last-checkpoint/trainer_state.json

{
  "best_metric": 0.8137642741203308,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06072874493927125,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020242914979757085,
      "eval_loss": 1.118082880973816,
      "eval_runtime": 26.5534,
      "eval_samples_per_second": 7.833,
      "eval_steps_per_second": 3.917,
      "step": 1
    },
    {
      "epoch": 0.006072874493927126,
      "grad_norm": 0.8115025758743286,
      "learning_rate": 3e-05,
      "loss": 1.1044,
      "step": 3
    },
    {
      "epoch": 0.010121457489878543,
      "eval_loss": 1.1003472805023193,
      "eval_runtime": 27.0132,
      "eval_samples_per_second": 7.7,
      "eval_steps_per_second": 3.85,
      "step": 5
    },
    {
      "epoch": 0.012145748987854251,
      "grad_norm": 0.8825178146362305,
      "learning_rate": 6e-05,
      "loss": 1.1099,
      "step": 6
    },
    {
      "epoch": 0.018218623481781375,
      "grad_norm": 0.8290417194366455,
      "learning_rate": 9e-05,
      "loss": 0.9974,
      "step": 9
    },
    {
      "epoch": 0.020242914979757085,
      "eval_loss": 0.9930984973907471,
      "eval_runtime": 27.2052,
      "eval_samples_per_second": 7.646,
      "eval_steps_per_second": 3.823,
      "step": 10
    },
    {
      "epoch": 0.024291497975708502,
      "grad_norm": 1.1878786087036133,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9666,
      "step": 12
    },
    {
      "epoch": 0.030364372469635626,
      "grad_norm": 1.2937405109405518,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.899,
      "step": 15
    },
    {
      "epoch": 0.030364372469635626,
      "eval_loss": 0.8926659822463989,
      "eval_runtime": 27.3053,
      "eval_samples_per_second": 7.618,
      "eval_steps_per_second": 3.809,
      "step": 15
    },
    {
      "epoch": 0.03643724696356275,
      "grad_norm": 1.1668306589126587,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8377,
      "step": 18
    },
    {
      "epoch": 0.04048582995951417,
      "eval_loss": 0.8399719595909119,
      "eval_runtime": 27.3294,
      "eval_samples_per_second": 7.611,
      "eval_steps_per_second": 3.805,
      "step": 20
    },
    {
      "epoch": 0.04251012145748988,
      "grad_norm": 1.021464467048645,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.875,
      "step": 21
    },
    {
      "epoch": 0.048582995951417005,
      "grad_norm": 1.176374912261963,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7684,
      "step": 24
    },
    {
      "epoch": 0.05060728744939271,
      "eval_loss": 0.8207021951675415,
      "eval_runtime": 27.3776,
      "eval_samples_per_second": 7.597,
      "eval_steps_per_second": 3.799,
      "step": 25
    },
    {
      "epoch": 0.05465587044534413,
      "grad_norm": 0.9073843955993652,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.8368,
      "step": 27
    },
    {
      "epoch": 0.06072874493927125,
      "grad_norm": 1.1118440628051758,
      "learning_rate": 0.0,
      "loss": 0.8223,
      "step": 30
    },
    {
      "epoch": 0.06072874493927125,
      "eval_loss": 0.8137642741203308,
      "eval_runtime": 27.3651,
      "eval_samples_per_second": 7.601,
      "eval_steps_per_second": 3.8,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}