checkpoint-1521/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 1521,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19723865877712032,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.2181,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 100
    },
    {
      "epoch": 0.39447731755424065,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.5897,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 200
    },
    {
      "epoch": 0.591715976331361,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 2.847,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 300
    },
    {
      "epoch": 0.7889546351084813,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 2.166,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 400
    },
    {
      "epoch": 0.9861932938856016,
      "grad_norm": 8.998483657836914,
      "learning_rate": 1.4372355430183358e-05,
      "loss": 0.28,
      "step": 500
    },
    {
      "epoch": 0.9861932938856016,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.2219,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 500
    },
    {
      "epoch": 1.183431952662722,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 3.4138,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 600
    },
    {
      "epoch": 1.3806706114398422,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.3764,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 700
    },
    {
      "epoch": 1.5779092702169626,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.2387,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 800
    },
    {
      "epoch": 1.7751479289940828,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.2026,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 900
    },
    {
      "epoch": 1.972386587771203,
      "grad_norm": 0.12859900295734406,
      "learning_rate": 7.320169252468266e-06,
      "loss": 0.0393,
      "step": 1000
    },
    {
      "epoch": 1.972386587771203,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 4.1539,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 1000
    },
    {
      "epoch": 2.1696252465483234,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.2677,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 1100
    },
    {
      "epoch": 2.366863905325444,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.2481,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 1200
    },
    {
      "epoch": 2.564102564102564,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.5014,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 1300
    },
    {
      "epoch": 2.7613412228796843,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.6007,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 1400
    },
    {
      "epoch": 2.9585798816568047,
      "grad_norm": 2.3075523376464844,
      "learning_rate": 2.679830747531735e-07,
      "loss": 0.0274,
      "step": 1500
    },
    {
      "epoch": 2.9585798816568047,
      "eval_pearson_cosine": NaN,
      "eval_runtime": 1.6228,
      "eval_samples_per_second": 0.0,
      "eval_spearman_cosine": NaN,
      "eval_steps_per_second": 0.0,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1521,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}