checkpoint-281/trainer_state.json

{
  "best_metric": 0.7993471622467041,
  "best_model_checkpoint": "ryukijano-paligemma-finetuned\\checkpoint-281",
  "epoch": 8.992,
  "eval_steps": 500,
  "global_step": 281,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 4.558422088623047,
      "learning_rate": 1.6129032258064516e-06,
      "loss": 1.5484,
      "step": 25
    },
    {
      "epoch": 0.992,
      "eval_loss": 1.8585567474365234,
      "eval_runtime": 19.9397,
      "eval_samples_per_second": 12.538,
      "eval_steps_per_second": 6.269,
      "step": 31
    },
    {
      "epoch": 1.6,
      "grad_norm": 4.804387092590332,
      "learning_rate": 3.225806451612903e-06,
      "loss": 1.5841,
      "step": 50
    },
    {
      "epoch": 1.984,
      "eval_loss": 1.803800106048584,
      "eval_runtime": 20.1703,
      "eval_samples_per_second": 12.394,
      "eval_steps_per_second": 6.197,
      "step": 62
    },
    {
      "epoch": 2.4,
      "grad_norm": 4.384600639343262,
      "learning_rate": 4.838709677419355e-06,
      "loss": 1.5184,
      "step": 75
    },
    {
      "epoch": 2.976,
      "eval_loss": 1.677108883857727,
      "eval_runtime": 19.7443,
      "eval_samples_per_second": 12.662,
      "eval_steps_per_second": 6.331,
      "step": 93
    },
    {
      "epoch": 3.2,
      "grad_norm": 4.877094268798828,
      "learning_rate": 6.451612903225806e-06,
      "loss": 1.3985,
      "step": 100
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.035943508148193,
      "learning_rate": 8.064516129032258e-06,
      "loss": 1.2081,
      "step": 125
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.4368913173675537,
      "eval_runtime": 20.3141,
      "eval_samples_per_second": 12.307,
      "eval_steps_per_second": 6.153,
      "step": 125
    },
    {
      "epoch": 4.8,
      "grad_norm": 3.080859422683716,
      "learning_rate": 9.67741935483871e-06,
      "loss": 1.0413,
      "step": 150
    },
    {
      "epoch": 4.992,
      "eval_loss": 1.1628715991973877,
      "eval_runtime": 20.1314,
      "eval_samples_per_second": 12.418,
      "eval_steps_per_second": 6.209,
      "step": 156
    },
    {
      "epoch": 5.6,
      "grad_norm": 2.4689671993255615,
      "learning_rate": 1.1290322580645164e-05,
      "loss": 0.8372,
      "step": 175
    },
    {
      "epoch": 5.984,
      "eval_loss": 0.9508486390113831,
      "eval_runtime": 20.101,
      "eval_samples_per_second": 12.437,
      "eval_steps_per_second": 6.219,
      "step": 187
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.9029561281204224,
      "learning_rate": 1.2903225806451613e-05,
      "loss": 0.7411,
      "step": 200
    },
    {
      "epoch": 6.976,
      "eval_loss": 0.8626062870025635,
      "eval_runtime": 19.8558,
      "eval_samples_per_second": 12.591,
      "eval_steps_per_second": 6.295,
      "step": 218
    },
    {
      "epoch": 7.2,
      "grad_norm": 2.5312154293060303,
      "learning_rate": 1.4516129032258066e-05,
      "loss": 0.6682,
      "step": 225
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.895367383956909,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 0.5702,
      "step": 250
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8156193494796753,
      "eval_runtime": 20.1295,
      "eval_samples_per_second": 12.42,
      "eval_steps_per_second": 6.21,
      "step": 250
    },
    {
      "epoch": 8.8,
      "grad_norm": 3.090899705886841,
      "learning_rate": 1.774193548387097e-05,
      "loss": 0.5168,
      "step": 275
    },
    {
      "epoch": 8.992,
      "eval_loss": 0.7993471622467041,
      "eval_runtime": 20.053,
      "eval_samples_per_second": 12.467,
      "eval_steps_per_second": 6.233,
      "step": 281
    }
  ],
  "logging_steps": 25,
  "max_steps": 3100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "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": 3.5386074301492224e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}