last-checkpoint/trainer_state.json

{
  "best_metric": 1.772423267364502,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.01754642491592338,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005848808305307793,
      "eval_loss": 2.1095759868621826,
      "eval_runtime": 144.7912,
      "eval_samples_per_second": 4.973,
      "eval_steps_per_second": 2.486,
      "step": 1
    },
    {
      "epoch": 0.001754642491592338,
      "grad_norm": 1.3112645149230957,
      "learning_rate": 6e-05,
      "loss": 2.2311,
      "step": 3
    },
    {
      "epoch": 0.0029244041526538967,
      "eval_loss": 2.0583279132843018,
      "eval_runtime": 165.0251,
      "eval_samples_per_second": 4.363,
      "eval_steps_per_second": 2.181,
      "step": 5
    },
    {
      "epoch": 0.003509284983184676,
      "grad_norm": 0.762748122215271,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.8514,
      "step": 6
    },
    {
      "epoch": 0.005263927474777014,
      "grad_norm": 1.0121811628341675,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.9707,
      "step": 9
    },
    {
      "epoch": 0.005848808305307793,
      "eval_loss": 1.9345818758010864,
      "eval_runtime": 161.5017,
      "eval_samples_per_second": 4.458,
      "eval_steps_per_second": 2.229,
      "step": 10
    },
    {
      "epoch": 0.007018569966369352,
      "grad_norm": 1.275268793106079,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.8981,
      "step": 12
    },
    {
      "epoch": 0.00877321245796169,
      "grad_norm": 0.8033922910690308,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5351,
      "step": 15
    },
    {
      "epoch": 0.00877321245796169,
      "eval_loss": 1.8322913646697998,
      "eval_runtime": 163.0438,
      "eval_samples_per_second": 4.416,
      "eval_steps_per_second": 2.208,
      "step": 15
    },
    {
      "epoch": 0.010527854949554029,
      "grad_norm": 1.3494081497192383,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.7886,
      "step": 18
    },
    {
      "epoch": 0.011697616610615587,
      "eval_loss": 1.7933586835861206,
      "eval_runtime": 162.0286,
      "eval_samples_per_second": 4.444,
      "eval_steps_per_second": 2.222,
      "step": 20
    },
    {
      "epoch": 0.012282497441146366,
      "grad_norm": 1.2276713848114014,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.5985,
      "step": 21
    },
    {
      "epoch": 0.014037139932738705,
      "grad_norm": 0.8209657669067383,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 1.7915,
      "step": 24
    },
    {
      "epoch": 0.014622020763269484,
      "eval_loss": 1.7752649784088135,
      "eval_runtime": 163.0051,
      "eval_samples_per_second": 4.417,
      "eval_steps_per_second": 2.209,
      "step": 25
    },
    {
      "epoch": 0.015791782424331043,
      "grad_norm": 1.2699406147003174,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.833,
      "step": 27
    },
    {
      "epoch": 0.01754642491592338,
      "grad_norm": 0.857429563999176,
      "learning_rate": 0.0,
      "loss": 1.8152,
      "step": 30
    },
    {
      "epoch": 0.01754642491592338,
      "eval_loss": 1.772423267364502,
      "eval_runtime": 161.964,
      "eval_samples_per_second": 4.445,
      "eval_steps_per_second": 2.223,
      "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": 1.1684724716077056e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}