last-checkpoint/trainer_state.json

{
  "best_metric": 2.6249186992645264,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.05052631578947368,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016842105263157896,
      "eval_loss": 2.92533802986145,
      "eval_runtime": 3.745,
      "eval_samples_per_second": 66.756,
      "eval_steps_per_second": 33.378,
      "step": 1
    },
    {
      "epoch": 0.0050526315789473685,
      "grad_norm": 35.71746063232422,
      "learning_rate": 0.00012,
      "loss": 11.3872,
      "step": 3
    },
    {
      "epoch": 0.008421052631578947,
      "eval_loss": 2.8504750728607178,
      "eval_runtime": 3.7695,
      "eval_samples_per_second": 66.321,
      "eval_steps_per_second": 33.161,
      "step": 5
    },
    {
      "epoch": 0.010105263157894737,
      "grad_norm": 35.931671142578125,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.7503,
      "step": 6
    },
    {
      "epoch": 0.015157894736842105,
      "grad_norm": 32.63925552368164,
      "learning_rate": 0.00018763066800438636,
      "loss": 10.862,
      "step": 9
    },
    {
      "epoch": 0.016842105263157894,
      "eval_loss": 2.722824811935425,
      "eval_runtime": 3.794,
      "eval_samples_per_second": 65.893,
      "eval_steps_per_second": 32.946,
      "step": 10
    },
    {
      "epoch": 0.020210526315789474,
      "grad_norm": 49.80840301513672,
      "learning_rate": 0.000163742398974869,
      "loss": 10.0518,
      "step": 12
    },
    {
      "epoch": 0.02526315789473684,
      "grad_norm": 42.67620086669922,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.1562,
      "step": 15
    },
    {
      "epoch": 0.02526315789473684,
      "eval_loss": 2.6727020740509033,
      "eval_runtime": 3.8096,
      "eval_samples_per_second": 65.624,
      "eval_steps_per_second": 32.812,
      "step": 15
    },
    {
      "epoch": 0.03031578947368421,
      "grad_norm": 66.15996551513672,
      "learning_rate": 9.372094804706867e-05,
      "loss": 10.1741,
      "step": 18
    },
    {
      "epoch": 0.03368421052631579,
      "eval_loss": 2.6460254192352295,
      "eval_runtime": 3.806,
      "eval_samples_per_second": 65.686,
      "eval_steps_per_second": 32.843,
      "step": 20
    },
    {
      "epoch": 0.03536842105263158,
      "grad_norm": 45.487239837646484,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 10.2749,
      "step": 21
    },
    {
      "epoch": 0.04042105263157895,
      "grad_norm": 51.95940017700195,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 11.3656,
      "step": 24
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 2.626051425933838,
      "eval_runtime": 3.8337,
      "eval_samples_per_second": 65.211,
      "eval_steps_per_second": 32.606,
      "step": 25
    },
    {
      "epoch": 0.04547368421052632,
      "grad_norm": 39.46547317504883,
      "learning_rate": 7.022351411174866e-06,
      "loss": 10.9621,
      "step": 27
    },
    {
      "epoch": 0.05052631578947368,
      "grad_norm": 38.4549674987793,
      "learning_rate": 0.0,
      "loss": 9.9003,
      "step": 30
    },
    {
      "epoch": 0.05052631578947368,
      "eval_loss": 2.6249186992645264,
      "eval_runtime": 3.842,
      "eval_samples_per_second": 65.07,
      "eval_steps_per_second": 32.535,
      "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": 531009959362560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}