checkpoint-100/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9655172413793105,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 0.383268266916275,
      "learning_rate": 2e-05,
      "loss": 0.8272,
      "step": 5
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.5146570801734924,
      "learning_rate": 4e-05,
      "loss": 0.9387,
      "step": 10
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 0.3668777048587799,
      "learning_rate": 6e-05,
      "loss": 0.9139,
      "step": 15
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.4035521149635315,
      "learning_rate": 8e-05,
      "loss": 0.6747,
      "step": 20
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.3319677710533142,
      "learning_rate": 0.0001,
      "loss": 0.8404,
      "step": 25
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 0.30683422088623047,
      "learning_rate": 0.00012,
      "loss": 0.8286,
      "step": 30
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.31191521883010864,
      "learning_rate": 0.00014,
      "loss": 0.8088,
      "step": 35
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 1.6001628637313843,
      "learning_rate": 0.00016,
      "loss": 0.7695,
      "step": 40
    },
    {
      "epoch": 0.8866995073891626,
      "grad_norm": 0.249281644821167,
      "learning_rate": 0.00018,
      "loss": 0.4185,
      "step": 45
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.3532997965812683,
      "learning_rate": 0.0002,
      "loss": 0.7676,
      "step": 50
    },
    {
      "epoch": 1.0788177339901477,
      "grad_norm": 0.31705552339553833,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.5267,
      "step": 55
    },
    {
      "epoch": 1.1773399014778325,
      "grad_norm": 0.8706707954406738,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6788,
      "step": 60
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.30066409707069397,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.5776,
      "step": 65
    },
    {
      "epoch": 1.374384236453202,
      "grad_norm": 0.45960843563079834,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6163,
      "step": 70
    },
    {
      "epoch": 1.4729064039408866,
      "grad_norm": 0.3609830439090729,
      "learning_rate": 0.0001,
      "loss": 0.6811,
      "step": 75
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.3113192319869995,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.3922,
      "step": 80
    },
    {
      "epoch": 1.6699507389162562,
      "grad_norm": 0.588917076587677,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.6865,
      "step": 85
    },
    {
      "epoch": 1.7684729064039408,
      "grad_norm": 0.49402135610580444,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6516,
      "step": 90
    },
    {
      "epoch": 1.8669950738916257,
      "grad_norm": 0.4498872756958008,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.5217,
      "step": 95
    },
    {
      "epoch": 1.9655172413793105,
      "grad_norm": 0.38511091470718384,
      "learning_rate": 0.0,
      "loss": 0.4743,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0276136262107136e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}