,
      "eval_samples_per_second": 62.519,
      "eval_steps_per_second": 31.26,
      "step": 10
    },
    {
      "epoch": 0.00048123677852079846,
      "grad_norm": 1.1680842638015747,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.236,
      "step": 12
    },
    {
      "epoch": 0.000601545973150998,
      "grad_norm": 1.037770390510559,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.5245,
      "step": 15
    },
    {
      "epoch": 0.000601545973150998,
      "eval_loss": 2.8045854568481445,
      "eval_runtime": 167.5128,
      "eval_samples_per_second": 62.682,
      "eval_steps_per_second": 31.341,
      "step": 15
    },
    {
      "epoch": 0.0007218551677811977,
      "grad_norm": 1.0737652778625488,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.5629,
      "step": 18
    },
    {
      "epoch": 0.0008020612975346641,
      "eval_loss": 2.7786405086517334,
      "eval_runtime": 168.2878,
      "eval_samples_per_second": 62.393,
      "eval_steps_per_second": 31.197,
      "step": 20
    },
    {
      "epoch": 0.0008421643624113973,
      "grad_norm": 1.4385324716567993,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 11.0936,
      "step": 21
    },
    {
      "epoch": 0.0009624735570415969,
      "grad_norm": 1.2842581272125244,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.5965,
      "step": 24
    },
    {
      "epoch": 0.00100257662191833,
      "eval_loss": 2.7664456367492676,
      "eval_runtime": 167.7922,
      "eval_samples_per_second": 62.577,
      "eval_steps_per_second": 31.289,
      "step": 25
    },
    {
      "epoch": 0.0010827827516717964,
      "grad_norm": 1.403336524963379,
      "learning_rate": 5.449673790581611e-06,
      "loss": 10.7527,
      "step": 27
    },
    {
      "epoch": 0.001203091946301996,
      "grad_norm": 1.1576800346374512,
      "learning_rate": 0.0,
      "loss": 11.1552,
      "step": 30
    },
    {
      "epoch": 0.001203091946301996,
      "eval_loss": 2.7641873359680176,
      "eval_runtime": 167.309,
      "eval_samples_per_second": 62.758,
      "eval_steps_per_second": 31.379,
      "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": 129293195673600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}