trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.886075949367089,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.32324039936065674,
      "learning_rate": 0.0001997790438338385,
      "loss": 1.5745,
      "step": 10
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.8489105105400085,
      "learning_rate": 0.00019730448705798239,
      "loss": 1.0497,
      "step": 20
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.7880690097808838,
      "learning_rate": 0.00019214762118704076,
      "loss": 0.7976,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.29379141330719,
      "learning_rate": 0.0001844506011066308,
      "loss": 0.8209,
      "step": 40
    },
    {
      "epoch": 1.2531645569620253,
      "grad_norm": 1.0279569625854492,
      "learning_rate": 0.00017442560394846516,
      "loss": 0.6251,
      "step": 50
    },
    {
      "epoch": 1.5063291139240507,
      "grad_norm": 0.636813223361969,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.5924,
      "step": 60
    },
    {
      "epoch": 1.759493670886076,
      "grad_norm": 0.7099205255508423,
      "learning_rate": 0.00014855363571801523,
      "loss": 0.5931,
      "step": 70
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2306174039840698,
      "learning_rate": 0.00013341985493931877,
      "loss": 0.6078,
      "step": 80
    },
    {
      "epoch": 2.2531645569620253,
      "grad_norm": 0.7018842101097107,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.4799,
      "step": 90
    },
    {
      "epoch": 2.5063291139240507,
      "grad_norm": 0.35523730516433716,
      "learning_rate": 0.00010083109959960973,
      "loss": 0.4349,
      "step": 100
    },
    {
      "epoch": 2.759493670886076,
      "grad_norm": 0.5931728482246399,
      "learning_rate": 8.427447122476148e-05,
      "loss": 0.4463,
      "step": 110
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0323467254638672,
      "learning_rate": 6.815133497483157e-05,
      "loss": 0.4688,
      "step": 120
    },
    {
      "epoch": 3.2531645569620253,
      "grad_norm": 0.34674957394599915,
      "learning_rate": 5.290614347797802e-05,
      "loss": 0.3858,
      "step": 130
    },
    {
      "epoch": 3.5063291139240507,
      "grad_norm": 0.40083837509155273,
      "learning_rate": 3.89591478145437e-05,
      "loss": 0.4163,
      "step": 140
    },
    {
      "epoch": 3.759493670886076,
      "grad_norm": 0.5980750322341919,
      "learning_rate": 2.669481281701739e-05,
      "loss": 0.3411,
      "step": 150
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.8719474673271179,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.3478,
      "step": 160
    },
    {
      "epoch": 4.253164556962025,
      "grad_norm": 0.31751662492752075,
      "learning_rate": 8.510742282896544e-06,
      "loss": 0.3534,
      "step": 170
    },
    {
      "epoch": 4.506329113924051,
      "grad_norm": 0.37393781542778015,
      "learning_rate": 3.092271377092215e-06,
      "loss": 0.3226,
      "step": 180
    },
    {
      "epoch": 4.759493670886076,
      "grad_norm": 0.4498203992843628,
      "learning_rate": 3.451724678784518e-07,
      "loss": 0.303,
      "step": 190
    }
  ],
  "logging_steps": 10,
  "max_steps": 195,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1684049994579968e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}