last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017504704389304626,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017504704389304627,
      "grad_norm": 1.2686787843704224,
      "learning_rate": 2e-05,
      "loss": 5.5784,
      "step": 1
    },
    {
      "epoch": 0.00017504704389304627,
      "eval_loss": 1.750502109527588,
      "eval_runtime": 259.2409,
      "eval_samples_per_second": 9.281,
      "eval_steps_per_second": 4.64,
      "step": 1
    },
    {
      "epoch": 0.00035009408778609254,
      "grad_norm": 1.0817018747329712,
      "learning_rate": 4e-05,
      "loss": 6.5125,
      "step": 2
    },
    {
      "epoch": 0.0005251411316791387,
      "grad_norm": 1.318281650543213,
      "learning_rate": 6e-05,
      "loss": 8.5902,
      "step": 3
    },
    {
      "epoch": 0.0005251411316791387,
      "eval_loss": 1.7480651140213013,
      "eval_runtime": 259.3052,
      "eval_samples_per_second": 9.279,
      "eval_steps_per_second": 4.639,
      "step": 3
    },
    {
      "epoch": 0.0007001881755721851,
      "grad_norm": 1.4432563781738281,
      "learning_rate": 8e-05,
      "loss": 7.782,
      "step": 4
    },
    {
      "epoch": 0.0008752352194652313,
      "grad_norm": 1.888183832168579,
      "learning_rate": 0.0001,
      "loss": 6.0493,
      "step": 5
    },
    {
      "epoch": 0.0010502822633582775,
      "grad_norm": 1.234459638595581,
      "learning_rate": 0.00012,
      "loss": 6.7613,
      "step": 6
    },
    {
      "epoch": 0.0010502822633582775,
      "eval_loss": 1.7166799306869507,
      "eval_runtime": 259.3631,
      "eval_samples_per_second": 9.277,
      "eval_steps_per_second": 4.638,
      "step": 6
    },
    {
      "epoch": 0.0012253293072513238,
      "grad_norm": 1.4830865859985352,
      "learning_rate": 0.00014,
      "loss": 7.4038,
      "step": 7
    },
    {
      "epoch": 0.0014003763511443701,
      "grad_norm": 1.2412511110305786,
      "learning_rate": 0.00016,
      "loss": 6.6294,
      "step": 8
    },
    {
      "epoch": 0.0015754233950374162,
      "grad_norm": 1.1326746940612793,
      "learning_rate": 0.00018,
      "loss": 5.4906,
      "step": 9
    },
    {
      "epoch": 0.0015754233950374162,
      "eval_loss": 1.6536381244659424,
      "eval_runtime": 259.4768,
      "eval_samples_per_second": 9.273,
      "eval_steps_per_second": 4.636,
      "step": 9
    },
    {
      "epoch": 0.0017504704389304626,
      "grad_norm": 1.13351571559906,
      "learning_rate": 0.0002,
      "loss": 7.1411,
      "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": 2239530207805440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}