End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_100_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: distilbert_lda_100_v1_book_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.254232462261425
+    - name: Accuracy
+      type: accuracy
+      value: 0.718120813369751
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_100_v1_book_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7496
-- Matthews Correlation: 0.3430
-- Accuracy: 0.7373
+- Loss: 0.5656
+- Matthews Correlation: 0.2542
+- Accuracy: 0.7181
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.718120813369751,
+    "eval_loss": 0.5656152963638306,
+    "eval_matthews_correlation": 0.254232462261425,
+    "eval_runtime": 0.3445,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3027.863,
+    "eval_steps_per_second": 14.515,
+    "total_flos": 4530914903629824.0,
+    "train_loss": 0.38461392942596884,
+    "train_runtime": 57.3363,
+    "train_samples": 8551,
+    "train_samples_per_second": 7456.876,
+    "train_steps_per_second": 29.65
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.718120813369751,
+    "eval_loss": 0.5656152963638306,
+    "eval_matthews_correlation": 0.254232462261425,
+    "eval_runtime": 0.3445,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3027.863,
+    "eval_steps_per_second": 14.515
+}

logs/events.out.tfevents.1733764549.ki-g0009.1845686.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84be6d1897e7faae16da652973ea50d69b2c83b6f5d8a9ffae17313d294dbe3
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 4530914903629824.0,
+    "train_loss": 0.38461392942596884,
+    "train_runtime": 57.3363,
+    "train_samples": 8551,
+    "train_samples_per_second": 7456.876,
+    "train_steps_per_second": 29.65
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": 0.5656152963638306,
+  "best_model_checkpoint": "distilbert_lda_100_v1_book_cola/checkpoint-102",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5555246472358704,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6088,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6094817519187927,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3205,
+      "eval_samples_per_second": 3254.572,
+      "eval_steps_per_second": 15.602,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.445493459701538,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5811,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7008628845214844,
+      "eval_loss": 0.5893582701683044,
+      "eval_matthews_correlation": 0.18064295823559037,
+      "eval_runtime": 0.3252,
+      "eval_samples_per_second": 3207.55,
+      "eval_steps_per_second": 15.377,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.7831716537475586,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4993,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.718120813369751,
+      "eval_loss": 0.5656152963638306,
+      "eval_matthews_correlation": 0.254232462261425,
+      "eval_runtime": 0.3241,
+      "eval_samples_per_second": 3218.486,
+      "eval_steps_per_second": 15.429,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.308906555175781,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4235,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7267497777938843,
+      "eval_loss": 0.6413943767547607,
+      "eval_matthews_correlation": 0.264343150430225,
+      "eval_runtime": 0.3194,
+      "eval_samples_per_second": 3265.799,
+      "eval_steps_per_second": 15.656,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.122441291809082,
+      "learning_rate": 4.5e-05,
+      "loss": 0.335,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7277085185050964,
+      "eval_loss": 0.6178256869316101,
+      "eval_matthews_correlation": 0.3053388692306635,
+      "eval_runtime": 0.3275,
+      "eval_samples_per_second": 3184.95,
+      "eval_steps_per_second": 15.268,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.9515864849090576,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2571,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7334611415863037,
+      "eval_loss": 0.6786776781082153,
+      "eval_matthews_correlation": 0.31846150712626237,
+      "eval_runtime": 0.35,
+      "eval_samples_per_second": 2979.932,
+      "eval_steps_per_second": 14.285,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.923041343688965,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1982,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.743048906326294,
+      "eval_loss": 0.7715895771980286,
+      "eval_matthews_correlation": 0.3333152417227179,
+      "eval_runtime": 0.3529,
+      "eval_samples_per_second": 2955.605,
+      "eval_steps_per_second": 14.169,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.649866104125977,
+      "learning_rate": 4.2e-05,
+      "loss": 0.174,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7372962832450867,
+      "eval_loss": 0.7495919466018677,
+      "eval_matthews_correlation": 0.3429503484906003,
+      "eval_runtime": 0.3369,
+      "eval_samples_per_second": 3095.808,
+      "eval_steps_per_second": 14.841,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 4530914903629824.0,
+      "train_loss": 0.38461392942596884,
+      "train_runtime": 57.3363,
+      "train_samples_per_second": 7456.876,
+      "train_steps_per_second": 29.65
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1700,
+  "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": 4530914903629824.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}