trainer_state.json

{
  "best_metric": 0.266584187746048,
  "best_model_checkpoint": "./model/sent_2class_bertin_project_bertin_roberta_base_spanish/checkpoint-1078",
  "epoch": 10.0,
  "global_step": 10780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2.7e-06,
      "loss": 0.3488,
      "step": 1078
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8970315398886828,
      "eval_f1": 0.8961910338994079,
      "eval_loss": 0.266584187746048,
      "eval_precision": 0.8957628528645112,
      "eval_recall": 0.8966965120197903,
      "eval_runtime": 21.586,
      "eval_samples_per_second": 99.88,
      "eval_steps_per_second": 6.254,
      "step": 1078
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.2263,
      "step": 2156
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.898886827458256,
      "eval_f1": 0.8977834612105712,
      "eval_loss": 0.27391624450683594,
      "eval_precision": 0.8984546268833581,
      "eval_recall": 0.8972142020797937,
      "eval_runtime": 21.5769,
      "eval_samples_per_second": 99.922,
      "eval_steps_per_second": 6.257,
      "step": 2156
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.1e-06,
      "loss": 0.1778,
      "step": 3234
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9025974025974026,
      "eval_f1": 0.9005949897907656,
      "eval_loss": 0.2852832078933716,
      "eval_precision": 0.9078802796803653,
      "eval_recall": 0.8972558952389886,
      "eval_runtime": 21.6014,
      "eval_samples_per_second": 99.808,
      "eval_steps_per_second": 6.25,
      "step": 3234
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.8e-06,
      "loss": 0.1403,
      "step": 4312
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8882189239332097,
      "eval_f1": 0.8875278557938429,
      "eval_loss": 0.4905070662498474,
      "eval_precision": 0.8867163445635435,
      "eval_recall": 0.8889302925122561,
      "eval_runtime": 21.5859,
      "eval_samples_per_second": 99.88,
      "eval_steps_per_second": 6.254,
      "step": 4312
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.5e-06,
      "loss": 0.1057,
      "step": 5390
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_f1": 0.896845694799659,
      "eval_loss": 0.5339986085891724,
      "eval_precision": 0.8975153439448489,
      "eval_recall": 0.8962778432128748,
      "eval_runtime": 21.6294,
      "eval_samples_per_second": 99.679,
      "eval_steps_per_second": 6.242,
      "step": 5390
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.0784,
      "step": 6468
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_f1": 0.8963577501817979,
      "eval_loss": 0.5496116280555725,
      "eval_precision": 0.8998756153165819,
      "eval_recall": 0.894290469291251,
      "eval_runtime": 21.5964,
      "eval_samples_per_second": 99.831,
      "eval_steps_per_second": 6.251,
      "step": 6468
    },
    {
      "epoch": 7.0,
      "learning_rate": 9e-07,
      "loss": 0.0613,
      "step": 7546
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8984230055658627,
      "eval_f1": 0.8971592486956067,
      "eval_loss": 0.6363572478294373,
      "eval_precision": 0.8986339225376554,
      "eval_recall": 0.8960685088094171,
      "eval_runtime": 21.6326,
      "eval_samples_per_second": 99.665,
      "eval_steps_per_second": 6.241,
      "step": 7546
    },
    {
      "epoch": 8.0,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.0461,
      "step": 8624
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.900278293135436,
      "eval_f1": 0.8989520476739503,
      "eval_loss": 0.6520560383796692,
      "eval_precision": 0.9009346244640362,
      "eval_recall": 0.8975798858302324,
      "eval_runtime": 21.6557,
      "eval_samples_per_second": 99.558,
      "eval_steps_per_second": 6.234,
      "step": 8624
    },
    {
      "epoch": 9.0,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.0374,
      "step": 9702
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.897495361781076,
      "eval_f1": 0.8959944382052516,
      "eval_loss": 0.6639323830604553,
      "eval_precision": 0.8988044556565169,
      "eval_recall": 0.8942287981599419,
      "eval_runtime": 21.6348,
      "eval_samples_per_second": 99.654,
      "eval_steps_per_second": 6.24,
      "step": 9702
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.0306,
      "step": 10780
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8965677179962894,
      "eval_f1": 0.8953454329048005,
      "eval_loss": 0.6889322996139526,
      "eval_precision": 0.8964728057179624,
      "eval_recall": 0.8944667966103461,
      "eval_runtime": 21.547,
      "eval_samples_per_second": 100.06,
      "eval_steps_per_second": 6.265,
      "step": 10780
    }
  ],
  "max_steps": 10780,
  "num_train_epochs": 10,
  "total_flos": 4.53813948284928e+16,
  "trial_name": null,
  "trial_params": null
}