last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013892747985551543,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001389274798555154,
      "grad_norm": 0.5198307037353516,
      "learning_rate": 2e-05,
      "loss": 5.6224,
      "step": 1
    },
    {
      "epoch": 0.0001389274798555154,
      "eval_loss": 1.1990605592727661,
      "eval_runtime": 185.4205,
      "eval_samples_per_second": 16.347,
      "eval_steps_per_second": 8.176,
      "step": 1
    },
    {
      "epoch": 0.0002778549597110308,
      "grad_norm": 0.5348038077354431,
      "learning_rate": 4e-05,
      "loss": 4.2674,
      "step": 2
    },
    {
      "epoch": 0.0004167824395665463,
      "grad_norm": 1.1177834272384644,
      "learning_rate": 6e-05,
      "loss": 4.9679,
      "step": 3
    },
    {
      "epoch": 0.0004167824395665463,
      "eval_loss": 1.198678970336914,
      "eval_runtime": 185.4929,
      "eval_samples_per_second": 16.34,
      "eval_steps_per_second": 8.173,
      "step": 3
    },
    {
      "epoch": 0.0005557099194220616,
      "grad_norm": 0.5691863894462585,
      "learning_rate": 8e-05,
      "loss": 3.8051,
      "step": 4
    },
    {
      "epoch": 0.0006946373992775772,
      "grad_norm": 0.5815349817276001,
      "learning_rate": 0.0001,
      "loss": 4.9314,
      "step": 5
    },
    {
      "epoch": 0.0008335648791330926,
      "grad_norm": 0.7734096646308899,
      "learning_rate": 0.00012,
      "loss": 5.3064,
      "step": 6
    },
    {
      "epoch": 0.0008335648791330926,
      "eval_loss": 1.192445158958435,
      "eval_runtime": 185.5567,
      "eval_samples_per_second": 16.335,
      "eval_steps_per_second": 8.17,
      "step": 6
    },
    {
      "epoch": 0.000972492358988608,
      "grad_norm": 0.7191041111946106,
      "learning_rate": 0.00014,
      "loss": 4.1163,
      "step": 7
    },
    {
      "epoch": 0.0011114198388441233,
      "grad_norm": 1.3875627517700195,
      "learning_rate": 0.00016,
      "loss": 5.7162,
      "step": 8
    },
    {
      "epoch": 0.0012503473186996387,
      "grad_norm": 0.97846519947052,
      "learning_rate": 0.00018,
      "loss": 5.0321,
      "step": 9
    },
    {
      "epoch": 0.0012503473186996387,
      "eval_loss": 1.1586050987243652,
      "eval_runtime": 185.5947,
      "eval_samples_per_second": 16.331,
      "eval_steps_per_second": 8.168,
      "step": 9
    },
    {
      "epoch": 0.0013892747985551543,
      "grad_norm": 1.2583094835281372,
      "learning_rate": 0.0002,
      "loss": 5.2049,
      "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": 3094623559876608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}