checkpoint-5515/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 5515,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018132366273798732,
      "grad_norm": 7.9868855476379395,
      "learning_rate": 0.0,
      "loss": 3.5226,
      "step": 1
    },
    {
      "epoch": 0.1813236627379873,
      "grad_norm": 6.11737060546875,
      "learning_rate": 7.2443799854967376e-06,
      "loss": 2.9981,
      "step": 1000
    },
    {
      "epoch": 0.1813236627379873,
      "eval_cosine_accuracy": 0.9449994564056396,
      "eval_loss": 0.5478581190109253,
      "eval_runtime": 35.5173,
      "eval_samples_per_second": 267.728,
      "eval_steps_per_second": 2.112,
      "step": 1000
    },
    {
      "epoch": 0.3626473254759746,
      "grad_norm": 6.732676029205322,
      "learning_rate": 1.4496011602610589e-05,
      "loss": 2.3032,
      "step": 2000
    },
    {
      "epoch": 0.3626473254759746,
      "eval_cosine_accuracy": 0.9554106593132019,
      "eval_loss": 0.4920719563961029,
      "eval_runtime": 35.1849,
      "eval_samples_per_second": 270.258,
      "eval_steps_per_second": 2.132,
      "step": 2000
    },
    {
      "epoch": 0.543970988213962,
      "grad_norm": 7.598336696624756,
      "learning_rate": 1.980577829713503e-05,
      "loss": 1.8788,
      "step": 3000
    },
    {
      "epoch": 0.543970988213962,
      "eval_cosine_accuracy": 0.9590913653373718,
      "eval_loss": 0.45673736929893494,
      "eval_runtime": 35.2853,
      "eval_samples_per_second": 269.489,
      "eval_steps_per_second": 2.126,
      "step": 3000
    },
    {
      "epoch": 0.7252946509519492,
      "grad_norm": 10.34838581085205,
      "learning_rate": 1.8999879115122698e-05,
      "loss": 1.2997,
      "step": 4000
    },
    {
      "epoch": 0.7252946509519492,
      "eval_cosine_accuracy": 0.954990029335022,
      "eval_loss": 0.45149004459381104,
      "eval_runtime": 35.2489,
      "eval_samples_per_second": 269.768,
      "eval_steps_per_second": 2.128,
      "step": 4000
    },
    {
      "epoch": 0.9066183136899365,
      "grad_norm": 8.401123046875,
      "learning_rate": 1.8195591731474395e-05,
      "loss": 0.9457,
      "step": 5000
    },
    {
      "epoch": 0.9066183136899365,
      "eval_cosine_accuracy": 0.9530970454216003,
      "eval_loss": 0.44349202513694763,
      "eval_runtime": 35.1475,
      "eval_samples_per_second": 270.546,
      "eval_steps_per_second": 2.134,
      "step": 5000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 27575,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}