last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016181229773462784,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016181229773462783,
      "grad_norm": 0.15954121947288513,
      "learning_rate": 2e-05,
      "loss": 11.9209,
      "step": 1
    },
    {
      "epoch": 0.00016181229773462783,
      "eval_loss": 11.928426742553711,
      "eval_runtime": 39.4665,
      "eval_samples_per_second": 65.955,
      "eval_steps_per_second": 32.99,
      "step": 1
    },
    {
      "epoch": 0.00032362459546925567,
      "grad_norm": 0.11309516429901123,
      "learning_rate": 4e-05,
      "loss": 11.9281,
      "step": 2
    },
    {
      "epoch": 0.0004854368932038835,
      "grad_norm": 0.12080027163028717,
      "learning_rate": 6e-05,
      "loss": 11.9262,
      "step": 3
    },
    {
      "epoch": 0.0004854368932038835,
      "eval_loss": 11.928329467773438,
      "eval_runtime": 35.764,
      "eval_samples_per_second": 72.783,
      "eval_steps_per_second": 36.405,
      "step": 3
    },
    {
      "epoch": 0.0006472491909385113,
      "grad_norm": 0.13808807730674744,
      "learning_rate": 8e-05,
      "loss": 11.9425,
      "step": 4
    },
    {
      "epoch": 0.0008090614886731392,
      "grad_norm": 0.12505756318569183,
      "learning_rate": 0.0001,
      "loss": 11.9319,
      "step": 5
    },
    {
      "epoch": 0.000970873786407767,
      "grad_norm": 0.12180116027593613,
      "learning_rate": 0.00012,
      "loss": 11.9318,
      "step": 6
    },
    {
      "epoch": 0.000970873786407767,
      "eval_loss": 11.927722930908203,
      "eval_runtime": 35.8785,
      "eval_samples_per_second": 72.55,
      "eval_steps_per_second": 36.289,
      "step": 6
    },
    {
      "epoch": 0.0011326860841423948,
      "grad_norm": 0.16290314495563507,
      "learning_rate": 0.00014,
      "loss": 11.9361,
      "step": 7
    },
    {
      "epoch": 0.0012944983818770227,
      "grad_norm": 0.1769724041223526,
      "learning_rate": 0.00016,
      "loss": 11.9299,
      "step": 8
    },
    {
      "epoch": 0.0014563106796116505,
      "grad_norm": 0.12376486510038376,
      "learning_rate": 0.00018,
      "loss": 11.9302,
      "step": 9
    },
    {
      "epoch": 0.0014563106796116505,
      "eval_loss": 11.926767349243164,
      "eval_runtime": 35.9504,
      "eval_samples_per_second": 72.405,
      "eval_steps_per_second": 36.217,
      "step": 9
    },
    {
      "epoch": 0.0016181229773462784,
      "grad_norm": 0.1310613751411438,
      "learning_rate": 0.0002,
      "loss": 11.9309,
      "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": 1470582226944.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}