last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18691588785046728,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.9504849910736084,
      "learning_rate": 2e-05,
      "loss": 2.0864,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 2.4634759426116943,
      "eval_runtime": 1.9807,
      "eval_samples_per_second": 11.612,
      "eval_steps_per_second": 6.059,
      "step": 1
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 1.128625512123108,
      "learning_rate": 4e-05,
      "loss": 2.052,
      "step": 2
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 1.1591551303863525,
      "learning_rate": 6e-05,
      "loss": 2.0881,
      "step": 3
    },
    {
      "epoch": 0.056074766355140186,
      "eval_loss": 2.4596502780914307,
      "eval_runtime": 0.7432,
      "eval_samples_per_second": 30.947,
      "eval_steps_per_second": 16.146,
      "step": 3
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 1.0428029298782349,
      "learning_rate": 8e-05,
      "loss": 2.0578,
      "step": 4
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.082016944885254,
      "learning_rate": 0.0001,
      "loss": 1.9756,
      "step": 5
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 1.079058289527893,
      "learning_rate": 0.00012,
      "loss": 2.1077,
      "step": 6
    },
    {
      "epoch": 0.11214953271028037,
      "eval_loss": 2.4028377532958984,
      "eval_runtime": 0.7562,
      "eval_samples_per_second": 30.415,
      "eval_steps_per_second": 15.868,
      "step": 6
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 1.3398456573486328,
      "learning_rate": 0.00014,
      "loss": 2.3719,
      "step": 7
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 1.376936912536621,
      "learning_rate": 0.00016,
      "loss": 1.7642,
      "step": 8
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 1.6025842428207397,
      "learning_rate": 0.00018,
      "loss": 1.9801,
      "step": 9
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 2.127096652984619,
      "eval_runtime": 0.7449,
      "eval_samples_per_second": 30.878,
      "eval_steps_per_second": 16.11,
      "step": 9
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 1.239439845085144,
      "learning_rate": 0.0002,
      "loss": 1.8532,
      "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": 1895803354349568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}