small/checkpoints/checkpoint-200/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 0.17182618379592896,
  "best_model_checkpoint": "cache/small/checkpoints/checkpoint-200",
  "epoch": 0.01025010250102501,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025625256252562525,
      "grad_norm": 1.85740065574646,
      "learning_rate": 9.800000000000001e-06,
      "loss": 3.735545654296875,
      "step": 50
    },
    {
      "epoch": 0.005125051250512505,
      "grad_norm": 3.0535006523132324,
      "learning_rate": 1.9800000000000004e-05,
      "loss": 3.4337332153320315,
      "step": 100
    },
    {
      "epoch": 0.007687576875768758,
      "grad_norm": 3.3642959594726562,
      "learning_rate": 2.98e-05,
      "loss": 3.057893981933594,
      "step": 150
    },
    {
      "epoch": 0.01025010250102501,
      "grad_norm": 4.062570571899414,
      "learning_rate": 3.9800000000000005e-05,
      "loss": 2.7298809814453127,
      "step": 200
    },
    {
      "epoch": 0.01025010250102501,
      "eval_loss": 3.3121352195739746,
      "eval_runtime": 1.9467,
      "eval_samples_per_second": 5136.982,
      "eval_steps_per_second": 5.137,
      "eval_teacher_cosine_loss": 0.828173816204071,
      "eval_teacher_cosine_mean": 0.17182618379592896,
      "eval_teacher_cosine_p10": 0.10700135678052902,
      "eval_teacher_cosine_p50": 0.1718333214521408,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 234144,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}