last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016431828451710965,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016431828451710963,
      "grad_norm": 1.6920582056045532,
      "learning_rate": 2e-05,
      "loss": 1.9238,
      "step": 1
    },
    {
      "epoch": 0.00016431828451710963,
      "eval_loss": 1.8038899898529053,
      "eval_runtime": 188.5099,
      "eval_samples_per_second": 13.596,
      "eval_steps_per_second": 6.801,
      "step": 1
    },
    {
      "epoch": 0.00032863656903421926,
      "grad_norm": 1.5381139516830444,
      "learning_rate": 4e-05,
      "loss": 1.3894,
      "step": 2
    },
    {
      "epoch": 0.0004929548535513289,
      "grad_norm": 2.7109837532043457,
      "learning_rate": 6e-05,
      "loss": 1.9371,
      "step": 3
    },
    {
      "epoch": 0.0004929548535513289,
      "eval_loss": 1.794869065284729,
      "eval_runtime": 193.4515,
      "eval_samples_per_second": 13.249,
      "eval_steps_per_second": 6.627,
      "step": 3
    },
    {
      "epoch": 0.0006572731380684385,
      "grad_norm": 1.109828233718872,
      "learning_rate": 8e-05,
      "loss": 1.645,
      "step": 4
    },
    {
      "epoch": 0.0008215914225855482,
      "grad_norm": 1.2177774906158447,
      "learning_rate": 0.0001,
      "loss": 1.7819,
      "step": 5
    },
    {
      "epoch": 0.0009859097071026578,
      "grad_norm": 1.7350780963897705,
      "learning_rate": 0.00012,
      "loss": 1.7212,
      "step": 6
    },
    {
      "epoch": 0.0009859097071026578,
      "eval_loss": 1.7177189588546753,
      "eval_runtime": 194.4652,
      "eval_samples_per_second": 13.18,
      "eval_steps_per_second": 6.592,
      "step": 6
    },
    {
      "epoch": 0.0011502279916197674,
      "grad_norm": 1.5537827014923096,
      "learning_rate": 0.00014,
      "loss": 1.656,
      "step": 7
    },
    {
      "epoch": 0.001314546276136877,
      "grad_norm": 0.7878876328468323,
      "learning_rate": 0.00016,
      "loss": 1.6709,
      "step": 8
    },
    {
      "epoch": 0.0014788645606539869,
      "grad_norm": 1.0037742853164673,
      "learning_rate": 0.00018,
      "loss": 1.458,
      "step": 9
    },
    {
      "epoch": 0.0014788645606539869,
      "eval_loss": 1.6837400197982788,
      "eval_runtime": 194.1291,
      "eval_samples_per_second": 13.203,
      "eval_steps_per_second": 6.604,
      "step": 9
    },
    {
      "epoch": 0.0016431828451710965,
      "grad_norm": 0.7114524245262146,
      "learning_rate": 0.0002,
      "loss": 1.516,
      "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": 868823083253760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}