last-checkpoint/trainer_state.json

{
  "best_metric": 1.100005030632019,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.002071072297682125,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.903574325607083e-05,
      "eval_loss": 1.6781178712844849,
      "eval_runtime": 838.6739,
      "eval_samples_per_second": 7.272,
      "eval_steps_per_second": 3.637,
      "step": 1
    },
    {
      "epoch": 0.00020710722976821248,
      "grad_norm": 0.9852650761604309,
      "learning_rate": 6e-05,
      "loss": 1.4438,
      "step": 3
    },
    {
      "epoch": 0.00034517871628035417,
      "eval_loss": 1.6058242321014404,
      "eval_runtime": 842.8088,
      "eval_samples_per_second": 7.237,
      "eval_steps_per_second": 3.619,
      "step": 5
    },
    {
      "epoch": 0.00041421445953642496,
      "grad_norm": 1.22545325756073,
      "learning_rate": 0.00012,
      "loss": 1.5041,
      "step": 6
    },
    {
      "epoch": 0.0006213216893046374,
      "grad_norm": 1.2531858682632446,
      "learning_rate": 0.00018,
      "loss": 1.5687,
      "step": 9
    },
    {
      "epoch": 0.0006903574325607083,
      "eval_loss": 1.2398513555526733,
      "eval_runtime": 842.4208,
      "eval_samples_per_second": 7.24,
      "eval_steps_per_second": 3.621,
      "step": 10
    },
    {
      "epoch": 0.0008284289190728499,
      "grad_norm": 0.8861536979675293,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.0794,
      "step": 12
    },
    {
      "epoch": 0.0010355361488410624,
      "grad_norm": 1.037650465965271,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.0982,
      "step": 15
    },
    {
      "epoch": 0.0010355361488410624,
      "eval_loss": 1.1215226650238037,
      "eval_runtime": 841.4678,
      "eval_samples_per_second": 7.248,
      "eval_steps_per_second": 3.625,
      "step": 15
    },
    {
      "epoch": 0.0012426433786092749,
      "grad_norm": 0.8788531422615051,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0643,
      "step": 18
    },
    {
      "epoch": 0.0013807148651214167,
      "eval_loss": 1.106920838356018,
      "eval_runtime": 841.147,
      "eval_samples_per_second": 7.251,
      "eval_steps_per_second": 3.626,
      "step": 20
    },
    {
      "epoch": 0.0014497506083774874,
      "grad_norm": 0.7518830299377441,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.8878,
      "step": 21
    },
    {
      "epoch": 0.0016568578381456998,
      "grad_norm": 0.9861083626747131,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.0354,
      "step": 24
    },
    {
      "epoch": 0.0017258935814017707,
      "eval_loss": 1.101482629776001,
      "eval_runtime": 841.5375,
      "eval_samples_per_second": 7.247,
      "eval_steps_per_second": 3.624,
      "step": 25
    },
    {
      "epoch": 0.0018639650679139123,
      "grad_norm": 0.7286344170570374,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2035,
      "step": 27
    },
    {
      "epoch": 0.002071072297682125,
      "grad_norm": 0.6946622729301453,
      "learning_rate": 0.0,
      "loss": 0.9832,
      "step": 30
    },
    {
      "epoch": 0.002071072297682125,
      "eval_loss": 1.100005030632019,
      "eval_runtime": 842.0664,
      "eval_samples_per_second": 7.243,
      "eval_steps_per_second": 3.622,
      "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": 1.1777665174339584e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}