last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006832117785710625,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.832117785710625e-05,
      "grad_norm": 2.1177237033843994,
      "learning_rate": 2e-05,
      "loss": 3.873,
      "step": 1
    },
    {
      "epoch": 0.0001366423557142125,
      "grad_norm": 3.6529266834259033,
      "learning_rate": 4e-05,
      "loss": 5.6106,
      "step": 2
    },
    {
      "epoch": 0.00020496353357131876,
      "grad_norm": 2.8866329193115234,
      "learning_rate": 6e-05,
      "loss": 4.1739,
      "step": 3
    },
    {
      "epoch": 0.00020496353357131876,
      "eval_loss": 4.499691486358643,
      "eval_runtime": 294.3375,
      "eval_samples_per_second": 20.939,
      "eval_steps_per_second": 10.471,
      "step": 3
    },
    {
      "epoch": 0.000273284711428425,
      "grad_norm": 3.1876351833343506,
      "learning_rate": 8e-05,
      "loss": 4.5918,
      "step": 4
    },
    {
      "epoch": 0.00034160588928553126,
      "grad_norm": 3.4983630180358887,
      "learning_rate": 0.0001,
      "loss": 4.8883,
      "step": 5
    },
    {
      "epoch": 0.0004099270671426375,
      "grad_norm": 3.2121989727020264,
      "learning_rate": 0.00012,
      "loss": 4.3112,
      "step": 6
    },
    {
      "epoch": 0.0004099270671426375,
      "eval_loss": 4.1929216384887695,
      "eval_runtime": 313.2443,
      "eval_samples_per_second": 19.675,
      "eval_steps_per_second": 9.839,
      "step": 6
    },
    {
      "epoch": 0.0004782482449997438,
      "grad_norm": 2.577486276626587,
      "learning_rate": 0.00014,
      "loss": 3.7822,
      "step": 7
    },
    {
      "epoch": 0.00054656942285685,
      "grad_norm": 3.868285894393921,
      "learning_rate": 0.00016,
      "loss": 4.489,
      "step": 8
    },
    {
      "epoch": 0.0006148906007139563,
      "grad_norm": 3.044187545776367,
      "learning_rate": 0.00018,
      "loss": 3.7794,
      "step": 9
    },
    {
      "epoch": 0.0006148906007139563,
      "eval_loss": 3.3595550060272217,
      "eval_runtime": 317.28,
      "eval_samples_per_second": 19.424,
      "eval_steps_per_second": 9.714,
      "step": 9
    },
    {
      "epoch": 0.0006832117785710625,
      "grad_norm": 2.7369019985198975,
      "learning_rate": 0.0002,
      "loss": 3.547,
      "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": 1643165232660480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}