last-checkpoint/trainer_state.json

{
  "best_metric": 1.8506921529769897,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0027935561970388306,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.311853990129435e-05,
      "eval_loss": 2.239907741546631,
      "eval_runtime": 530.5579,
      "eval_samples_per_second": 17.046,
      "eval_steps_per_second": 4.262,
      "step": 1
    },
    {
      "epoch": 0.00027935561970388306,
      "grad_norm": 0.5319666266441345,
      "learning_rate": 3e-05,
      "loss": 1.4587,
      "step": 3
    },
    {
      "epoch": 0.00046559269950647176,
      "eval_loss": 2.222862958908081,
      "eval_runtime": 531.5266,
      "eval_samples_per_second": 17.015,
      "eval_steps_per_second": 4.254,
      "step": 5
    },
    {
      "epoch": 0.0005587112394077661,
      "grad_norm": 0.6885255575180054,
      "learning_rate": 4.980286753286195e-05,
      "loss": 1.5013,
      "step": 6
    },
    {
      "epoch": 0.0008380668591116492,
      "grad_norm": 0.6666805148124695,
      "learning_rate": 4.690766700109659e-05,
      "loss": 1.5717,
      "step": 9
    },
    {
      "epoch": 0.0009311853990129435,
      "eval_loss": 2.1020290851593018,
      "eval_runtime": 530.0403,
      "eval_samples_per_second": 17.063,
      "eval_steps_per_second": 4.266,
      "step": 10
    },
    {
      "epoch": 0.0011174224788155322,
      "grad_norm": 0.6238915324211121,
      "learning_rate": 4.093559974371725e-05,
      "loss": 1.4998,
      "step": 12
    },
    {
      "epoch": 0.0013967780985194153,
      "grad_norm": 0.6593775749206543,
      "learning_rate": 3.272542485937369e-05,
      "loss": 1.5247,
      "step": 15
    },
    {
      "epoch": 0.0013967780985194153,
      "eval_loss": 1.9904972314834595,
      "eval_runtime": 530.8616,
      "eval_samples_per_second": 17.036,
      "eval_steps_per_second": 4.259,
      "step": 15
    },
    {
      "epoch": 0.0016761337182232983,
      "grad_norm": 0.750754714012146,
      "learning_rate": 2.3430237011767167e-05,
      "loss": 1.5183,
      "step": 18
    },
    {
      "epoch": 0.001862370798025887,
      "eval_loss": 1.9088382720947266,
      "eval_runtime": 531.5204,
      "eval_samples_per_second": 17.015,
      "eval_steps_per_second": 4.254,
      "step": 20
    },
    {
      "epoch": 0.0019554893379271814,
      "grad_norm": 0.8892120122909546,
      "learning_rate": 1.4355517710873184e-05,
      "loss": 1.5314,
      "step": 21
    },
    {
      "epoch": 0.0022348449576310644,
      "grad_norm": 1.0052318572998047,
      "learning_rate": 6.775784314464717e-06,
      "loss": 1.5404,
      "step": 24
    },
    {
      "epoch": 0.002327963497532359,
      "eval_loss": 1.8609997034072876,
      "eval_runtime": 530.1572,
      "eval_samples_per_second": 17.059,
      "eval_steps_per_second": 4.265,
      "step": 25
    },
    {
      "epoch": 0.0025142005773349475,
      "grad_norm": 1.1246418952941895,
      "learning_rate": 1.7555878527937164e-06,
      "loss": 1.5776,
      "step": 27
    },
    {
      "epoch": 0.0027935561970388306,
      "grad_norm": 1.5440231561660767,
      "learning_rate": 0.0,
      "loss": 1.7174,
      "step": 30
    },
    {
      "epoch": 0.0027935561970388306,
      "eval_loss": 1.8506921529769897,
      "eval_runtime": 530.694,
      "eval_samples_per_second": 17.042,
      "eval_steps_per_second": 4.26,
      "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": 2.570894304922829e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}