last-checkpoint/trainer_state.json

{
  "best_metric": 10.723381996154785,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.6346687822292741,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015866719555731853,
      "eval_loss": 11.10545825958252,
      "eval_runtime": 13.7406,
      "eval_samples_per_second": 308.939,
      "eval_steps_per_second": 9.679,
      "step": 1
    },
    {
      "epoch": 0.07933359777865927,
      "grad_norm": 0.8941733241081238,
      "learning_rate": 0.000214,
      "loss": 43.6515,
      "step": 50
    },
    {
      "epoch": 0.07933359777865927,
      "eval_loss": 10.841012954711914,
      "eval_runtime": 13.9719,
      "eval_samples_per_second": 303.824,
      "eval_steps_per_second": 9.519,
      "step": 50
    },
    {
      "epoch": 0.15866719555731854,
      "grad_norm": 0.8710558414459229,
      "learning_rate": 0.000214,
      "loss": 43.3002,
      "step": 100
    },
    {
      "epoch": 0.15866719555731854,
      "eval_loss": 10.81404972076416,
      "eval_runtime": 13.8126,
      "eval_samples_per_second": 307.328,
      "eval_steps_per_second": 9.629,
      "step": 100
    },
    {
      "epoch": 0.2380007933359778,
      "grad_norm": 0.8417547345161438,
      "learning_rate": 0.000214,
      "loss": 43.2285,
      "step": 150
    },
    {
      "epoch": 0.2380007933359778,
      "eval_loss": 10.799485206604004,
      "eval_runtime": 13.9045,
      "eval_samples_per_second": 305.297,
      "eval_steps_per_second": 9.565,
      "step": 150
    },
    {
      "epoch": 0.31733439111463707,
      "grad_norm": 0.9496287703514099,
      "learning_rate": 0.000214,
      "loss": 43.1918,
      "step": 200
    },
    {
      "epoch": 0.31733439111463707,
      "eval_loss": 10.78759765625,
      "eval_runtime": 13.8071,
      "eval_samples_per_second": 307.45,
      "eval_steps_per_second": 9.633,
      "step": 200
    },
    {
      "epoch": 0.3966679888932963,
      "grad_norm": 1.0544140338897705,
      "learning_rate": 0.000214,
      "loss": 43.1369,
      "step": 250
    },
    {
      "epoch": 0.3966679888932963,
      "eval_loss": 10.775155067443848,
      "eval_runtime": 13.8091,
      "eval_samples_per_second": 307.407,
      "eval_steps_per_second": 9.631,
      "step": 250
    },
    {
      "epoch": 0.4760015866719556,
      "grad_norm": 1.0072389841079712,
      "learning_rate": 0.000214,
      "loss": 43.1038,
      "step": 300
    },
    {
      "epoch": 0.4760015866719556,
      "eval_loss": 10.764233589172363,
      "eval_runtime": 13.9024,
      "eval_samples_per_second": 305.343,
      "eval_steps_per_second": 9.567,
      "step": 300
    },
    {
      "epoch": 0.5553351844506148,
      "grad_norm": 1.1393954753875732,
      "learning_rate": 0.000214,
      "loss": 43.0364,
      "step": 350
    },
    {
      "epoch": 0.5553351844506148,
      "eval_loss": 10.749459266662598,
      "eval_runtime": 13.8128,
      "eval_samples_per_second": 307.324,
      "eval_steps_per_second": 9.629,
      "step": 350
    },
    {
      "epoch": 0.6346687822292741,
      "grad_norm": 1.3822325468063354,
      "learning_rate": 0.000214,
      "loss": 42.9207,
      "step": 400
    },
    {
      "epoch": 0.6346687822292741,
      "eval_loss": 10.723381996154785,
      "eval_runtime": 13.8167,
      "eval_samples_per_second": 307.237,
      "eval_steps_per_second": 9.626,
      "step": 400
    }
  ],
  "logging_steps": 50,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 96027348566016.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}