last-checkpoint/trainer_state.json

{
  "best_metric": 1.1394572257995605,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.025353898161842383,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008451299387280794,
      "eval_loss": 5.645318984985352,
      "eval_runtime": 72.9629,
      "eval_samples_per_second": 6.839,
      "eval_steps_per_second": 3.426,
      "step": 1
    },
    {
      "epoch": 0.002535389816184238,
      "grad_norm": 5.799225330352783,
      "learning_rate": 0.00012,
      "loss": 5.0106,
      "step": 3
    },
    {
      "epoch": 0.0042256496936403974,
      "eval_loss": 3.306253671646118,
      "eval_runtime": 74.7181,
      "eval_samples_per_second": 6.678,
      "eval_steps_per_second": 3.346,
      "step": 5
    },
    {
      "epoch": 0.005070779632368476,
      "grad_norm": 8.123356819152832,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.0985,
      "step": 6
    },
    {
      "epoch": 0.007606169448552715,
      "grad_norm": 10.485133171081543,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.7403,
      "step": 9
    },
    {
      "epoch": 0.008451299387280795,
      "eval_loss": 1.317594051361084,
      "eval_runtime": 75.2253,
      "eval_samples_per_second": 6.633,
      "eval_steps_per_second": 3.323,
      "step": 10
    },
    {
      "epoch": 0.010141559264736952,
      "grad_norm": 2.6403181552886963,
      "learning_rate": 0.000163742398974869,
      "loss": 1.2473,
      "step": 12
    },
    {
      "epoch": 0.012676949080921191,
      "grad_norm": 1.7580329179763794,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2577,
      "step": 15
    },
    {
      "epoch": 0.012676949080921191,
      "eval_loss": 1.1970915794372559,
      "eval_runtime": 75.3571,
      "eval_samples_per_second": 6.622,
      "eval_steps_per_second": 3.318,
      "step": 15
    },
    {
      "epoch": 0.01521233889710543,
      "grad_norm": 1.215514063835144,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.1374,
      "step": 18
    },
    {
      "epoch": 0.01690259877456159,
      "eval_loss": 1.1583677530288696,
      "eval_runtime": 75.4072,
      "eval_samples_per_second": 6.617,
      "eval_steps_per_second": 3.315,
      "step": 20
    },
    {
      "epoch": 0.017747728713289668,
      "grad_norm": 1.0871113538742065,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.2662,
      "step": 21
    },
    {
      "epoch": 0.020283118529473905,
      "grad_norm": 1.0731533765792847,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.2018,
      "step": 24
    },
    {
      "epoch": 0.021128248468201986,
      "eval_loss": 1.1418037414550781,
      "eval_runtime": 75.2574,
      "eval_samples_per_second": 6.631,
      "eval_steps_per_second": 3.322,
      "step": 25
    },
    {
      "epoch": 0.022818508345658146,
      "grad_norm": 2.0396690368652344,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.4101,
      "step": 27
    },
    {
      "epoch": 0.025353898161842383,
      "grad_norm": 1.3838458061218262,
      "learning_rate": 0.0,
      "loss": 1.2446,
      "step": 30
    },
    {
      "epoch": 0.025353898161842383,
      "eval_loss": 1.1394572257995605,
      "eval_runtime": 74.6998,
      "eval_samples_per_second": 6.68,
      "eval_steps_per_second": 3.347,
      "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": 1.150341542313984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}