last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00034919554077294433,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.491955407729443e-05,
      "grad_norm": 1.5854488611221313,
      "learning_rate": 2e-05,
      "loss": 2.0741,
      "step": 1
    },
    {
      "epoch": 3.491955407729443e-05,
      "eval_loss": 2.1542773246765137,
      "eval_runtime": 357.8677,
      "eval_samples_per_second": 16.847,
      "eval_steps_per_second": 16.847,
      "step": 1
    },
    {
      "epoch": 6.983910815458886e-05,
      "grad_norm": 1.4733368158340454,
      "learning_rate": 4e-05,
      "loss": 1.5595,
      "step": 2
    },
    {
      "epoch": 0.00010475866223188329,
      "grad_norm": 2.865410804748535,
      "learning_rate": 6e-05,
      "loss": 1.7822,
      "step": 3
    },
    {
      "epoch": 0.00010475866223188329,
      "eval_loss": 2.1372852325439453,
      "eval_runtime": 356.9492,
      "eval_samples_per_second": 16.89,
      "eval_steps_per_second": 16.89,
      "step": 3
    },
    {
      "epoch": 0.00013967821630917772,
      "grad_norm": 2.658249616622925,
      "learning_rate": 8e-05,
      "loss": 2.1342,
      "step": 4
    },
    {
      "epoch": 0.00017459777038647217,
      "grad_norm": 2.390005111694336,
      "learning_rate": 0.0001,
      "loss": 1.829,
      "step": 5
    },
    {
      "epoch": 0.00020951732446376658,
      "grad_norm": 1.4543702602386475,
      "learning_rate": 0.00012,
      "loss": 1.679,
      "step": 6
    },
    {
      "epoch": 0.00020951732446376658,
      "eval_loss": 2.071124315261841,
      "eval_runtime": 357.0228,
      "eval_samples_per_second": 16.887,
      "eval_steps_per_second": 16.887,
      "step": 6
    },
    {
      "epoch": 0.00024443687854106103,
      "grad_norm": 1.8792164325714111,
      "learning_rate": 0.00014,
      "loss": 2.4839,
      "step": 7
    },
    {
      "epoch": 0.00027935643261835545,
      "grad_norm": 2.3412582874298096,
      "learning_rate": 0.00016,
      "loss": 1.5353,
      "step": 8
    },
    {
      "epoch": 0.0003142759866956499,
      "grad_norm": 1.6153055429458618,
      "learning_rate": 0.00018,
      "loss": 1.6283,
      "step": 9
    },
    {
      "epoch": 0.0003142759866956499,
      "eval_loss": 2.0233631134033203,
      "eval_runtime": 358.2408,
      "eval_samples_per_second": 16.829,
      "eval_steps_per_second": 16.829,
      "step": 9
    },
    {
      "epoch": 0.00034919554077294433,
      "grad_norm": 2.771148443222046,
      "learning_rate": 0.0002,
      "loss": 1.4844,
      "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": 360477150412800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}