last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000871795244356942,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.9059841478564733e-05,
      "eval_loss": 2.155848264694214,
      "eval_runtime": 536.5615,
      "eval_samples_per_second": 27.005,
      "eval_steps_per_second": 13.503,
      "step": 1
    },
    {
      "epoch": 8.71795244356942e-05,
      "grad_norm": 4.412446975708008,
      "learning_rate": 6e-05,
      "loss": 9.0486,
      "step": 3
    },
    {
      "epoch": 0.00014529920739282366,
      "eval_loss": 2.064180374145508,
      "eval_runtime": 536.2694,
      "eval_samples_per_second": 27.02,
      "eval_steps_per_second": 13.51,
      "step": 5
    },
    {
      "epoch": 0.0001743590488713884,
      "grad_norm": 3.468630075454712,
      "learning_rate": 0.00012,
      "loss": 8.083,
      "step": 6
    },
    {
      "epoch": 0.0002615385733070826,
      "grad_norm": 3.6663637161254883,
      "learning_rate": 0.00018,
      "loss": 8.2768,
      "step": 9
    },
    {
      "epoch": 0.00029059841478564733,
      "eval_loss": 1.7950310707092285,
      "eval_runtime": 536.2891,
      "eval_samples_per_second": 27.019,
      "eval_steps_per_second": 13.51,
      "step": 10
    },
    {
      "epoch": 0.0003487180977427768,
      "grad_norm": 4.114701271057129,
      "learning_rate": 0.00019510565162951537,
      "loss": 7.2808,
      "step": 12
    },
    {
      "epoch": 0.000435897622178471,
      "grad_norm": 4.156654357910156,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.6025,
      "step": 15
    },
    {
      "epoch": 0.000435897622178471,
      "eval_loss": 1.5644091367721558,
      "eval_runtime": 537.4975,
      "eval_samples_per_second": 26.958,
      "eval_steps_per_second": 13.479,
      "step": 15
    },
    {
      "epoch": 0.0005230771466141652,
      "grad_norm": 3.9214437007904053,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.0271,
      "step": 18
    },
    {
      "epoch": 0.0005811968295712947,
      "eval_loss": 1.4372557401657104,
      "eval_runtime": 535.8345,
      "eval_samples_per_second": 27.042,
      "eval_steps_per_second": 13.521,
      "step": 20
    },
    {
      "epoch": 0.0006102566710498594,
      "grad_norm": 3.9005424976348877,
      "learning_rate": 8.435655349597689e-05,
      "loss": 5.7874,
      "step": 21
    },
    {
      "epoch": 0.0006974361954855536,
      "grad_norm": 3.8502655029296875,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.005,
      "step": 24
    },
    {
      "epoch": 0.0007264960369641184,
      "eval_loss": 1.3938194513320923,
      "eval_runtime": 537.5193,
      "eval_samples_per_second": 26.957,
      "eval_steps_per_second": 13.479,
      "step": 25
    },
    {
      "epoch": 0.0007846157199212478,
      "grad_norm": 3.130795955657959,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 5.8796,
      "step": 27
    },
    {
      "epoch": 0.000871795244356942,
      "grad_norm": 4.091054439544678,
      "learning_rate": 0.0,
      "loss": 5.2588,
      "step": 30
    },
    {
      "epoch": 0.000871795244356942,
      "eval_loss": 1.3867002725601196,
      "eval_runtime": 536.044,
      "eval_samples_per_second": 27.031,
      "eval_steps_per_second": 13.516,
      "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": 1953283178496000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}