last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016351892731583682,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001635189273158368,
      "eval_loss": 2.2701847553253174,
      "eval_runtime": 45.6108,
      "eval_samples_per_second": 56.456,
      "eval_steps_per_second": 28.239,
      "step": 1
    },
    {
      "epoch": 0.001635189273158368,
      "grad_norm": 1.6498826742172241,
      "learning_rate": 0.00019967573081342103,
      "loss": 1.8962,
      "step": 10
    },
    {
      "epoch": 0.003270378546316736,
      "grad_norm": 2.2788889408111572,
      "learning_rate": 0.0001970941817426052,
      "loss": 1.6468,
      "step": 20
    },
    {
      "epoch": 0.0049055678194751045,
      "grad_norm": 1.7382475137710571,
      "learning_rate": 0.00019199794436588243,
      "loss": 1.7137,
      "step": 30
    },
    {
      "epoch": 0.006540757092633472,
      "grad_norm": 1.3833692073822021,
      "learning_rate": 0.0001845190085543795,
      "loss": 1.7509,
      "step": 40
    },
    {
      "epoch": 0.008175946365791841,
      "grad_norm": 1.2240101099014282,
      "learning_rate": 0.00017485107481711012,
      "loss": 1.6796,
      "step": 50
    },
    {
      "epoch": 0.008175946365791841,
      "eval_loss": 1.7598543167114258,
      "eval_runtime": 44.6389,
      "eval_samples_per_second": 57.685,
      "eval_steps_per_second": 28.854,
      "step": 50
    },
    {
      "epoch": 0.009811135638950209,
      "grad_norm": 1.3060485124588013,
      "learning_rate": 0.00016324453755953773,
      "loss": 1.5988,
      "step": 60
    },
    {
      "epoch": 0.011446324912108577,
      "grad_norm": 1.2081083059310913,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6312,
      "step": 70
    },
    {
      "epoch": 0.013081514185266945,
      "grad_norm": 1.0915815830230713,
      "learning_rate": 0.00013546048870425356,
      "loss": 1.6993,
      "step": 80
    },
    {
      "epoch": 0.014716703458425313,
      "grad_norm": 1.5986297130584717,
      "learning_rate": 0.00012000256937760445,
      "loss": 1.6293,
      "step": 90
    },
    {
      "epoch": 0.016351892731583682,
      "grad_norm": 1.1840400695800781,
      "learning_rate": 0.00010402659401094152,
      "loss": 1.5559,
      "step": 100
    },
    {
      "epoch": 0.016351892731583682,
      "eval_loss": 1.7379602193832397,
      "eval_runtime": 44.7506,
      "eval_samples_per_second": 57.541,
      "eval_steps_per_second": 28.782,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 890381638041600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}