last-checkpoint/trainer_state.json

{
  "best_metric": 0.5719356536865234,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06359300476947535,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021197668256491787,
      "eval_loss": 1.146639108657837,
      "eval_runtime": 116.7748,
      "eval_samples_per_second": 3.408,
      "eval_steps_per_second": 0.856,
      "step": 1
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.7560529708862305,
      "learning_rate": 0.00012,
      "loss": 4.3738,
      "step": 3
    },
    {
      "epoch": 0.010598834128245893,
      "eval_loss": 1.0721842050552368,
      "eval_runtime": 120.2006,
      "eval_samples_per_second": 3.311,
      "eval_steps_per_second": 0.832,
      "step": 5
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 0.9589040279388428,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.1859,
      "step": 6
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 0.9749143719673157,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.6312,
      "step": 9
    },
    {
      "epoch": 0.021197668256491786,
      "eval_loss": 0.8010535836219788,
      "eval_runtime": 120.0012,
      "eval_samples_per_second": 3.317,
      "eval_steps_per_second": 0.833,
      "step": 10
    },
    {
      "epoch": 0.025437201907790145,
      "grad_norm": 0.9566070437431335,
      "learning_rate": 0.000163742398974869,
      "loss": 2.9623,
      "step": 12
    },
    {
      "epoch": 0.03179650238473768,
      "grad_norm": 0.7144882678985596,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.6517,
      "step": 15
    },
    {
      "epoch": 0.03179650238473768,
      "eval_loss": 0.6578609347343445,
      "eval_runtime": 118.7794,
      "eval_samples_per_second": 3.351,
      "eval_steps_per_second": 0.842,
      "step": 15
    },
    {
      "epoch": 0.03815580286168521,
      "grad_norm": 0.6463198065757751,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.3795,
      "step": 18
    },
    {
      "epoch": 0.04239533651298357,
      "eval_loss": 0.5995034575462341,
      "eval_runtime": 120.2682,
      "eval_samples_per_second": 3.309,
      "eval_steps_per_second": 0.831,
      "step": 20
    },
    {
      "epoch": 0.04451510333863275,
      "grad_norm": 0.510029673576355,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.2456,
      "step": 21
    },
    {
      "epoch": 0.05087440381558029,
      "grad_norm": 0.579888105392456,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.1742,
      "step": 24
    },
    {
      "epoch": 0.052994170641229466,
      "eval_loss": 0.5767956376075745,
      "eval_runtime": 119.5601,
      "eval_samples_per_second": 3.329,
      "eval_steps_per_second": 0.836,
      "step": 25
    },
    {
      "epoch": 0.057233704292527825,
      "grad_norm": 0.5771500468254089,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.1709,
      "step": 27
    },
    {
      "epoch": 0.06359300476947535,
      "grad_norm": 0.5936694741249084,
      "learning_rate": 0.0,
      "loss": 2.1232,
      "step": 30
    },
    {
      "epoch": 0.06359300476947535,
      "eval_loss": 0.5719356536865234,
      "eval_runtime": 118.8779,
      "eval_samples_per_second": 3.348,
      "eval_steps_per_second": 0.841,
      "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": 3.920787866124288e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}