last-checkpoint/trainer_state.json

{
  "best_metric": 1.6474578380584717,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0050025012506253125,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016675004168751042,
      "eval_loss": 2.469324827194214,
      "eval_runtime": 583.3719,
      "eval_samples_per_second": 8.657,
      "eval_steps_per_second": 2.165,
      "step": 1
    },
    {
      "epoch": 0.0005002501250625312,
      "grad_norm": 3.5338683128356934,
      "learning_rate": 0.00012,
      "loss": 2.159,
      "step": 3
    },
    {
      "epoch": 0.0008337502084375521,
      "eval_loss": 2.2314727306365967,
      "eval_runtime": 588.0986,
      "eval_samples_per_second": 8.587,
      "eval_steps_per_second": 2.148,
      "step": 5
    },
    {
      "epoch": 0.0010005002501250625,
      "grad_norm": 1.2442879676818848,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.8272,
      "step": 6
    },
    {
      "epoch": 0.0015007503751875938,
      "grad_norm": 0.7914564609527588,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.8582,
      "step": 9
    },
    {
      "epoch": 0.0016675004168751042,
      "eval_loss": 1.9895354509353638,
      "eval_runtime": 588.2092,
      "eval_samples_per_second": 8.585,
      "eval_steps_per_second": 2.147,
      "step": 10
    },
    {
      "epoch": 0.002001000500250125,
      "grad_norm": 0.7925866842269897,
      "learning_rate": 0.000163742398974869,
      "loss": 1.7165,
      "step": 12
    },
    {
      "epoch": 0.0025012506253126563,
      "grad_norm": 0.9452189207077026,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7026,
      "step": 15
    },
    {
      "epoch": 0.0025012506253126563,
      "eval_loss": 1.7677969932556152,
      "eval_runtime": 587.6825,
      "eval_samples_per_second": 8.593,
      "eval_steps_per_second": 2.149,
      "step": 15
    },
    {
      "epoch": 0.0030015007503751876,
      "grad_norm": 0.8682422041893005,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.6016,
      "step": 18
    },
    {
      "epoch": 0.0033350008337502085,
      "eval_loss": 1.6838022470474243,
      "eval_runtime": 587.6274,
      "eval_samples_per_second": 8.594,
      "eval_steps_per_second": 2.149,
      "step": 20
    },
    {
      "epoch": 0.003501750875437719,
      "grad_norm": 0.7741876840591431,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.5741,
      "step": 21
    },
    {
      "epoch": 0.00400200100050025,
      "grad_norm": 0.7283011078834534,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.6454,
      "step": 24
    },
    {
      "epoch": 0.00416875104218776,
      "eval_loss": 1.6534961462020874,
      "eval_runtime": 587.7652,
      "eval_samples_per_second": 8.592,
      "eval_steps_per_second": 2.149,
      "step": 25
    },
    {
      "epoch": 0.004502251125562781,
      "grad_norm": 1.129853367805481,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.6665,
      "step": 27
    },
    {
      "epoch": 0.0050025012506253125,
      "grad_norm": 0.9340394139289856,
      "learning_rate": 0.0,
      "loss": 1.6475,
      "step": 30
    },
    {
      "epoch": 0.0050025012506253125,
      "eval_loss": 1.6474578380584717,
      "eval_runtime": 587.2295,
      "eval_samples_per_second": 8.6,
      "eval_steps_per_second": 2.151,
      "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": 2.016337056497664e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}