last-checkpoint/trainer_state.json

{
  "best_metric": 0.49480313062667847,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.11650485436893204,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003883495145631068,
      "eval_loss": 1.0708863735198975,
      "eval_runtime": 36.8376,
      "eval_samples_per_second": 5.891,
      "eval_steps_per_second": 1.493,
      "step": 1
    },
    {
      "epoch": 0.011650485436893204,
      "grad_norm": 0.9972766041755676,
      "learning_rate": 0.00012,
      "loss": 2.9957,
      "step": 3
    },
    {
      "epoch": 0.019417475728155338,
      "eval_loss": 0.950129508972168,
      "eval_runtime": 37.5993,
      "eval_samples_per_second": 5.771,
      "eval_steps_per_second": 1.463,
      "step": 5
    },
    {
      "epoch": 0.02330097087378641,
      "grad_norm": 0.9317790269851685,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.0089,
      "step": 6
    },
    {
      "epoch": 0.03495145631067961,
      "grad_norm": 1.0619981288909912,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.5937,
      "step": 9
    },
    {
      "epoch": 0.038834951456310676,
      "eval_loss": 0.6780943870544434,
      "eval_runtime": 37.7566,
      "eval_samples_per_second": 5.747,
      "eval_steps_per_second": 1.457,
      "step": 10
    },
    {
      "epoch": 0.04660194174757282,
      "grad_norm": 3.01274037361145,
      "learning_rate": 0.000163742398974869,
      "loss": 2.4687,
      "step": 12
    },
    {
      "epoch": 0.05825242718446602,
      "grad_norm": 1.2839837074279785,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2457,
      "step": 15
    },
    {
      "epoch": 0.05825242718446602,
      "eval_loss": 0.5668467283248901,
      "eval_runtime": 37.7843,
      "eval_samples_per_second": 5.743,
      "eval_steps_per_second": 1.456,
      "step": 15
    },
    {
      "epoch": 0.06990291262135923,
      "grad_norm": 1.24266517162323,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.3707,
      "step": 18
    },
    {
      "epoch": 0.07766990291262135,
      "eval_loss": 0.5173833966255188,
      "eval_runtime": 37.7177,
      "eval_samples_per_second": 5.753,
      "eval_steps_per_second": 1.458,
      "step": 20
    },
    {
      "epoch": 0.08155339805825243,
      "grad_norm": 0.9959689378738403,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.8811,
      "step": 21
    },
    {
      "epoch": 0.09320388349514563,
      "grad_norm": 0.9961031675338745,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.0414,
      "step": 24
    },
    {
      "epoch": 0.0970873786407767,
      "eval_loss": 0.4978864789009094,
      "eval_runtime": 37.7461,
      "eval_samples_per_second": 5.749,
      "eval_steps_per_second": 1.457,
      "step": 25
    },
    {
      "epoch": 0.10485436893203884,
      "grad_norm": 1.0980758666992188,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.0524,
      "step": 27
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 1.2487680912017822,
      "learning_rate": 0.0,
      "loss": 1.8476,
      "step": 30
    },
    {
      "epoch": 0.11650485436893204,
      "eval_loss": 0.49480313062667847,
      "eval_runtime": 37.7726,
      "eval_samples_per_second": 5.745,
      "eval_steps_per_second": 1.456,
      "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": 3.80869797740544e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}