last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0012186205215695832,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012186205215695832,
      "grad_norm": 0.6814508438110352,
      "learning_rate": 2e-05,
      "loss": 1.5013,
      "step": 1
    },
    {
      "epoch": 0.00012186205215695832,
      "eval_loss": 1.4393564462661743,
      "eval_runtime": 47.4864,
      "eval_samples_per_second": 72.779,
      "eval_steps_per_second": 36.389,
      "step": 1
    },
    {
      "epoch": 0.00024372410431391665,
      "grad_norm": 0.5904664993286133,
      "learning_rate": 4e-05,
      "loss": 1.3063,
      "step": 2
    },
    {
      "epoch": 0.000365586156470875,
      "grad_norm": 0.5635495185852051,
      "learning_rate": 6e-05,
      "loss": 1.2788,
      "step": 3
    },
    {
      "epoch": 0.000365586156470875,
      "eval_loss": 1.4376599788665771,
      "eval_runtime": 47.026,
      "eval_samples_per_second": 73.491,
      "eval_steps_per_second": 36.746,
      "step": 3
    },
    {
      "epoch": 0.0004874482086278333,
      "grad_norm": 0.7366768717765808,
      "learning_rate": 8e-05,
      "loss": 1.3888,
      "step": 4
    },
    {
      "epoch": 0.0006093102607847916,
      "grad_norm": 0.49705398082733154,
      "learning_rate": 0.0001,
      "loss": 1.2223,
      "step": 5
    },
    {
      "epoch": 0.00073117231294175,
      "grad_norm": 0.6044642329216003,
      "learning_rate": 0.00012,
      "loss": 1.3472,
      "step": 6
    },
    {
      "epoch": 0.00073117231294175,
      "eval_loss": 1.4210509061813354,
      "eval_runtime": 47.4705,
      "eval_samples_per_second": 72.803,
      "eval_steps_per_second": 36.402,
      "step": 6
    },
    {
      "epoch": 0.0008530343650987082,
      "grad_norm": 0.627808153629303,
      "learning_rate": 0.00014,
      "loss": 1.3771,
      "step": 7
    },
    {
      "epoch": 0.0009748964172556666,
      "grad_norm": 0.5471099019050598,
      "learning_rate": 0.00016,
      "loss": 1.2536,
      "step": 8
    },
    {
      "epoch": 0.0010967584694126249,
      "grad_norm": 0.6972594261169434,
      "learning_rate": 0.00018,
      "loss": 1.2661,
      "step": 9
    },
    {
      "epoch": 0.0010967584694126249,
      "eval_loss": 1.3777228593826294,
      "eval_runtime": 46.9103,
      "eval_samples_per_second": 73.673,
      "eval_steps_per_second": 36.836,
      "step": 9
    },
    {
      "epoch": 0.0012186205215695832,
      "grad_norm": 0.7863947153091431,
      "learning_rate": 0.0002,
      "loss": 1.2169,
      "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": 276627342753792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}