last-checkpoint/trainer_state.json

{
  "best_metric": 3.928459882736206,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.010145417653026716,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033818058843422386,
      "eval_loss": 4.138824939727783,
      "eval_runtime": 797.7592,
      "eval_samples_per_second": 3.121,
      "eval_steps_per_second": 0.781,
      "step": 1
    },
    {
      "epoch": 0.0010145417653026716,
      "grad_norm": 0.9579305648803711,
      "learning_rate": 0.00012,
      "loss": 3.8791,
      "step": 3
    },
    {
      "epoch": 0.0016909029421711193,
      "eval_loss": 4.028163909912109,
      "eval_runtime": 800.1734,
      "eval_samples_per_second": 3.112,
      "eval_steps_per_second": 0.779,
      "step": 5
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": 1.070989966392517,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.9871,
      "step": 6
    },
    {
      "epoch": 0.003043625295908015,
      "grad_norm": 0.7759875059127808,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.8609,
      "step": 9
    },
    {
      "epoch": 0.0033818058843422386,
      "eval_loss": 3.973855972290039,
      "eval_runtime": 802.0323,
      "eval_samples_per_second": 3.105,
      "eval_steps_per_second": 0.777,
      "step": 10
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": 0.7216101288795471,
      "learning_rate": 0.000163742398974869,
      "loss": 3.869,
      "step": 12
    },
    {
      "epoch": 0.005072708826513358,
      "grad_norm": 0.6455993056297302,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.879,
      "step": 15
    },
    {
      "epoch": 0.005072708826513358,
      "eval_loss": 3.964207172393799,
      "eval_runtime": 803.7899,
      "eval_samples_per_second": 3.098,
      "eval_steps_per_second": 0.775,
      "step": 15
    },
    {
      "epoch": 0.00608725059181603,
      "grad_norm": 0.7790849208831787,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.896,
      "step": 18
    },
    {
      "epoch": 0.006763611768684477,
      "eval_loss": 3.963434934616089,
      "eval_runtime": 803.3508,
      "eval_samples_per_second": 3.1,
      "eval_steps_per_second": 0.776,
      "step": 20
    },
    {
      "epoch": 0.007101792357118702,
      "grad_norm": 0.8026948571205139,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.7612,
      "step": 21
    },
    {
      "epoch": 0.008116334122421373,
      "grad_norm": 1.0372897386550903,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.9055,
      "step": 24
    },
    {
      "epoch": 0.008454514710855596,
      "eval_loss": 3.9400546550750732,
      "eval_runtime": 804.2628,
      "eval_samples_per_second": 3.096,
      "eval_steps_per_second": 0.775,
      "step": 25
    },
    {
      "epoch": 0.009130875887724045,
      "grad_norm": 0.9315910935401917,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.8441,
      "step": 27
    },
    {
      "epoch": 0.010145417653026716,
      "grad_norm": 0.9024998545646667,
      "learning_rate": 0.0,
      "loss": 4.0826,
      "step": 30
    },
    {
      "epoch": 0.010145417653026716,
      "eval_loss": 3.928459882736206,
      "eval_runtime": 805.0922,
      "eval_samples_per_second": 3.093,
      "eval_steps_per_second": 0.774,
      "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": 2.5690961111678976e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}