last-checkpoint/trainer_state.json

{
  "best_metric": 1.5604957342147827,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0004968944099378882,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6563146997929607e-05,
      "eval_loss": 1.7354477643966675,
      "eval_runtime": 3029.7416,
      "eval_samples_per_second": 8.39,
      "eval_steps_per_second": 4.195,
      "step": 1
    },
    {
      "epoch": 4.968944099378882e-05,
      "grad_norm": 0.46449899673461914,
      "learning_rate": 6e-05,
      "loss": 1.7907,
      "step": 3
    },
    {
      "epoch": 8.281573498964803e-05,
      "eval_loss": 1.7044700384140015,
      "eval_runtime": 3033.6502,
      "eval_samples_per_second": 8.38,
      "eval_steps_per_second": 4.19,
      "step": 5
    },
    {
      "epoch": 9.937888198757764e-05,
      "grad_norm": 0.5845046043395996,
      "learning_rate": 0.00012,
      "loss": 1.814,
      "step": 6
    },
    {
      "epoch": 0.00014906832298136645,
      "grad_norm": 0.32533901929855347,
      "learning_rate": 0.00018,
      "loss": 1.5945,
      "step": 9
    },
    {
      "epoch": 0.00016563146997929605,
      "eval_loss": 1.6549012660980225,
      "eval_runtime": 3029.9283,
      "eval_samples_per_second": 8.39,
      "eval_steps_per_second": 4.195,
      "step": 10
    },
    {
      "epoch": 0.00019875776397515528,
      "grad_norm": 0.5781303644180298,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.5987,
      "step": 12
    },
    {
      "epoch": 0.0002484472049689441,
      "grad_norm": 0.37722793221473694,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.7165,
      "step": 15
    },
    {
      "epoch": 0.0002484472049689441,
      "eval_loss": 1.5890259742736816,
      "eval_runtime": 3030.0327,
      "eval_samples_per_second": 8.39,
      "eval_steps_per_second": 4.195,
      "step": 15
    },
    {
      "epoch": 0.0002981366459627329,
      "grad_norm": 0.30050724744796753,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7152,
      "step": 18
    },
    {
      "epoch": 0.0003312629399585921,
      "eval_loss": 1.5705841779708862,
      "eval_runtime": 3031.3045,
      "eval_samples_per_second": 8.386,
      "eval_steps_per_second": 4.193,
      "step": 20
    },
    {
      "epoch": 0.00034782608695652176,
      "grad_norm": 0.34454429149627686,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.5959,
      "step": 21
    },
    {
      "epoch": 0.00039751552795031056,
      "grad_norm": 0.30111217498779297,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.5235,
      "step": 24
    },
    {
      "epoch": 0.00041407867494824016,
      "eval_loss": 1.5620274543762207,
      "eval_runtime": 3033.885,
      "eval_samples_per_second": 8.379,
      "eval_steps_per_second": 4.19,
      "step": 25
    },
    {
      "epoch": 0.00044720496894409936,
      "grad_norm": 0.2756118178367615,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.5289,
      "step": 27
    },
    {
      "epoch": 0.0004968944099378882,
      "grad_norm": 0.2829815149307251,
      "learning_rate": 0.0,
      "loss": 1.5688,
      "step": 30
    },
    {
      "epoch": 0.0004968944099378882,
      "eval_loss": 1.5604957342147827,
      "eval_runtime": 3033.3725,
      "eval_samples_per_second": 8.38,
      "eval_steps_per_second": 4.19,
      "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": 4939038012211200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}