End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_20_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: distilbert_lda_20_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: 0.34207719768221
+    - name: Accuracy
+      type: accuracy
+      value: 0.7459251880645752
 ---
 
 <!-- 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_20_v1_book_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_20_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/distilbert_lda_20_v1_book) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8104
-- Matthews Correlation: 0.4019
-- Accuracy: 0.7584
+- Loss: 0.5378
+- Matthews Correlation: 0.3421
+- Accuracy: 0.7459
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7459251880645752,
+    "eval_loss": 0.5377989411354065,
+    "eval_matthews_correlation": 0.34207719768221,
+    "eval_runtime": 0.4708,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2215.18,
+    "eval_steps_per_second": 10.619,
+    "total_flos": 4530914903629824.0,
+    "train_loss": 0.3661302398232853,
+    "train_runtime": 85.5164,
+    "train_samples": 8551,
+    "train_samples_per_second": 4999.623,
+    "train_steps_per_second": 19.879
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7459251880645752,
+    "eval_loss": 0.5377989411354065,
+    "eval_matthews_correlation": 0.34207719768221,
+    "eval_runtime": 0.4708,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2215.18,
+    "eval_steps_per_second": 10.619
+}

logs/events.out.tfevents.1733759325.ki-g0008.150368.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fd46fc1e66964c6180979eb4426fba4379aac726b10d76050a9b88850d4d5e
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 4530914903629824.0,
+    "train_loss": 0.3661302398232853,
+    "train_runtime": 85.5164,
+    "train_samples": 8551,
+    "train_samples_per_second": 4999.623,
+    "train_steps_per_second": 19.879
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": 0.5377989411354065,
+  "best_model_checkpoint": "distilbert_lda_20_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": 0.44674888253211975,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6102,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.617717444896698,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4929,
+      "eval_samples_per_second": 2115.947,
+      "eval_steps_per_second": 10.144,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9451546669006348,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5983,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.5929555296897888,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4699,
+      "eval_samples_per_second": 2219.585,
+      "eval_steps_per_second": 10.64,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.8023204803466797,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5164,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7459251880645752,
+      "eval_loss": 0.5377989411354065,
+      "eval_matthews_correlation": 0.34207719768221,
+      "eval_runtime": 0.4636,
+      "eval_samples_per_second": 2249.796,
+      "eval_steps_per_second": 10.785,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.13676643371582,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.404,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7468839883804321,
+      "eval_loss": 0.6223514080047607,
+      "eval_matthews_correlation": 0.3392550709703511,
+      "eval_runtime": 0.4919,
+      "eval_samples_per_second": 2120.303,
+      "eval_steps_per_second": 10.164,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.730041980743408,
+      "learning_rate": 4.5e-05,
+      "loss": 0.299,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7564716935157776,
+      "eval_loss": 0.6097568869590759,
+      "eval_matthews_correlation": 0.37874357276848103,
+      "eval_runtime": 0.4725,
+      "eval_samples_per_second": 2207.374,
+      "eval_steps_per_second": 10.582,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.243797779083252,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.214,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7603068351745605,
+      "eval_loss": 0.7013071179389954,
+      "eval_matthews_correlation": 0.38945391483386416,
+      "eval_runtime": 0.4977,
+      "eval_samples_per_second": 2095.686,
+      "eval_steps_per_second": 10.046,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.19760513305664,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1642,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7631831169128418,
+      "eval_loss": 0.8343352675437927,
+      "eval_matthews_correlation": 0.3923126748259827,
+      "eval_runtime": 0.4876,
+      "eval_samples_per_second": 2139.131,
+      "eval_steps_per_second": 10.255,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.053338527679443,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1228,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7583892345428467,
+      "eval_loss": 0.8104491829872131,
+      "eval_matthews_correlation": 0.40188104133596453,
+      "eval_runtime": 0.4774,
+      "eval_samples_per_second": 2184.785,
+      "eval_steps_per_second": 10.474,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 4530914903629824.0,
+      "train_loss": 0.3661302398232853,
+      "train_runtime": 85.5164,
+      "train_samples_per_second": 4999.623,
+      "train_steps_per_second": 19.879
+    }
+  ],
+  "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
+}