last-checkpoint/trainer_state.json

{
  "best_metric": 1.2018967866897583,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.09716599190283401,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032388663967611335,
      "eval_loss": 3.423007011413574,
      "eval_runtime": 7.1963,
      "eval_samples_per_second": 36.13,
      "eval_steps_per_second": 9.032,
      "step": 1
    },
    {
      "epoch": 0.009716599190283401,
      "grad_norm": 2.631000280380249,
      "learning_rate": 0.00012,
      "loss": 2.1946,
      "step": 3
    },
    {
      "epoch": 0.016194331983805668,
      "eval_loss": 2.199885368347168,
      "eval_runtime": 7.2809,
      "eval_samples_per_second": 35.71,
      "eval_steps_per_second": 8.927,
      "step": 5
    },
    {
      "epoch": 0.019433198380566803,
      "grad_norm": 2.1495156288146973,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.9943,
      "step": 6
    },
    {
      "epoch": 0.029149797570850202,
      "grad_norm": 2.3641982078552246,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.7553,
      "step": 9
    },
    {
      "epoch": 0.032388663967611336,
      "eval_loss": 1.5183616876602173,
      "eval_runtime": 7.31,
      "eval_samples_per_second": 35.568,
      "eval_steps_per_second": 8.892,
      "step": 10
    },
    {
      "epoch": 0.038866396761133605,
      "grad_norm": 1.614790439605713,
      "learning_rate": 0.000163742398974869,
      "loss": 1.4998,
      "step": 12
    },
    {
      "epoch": 0.048582995951417005,
      "grad_norm": 0.8673895001411438,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4005,
      "step": 15
    },
    {
      "epoch": 0.048582995951417005,
      "eval_loss": 1.308341145515442,
      "eval_runtime": 7.1234,
      "eval_samples_per_second": 36.5,
      "eval_steps_per_second": 9.125,
      "step": 15
    },
    {
      "epoch": 0.058299595141700404,
      "grad_norm": 0.9261519312858582,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.3996,
      "step": 18
    },
    {
      "epoch": 0.06477732793522267,
      "eval_loss": 1.2375595569610596,
      "eval_runtime": 7.2083,
      "eval_samples_per_second": 36.07,
      "eval_steps_per_second": 9.017,
      "step": 20
    },
    {
      "epoch": 0.0680161943319838,
      "grad_norm": 0.745496928691864,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.2622,
      "step": 21
    },
    {
      "epoch": 0.07773279352226721,
      "grad_norm": 0.7845839262008667,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.252,
      "step": 24
    },
    {
      "epoch": 0.08097165991902834,
      "eval_loss": 1.2060513496398926,
      "eval_runtime": 7.2123,
      "eval_samples_per_second": 36.049,
      "eval_steps_per_second": 9.012,
      "step": 25
    },
    {
      "epoch": 0.0874493927125506,
      "grad_norm": 0.9540892839431763,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.2789,
      "step": 27
    },
    {
      "epoch": 0.09716599190283401,
      "grad_norm": 0.8427168130874634,
      "learning_rate": 0.0,
      "loss": 1.2617,
      "step": 30
    },
    {
      "epoch": 0.09716599190283401,
      "eval_loss": 1.2018967866897583,
      "eval_runtime": 7.2958,
      "eval_samples_per_second": 35.637,
      "eval_steps_per_second": 8.909,
      "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": 6542106046758912.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}