checkpoint-328/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 328,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.00019393939393939395,
      "loss": 0.5722,
      "step": 32
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017898305084745764,
      "loss": 0.6073,
      "step": 64
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00015728813559322036,
      "loss": 0.6517,
      "step": 96
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00013559322033898305,
      "loss": 0.4895,
      "step": 128
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00011389830508474577,
      "loss": 0.6097,
      "step": 160
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.220338983050847e-05,
      "loss": 0.6041,
      "step": 192
    },
    {
      "epoch": 1.37,
      "learning_rate": 7.05084745762712e-05,
      "loss": 0.4871,
      "step": 224
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.88135593220339e-05,
      "loss": 0.601,
      "step": 256
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.711864406779661e-05,
      "loss": 0.5946,
      "step": 288
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.423728813559322e-06,
      "loss": 0.5771,
      "step": 320
    }
  ],
  "logging_steps": 32,
  "max_steps": 328,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.016694903743447e+17,
  "trial_name": null,
  "trial_params": null
}