last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07357449417535254,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002452483139178418,
      "eval_loss": 11.110869407653809,
      "eval_runtime": 0.6695,
      "eval_samples_per_second": 256.911,
      "eval_steps_per_second": 128.456,
      "step": 1
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 0.7765430808067322,
      "learning_rate": 6e-05,
      "loss": 44.4524,
      "step": 3
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 11.1087646484375,
      "eval_runtime": 0.6559,
      "eval_samples_per_second": 262.233,
      "eval_steps_per_second": 131.116,
      "step": 5
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 0.8166353106498718,
      "learning_rate": 0.00012,
      "loss": 44.4704,
      "step": 6
    },
    {
      "epoch": 0.022072348252605765,
      "grad_norm": 0.7704782485961914,
      "learning_rate": 0.00018,
      "loss": 44.4727,
      "step": 9
    },
    {
      "epoch": 0.024524831391784182,
      "eval_loss": 11.100621223449707,
      "eval_runtime": 0.653,
      "eval_samples_per_second": 263.406,
      "eval_steps_per_second": 131.703,
      "step": 10
    },
    {
      "epoch": 0.029429797670141016,
      "grad_norm": 0.8236488103866577,
      "learning_rate": 0.00019510565162951537,
      "loss": 44.4103,
      "step": 12
    },
    {
      "epoch": 0.03678724708767627,
      "grad_norm": 0.9741674661636353,
      "learning_rate": 0.00017071067811865476,
      "loss": 44.4028,
      "step": 15
    },
    {
      "epoch": 0.03678724708767627,
      "eval_loss": 11.085661888122559,
      "eval_runtime": 0.6846,
      "eval_samples_per_second": 251.257,
      "eval_steps_per_second": 125.629,
      "step": 15
    },
    {
      "epoch": 0.04414469650521153,
      "grad_norm": 1.00701904296875,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.349,
      "step": 18
    },
    {
      "epoch": 0.049049662783568364,
      "eval_loss": 11.071290016174316,
      "eval_runtime": 0.6882,
      "eval_samples_per_second": 249.923,
      "eval_steps_per_second": 124.962,
      "step": 20
    },
    {
      "epoch": 0.05150214592274678,
      "grad_norm": 1.1043449640274048,
      "learning_rate": 8.435655349597689e-05,
      "loss": 44.2863,
      "step": 21
    },
    {
      "epoch": 0.05885959534028203,
      "grad_norm": 1.0619176626205444,
      "learning_rate": 4.12214747707527e-05,
      "loss": 44.2996,
      "step": 24
    },
    {
      "epoch": 0.061312078479460456,
      "eval_loss": 11.062753677368164,
      "eval_runtime": 0.6727,
      "eval_samples_per_second": 255.701,
      "eval_steps_per_second": 127.85,
      "step": 25
    },
    {
      "epoch": 0.06621704475781728,
      "grad_norm": 1.1007205247879028,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 44.2594,
      "step": 27
    },
    {
      "epoch": 0.07357449417535254,
      "grad_norm": 1.1125785112380981,
      "learning_rate": 0.0,
      "loss": 44.2477,
      "step": 30
    },
    {
      "epoch": 0.07357449417535254,
      "eval_loss": 11.061006546020508,
      "eval_runtime": 0.6899,
      "eval_samples_per_second": 249.323,
      "eval_steps_per_second": 124.661,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 634386382848.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}