last-checkpoint/trainer_state.json

{
  "best_metric": 5.112382888793945,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.07672634271099744,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025575447570332483,
      "eval_loss": 7.382377624511719,
      "eval_runtime": 73.8799,
      "eval_samples_per_second": 4.467,
      "eval_steps_per_second": 1.123,
      "step": 1
    },
    {
      "epoch": 0.0076726342710997444,
      "grad_norm": 9.789273262023926,
      "learning_rate": 0.00012,
      "loss": 19.5983,
      "step": 3
    },
    {
      "epoch": 0.01278772378516624,
      "eval_loss": 7.120743274688721,
      "eval_runtime": 74.8569,
      "eval_samples_per_second": 4.408,
      "eval_steps_per_second": 1.109,
      "step": 5
    },
    {
      "epoch": 0.015345268542199489,
      "grad_norm": 7.50346040725708,
      "learning_rate": 0.0001992114701314478,
      "loss": 20.4009,
      "step": 6
    },
    {
      "epoch": 0.023017902813299233,
      "grad_norm": 7.749037265777588,
      "learning_rate": 0.00018763066800438636,
      "loss": 18.8201,
      "step": 9
    },
    {
      "epoch": 0.02557544757033248,
      "eval_loss": 5.987125873565674,
      "eval_runtime": 74.814,
      "eval_samples_per_second": 4.411,
      "eval_steps_per_second": 1.109,
      "step": 10
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": 7.037360191345215,
      "learning_rate": 0.000163742398974869,
      "loss": 17.4451,
      "step": 12
    },
    {
      "epoch": 0.03836317135549872,
      "grad_norm": 8.117260932922363,
      "learning_rate": 0.00013090169943749476,
      "loss": 16.0837,
      "step": 15
    },
    {
      "epoch": 0.03836317135549872,
      "eval_loss": 5.5802226066589355,
      "eval_runtime": 75.7254,
      "eval_samples_per_second": 4.358,
      "eval_steps_per_second": 1.096,
      "step": 15
    },
    {
      "epoch": 0.04603580562659847,
      "grad_norm": 7.076067924499512,
      "learning_rate": 9.372094804706867e-05,
      "loss": 16.2765,
      "step": 18
    },
    {
      "epoch": 0.05115089514066496,
      "eval_loss": 5.251645565032959,
      "eval_runtime": 75.0851,
      "eval_samples_per_second": 4.395,
      "eval_steps_per_second": 1.105,
      "step": 20
    },
    {
      "epoch": 0.05370843989769821,
      "grad_norm": 8.359580993652344,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 15.5105,
      "step": 21
    },
    {
      "epoch": 0.061381074168797956,
      "grad_norm": 8.11271858215332,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 16.5227,
      "step": 24
    },
    {
      "epoch": 0.0639386189258312,
      "eval_loss": 5.127615928649902,
      "eval_runtime": 75.2873,
      "eval_samples_per_second": 4.383,
      "eval_steps_per_second": 1.102,
      "step": 25
    },
    {
      "epoch": 0.06905370843989769,
      "grad_norm": 9.202075004577637,
      "learning_rate": 7.022351411174866e-06,
      "loss": 16.8827,
      "step": 27
    },
    {
      "epoch": 0.07672634271099744,
      "grad_norm": 12.595846176147461,
      "learning_rate": 0.0,
      "loss": 17.2095,
      "step": 30
    },
    {
      "epoch": 0.07672634271099744,
      "eval_loss": 5.112382888793945,
      "eval_runtime": 75.2566,
      "eval_samples_per_second": 4.385,
      "eval_steps_per_second": 1.103,
      "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": 4.085054963712e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}