checkpoint-5518/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 1000,
  "global_step": 5518,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036258158085569254,
      "grad_norm": 7.228061676025391,
      "learning_rate": 0.0,
      "loss": 4.1707,
      "step": 1
    },
    {
      "epoch": 0.36258158085569253,
      "grad_norm": 5.754242897033691,
      "learning_rate": 1.5090634441087614e-05,
      "loss": 3.3117,
      "step": 1000
    },
    {
      "epoch": 0.36258158085569253,
      "eval_cosine_accuracy": 0.9497318267822266,
      "eval_loss": 0.5286146402359009,
      "eval_runtime": 34.6121,
      "eval_samples_per_second": 274.73,
      "eval_steps_per_second": 1.098,
      "step": 1000
    },
    {
      "epoch": 0.7251631617113851,
      "grad_norm": 7.097472190856934,
      "learning_rate": 3.01963746223565e-05,
      "loss": 1.9469,
      "step": 2000
    },
    {
      "epoch": 0.7251631617113851,
      "eval_cosine_accuracy": 0.9579346179962158,
      "eval_loss": 0.4524660110473633,
      "eval_runtime": 33.9797,
      "eval_samples_per_second": 279.843,
      "eval_steps_per_second": 1.118,
      "step": 2000
    },
    {
      "epoch": 1.0876811594202898,
      "grad_norm": 6.607709884643555,
      "learning_rate": 4.530211480362538e-05,
      "loss": 1.4282,
      "step": 3000
    },
    {
      "epoch": 1.0876811594202898,
      "eval_cosine_accuracy": 0.9617204666137695,
      "eval_loss": 0.4302012026309967,
      "eval_runtime": 34.5566,
      "eval_samples_per_second": 275.172,
      "eval_steps_per_second": 1.1,
      "step": 3000
    },
    {
      "epoch": 1.45,
      "grad_norm": 5.233509540557861,
      "learning_rate": 4.739764314851186e-05,
      "loss": 1.556,
      "step": 4000
    },
    {
      "epoch": 1.45,
      "eval_cosine_accuracy": 0.9664528369903564,
      "eval_loss": 0.4086464047431946,
      "eval_runtime": 33.7595,
      "eval_samples_per_second": 281.669,
      "eval_steps_per_second": 1.126,
      "step": 4000
    },
    {
      "epoch": 1.8123188405797102,
      "grad_norm": 5.165083408355713,
      "learning_rate": 4.362441456413356e-05,
      "loss": 1.3647,
      "step": 5000
    },
    {
      "epoch": 1.8123188405797102,
      "eval_cosine_accuracy": 0.9669786691665649,
      "eval_loss": 0.4053584337234497,
      "eval_runtime": 34.8117,
      "eval_samples_per_second": 273.155,
      "eval_steps_per_second": 1.092,
      "step": 5000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 16548,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 256,
  "trial_name": null,
  "trial_params": null
}