last-checkpoint/trainer_state.json

{
  "best_metric": 0.389055460691452,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.12320328542094455,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004106776180698152,
      "eval_loss": 0.589090883731842,
      "eval_runtime": 38.7527,
      "eval_samples_per_second": 5.29,
      "eval_steps_per_second": 1.342,
      "step": 1
    },
    {
      "epoch": 0.012320328542094456,
      "grad_norm": 0.14734984934329987,
      "learning_rate": 0.00012,
      "loss": 2.0434,
      "step": 3
    },
    {
      "epoch": 0.02053388090349076,
      "eval_loss": 0.5575751066207886,
      "eval_runtime": 38.7605,
      "eval_samples_per_second": 5.289,
      "eval_steps_per_second": 1.342,
      "step": 5
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 0.16837503015995026,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.6752,
      "step": 6
    },
    {
      "epoch": 0.03696098562628337,
      "grad_norm": 0.17675945162773132,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.7225,
      "step": 9
    },
    {
      "epoch": 0.04106776180698152,
      "eval_loss": 0.4586701989173889,
      "eval_runtime": 38.1049,
      "eval_samples_per_second": 5.38,
      "eval_steps_per_second": 1.365,
      "step": 10
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.21885457634925842,
      "learning_rate": 0.000163742398974869,
      "loss": 1.4855,
      "step": 12
    },
    {
      "epoch": 0.061601642710472276,
      "grad_norm": 0.20970964431762695,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2824,
      "step": 15
    },
    {
      "epoch": 0.061601642710472276,
      "eval_loss": 0.41965946555137634,
      "eval_runtime": 38.7722,
      "eval_samples_per_second": 5.287,
      "eval_steps_per_second": 1.341,
      "step": 15
    },
    {
      "epoch": 0.07392197125256673,
      "grad_norm": 0.21281249821186066,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.2334,
      "step": 18
    },
    {
      "epoch": 0.08213552361396304,
      "eval_loss": 0.40152639150619507,
      "eval_runtime": 38.0979,
      "eval_samples_per_second": 5.381,
      "eval_steps_per_second": 1.365,
      "step": 20
    },
    {
      "epoch": 0.08624229979466119,
      "grad_norm": 0.24816812574863434,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.3891,
      "step": 21
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.27626967430114746,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.2348,
      "step": 24
    },
    {
      "epoch": 0.1026694045174538,
      "eval_loss": 0.3887929320335388,
      "eval_runtime": 38.7693,
      "eval_samples_per_second": 5.288,
      "eval_steps_per_second": 1.341,
      "step": 25
    },
    {
      "epoch": 0.11088295687885011,
      "grad_norm": 0.28312671184539795,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.4244,
      "step": 27
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 0.29587483406066895,
      "learning_rate": 0.0,
      "loss": 1.4884,
      "step": 30
    },
    {
      "epoch": 0.12320328542094455,
      "eval_loss": 0.389055460691452,
      "eval_runtime": 38.768,
      "eval_samples_per_second": 5.288,
      "eval_steps_per_second": 1.341,
      "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": 6.792178059706368e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}