checkpoint-225/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 1.3508174419403076,
      "learning_rate": 0.0002,
      "loss": 2.5227,
      "step": 5
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.8602172136306763,
      "learning_rate": 0.0002,
      "loss": 2.6438,
      "step": 10
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.7185380458831787,
      "learning_rate": 0.0002,
      "loss": 0.7979,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.46760892868042,
      "learning_rate": 0.0002,
      "loss": 0.4091,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5913628935813904,
      "learning_rate": 0.0002,
      "loss": 0.274,
      "step": 25
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.46462497115135193,
      "learning_rate": 0.0002,
      "loss": 0.1921,
      "step": 30
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.47151607275009155,
      "learning_rate": 0.0002,
      "loss": 0.2399,
      "step": 35
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.45026347041130066,
      "learning_rate": 0.0002,
      "loss": 0.5266,
      "step": 40
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.8638098835945129,
      "learning_rate": 0.0002,
      "loss": 0.1596,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.41460809111595154,
      "learning_rate": 0.0002,
      "loss": 0.291,
      "step": 50
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.30362772941589355,
      "learning_rate": 0.0002,
      "loss": 0.0818,
      "step": 55
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.46699783205986023,
      "learning_rate": 0.0002,
      "loss": 0.1198,
      "step": 60
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.3688370883464813,
      "learning_rate": 0.0002,
      "loss": 0.0892,
      "step": 65
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.6380140781402588,
      "learning_rate": 0.0002,
      "loss": 0.1068,
      "step": 70
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.31224119663238525,
      "learning_rate": 0.0002,
      "loss": 0.1673,
      "step": 75
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.455768883228302,
      "learning_rate": 0.0002,
      "loss": 0.0405,
      "step": 80
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.29344627261161804,
      "learning_rate": 0.0002,
      "loss": 0.1494,
      "step": 85
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.4940664768218994,
      "learning_rate": 0.0002,
      "loss": 0.0483,
      "step": 90
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.2362147718667984,
      "learning_rate": 0.0002,
      "loss": 0.0396,
      "step": 95
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2028852105140686,
      "learning_rate": 0.0002,
      "loss": 0.0475,
      "step": 100
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.12950176000595093,
      "learning_rate": 0.0002,
      "loss": 0.0272,
      "step": 105
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.3273729383945465,
      "learning_rate": 0.0002,
      "loss": 0.0302,
      "step": 110
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.2938006818294525,
      "learning_rate": 0.0002,
      "loss": 0.0487,
      "step": 115
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.6171326041221619,
      "learning_rate": 0.0002,
      "loss": 0.1138,
      "step": 120
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2811235785484314,
      "learning_rate": 0.0002,
      "loss": 0.0313,
      "step": 125
    },
    {
      "epoch": 5.2,
      "grad_norm": 0.5635420680046082,
      "learning_rate": 0.0002,
      "loss": 0.0242,
      "step": 130
    },
    {
      "epoch": 5.4,
      "grad_norm": 0.5491178035736084,
      "learning_rate": 0.0002,
      "loss": 0.0486,
      "step": 135
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.1552320271730423,
      "learning_rate": 0.0002,
      "loss": 0.0332,
      "step": 140
    },
    {
      "epoch": 5.8,
      "grad_norm": 0.4321906864643097,
      "learning_rate": 0.0002,
      "loss": 0.0241,
      "step": 145
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3396056592464447,
      "learning_rate": 0.0002,
      "loss": 0.034,
      "step": 150
    },
    {
      "epoch": 6.2,
      "grad_norm": 0.09246141463518143,
      "learning_rate": 0.0002,
      "loss": 0.02,
      "step": 155
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.1537373661994934,
      "learning_rate": 0.0002,
      "loss": 0.0258,
      "step": 160
    },
    {
      "epoch": 6.6,
      "grad_norm": 0.08097207546234131,
      "learning_rate": 0.0002,
      "loss": 0.032,
      "step": 165
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.10840635746717453,
      "learning_rate": 0.0002,
      "loss": 0.0343,
      "step": 170
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.07061374932527542,
      "learning_rate": 0.0002,
      "loss": 0.034,
      "step": 175
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.1112145483493805,
      "learning_rate": 0.0002,
      "loss": 0.0196,
      "step": 180
    },
    {
      "epoch": 7.4,
      "grad_norm": 0.06888523697853088,
      "learning_rate": 0.0002,
      "loss": 0.0238,
      "step": 185
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.1332859843969345,
      "learning_rate": 0.0002,
      "loss": 0.0349,
      "step": 190
    },
    {
      "epoch": 7.8,
      "grad_norm": 0.07381593436002731,
      "learning_rate": 0.0002,
      "loss": 0.027,
      "step": 195
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.12291029840707779,
      "learning_rate": 0.0002,
      "loss": 0.0309,
      "step": 200
    },
    {
      "epoch": 8.2,
      "grad_norm": 0.08110173791646957,
      "learning_rate": 0.0002,
      "loss": 0.0192,
      "step": 205
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.0632745772600174,
      "learning_rate": 0.0002,
      "loss": 0.0219,
      "step": 210
    },
    {
      "epoch": 8.6,
      "grad_norm": 0.07048214226961136,
      "learning_rate": 0.0002,
      "loss": 0.0218,
      "step": 215
    },
    {
      "epoch": 8.8,
      "grad_norm": 0.07824481278657913,
      "learning_rate": 0.0002,
      "loss": 0.0673,
      "step": 220
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.14880645275115967,
      "learning_rate": 0.0002,
      "loss": 0.0519,
      "step": 225
    }
  ],
  "logging_steps": 5,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7217479693885440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}