checkpoint-948/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 1000,
  "global_step": 948,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15822784810126583,
      "grad_norm": 0.22299839556217194,
      "learning_rate": 9.987121632940603e-05,
      "loss": 1.2749,
      "step": 50
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 0.29688388109207153,
      "learning_rate": 9.853447789039338e-05,
      "loss": 1.112,
      "step": 100
    },
    {
      "epoch": 0.47468354430379744,
      "grad_norm": 0.34126031398773193,
      "learning_rate": 9.578324417078541e-05,
      "loss": 1.0716,
      "step": 150
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 0.3432747423648834,
      "learning_rate": 9.169769749212656e-05,
      "loss": 1.0426,
      "step": 200
    },
    {
      "epoch": 0.7911392405063291,
      "grad_norm": 0.35207387804985046,
      "learning_rate": 8.639690757035497e-05,
      "loss": 1.0167,
      "step": 250
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 0.3663095533847809,
      "learning_rate": 8.003536133216028e-05,
      "loss": 0.9973,
      "step": 300
    },
    {
      "epoch": 1.1075949367088607,
      "grad_norm": 0.4503985643386841,
      "learning_rate": 7.279846052743947e-05,
      "loss": 0.9599,
      "step": 350
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.43278568983078003,
      "learning_rate": 6.489711835603232e-05,
      "loss": 0.9332,
      "step": 400
    },
    {
      "epoch": 1.4240506329113924,
      "grad_norm": 0.44808298349380493,
      "learning_rate": 5.6561612585365554e-05,
      "loss": 0.9252,
      "step": 450
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 0.45410802960395813,
      "learning_rate": 4.8034874304563326e-05,
      "loss": 0.9253,
      "step": 500
    },
    {
      "epoch": 1.740506329113924,
      "grad_norm": 0.47317686676979065,
      "learning_rate": 3.9565407908466436e-05,
      "loss": 0.9377,
      "step": 550
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 0.4796537756919861,
      "learning_rate": 3.140004865248845e-05,
      "loss": 0.9257,
      "step": 600
    },
    {
      "epoch": 2.0569620253164556,
      "grad_norm": 0.5124043822288513,
      "learning_rate": 2.3776768853093317e-05,
      "loss": 0.9008,
      "step": 650
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 0.5075053572654724,
      "learning_rate": 1.6917742390944913e-05,
      "loss": 0.8689,
      "step": 700
    },
    {
      "epoch": 2.3734177215189876,
      "grad_norm": 0.5190396904945374,
      "learning_rate": 1.1022869645771195e-05,
      "loss": 0.8626,
      "step": 750
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 0.5119550824165344,
      "learning_rate": 6.263951573102922e-06,
      "loss": 0.8686,
      "step": 800
    },
    {
      "epoch": 2.689873417721519,
      "grad_norm": 0.5137431025505066,
      "learning_rate": 2.7796827143696634e-06,
      "loss": 0.8754,
      "step": 850
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 0.5047231912612915,
      "learning_rate": 6.716090647324702e-07,
      "loss": 0.8636,
      "step": 900
    }
  ],
  "logging_steps": 50,
  "max_steps": 948,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.516545844872479e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}