last-checkpoint/trainer_state.json

{
  "best_metric": 1.733486294746399,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0015142720137293997,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0475733790979985e-05,
      "eval_loss": 1.9227821826934814,
      "eval_runtime": 1395.4982,
      "eval_samples_per_second": 5.978,
      "eval_steps_per_second": 2.989,
      "step": 1
    },
    {
      "epoch": 0.00015142720137293996,
      "grad_norm": 0.37583640217781067,
      "learning_rate": 3e-05,
      "loss": 1.9299,
      "step": 3
    },
    {
      "epoch": 0.0002523786689548999,
      "eval_loss": 1.9086353778839111,
      "eval_runtime": 1404.9667,
      "eval_samples_per_second": 5.938,
      "eval_steps_per_second": 2.969,
      "step": 5
    },
    {
      "epoch": 0.0003028544027458799,
      "grad_norm": 0.4073977768421173,
      "learning_rate": 6e-05,
      "loss": 1.8799,
      "step": 6
    },
    {
      "epoch": 0.00045428160411881987,
      "grad_norm": 0.49786943197250366,
      "learning_rate": 9e-05,
      "loss": 1.8351,
      "step": 9
    },
    {
      "epoch": 0.0005047573379097999,
      "eval_loss": 1.800294280052185,
      "eval_runtime": 1404.6504,
      "eval_samples_per_second": 5.939,
      "eval_steps_per_second": 2.969,
      "step": 10
    },
    {
      "epoch": 0.0006057088054917598,
      "grad_norm": 0.31189802289009094,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7429,
      "step": 12
    },
    {
      "epoch": 0.0007571360068646998,
      "grad_norm": 0.49632543325424194,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7142,
      "step": 15
    },
    {
      "epoch": 0.0007571360068646998,
      "eval_loss": 1.7793023586273193,
      "eval_runtime": 1404.032,
      "eval_samples_per_second": 5.941,
      "eval_steps_per_second": 2.971,
      "step": 15
    },
    {
      "epoch": 0.0009085632082376397,
      "grad_norm": 0.2652880847454071,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.773,
      "step": 18
    },
    {
      "epoch": 0.0010095146758195997,
      "eval_loss": 1.7412056922912598,
      "eval_runtime": 1403.7973,
      "eval_samples_per_second": 5.942,
      "eval_steps_per_second": 2.971,
      "step": 20
    },
    {
      "epoch": 0.0010599904096105796,
      "grad_norm": 0.23081372678279877,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.8133,
      "step": 21
    },
    {
      "epoch": 0.0012114176109835196,
      "grad_norm": 0.24668963253498077,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.7785,
      "step": 24
    },
    {
      "epoch": 0.0012618933447744996,
      "eval_loss": 1.735094666481018,
      "eval_runtime": 1403.5657,
      "eval_samples_per_second": 5.943,
      "eval_steps_per_second": 2.972,
      "step": 25
    },
    {
      "epoch": 0.0013628448123564597,
      "grad_norm": 0.2573795020580292,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.6955,
      "step": 27
    },
    {
      "epoch": 0.0015142720137293997,
      "grad_norm": 0.25954729318618774,
      "learning_rate": 0.0,
      "loss": 1.7924,
      "step": 30
    },
    {
      "epoch": 0.0015142720137293997,
      "eval_loss": 1.733486294746399,
      "eval_runtime": 1403.6226,
      "eval_samples_per_second": 5.943,
      "eval_steps_per_second": 2.972,
      "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": 1.388598679044096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}