End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/tinybert_train_book_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tinybert_train_book_v2_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: 0.35481258251848646
+    - name: Accuracy
+      type: accuracy
+      value: 0.7497603297233582
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,11 +35,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinybert_train_book_v2_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_v2](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_v2) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_v2](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_v2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7774
-- Matthews Correlation: 0.3592
-- Accuracy: 0.7488
+- Loss: 0.5581
+- Matthews Correlation: 0.3548
+- Accuracy: 0.7498
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7497603297233582,
+    "eval_loss": 0.5581100583076477,
+    "eval_matthews_correlation": 0.35481258251848646,
+    "eval_runtime": 0.3533,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2952.4,
+    "eval_steps_per_second": 14.153,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.3773518309873693,
+    "train_runtime": 46.993,
+    "train_samples": 8551,
+    "train_samples_per_second": 9098.161,
+    "train_steps_per_second": 36.176
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7497603297233582,
+    "eval_loss": 0.5581100583076477,
+    "eval_matthews_correlation": 0.35481258251848646,
+    "eval_runtime": 0.3533,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2952.4,
+    "eval_steps_per_second": 14.153
+}

logs/events.out.tfevents.1738231700.ki-g0008.245006.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870e04a55256cfcab78e8e280fac2660a5520973f9dfa5e7e9e2e8d2873df7c3
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.3773518309873693,
+    "train_runtime": 46.993,
+    "train_samples": 8551,
+    "train_samples_per_second": 9098.161,
+    "train_steps_per_second": 36.176
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": 0.5581100583076477,
+  "best_model_checkpoint": "tinybert_train_book_v2_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": 1.3034567832946777,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6023,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7018216848373413,
+      "eval_loss": 0.5806717276573181,
+      "eval_matthews_correlation": 0.1550399777186799,
+      "eval_runtime": 0.3035,
+      "eval_samples_per_second": 3437.119,
+      "eval_steps_per_second": 16.477,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.8895254135131836,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5434,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7133269309997559,
+      "eval_loss": 0.5668395161628723,
+      "eval_matthews_correlation": 0.21705984014592772,
+      "eval_runtime": 0.3245,
+      "eval_samples_per_second": 3214.498,
+      "eval_steps_per_second": 15.41,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.620703935623169,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4545,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7497603297233582,
+      "eval_loss": 0.5581100583076477,
+      "eval_matthews_correlation": 0.35481258251848646,
+      "eval_runtime": 0.345,
+      "eval_samples_per_second": 3022.802,
+      "eval_steps_per_second": 14.491,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.225790977478027,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3891,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7315436005592346,
+      "eval_loss": 0.5983896851539612,
+      "eval_matthews_correlation": 0.29453632641332533,
+      "eval_runtime": 0.3303,
+      "eval_samples_per_second": 3157.438,
+      "eval_steps_per_second": 15.136,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.967442035675049,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3257,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7401725649833679,
+      "eval_loss": 0.5830952525138855,
+      "eval_matthews_correlation": 0.3678718439293352,
+      "eval_runtime": 0.3664,
+      "eval_samples_per_second": 2846.805,
+      "eval_steps_per_second": 13.647,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.949800491333008,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2676,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7353787422180176,
+      "eval_loss": 0.6335519552230835,
+      "eval_matthews_correlation": 0.34521400719988937,
+      "eval_runtime": 0.3768,
+      "eval_samples_per_second": 2768.22,
+      "eval_steps_per_second": 13.27,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 7.603007793426514,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2335,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7555129528045654,
+      "eval_loss": 0.6995111703872681,
+      "eval_matthews_correlation": 0.3774294637163563,
+      "eval_runtime": 0.374,
+      "eval_samples_per_second": 2788.734,
+      "eval_steps_per_second": 13.369,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.508959770202637,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2028,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7488015294075012,
+      "eval_loss": 0.777448296546936,
+      "eval_matthews_correlation": 0.35918776049405,
+      "eval_runtime": 0.3108,
+      "eval_samples_per_second": 3355.667,
+      "eval_steps_per_second": 16.087,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 1793902531485696.0,
+      "train_loss": 0.3773518309873693,
+      "train_runtime": 46.993,
+      "train_samples_per_second": 9098.161,
+      "train_steps_per_second": 36.176
+    }
+  ],
+  "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": 1793902531485696.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}