checkpoint-5900/trainer_state.json

{
  "best_metric": 1.945926547050476,
  "best_model_checkpoint": "facial_emotions_image_detection/checkpoint-5900",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 5900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.423728813559322,
      "grad_norm": 0.2695070207118988,
      "learning_rate": 0.009230769230769232,
      "loss": 1.9572,
      "step": 500
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.19489270448684692,
      "learning_rate": 0.008376068376068376,
      "loss": 1.9517,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1428684942391736,
      "eval_loss": 1.9890856742858887,
      "eval_runtime": 297.1554,
      "eval_samples_per_second": 84.703,
      "eval_steps_per_second": 10.59,
      "step": 1180
    },
    {
      "epoch": 1.271186440677966,
      "grad_norm": 0.2716714143753052,
      "learning_rate": 0.007521367521367521,
      "loss": 1.9581,
      "step": 1500
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 0.19123496115207672,
      "learning_rate": 0.006666666666666666,
      "loss": 1.9525,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.14282876440206596,
      "eval_loss": 1.9473849534988403,
      "eval_runtime": 294.7507,
      "eval_samples_per_second": 85.394,
      "eval_steps_per_second": 10.677,
      "step": 2360
    },
    {
      "epoch": 2.1186440677966103,
      "grad_norm": 0.14484408497810364,
      "learning_rate": 0.005811965811965813,
      "loss": 1.9495,
      "step": 2500
    },
    {
      "epoch": 2.542372881355932,
      "grad_norm": 0.17980092763900757,
      "learning_rate": 0.004957264957264958,
      "loss": 1.9495,
      "step": 3000
    },
    {
      "epoch": 2.9661016949152543,
      "grad_norm": 0.20096652209758759,
      "learning_rate": 0.0041025641025641026,
      "loss": 1.9493,
      "step": 3500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.1428684942391736,
      "eval_loss": 1.9461429119110107,
      "eval_runtime": 300.123,
      "eval_samples_per_second": 83.866,
      "eval_steps_per_second": 10.486,
      "step": 3540
    },
    {
      "epoch": 3.389830508474576,
      "grad_norm": 0.15317220985889435,
      "learning_rate": 0.003247863247863248,
      "loss": 1.948,
      "step": 4000
    },
    {
      "epoch": 3.8135593220338984,
      "grad_norm": 0.10403087735176086,
      "learning_rate": 0.002393162393162393,
      "loss": 1.9469,
      "step": 4500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.14282876440206596,
      "eval_loss": 1.946163535118103,
      "eval_runtime": 295.9371,
      "eval_samples_per_second": 85.052,
      "eval_steps_per_second": 10.634,
      "step": 4720
    },
    {
      "epoch": 4.237288135593221,
      "grad_norm": 0.14330194890499115,
      "learning_rate": 0.0015384615384615387,
      "loss": 1.9469,
      "step": 5000
    },
    {
      "epoch": 4.661016949152542,
      "grad_norm": 0.16747227311134338,
      "learning_rate": 0.0006837606837606839,
      "loss": 1.9463,
      "step": 5500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.14282876440206596,
      "eval_loss": 1.945926547050476,
      "eval_runtime": 296.7174,
      "eval_samples_per_second": 84.828,
      "eval_steps_per_second": 10.606,
      "step": 5900
    }
  ],
  "logging_steps": 500,
  "max_steps": 5900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4628430940219873e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}