last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006100971071228837,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020336570237429458,
      "eval_loss": 1.8808537721633911,
      "eval_runtime": 114.6842,
      "eval_samples_per_second": 18.058,
      "eval_steps_per_second": 9.034,
      "step": 1
    },
    {
      "epoch": 0.0006100971071228837,
      "grad_norm": 2.1337409019470215,
      "learning_rate": 6e-05,
      "loss": 1.6544,
      "step": 3
    },
    {
      "epoch": 0.001016828511871473,
      "eval_loss": 1.799464225769043,
      "eval_runtime": 115.7957,
      "eval_samples_per_second": 17.885,
      "eval_steps_per_second": 8.947,
      "step": 5
    },
    {
      "epoch": 0.0012201942142457674,
      "grad_norm": 1.7321535348892212,
      "learning_rate": 0.00012,
      "loss": 1.5588,
      "step": 6
    },
    {
      "epoch": 0.0018302913213686513,
      "grad_norm": 2.699079751968384,
      "learning_rate": 0.00018,
      "loss": 1.5007,
      "step": 9
    },
    {
      "epoch": 0.002033657023742946,
      "eval_loss": 1.5931826829910278,
      "eval_runtime": 115.7565,
      "eval_samples_per_second": 17.891,
      "eval_steps_per_second": 8.95,
      "step": 10
    },
    {
      "epoch": 0.0024403884284915347,
      "grad_norm": 3.7128841876983643,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.445,
      "step": 12
    },
    {
      "epoch": 0.0030504855356144186,
      "grad_norm": 2.098191261291504,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.3757,
      "step": 15
    },
    {
      "epoch": 0.0030504855356144186,
      "eval_loss": 1.521304965019226,
      "eval_runtime": 115.7149,
      "eval_samples_per_second": 17.897,
      "eval_steps_per_second": 8.953,
      "step": 15
    },
    {
      "epoch": 0.0036605826427373025,
      "grad_norm": 1.6114972829818726,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4386,
      "step": 18
    },
    {
      "epoch": 0.004067314047485892,
      "eval_loss": 1.4969481229782104,
      "eval_runtime": 115.7084,
      "eval_samples_per_second": 17.898,
      "eval_steps_per_second": 8.954,
      "step": 20
    },
    {
      "epoch": 0.004270679749860186,
      "grad_norm": 1.37641441822052,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.5019,
      "step": 21
    },
    {
      "epoch": 0.0048807768569830694,
      "grad_norm": 1.7818759679794312,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.4352,
      "step": 24
    },
    {
      "epoch": 0.005084142559357364,
      "eval_loss": 1.4820669889450073,
      "eval_runtime": 115.7161,
      "eval_samples_per_second": 17.897,
      "eval_steps_per_second": 8.953,
      "step": 25
    },
    {
      "epoch": 0.005490873964105953,
      "grad_norm": 1.5027129650115967,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.3072,
      "step": 27
    },
    {
      "epoch": 0.006100971071228837,
      "grad_norm": 1.505488634109497,
      "learning_rate": 0.0,
      "loss": 1.2843,
      "step": 30
    },
    {
      "epoch": 0.006100971071228837,
      "eval_loss": 1.4783607721328735,
      "eval_runtime": 115.7322,
      "eval_samples_per_second": 17.895,
      "eval_steps_per_second": 8.952,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4583933198991360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}