last-checkpoint/trainer_state.json

{
  "best_metric": 3.9313950538635254,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005042440541221951,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016808135137406504,
      "eval_loss": 4.548350811004639,
      "eval_runtime": 58.465,
      "eval_samples_per_second": 42.846,
      "eval_steps_per_second": 21.432,
      "step": 1
    },
    {
      "epoch": 0.0005042440541221952,
      "grad_norm": 0.7331871390342712,
      "learning_rate": 6e-05,
      "loss": 4.3605,
      "step": 3
    },
    {
      "epoch": 0.0008404067568703252,
      "eval_loss": 4.5230183601379395,
      "eval_runtime": 57.8813,
      "eval_samples_per_second": 43.278,
      "eval_steps_per_second": 21.648,
      "step": 5
    },
    {
      "epoch": 0.0010084881082443903,
      "grad_norm": 1.129091501235962,
      "learning_rate": 0.00012,
      "loss": 4.496,
      "step": 6
    },
    {
      "epoch": 0.0015127321623665854,
      "grad_norm": 0.8002145290374756,
      "learning_rate": 0.00018,
      "loss": 4.6274,
      "step": 9
    },
    {
      "epoch": 0.0016808135137406505,
      "eval_loss": 4.304622173309326,
      "eval_runtime": 57.9016,
      "eval_samples_per_second": 43.263,
      "eval_steps_per_second": 21.64,
      "step": 10
    },
    {
      "epoch": 0.0020169762164887806,
      "grad_norm": 0.7687255144119263,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.9261,
      "step": 12
    },
    {
      "epoch": 0.0025212202706109757,
      "grad_norm": 1.191295862197876,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.3418,
      "step": 15
    },
    {
      "epoch": 0.0025212202706109757,
      "eval_loss": 4.126147747039795,
      "eval_runtime": 57.9307,
      "eval_samples_per_second": 43.241,
      "eval_steps_per_second": 21.629,
      "step": 15
    },
    {
      "epoch": 0.0030254643247331708,
      "grad_norm": 0.7187232375144958,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.2573,
      "step": 18
    },
    {
      "epoch": 0.003361627027481301,
      "eval_loss": 3.9761948585510254,
      "eval_runtime": 57.935,
      "eval_samples_per_second": 43.238,
      "eval_steps_per_second": 21.628,
      "step": 20
    },
    {
      "epoch": 0.003529708378855366,
      "grad_norm": 0.8214964270591736,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.8518,
      "step": 21
    },
    {
      "epoch": 0.004033952432977561,
      "grad_norm": 0.7705588936805725,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.9388,
      "step": 24
    },
    {
      "epoch": 0.004202033784351626,
      "eval_loss": 3.9394900798797607,
      "eval_runtime": 58.05,
      "eval_samples_per_second": 43.152,
      "eval_steps_per_second": 21.585,
      "step": 25
    },
    {
      "epoch": 0.004538196487099756,
      "grad_norm": 0.7781285047531128,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 4.0402,
      "step": 27
    },
    {
      "epoch": 0.005042440541221951,
      "grad_norm": 1.2990456819534302,
      "learning_rate": 0.0,
      "loss": 4.078,
      "step": 30
    },
    {
      "epoch": 0.005042440541221951,
      "eval_loss": 3.9313950538635254,
      "eval_runtime": 57.9877,
      "eval_samples_per_second": 43.199,
      "eval_steps_per_second": 21.608,
      "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": 1544053158051840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}