checkpoint-336/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.993325917686318,
  "eval_steps": 500,
  "global_step": 336,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11865035224323323,
      "grad_norm": 0.5938982963562012,
      "learning_rate": 9.723076923076924e-05,
      "loss": 1.2521,
      "step": 20
    },
    {
      "epoch": 0.23730070448646645,
      "grad_norm": 0.19858305156230927,
      "learning_rate": 9.107692307692308e-05,
      "loss": 0.3248,
      "step": 40
    },
    {
      "epoch": 0.3559510567296997,
      "grad_norm": 0.05706700682640076,
      "learning_rate": 8.492307692307693e-05,
      "loss": 0.0197,
      "step": 60
    },
    {
      "epoch": 0.4746014089729329,
      "grad_norm": 0.0070083774626255035,
      "learning_rate": 7.876923076923077e-05,
      "loss": 0.0028,
      "step": 80
    },
    {
      "epoch": 0.5932517612161661,
      "grad_norm": 0.004076245240867138,
      "learning_rate": 7.261538461538462e-05,
      "loss": 0.0007,
      "step": 100
    },
    {
      "epoch": 0.7119021134593994,
      "grad_norm": 0.003080987138673663,
      "learning_rate": 6.646153846153846e-05,
      "loss": 0.0005,
      "step": 120
    },
    {
      "epoch": 0.8305524657026325,
      "grad_norm": 0.0025518136098980904,
      "learning_rate": 6.030769230769231e-05,
      "loss": 0.0004,
      "step": 140
    },
    {
      "epoch": 0.9492028179458658,
      "grad_norm": 0.0022116131149232388,
      "learning_rate": 5.4153846153846156e-05,
      "loss": 0.0004,
      "step": 160
    },
    {
      "epoch": 1.067853170189099,
      "grad_norm": 0.0019687730818986893,
      "learning_rate": 4.8e-05,
      "loss": 0.0003,
      "step": 180
    },
    {
      "epoch": 1.1865035224323321,
      "grad_norm": 0.0017901354003697634,
      "learning_rate": 4.1846153846153846e-05,
      "loss": 0.0003,
      "step": 200
    },
    {
      "epoch": 1.3051538746755655,
      "grad_norm": 0.0016503820661455393,
      "learning_rate": 3.569230769230769e-05,
      "loss": 0.0003,
      "step": 220
    },
    {
      "epoch": 1.4238042269187987,
      "grad_norm": 0.0015508969081565738,
      "learning_rate": 2.9538461538461543e-05,
      "loss": 0.0003,
      "step": 240
    },
    {
      "epoch": 1.5424545791620319,
      "grad_norm": 0.001471668598242104,
      "learning_rate": 2.3384615384615385e-05,
      "loss": 0.0002,
      "step": 260
    },
    {
      "epoch": 1.6611049314052653,
      "grad_norm": 0.0014170887880027294,
      "learning_rate": 1.723076923076923e-05,
      "loss": 0.0002,
      "step": 280
    },
    {
      "epoch": 1.7797552836484982,
      "grad_norm": 0.0013795532286167145,
      "learning_rate": 1.1076923076923077e-05,
      "loss": 0.0002,
      "step": 300
    },
    {
      "epoch": 1.8984056358917316,
      "grad_norm": 0.0013580905506387353,
      "learning_rate": 4.923076923076923e-06,
      "loss": 0.0002,
      "step": 320
    }
  ],
  "logging_steps": 20,
  "max_steps": 336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3387692641288192e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}