last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026263952724885097,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008754650908295032,
      "eval_loss": 1.6056385040283203,
      "eval_runtime": 76.0073,
      "eval_samples_per_second": 6.328,
      "eval_steps_per_second": 3.171,
      "step": 1
    },
    {
      "epoch": 0.0026263952724885093,
      "grad_norm": 0.23281846940517426,
      "learning_rate": 4e-05,
      "loss": 1.5615,
      "step": 3
    },
    {
      "epoch": 0.004377325454147516,
      "eval_loss": 1.5978538990020752,
      "eval_runtime": 75.7017,
      "eval_samples_per_second": 6.354,
      "eval_steps_per_second": 3.184,
      "step": 5
    },
    {
      "epoch": 0.005252790544977019,
      "grad_norm": 0.31518062949180603,
      "learning_rate": 8e-05,
      "loss": 1.6489,
      "step": 6
    },
    {
      "epoch": 0.007879185817465528,
      "grad_norm": 0.5230422019958496,
      "learning_rate": 0.00012,
      "loss": 1.588,
      "step": 9
    },
    {
      "epoch": 0.008754650908295032,
      "eval_loss": 1.4588658809661865,
      "eval_runtime": 75.8609,
      "eval_samples_per_second": 6.341,
      "eval_steps_per_second": 3.177,
      "step": 10
    },
    {
      "epoch": 0.010505581089954037,
      "grad_norm": 0.4259694814682007,
      "learning_rate": 0.00016,
      "loss": 1.4812,
      "step": 12
    },
    {
      "epoch": 0.013131976362442548,
      "grad_norm": 0.23858828842639923,
      "learning_rate": 0.0002,
      "loss": 1.34,
      "step": 15
    },
    {
      "epoch": 0.013131976362442548,
      "eval_loss": 1.307140827178955,
      "eval_runtime": 75.9138,
      "eval_samples_per_second": 6.336,
      "eval_steps_per_second": 3.175,
      "step": 15
    },
    {
      "epoch": 0.015758371634931056,
      "grad_norm": 0.2780468165874481,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3348,
      "step": 18
    },
    {
      "epoch": 0.017509301816590064,
      "eval_loss": 1.2061057090759277,
      "eval_runtime": 75.8944,
      "eval_samples_per_second": 6.338,
      "eval_steps_per_second": 3.175,
      "step": 20
    },
    {
      "epoch": 0.018384766907419567,
      "grad_norm": 0.18443334102630615,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2121,
      "step": 21
    },
    {
      "epoch": 0.021011162179908074,
      "grad_norm": 0.1660495549440384,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.221,
      "step": 24
    },
    {
      "epoch": 0.02188662727073758,
      "eval_loss": 1.1656545400619507,
      "eval_runtime": 75.9507,
      "eval_samples_per_second": 6.333,
      "eval_steps_per_second": 3.173,
      "step": 25
    },
    {
      "epoch": 0.023637557452396585,
      "grad_norm": 0.18378210067749023,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.1388,
      "step": 27
    },
    {
      "epoch": 0.026263952724885097,
      "grad_norm": 0.17629104852676392,
      "learning_rate": 0.0,
      "loss": 1.1826,
      "step": 30
    },
    {
      "epoch": 0.026263952724885097,
      "eval_loss": 1.1577775478363037,
      "eval_runtime": 75.928,
      "eval_samples_per_second": 6.335,
      "eval_steps_per_second": 3.174,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.121357638762496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}