last-checkpoint/trainer_state.json

{
  "best_metric": 1.306259036064148,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0022862804122925676,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.620934707641892e-05,
      "eval_loss": 1.8073480129241943,
      "eval_runtime": 316.8081,
      "eval_samples_per_second": 17.44,
      "eval_steps_per_second": 8.721,
      "step": 1
    },
    {
      "epoch": 0.00022862804122925678,
      "grad_norm": 5.234768390655518,
      "learning_rate": 6e-05,
      "loss": 7.1043,
      "step": 3
    },
    {
      "epoch": 0.00038104673538209464,
      "eval_loss": 1.6780991554260254,
      "eval_runtime": 317.1358,
      "eval_samples_per_second": 17.422,
      "eval_steps_per_second": 8.712,
      "step": 5
    },
    {
      "epoch": 0.00045725608245851356,
      "grad_norm": 4.751891136169434,
      "learning_rate": 0.00012,
      "loss": 6.9796,
      "step": 6
    },
    {
      "epoch": 0.0006858841236877703,
      "grad_norm": 1.5303685665130615,
      "learning_rate": 0.00018,
      "loss": 6.136,
      "step": 9
    },
    {
      "epoch": 0.0007620934707641893,
      "eval_loss": 1.4311939477920532,
      "eval_runtime": 317.6144,
      "eval_samples_per_second": 17.395,
      "eval_steps_per_second": 8.699,
      "step": 10
    },
    {
      "epoch": 0.0009145121649170271,
      "grad_norm": 1.5748913288116455,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.0064,
      "step": 12
    },
    {
      "epoch": 0.0011431402061462838,
      "grad_norm": 1.372158408164978,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.818,
      "step": 15
    },
    {
      "epoch": 0.0011431402061462838,
      "eval_loss": 1.3485995531082153,
      "eval_runtime": 318.483,
      "eval_samples_per_second": 17.348,
      "eval_steps_per_second": 8.676,
      "step": 15
    },
    {
      "epoch": 0.0013717682473755406,
      "grad_norm": 1.4177851676940918,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.9339,
      "step": 18
    },
    {
      "epoch": 0.0015241869415283786,
      "eval_loss": 1.3187538385391235,
      "eval_runtime": 317.131,
      "eval_samples_per_second": 17.422,
      "eval_steps_per_second": 8.712,
      "step": 20
    },
    {
      "epoch": 0.0016003962886047974,
      "grad_norm": 1.3565210103988647,
      "learning_rate": 8.435655349597689e-05,
      "loss": 5.1341,
      "step": 21
    },
    {
      "epoch": 0.0018290243298340542,
      "grad_norm": 1.1311779022216797,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.3614,
      "step": 24
    },
    {
      "epoch": 0.001905233676910473,
      "eval_loss": 1.3094598054885864,
      "eval_runtime": 318.1539,
      "eval_samples_per_second": 17.366,
      "eval_steps_per_second": 8.684,
      "step": 25
    },
    {
      "epoch": 0.002057652371063311,
      "grad_norm": 1.2344831228256226,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 5.4583,
      "step": 27
    },
    {
      "epoch": 0.0022862804122925676,
      "grad_norm": 1.1939010620117188,
      "learning_rate": 0.0,
      "loss": 5.4103,
      "step": 30
    },
    {
      "epoch": 0.0022862804122925676,
      "eval_loss": 1.306259036064148,
      "eval_runtime": 316.9298,
      "eval_samples_per_second": 17.433,
      "eval_steps_per_second": 8.718,
      "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": 5526274525102080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}