{
  "best_global_step": 870,
  "best_metric": 3.4479944705963135,
  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_sh1_fr_30/checkpoint-870",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006896551724137931,
      "grad_norm": 34.13589859008789,
      "learning_rate": 0.0,
      "loss": 9.8164,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4214282035827637,
      "learning_rate": 2.88e-05,
      "loss": 6.0017,
      "step": 145
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.516501426696777,
      "eval_runtime": 4.3416,
      "eval_samples_per_second": 810.983,
      "eval_steps_per_second": 3.225,
      "step": 145
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7844622135162354,
      "learning_rate": 5.7799999999999995e-05,
      "loss": 4.1747,
      "step": 290
    },
    {
      "epoch": 2.0,
      "eval_loss": 4.028092384338379,
      "eval_runtime": 4.4671,
      "eval_samples_per_second": 788.2,
      "eval_steps_per_second": 3.134,
      "step": 290
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2072691917419434,
      "learning_rate": 8.680000000000001e-05,
      "loss": 3.8777,
      "step": 435
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.7704145908355713,
      "eval_runtime": 4.3729,
      "eval_samples_per_second": 805.181,
      "eval_steps_per_second": 3.202,
      "step": 435
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.2117047309875488,
      "learning_rate": 9.668067226890756e-05,
      "loss": 3.6723,
      "step": 580
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.6042661666870117,
      "eval_runtime": 4.4715,
      "eval_samples_per_second": 787.434,
      "eval_steps_per_second": 3.131,
      "step": 580
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.2041577100753784,
      "learning_rate": 9.058823529411765e-05,
      "loss": 3.5366,
      "step": 725
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.5113701820373535,
      "eval_runtime": 4.511,
      "eval_samples_per_second": 780.542,
      "eval_steps_per_second": 3.104,
      "step": 725
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1716428995132446,
      "learning_rate": 8.449579831932774e-05,
      "loss": 3.4452,
      "step": 870
    },
    {
      "epoch": 6.0,
      "eval_loss": 3.4479944705963135,
      "eval_runtime": 4.4139,
      "eval_samples_per_second": 797.713,
      "eval_steps_per_second": 3.172,
      "step": 870
    }
  ],
  "logging_steps": 500,
  "max_steps": 2900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 1.4474664050688e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}