last-checkpoint/trainer_state.json

{
  "best_metric": 0.8054594993591309,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.10978956999085086,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "eval_loss": 2.5816187858581543,
      "eval_runtime": 26.9741,
      "eval_samples_per_second": 4.263,
      "eval_steps_per_second": 2.15,
      "step": 1
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 1.2698482275009155,
      "learning_rate": 6e-05,
      "loss": 2.6578,
      "step": 3
    },
    {
      "epoch": 0.018298261665141813,
      "eval_loss": 2.296178102493286,
      "eval_runtime": 26.9636,
      "eval_samples_per_second": 4.265,
      "eval_steps_per_second": 2.151,
      "step": 5
    },
    {
      "epoch": 0.021957913998170174,
      "grad_norm": 1.6247072219848633,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.48,
      "step": 6
    },
    {
      "epoch": 0.03293687099725526,
      "grad_norm": 2.1021180152893066,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.8493,
      "step": 9
    },
    {
      "epoch": 0.036596523330283626,
      "eval_loss": 1.1891251802444458,
      "eval_runtime": 27.1091,
      "eval_samples_per_second": 4.242,
      "eval_steps_per_second": 2.14,
      "step": 10
    },
    {
      "epoch": 0.04391582799634035,
      "grad_norm": 1.1146501302719116,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.2096,
      "step": 12
    },
    {
      "epoch": 0.05489478499542543,
      "grad_norm": 0.576822817325592,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.972,
      "step": 15
    },
    {
      "epoch": 0.05489478499542543,
      "eval_loss": 0.8610323667526245,
      "eval_runtime": 27.0933,
      "eval_samples_per_second": 4.245,
      "eval_steps_per_second": 2.141,
      "step": 15
    },
    {
      "epoch": 0.06587374199451052,
      "grad_norm": 0.5784576535224915,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 0.8944,
      "step": 18
    },
    {
      "epoch": 0.07319304666056725,
      "eval_loss": 0.8226829767227173,
      "eval_runtime": 27.1025,
      "eval_samples_per_second": 4.243,
      "eval_steps_per_second": 2.14,
      "step": 20
    },
    {
      "epoch": 0.0768526989935956,
      "grad_norm": 0.5138906240463257,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.9201,
      "step": 21
    },
    {
      "epoch": 0.0878316559926807,
      "grad_norm": 0.4305804371833801,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 0.8424,
      "step": 24
    },
    {
      "epoch": 0.09149130832570906,
      "eval_loss": 0.807555615901947,
      "eval_runtime": 27.1058,
      "eval_samples_per_second": 4.243,
      "eval_steps_per_second": 2.14,
      "step": 25
    },
    {
      "epoch": 0.09881061299176579,
      "grad_norm": 0.4798426330089569,
      "learning_rate": 3.511175705587433e-06,
      "loss": 0.8389,
      "step": 27
    },
    {
      "epoch": 0.10978956999085086,
      "grad_norm": 0.43901804089546204,
      "learning_rate": 0.0,
      "loss": 0.8383,
      "step": 30
    },
    {
      "epoch": 0.10978956999085086,
      "eval_loss": 0.8054594993591309,
      "eval_runtime": 27.1169,
      "eval_samples_per_second": 4.241,
      "eval_steps_per_second": 2.139,
      "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": 9916411753267200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}