trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9879518072289155,
  "eval_steps": 500,
  "global_step": 186,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1606425702811245,
      "grad_norm": 55.777050153768585,
      "learning_rate": 5.263157894736842e-06,
      "loss": 3.9145,
      "step": 10
    },
    {
      "epoch": 0.321285140562249,
      "grad_norm": 6.574653822635258,
      "learning_rate": 9.999115304121459e-06,
      "loss": 0.3472,
      "step": 20
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 4.244131917524834,
      "learning_rate": 9.893330096656576e-06,
      "loss": 0.2294,
      "step": 30
    },
    {
      "epoch": 0.642570281124498,
      "grad_norm": 3.324081116501074,
      "learning_rate": 9.614885510995047e-06,
      "loss": 0.2041,
      "step": 40
    },
    {
      "epoch": 0.8032128514056225,
      "grad_norm": 3.1892405513679645,
      "learning_rate": 9.173606363381218e-06,
      "loss": 0.1989,
      "step": 50
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 2.4324918223476892,
      "learning_rate": 8.585063028536015e-06,
      "loss": 0.2037,
      "step": 60
    },
    {
      "epoch": 1.1244979919678715,
      "grad_norm": 2.16192012501172,
      "learning_rate": 7.870022044630569e-06,
      "loss": 0.1804,
      "step": 70
    },
    {
      "epoch": 1.285140562248996,
      "grad_norm": 46.57778152030111,
      "learning_rate": 7.053713373516538e-06,
      "loss": 0.1612,
      "step": 80
    },
    {
      "epoch": 1.4457831325301205,
      "grad_norm": 2.3080019184835585,
      "learning_rate": 6.164940170670266e-06,
      "loss": 0.1608,
      "step": 90
    },
    {
      "epoch": 1.606425702811245,
      "grad_norm": 2.4581039241773364,
      "learning_rate": 5.235062476295488e-06,
      "loss": 0.1577,
      "step": 100
    },
    {
      "epoch": 1.7670682730923695,
      "grad_norm": 2.2847917000132414,
      "learning_rate": 4.29689068767551e-06,
      "loss": 0.1529,
      "step": 110
    },
    {
      "epoch": 1.927710843373494,
      "grad_norm": 1.7632703410669297,
      "learning_rate": 3.3835278562017405e-06,
      "loss": 0.1576,
      "step": 120
    },
    {
      "epoch": 2.0883534136546187,
      "grad_norm": 1.161830645663707,
      "learning_rate": 2.5272016582081236e-06,
      "loss": 0.1296,
      "step": 130
    },
    {
      "epoch": 2.248995983935743,
      "grad_norm": 1.8411600296685922,
      "learning_rate": 1.7581272530970666e-06,
      "loss": 0.1004,
      "step": 140
    },
    {
      "epoch": 2.4096385542168672,
      "grad_norm": 2.21901118340881,
      "learning_rate": 1.103441152395588e-06,
      "loss": 0.0891,
      "step": 150
    },
    {
      "epoch": 2.570281124497992,
      "grad_norm": 1.888493064382548,
      "learning_rate": 5.862437177854629e-07,
      "loss": 0.0949,
      "step": 160
    },
    {
      "epoch": 2.7309236947791167,
      "grad_norm": 1.3428837781254024,
      "learning_rate": 2.2478407321721295e-07,
      "loss": 0.0925,
      "step": 170
    },
    {
      "epoch": 2.891566265060241,
      "grad_norm": 1.7122983109076155,
      "learning_rate": 3.181619118841517e-08,
      "loss": 0.0886,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 186,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4435300122624.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}