last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004216829365999705,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.216829365999705e-05,
      "grad_norm": 0.39630717039108276,
      "learning_rate": 2e-05,
      "loss": 4.4656,
      "step": 1
    },
    {
      "epoch": 4.216829365999705e-05,
      "eval_loss": 1.2347631454467773,
      "eval_runtime": 628.1068,
      "eval_samples_per_second": 15.897,
      "eval_steps_per_second": 7.949,
      "step": 1
    },
    {
      "epoch": 8.43365873199941e-05,
      "grad_norm": 0.36101648211479187,
      "learning_rate": 4e-05,
      "loss": 5.0924,
      "step": 2
    },
    {
      "epoch": 0.00012650488097999115,
      "grad_norm": 0.3448565602302551,
      "learning_rate": 6e-05,
      "loss": 4.9142,
      "step": 3
    },
    {
      "epoch": 0.00012650488097999115,
      "eval_loss": 1.2344515323638916,
      "eval_runtime": 628.4942,
      "eval_samples_per_second": 15.887,
      "eval_steps_per_second": 7.944,
      "step": 3
    },
    {
      "epoch": 0.0001686731746399882,
      "grad_norm": 0.36048734188079834,
      "learning_rate": 8e-05,
      "loss": 5.3073,
      "step": 4
    },
    {
      "epoch": 0.00021084146829998524,
      "grad_norm": 0.35351118445396423,
      "learning_rate": 0.0001,
      "loss": 4.7238,
      "step": 5
    },
    {
      "epoch": 0.0002530097619599823,
      "grad_norm": 0.4661104679107666,
      "learning_rate": 0.00012,
      "loss": 5.3615,
      "step": 6
    },
    {
      "epoch": 0.0002530097619599823,
      "eval_loss": 1.230110764503479,
      "eval_runtime": 629.238,
      "eval_samples_per_second": 15.868,
      "eval_steps_per_second": 7.935,
      "step": 6
    },
    {
      "epoch": 0.0002951780556199793,
      "grad_norm": 0.5142518281936646,
      "learning_rate": 0.00014,
      "loss": 4.9236,
      "step": 7
    },
    {
      "epoch": 0.0003373463492799764,
      "grad_norm": 1.1006965637207031,
      "learning_rate": 0.00016,
      "loss": 5.0177,
      "step": 8
    },
    {
      "epoch": 0.0003795146429399734,
      "grad_norm": 0.6855748295783997,
      "learning_rate": 0.00018,
      "loss": 4.5697,
      "step": 9
    },
    {
      "epoch": 0.0003795146429399734,
      "eval_loss": 1.207474708557129,
      "eval_runtime": 629.1326,
      "eval_samples_per_second": 15.871,
      "eval_steps_per_second": 7.936,
      "step": 9
    },
    {
      "epoch": 0.0004216829365999705,
      "grad_norm": 0.7536121010780334,
      "learning_rate": 0.0002,
      "loss": 4.7298,
      "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": 2972467366723584.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}