last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001007582054963601,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010075820549636011,
      "grad_norm": 8.359752932236722e+18,
      "learning_rate": 2e-05,
      "loss": 1.8654,
      "step": 1
    },
    {
      "epoch": 0.00010075820549636011,
      "eval_loss": 1.7779617309570312,
      "eval_runtime": 1454.9416,
      "eval_samples_per_second": 2.872,
      "eval_steps_per_second": 1.436,
      "step": 1
    },
    {
      "epoch": 0.00020151641099272022,
      "grad_norm": 2.626370165041791e+18,
      "learning_rate": 4e-05,
      "loss": 1.3359,
      "step": 2
    },
    {
      "epoch": 0.0003022746164890803,
      "grad_norm": 3.249743505089626e+18,
      "learning_rate": 6e-05,
      "loss": 1.3042,
      "step": 3
    },
    {
      "epoch": 0.0003022746164890803,
      "eval_loss": 1.7708849906921387,
      "eval_runtime": 1454.6249,
      "eval_samples_per_second": 2.873,
      "eval_steps_per_second": 1.437,
      "step": 3
    },
    {
      "epoch": 0.00040303282198544043,
      "grad_norm": 8.100253344674611e+18,
      "learning_rate": 8e-05,
      "loss": 1.5396,
      "step": 4
    },
    {
      "epoch": 0.0005037910274818005,
      "grad_norm": 4.612551334078448e+18,
      "learning_rate": 0.0001,
      "loss": 1.2117,
      "step": 5
    },
    {
      "epoch": 0.0006045492329781607,
      "grad_norm": 6.333141896013021e+18,
      "learning_rate": 0.00012,
      "loss": 1.6426,
      "step": 6
    },
    {
      "epoch": 0.0006045492329781607,
      "eval_loss": 1.7828969955444336,
      "eval_runtime": 1454.0873,
      "eval_samples_per_second": 2.874,
      "eval_steps_per_second": 1.437,
      "step": 6
    },
    {
      "epoch": 0.0007053074384745208,
      "grad_norm": 5.453606261071282e+18,
      "learning_rate": 0.00014,
      "loss": 1.3789,
      "step": 7
    },
    {
      "epoch": 0.0008060656439708809,
      "grad_norm": 7.580743446399287e+18,
      "learning_rate": 0.00016,
      "loss": 1.4,
      "step": 8
    },
    {
      "epoch": 0.000906823849467241,
      "grad_norm": 1.1626996814149845e+19,
      "learning_rate": 0.00018,
      "loss": 1.3397,
      "step": 9
    },
    {
      "epoch": 0.000906823849467241,
      "eval_loss": 1.7769960165023804,
      "eval_runtime": 1454.9997,
      "eval_samples_per_second": 2.872,
      "eval_steps_per_second": 1.436,
      "step": 9
    },
    {
      "epoch": 0.001007582054963601,
      "grad_norm": 9.149156101491524e+18,
      "learning_rate": 0.0002,
      "loss": 1.5154,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2058737544069120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}