End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_100_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_lda_100_v1_book_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8482518762584661
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_100_v1_book_qnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_100_v1_book) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6410
-- Accuracy: 0.8451
+- Loss: 0.3533
+- Accuracy: 0.8483
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8482518762584661,
+    "eval_loss": 0.35325977206230164,
+    "eval_runtime": 1.6659,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3279.318,
+    "eval_steps_per_second": 13.206,
+    "total_flos": 4.856261458098893e+16,
+    "train_loss": 0.23345495616102052,
+    "train_runtime": 500.4171,
+    "train_samples": 104743,
+    "train_samples_per_second": 10465.57,
+    "train_steps_per_second": 40.966
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8482518762584661,
+    "eval_loss": 0.35325977206230164,
+    "eval_runtime": 1.6659,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3279.318,
+    "eval_steps_per_second": 13.206
+}

logs/events.out.tfevents.1733765193.ki-g0009.1845686.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a81c6d24d00f69fb3c94212888c012fc84a47acafe469d758701ddb9adc15c
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 4.856261458098893e+16,
+    "train_loss": 0.23345495616102052,
+    "train_runtime": 500.4171,
+    "train_samples": 104743,
+    "train_samples_per_second": 10465.57,
+    "train_steps_per_second": 40.966
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.35325977206230164,
+  "best_model_checkpoint": "distilbert_lda_100_v1_book_qnli/checkpoint-820",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2870,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.58748197555542,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4749,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.829763866007688,
+      "eval_loss": 0.37372565269470215,
+      "eval_runtime": 1.7253,
+      "eval_samples_per_second": 3166.479,
+      "eval_steps_per_second": 12.752,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.76814079284668,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3589,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8482518762584661,
+      "eval_loss": 0.35325977206230164,
+      "eval_runtime": 1.6758,
+      "eval_samples_per_second": 3259.986,
+      "eval_steps_per_second": 13.128,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.550690650939941,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2756,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8506315211422295,
+      "eval_loss": 0.3594967722892761,
+      "eval_runtime": 1.7051,
+      "eval_samples_per_second": 3203.914,
+      "eval_steps_per_second": 12.902,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.16505241394043,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.201,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8339740069558851,
+      "eval_loss": 0.4855039417743683,
+      "eval_runtime": 1.7268,
+      "eval_samples_per_second": 3163.605,
+      "eval_steps_per_second": 12.74,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.6490440368652344,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1427,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8458722313747026,
+      "eval_loss": 0.48934316635131836,
+      "eval_runtime": 1.6931,
+      "eval_samples_per_second": 3226.695,
+      "eval_steps_per_second": 12.994,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 11.221846580505371,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1037,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8493501738971261,
+      "eval_loss": 0.5451710820198059,
+      "eval_runtime": 1.7455,
+      "eval_samples_per_second": 3129.713,
+      "eval_steps_per_second": 12.604,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 10.179837226867676,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0773,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8451400329489291,
+      "eval_loss": 0.6410212516784668,
+      "eval_runtime": 1.7235,
+      "eval_samples_per_second": 3169.69,
+      "eval_steps_per_second": 12.765,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "step": 2870,
+      "total_flos": 4.856261458098893e+16,
+      "train_loss": 0.23345495616102052,
+      "train_runtime": 500.4171,
+      "train_samples_per_second": 10465.57,
+      "train_steps_per_second": 40.966
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.856261458098893e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}