last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015908789606257458,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.302929868752486e-05,
      "eval_loss": 11.474228858947754,
      "eval_runtime": 36.228,
      "eval_samples_per_second": 219.167,
      "eval_steps_per_second": 109.584,
      "step": 1
    },
    {
      "epoch": 0.00015908789606257457,
      "grad_norm": 1151.3118896484375,
      "learning_rate": 6e-05,
      "loss": 42.5243,
      "step": 3
    },
    {
      "epoch": 0.00026514649343762427,
      "eval_loss": 11.444195747375488,
      "eval_runtime": 35.4652,
      "eval_samples_per_second": 223.881,
      "eval_steps_per_second": 111.941,
      "step": 5
    },
    {
      "epoch": 0.00031817579212514913,
      "grad_norm": 1112.416259765625,
      "learning_rate": 0.00012,
      "loss": 47.2916,
      "step": 6
    },
    {
      "epoch": 0.00047726368818772373,
      "grad_norm": 1181.1636962890625,
      "learning_rate": 0.00018,
      "loss": 41.1516,
      "step": 9
    },
    {
      "epoch": 0.0005302929868752485,
      "eval_loss": 11.341529846191406,
      "eval_runtime": 35.4038,
      "eval_samples_per_second": 224.269,
      "eval_steps_per_second": 112.135,
      "step": 10
    },
    {
      "epoch": 0.0006363515842502983,
      "grad_norm": 1189.462890625,
      "learning_rate": 0.00019510565162951537,
      "loss": 51.5067,
      "step": 12
    },
    {
      "epoch": 0.0007954394803128729,
      "grad_norm": 1243.0428466796875,
      "learning_rate": 0.00017071067811865476,
      "loss": 43.6285,
      "step": 15
    },
    {
      "epoch": 0.0007954394803128729,
      "eval_loss": 11.163180351257324,
      "eval_runtime": 35.4616,
      "eval_samples_per_second": 223.904,
      "eval_steps_per_second": 111.952,
      "step": 15
    },
    {
      "epoch": 0.0009545273763754475,
      "grad_norm": 1079.206298828125,
      "learning_rate": 0.00013090169943749476,
      "loss": 46.0199,
      "step": 18
    },
    {
      "epoch": 0.001060585973750497,
      "eval_loss": 11.0809965133667,
      "eval_runtime": 35.2178,
      "eval_samples_per_second": 225.454,
      "eval_steps_per_second": 112.727,
      "step": 20
    },
    {
      "epoch": 0.001113615272438022,
      "grad_norm": 1518.35986328125,
      "learning_rate": 8.435655349597689e-05,
      "loss": 45.4035,
      "step": 21
    },
    {
      "epoch": 0.0012727031685005965,
      "grad_norm": 1333.44287109375,
      "learning_rate": 4.12214747707527e-05,
      "loss": 49.1836,
      "step": 24
    },
    {
      "epoch": 0.0013257324671881213,
      "eval_loss": 11.057934761047363,
      "eval_runtime": 35.4103,
      "eval_samples_per_second": 224.228,
      "eval_steps_per_second": 112.114,
      "step": 25
    },
    {
      "epoch": 0.0014317910645631712,
      "grad_norm": 1666.79833984375,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 43.5465,
      "step": 27
    },
    {
      "epoch": 0.0015908789606257458,
      "grad_norm": 2032.2802734375,
      "learning_rate": 0.0,
      "loss": 42.8751,
      "step": 30
    },
    {
      "epoch": 0.0015908789606257458,
      "eval_loss": 11.05472469329834,
      "eval_runtime": 35.3871,
      "eval_samples_per_second": 224.376,
      "eval_steps_per_second": 112.188,
      "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": 67029675540480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}