last-checkpoint/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2836,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08815232722143865,
      "grad_norm": 48028.53125,
      "learning_rate": 4.561001410437236e-05,
      "loss": 0.7241,
      "step": 250
    },
    {
      "epoch": 0.1763046544428773,
      "grad_norm": 36453.3671875,
      "learning_rate": 4.120239774330042e-05,
      "loss": 0.0023,
      "step": 500
    },
    {
      "epoch": 0.2644569816643159,
      "grad_norm": 20.423324584960938,
      "learning_rate": 3.679478138222849e-05,
      "loss": 0.002,
      "step": 750
    },
    {
      "epoch": 0.3526093088857546,
      "grad_norm": 13388.93359375,
      "learning_rate": 3.2387165021156564e-05,
      "loss": 0.0013,
      "step": 1000
    },
    {
      "epoch": 0.4407616361071932,
      "grad_norm": 9583.7470703125,
      "learning_rate": 2.7979548660084627e-05,
      "loss": 0.0011,
      "step": 1250
    },
    {
      "epoch": 0.5289139633286318,
      "grad_norm": 0.8403513431549072,
      "learning_rate": 2.3571932299012694e-05,
      "loss": 0.0009,
      "step": 1500
    },
    {
      "epoch": 0.6170662905500706,
      "grad_norm": 1.9435118436813354,
      "learning_rate": 1.9164315937940765e-05,
      "loss": 0.0007,
      "step": 1750
    },
    {
      "epoch": 0.7052186177715092,
      "grad_norm": 1.006479263305664,
      "learning_rate": 1.4756699576868829e-05,
      "loss": 0.0009,
      "step": 2000
    },
    {
      "epoch": 0.7933709449929478,
      "grad_norm": 0.10926026105880737,
      "learning_rate": 1.0349083215796897e-05,
      "loss": 0.0004,
      "step": 2250
    },
    {
      "epoch": 0.8815232722143864,
      "grad_norm": 0.5444942712783813,
      "learning_rate": 5.9414668547249645e-06,
      "loss": 0.0005,
      "step": 2500
    },
    {
      "epoch": 0.9696755994358252,
      "grad_norm": 0.10924108326435089,
      "learning_rate": 1.5338504936530325e-06,
      "loss": 0.0004,
      "step": 2750
    }
  ],
  "logging_steps": 250,
  "max_steps": 2836,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6914716304670720.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}