last-checkpoint/trainer_state.json

{
  "best_metric": 2.0782320499420166,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.010290712631849755,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034302375439499187,
      "eval_loss": 2.4629766941070557,
      "eval_runtime": 281.3172,
      "eval_samples_per_second": 4.365,
      "eval_steps_per_second": 2.183,
      "step": 1
    },
    {
      "epoch": 0.0010290712631849757,
      "grad_norm": 0.5096926093101501,
      "learning_rate": 0.00012,
      "loss": 2.5,
      "step": 3
    },
    {
      "epoch": 0.0017151187719749593,
      "eval_loss": 2.3564834594726562,
      "eval_runtime": 296.0575,
      "eval_samples_per_second": 4.148,
      "eval_steps_per_second": 2.074,
      "step": 5
    },
    {
      "epoch": 0.0020581425263699513,
      "grad_norm": 0.37017369270324707,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.4354,
      "step": 6
    },
    {
      "epoch": 0.0030872137895549268,
      "grad_norm": 0.40904495120048523,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.2241,
      "step": 9
    },
    {
      "epoch": 0.0034302375439499186,
      "eval_loss": 2.2053143978118896,
      "eval_runtime": 295.4824,
      "eval_samples_per_second": 4.156,
      "eval_steps_per_second": 2.078,
      "step": 10
    },
    {
      "epoch": 0.004116285052739903,
      "grad_norm": 0.28495797514915466,
      "learning_rate": 0.000163742398974869,
      "loss": 2.2277,
      "step": 12
    },
    {
      "epoch": 0.005145356315924878,
      "grad_norm": 0.2962561547756195,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1012,
      "step": 15
    },
    {
      "epoch": 0.005145356315924878,
      "eval_loss": 2.138622999191284,
      "eval_runtime": 296.2609,
      "eval_samples_per_second": 4.145,
      "eval_steps_per_second": 2.072,
      "step": 15
    },
    {
      "epoch": 0.0061744275791098535,
      "grad_norm": 0.3018041253089905,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.0662,
      "step": 18
    },
    {
      "epoch": 0.006860475087899837,
      "eval_loss": 2.099807024002075,
      "eval_runtime": 295.8571,
      "eval_samples_per_second": 4.151,
      "eval_steps_per_second": 2.075,
      "step": 20
    },
    {
      "epoch": 0.0072034988422948285,
      "grad_norm": 0.24353356659412384,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.1351,
      "step": 21
    },
    {
      "epoch": 0.008232570105479805,
      "grad_norm": 0.22688663005828857,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.1239,
      "step": 24
    },
    {
      "epoch": 0.008575593859874796,
      "eval_loss": 2.081972599029541,
      "eval_runtime": 295.2455,
      "eval_samples_per_second": 4.159,
      "eval_steps_per_second": 2.08,
      "step": 25
    },
    {
      "epoch": 0.00926164136866478,
      "grad_norm": 0.2258845567703247,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.0864,
      "step": 27
    },
    {
      "epoch": 0.010290712631849755,
      "grad_norm": 0.22580111026763916,
      "learning_rate": 0.0,
      "loss": 2.0962,
      "step": 30
    },
    {
      "epoch": 0.010290712631849755,
      "eval_loss": 2.0782320499420166,
      "eval_runtime": 295.3833,
      "eval_samples_per_second": 4.157,
      "eval_steps_per_second": 2.079,
      "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": 1.2824117212348416e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}