last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0098015192354815,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00098015192354815,
      "grad_norm": 0.8281226754188538,
      "learning_rate": 2e-05,
      "loss": 2.3546,
      "step": 1
    },
    {
      "epoch": 0.00098015192354815,
      "eval_loss": 2.422258138656616,
      "eval_runtime": 4.0518,
      "eval_samples_per_second": 106.126,
      "eval_steps_per_second": 53.063,
      "step": 1
    },
    {
      "epoch": 0.0019603038470963,
      "grad_norm": 0.5358867645263672,
      "learning_rate": 4e-05,
      "loss": 2.1242,
      "step": 2
    },
    {
      "epoch": 0.00294045577064445,
      "grad_norm": 0.6448020339012146,
      "learning_rate": 6e-05,
      "loss": 2.1825,
      "step": 3
    },
    {
      "epoch": 0.00294045577064445,
      "eval_loss": 2.4217824935913086,
      "eval_runtime": 3.6396,
      "eval_samples_per_second": 118.143,
      "eval_steps_per_second": 59.072,
      "step": 3
    },
    {
      "epoch": 0.0039206076941926,
      "grad_norm": 0.542057454586029,
      "learning_rate": 8e-05,
      "loss": 2.0017,
      "step": 4
    },
    {
      "epoch": 0.00490075961774075,
      "grad_norm": 0.653765857219696,
      "learning_rate": 0.0001,
      "loss": 2.5302,
      "step": 5
    },
    {
      "epoch": 0.0058809115412889,
      "grad_norm": 0.537108838558197,
      "learning_rate": 0.00012,
      "loss": 2.5194,
      "step": 6
    },
    {
      "epoch": 0.0058809115412889,
      "eval_loss": 2.4095170497894287,
      "eval_runtime": 3.5216,
      "eval_samples_per_second": 122.104,
      "eval_steps_per_second": 61.052,
      "step": 6
    },
    {
      "epoch": 0.00686106346483705,
      "grad_norm": 0.6363251209259033,
      "learning_rate": 0.00014,
      "loss": 2.2288,
      "step": 7
    },
    {
      "epoch": 0.0078412153883852,
      "grad_norm": 0.6005361080169678,
      "learning_rate": 0.00016,
      "loss": 2.3312,
      "step": 8
    },
    {
      "epoch": 0.008821367311933349,
      "grad_norm": 0.6487131118774414,
      "learning_rate": 0.00018,
      "loss": 2.4898,
      "step": 9
    },
    {
      "epoch": 0.008821367311933349,
      "eval_loss": 2.3651981353759766,
      "eval_runtime": 3.5733,
      "eval_samples_per_second": 120.336,
      "eval_steps_per_second": 60.168,
      "step": 9
    },
    {
      "epoch": 0.0098015192354815,
      "grad_norm": 0.5703725814819336,
      "learning_rate": 0.0002,
      "loss": 2.1212,
      "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": 34292650475520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}