last-checkpoint/trainer_state.json

{
  "best_metric": 11.946277618408203,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.013557790080216925,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045192633600723084,
      "eval_loss": 11.950511932373047,
      "eval_runtime": 28.7217,
      "eval_samples_per_second": 32.449,
      "eval_steps_per_second": 16.225,
      "step": 1
    },
    {
      "epoch": 0.0013557790080216926,
      "grad_norm": 0.05842767655849457,
      "learning_rate": 6e-05,
      "loss": 11.9491,
      "step": 3
    },
    {
      "epoch": 0.002259631680036154,
      "eval_loss": 11.950288772583008,
      "eval_runtime": 28.8082,
      "eval_samples_per_second": 32.352,
      "eval_steps_per_second": 16.176,
      "step": 5
    },
    {
      "epoch": 0.002711558016043385,
      "grad_norm": 0.04878790304064751,
      "learning_rate": 0.00012,
      "loss": 11.9506,
      "step": 6
    },
    {
      "epoch": 0.004067337024065077,
      "grad_norm": 0.055045176297426224,
      "learning_rate": 0.00018,
      "loss": 11.9492,
      "step": 9
    },
    {
      "epoch": 0.004519263360072308,
      "eval_loss": 11.949509620666504,
      "eval_runtime": 28.9001,
      "eval_samples_per_second": 32.249,
      "eval_steps_per_second": 16.124,
      "step": 10
    },
    {
      "epoch": 0.00542311603208677,
      "grad_norm": 0.05678074061870575,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.9508,
      "step": 12
    },
    {
      "epoch": 0.006778895040108463,
      "grad_norm": 0.06515557318925858,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.9496,
      "step": 15
    },
    {
      "epoch": 0.006778895040108463,
      "eval_loss": 11.948259353637695,
      "eval_runtime": 28.8883,
      "eval_samples_per_second": 32.262,
      "eval_steps_per_second": 16.131,
      "step": 15
    },
    {
      "epoch": 0.008134674048130154,
      "grad_norm": 0.07017915695905685,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9489,
      "step": 18
    },
    {
      "epoch": 0.009038526720144616,
      "eval_loss": 11.947105407714844,
      "eval_runtime": 28.7664,
      "eval_samples_per_second": 32.399,
      "eval_steps_per_second": 16.199,
      "step": 20
    },
    {
      "epoch": 0.009490453056151846,
      "grad_norm": 0.08155731111764908,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.9477,
      "step": 21
    },
    {
      "epoch": 0.01084623206417354,
      "grad_norm": 0.08816022425889969,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.9463,
      "step": 24
    },
    {
      "epoch": 0.011298158400180771,
      "eval_loss": 11.946414947509766,
      "eval_runtime": 28.8235,
      "eval_samples_per_second": 32.335,
      "eval_steps_per_second": 16.167,
      "step": 25
    },
    {
      "epoch": 0.012202011072195233,
      "grad_norm": 0.08092248439788818,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.9461,
      "step": 27
    },
    {
      "epoch": 0.013557790080216925,
      "grad_norm": 0.08714073896408081,
      "learning_rate": 0.0,
      "loss": 11.9473,
      "step": 30
    },
    {
      "epoch": 0.013557790080216925,
      "eval_loss": 11.946277618408203,
      "eval_runtime": 28.6642,
      "eval_samples_per_second": 32.514,
      "eval_steps_per_second": 16.257,
      "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": 18455691264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}