last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.849002849002849,
  "eval_steps": 1000,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005698005698005698,
      "grad_norm": 6.307312488555908,
      "learning_rate": 0.0,
      "loss": 3.0911,
      "step": 1
    },
    {
      "epoch": 0.2849002849002849,
      "grad_norm": 4.076864719390869,
      "learning_rate": 0.0001977977977977978,
      "loss": 1.4649,
      "step": 50
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 2.819526195526123,
      "learning_rate": 0.0001952952952952953,
      "loss": 1.1601,
      "step": 100
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 3.7976534366607666,
      "learning_rate": 0.00019279279279279282,
      "loss": 1.1284,
      "step": 150
    },
    {
      "epoch": 1.1396011396011396,
      "grad_norm": 3.787907838821411,
      "learning_rate": 0.0001902902902902903,
      "loss": 0.91,
      "step": 200
    },
    {
      "epoch": 1.4245014245014245,
      "grad_norm": 3.807788133621216,
      "learning_rate": 0.0001877877877877878,
      "loss": 0.7007,
      "step": 250
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 3.6782045364379883,
      "learning_rate": 0.00018528528528528532,
      "loss": 0.6793,
      "step": 300
    },
    {
      "epoch": 1.9943019943019942,
      "grad_norm": 3.648346424102783,
      "learning_rate": 0.0001827827827827828,
      "loss": 0.7325,
      "step": 350
    },
    {
      "epoch": 2.2792022792022792,
      "grad_norm": 3.3711447715759277,
      "learning_rate": 0.00018028028028028027,
      "loss": 0.3936,
      "step": 400
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 3.362125873565674,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.3844,
      "step": 450
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 3.8006858825683594,
      "learning_rate": 0.00017527527527527528,
      "loss": 0.4327,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 4001,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 23,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5049248454213632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}