last-checkpoint/trainer_state.json

{
  "best_metric": 3.2455074787139893,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.08333333333333333,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002777777777777778,
      "eval_loss": 3.456601619720459,
      "eval_runtime": 1.7458,
      "eval_samples_per_second": 174.136,
      "eval_steps_per_second": 43.534,
      "step": 1
    },
    {
      "epoch": 0.008333333333333333,
      "grad_norm": 6.741215229034424,
      "learning_rate": 0.00012,
      "loss": 13.8937,
      "step": 3
    },
    {
      "epoch": 0.013888888888888888,
      "eval_loss": 3.3771238327026367,
      "eval_runtime": 1.7404,
      "eval_samples_per_second": 174.677,
      "eval_steps_per_second": 43.669,
      "step": 5
    },
    {
      "epoch": 0.016666666666666666,
      "grad_norm": 5.106968402862549,
      "learning_rate": 0.0001992114701314478,
      "loss": 13.9782,
      "step": 6
    },
    {
      "epoch": 0.025,
      "grad_norm": 5.924384117126465,
      "learning_rate": 0.00018763066800438636,
      "loss": 13.3747,
      "step": 9
    },
    {
      "epoch": 0.027777777777777776,
      "eval_loss": 3.3042805194854736,
      "eval_runtime": 1.7655,
      "eval_samples_per_second": 172.185,
      "eval_steps_per_second": 43.046,
      "step": 10
    },
    {
      "epoch": 0.03333333333333333,
      "grad_norm": 5.118800640106201,
      "learning_rate": 0.000163742398974869,
      "loss": 13.5492,
      "step": 12
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 5.077568054199219,
      "learning_rate": 0.00013090169943749476,
      "loss": 13.1588,
      "step": 15
    },
    {
      "epoch": 0.041666666666666664,
      "eval_loss": 3.2679872512817383,
      "eval_runtime": 1.767,
      "eval_samples_per_second": 172.04,
      "eval_steps_per_second": 43.01,
      "step": 15
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.772042274475098,
      "learning_rate": 9.372094804706867e-05,
      "loss": 12.9509,
      "step": 18
    },
    {
      "epoch": 0.05555555555555555,
      "eval_loss": 3.2530300617218018,
      "eval_runtime": 1.7876,
      "eval_samples_per_second": 170.063,
      "eval_steps_per_second": 42.516,
      "step": 20
    },
    {
      "epoch": 0.058333333333333334,
      "grad_norm": 4.678488254547119,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 13.2836,
      "step": 21
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 4.627444744110107,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 13.3123,
      "step": 24
    },
    {
      "epoch": 0.06944444444444445,
      "eval_loss": 3.247187852859497,
      "eval_runtime": 1.7611,
      "eval_samples_per_second": 172.619,
      "eval_steps_per_second": 43.155,
      "step": 25
    },
    {
      "epoch": 0.075,
      "grad_norm": 4.9202470779418945,
      "learning_rate": 7.022351411174866e-06,
      "loss": 12.9437,
      "step": 27
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 4.927825927734375,
      "learning_rate": 0.0,
      "loss": 12.9429,
      "step": 30
    },
    {
      "epoch": 0.08333333333333333,
      "eval_loss": 3.2455074787139893,
      "eval_runtime": 1.759,
      "eval_samples_per_second": 172.826,
      "eval_steps_per_second": 43.207,
      "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": 258667928616960.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}