trainer_state.json

{
  "best_metric": 0.7700450584385239,
  "best_model_checkpoint": "./checkpoints/clip-10240-supervised-multilingual/checkpoint-60",
  "epoch": 0.20865936358894105,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6e-06,
      "loss": 4.2235,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2e-05,
      "loss": 2.454,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8e-05,
      "loss": 1.9628,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.4e-05,
      "loss": 1.6604,
      "step": 80
    },
    {
      "epoch": 0.05,
      "learning_rate": 3e-05,
      "loss": 1.4726,
      "step": 100
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.9670329670329673e-05,
      "loss": 1.3632,
      "step": 120
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.934065934065934e-05,
      "loss": 1.2782,
      "step": 140
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.9010989010989013e-05,
      "loss": 1.2024,
      "step": 160
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.8681318681318685e-05,
      "loss": 1.1547,
      "step": 180
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.8351648351648353e-05,
      "loss": 1.1092,
      "step": 200
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.802197802197802e-05,
      "loss": 1.0757,
      "step": 220
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 1.044,
      "step": 240
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.7362637362637362e-05,
      "loss": 1.0206,
      "step": 260
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.7032967032967034e-05,
      "loss": 0.9943,
      "step": 280
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.6703296703296702e-05,
      "loss": 0.976,
      "step": 300
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.6373626373626374e-05,
      "loss": 0.955,
      "step": 320
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.6043956043956046e-05,
      "loss": 0.9377,
      "step": 340
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 0.9052,
      "step": 360
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.5384615384615386e-05,
      "loss": 0.9012,
      "step": 380
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.5054945054945058e-05,
      "loss": 0.8827,
      "step": 400
    }
  ],
  "max_steps": 1920,
  "num_train_epochs": 2,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}