last-checkpoint/trainer_state.json

{
  "best_metric": 0.8780689239501953,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0010044951156425001,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0224755782125007e-05,
      "eval_loss": 1.3837661743164062,
      "eval_runtime": 1292.9785,
      "eval_samples_per_second": 6.484,
      "eval_steps_per_second": 3.242,
      "step": 1
    },
    {
      "epoch": 0.00015067426734637502,
      "grad_norm": 2.247525691986084,
      "learning_rate": 6e-05,
      "loss": 5.2756,
      "step": 3
    },
    {
      "epoch": 0.00025112377891062503,
      "eval_loss": 1.3188445568084717,
      "eval_runtime": 1295.6444,
      "eval_samples_per_second": 6.471,
      "eval_steps_per_second": 3.235,
      "step": 5
    },
    {
      "epoch": 0.00030134853469275004,
      "grad_norm": 1.854863166809082,
      "learning_rate": 0.00012,
      "loss": 5.9855,
      "step": 6
    },
    {
      "epoch": 0.00045202280203912506,
      "grad_norm": 1.2117688655853271,
      "learning_rate": 0.00018,
      "loss": 4.9755,
      "step": 9
    },
    {
      "epoch": 0.0005022475578212501,
      "eval_loss": 1.1316041946411133,
      "eval_runtime": 1294.9521,
      "eval_samples_per_second": 6.474,
      "eval_steps_per_second": 3.237,
      "step": 10
    },
    {
      "epoch": 0.0006026970693855001,
      "grad_norm": 1.035812258720398,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.4551,
      "step": 12
    },
    {
      "epoch": 0.0007533713367318751,
      "grad_norm": 1.1360167264938354,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.4879,
      "step": 15
    },
    {
      "epoch": 0.0007533713367318751,
      "eval_loss": 0.9610100984573364,
      "eval_runtime": 1295.3043,
      "eval_samples_per_second": 6.473,
      "eval_steps_per_second": 3.236,
      "step": 15
    },
    {
      "epoch": 0.0009040456040782501,
      "grad_norm": 1.0687752962112427,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.783,
      "step": 18
    },
    {
      "epoch": 0.0010044951156425001,
      "eval_loss": 0.8780689239501953,
      "eval_runtime": 1295.1323,
      "eval_samples_per_second": 6.473,
      "eval_steps_per_second": 3.237,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6032849689903104.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}