last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009992505620784412,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009992505620784412,
      "grad_norm": 3.590458869934082,
      "learning_rate": 2e-05,
      "loss": 3.298,
      "step": 1
    },
    {
      "epoch": 0.0019985011241568824,
      "grad_norm": 4.2420244216918945,
      "learning_rate": 4e-05,
      "loss": 2.9857,
      "step": 2
    },
    {
      "epoch": 0.0029977516862353237,
      "grad_norm": 5.0277509689331055,
      "learning_rate": 6e-05,
      "loss": 3.7803,
      "step": 3
    },
    {
      "epoch": 0.0029977516862353237,
      "eval_loss": 3.599262237548828,
      "eval_runtime": 18.8601,
      "eval_samples_per_second": 22.375,
      "eval_steps_per_second": 11.188,
      "step": 3
    },
    {
      "epoch": 0.003997002248313765,
      "grad_norm": 3.9873037338256836,
      "learning_rate": 8e-05,
      "loss": 3.345,
      "step": 4
    },
    {
      "epoch": 0.004996252810392206,
      "grad_norm": 3.8236076831817627,
      "learning_rate": 0.0001,
      "loss": 2.9724,
      "step": 5
    },
    {
      "epoch": 0.005995503372470647,
      "grad_norm": 3.8733317852020264,
      "learning_rate": 0.00012,
      "loss": 2.9619,
      "step": 6
    },
    {
      "epoch": 0.005995503372470647,
      "eval_loss": 3.471137046813965,
      "eval_runtime": 20.7585,
      "eval_samples_per_second": 20.329,
      "eval_steps_per_second": 10.165,
      "step": 6
    },
    {
      "epoch": 0.0069947539345490885,
      "grad_norm": 4.72310209274292,
      "learning_rate": 0.00014,
      "loss": 3.3464,
      "step": 7
    },
    {
      "epoch": 0.00799400449662753,
      "grad_norm": 3.8101882934570312,
      "learning_rate": 0.00016,
      "loss": 2.6749,
      "step": 8
    },
    {
      "epoch": 0.008993255058705971,
      "grad_norm": 6.21740198135376,
      "learning_rate": 0.00018,
      "loss": 3.3801,
      "step": 9
    },
    {
      "epoch": 0.008993255058705971,
      "eval_loss": 3.144624948501587,
      "eval_runtime": 18.3231,
      "eval_samples_per_second": 23.031,
      "eval_steps_per_second": 11.516,
      "step": 9
    },
    {
      "epoch": 0.009992505620784412,
      "grad_norm": 5.031135559082031,
      "learning_rate": 0.0002,
      "loss": 3.5897,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}