last-checkpoint/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01990049751243781,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009950248756218905,
      "grad_norm": 0.8776684999465942,
      "learning_rate": 0.0,
      "loss": 1.6946,
      "step": 1
    },
    {
      "epoch": 0.001990049751243781,
      "grad_norm": 0.9731295704841614,
      "learning_rate": 7e-07,
      "loss": 1.852,
      "step": 2
    },
    {
      "epoch": 0.0029850746268656717,
      "grad_norm": 0.9005614519119263,
      "learning_rate": 1.4e-06,
      "loss": 1.7867,
      "step": 3
    },
    {
      "epoch": 0.003980099502487562,
      "grad_norm": 0.974780261516571,
      "learning_rate": 2.1e-06,
      "loss": 1.7229,
      "step": 4
    },
    {
      "epoch": 0.004975124378109453,
      "grad_norm": 0.711536169052124,
      "learning_rate": 2.8e-06,
      "loss": 1.6955,
      "step": 5
    },
    {
      "epoch": 0.005970149253731343,
      "grad_norm": 0.7311899065971375,
      "learning_rate": 3.5e-06,
      "loss": 1.8664,
      "step": 6
    },
    {
      "epoch": 0.006965174129353234,
      "grad_norm": 0.7126452326774597,
      "learning_rate": 4.2e-06,
      "loss": 1.8133,
      "step": 7
    },
    {
      "epoch": 0.007960199004975124,
      "grad_norm": 0.7019472122192383,
      "learning_rate": 4.9e-06,
      "loss": 1.6724,
      "step": 8
    },
    {
      "epoch": 0.008955223880597015,
      "grad_norm": 0.7028383016586304,
      "learning_rate": 5.6e-06,
      "loss": 1.7337,
      "step": 9
    },
    {
      "epoch": 0.009950248756218905,
      "grad_norm": 0.6948546767234802,
      "learning_rate": 6.299999999999999e-06,
      "loss": 1.6073,
      "step": 10
    },
    {
      "epoch": 0.010945273631840797,
      "grad_norm": 0.6322774291038513,
      "learning_rate": 7e-06,
      "loss": 1.6254,
      "step": 11
    },
    {
      "epoch": 0.011940298507462687,
      "grad_norm": 0.5230722427368164,
      "learning_rate": 7.699999999999999e-06,
      "loss": 1.704,
      "step": 12
    },
    {
      "epoch": 0.012935323383084577,
      "grad_norm": 0.38045769929885864,
      "learning_rate": 8.4e-06,
      "loss": 1.5992,
      "step": 13
    },
    {
      "epoch": 0.013930348258706468,
      "grad_norm": 0.43926432728767395,
      "learning_rate": 9.1e-06,
      "loss": 1.3649,
      "step": 14
    },
    {
      "epoch": 0.014925373134328358,
      "grad_norm": 0.6113471388816833,
      "learning_rate": 9.8e-06,
      "loss": 1.7055,
      "step": 15
    },
    {
      "epoch": 0.015920398009950248,
      "grad_norm": 0.549103856086731,
      "learning_rate": 1.05e-05,
      "loss": 1.6179,
      "step": 16
    },
    {
      "epoch": 0.01691542288557214,
      "grad_norm": 0.39344537258148193,
      "learning_rate": 1.12e-05,
      "loss": 1.517,
      "step": 17
    },
    {
      "epoch": 0.01791044776119403,
      "grad_norm": 0.3620043098926544,
      "learning_rate": 1.19e-05,
      "loss": 1.4598,
      "step": 18
    },
    {
      "epoch": 0.01890547263681592,
      "grad_norm": 0.271251380443573,
      "learning_rate": 1.2599999999999998e-05,
      "loss": 1.441,
      "step": 19
    },
    {
      "epoch": 0.01990049751243781,
      "grad_norm": 0.2406337559223175,
      "learning_rate": 1.33e-05,
      "loss": 1.5409,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.5380973908656128e+16,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}