End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/distilbert_lda_5
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: distilbert_lda_5_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: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_5_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6184
+- Loss: 0.6182
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6182230710983276,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.447,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2333.174,
+    "eval_steps_per_second": 11.185,
+    "total_flos": 5663643629537280.0,
+    "train_loss": 0.6425062516156365,
+    "train_runtime": 95.8918,
+    "train_samples": 8551,
+    "train_samples_per_second": 2675.203,
+    "train_steps_per_second": 10.637
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6182230710983276,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.447,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2333.174,
+    "eval_steps_per_second": 11.185
+}

logs/events.out.tfevents.1732267039.ki-g0008.1610975.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a1bd036aa9bd183192e40d00a5f46820fd3a0d9229def95ac4223afce67243
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5663643629537280.0,
+    "train_loss": 0.6425062516156365,
+    "train_runtime": 95.8918,
+    "train_samples": 8551,
+    "train_samples_per_second": 2675.203,
+    "train_steps_per_second": 10.637
+}

trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_metric": 0.6182230710983276,
+  "best_model_checkpoint": "distilbert_lda_5_cola/checkpoint-170",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3721345365047455,
+      "learning_rate": 0.0009666666666666667,
+      "loss": 0.9345,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6220000982284546,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4404,
+      "eval_samples_per_second": 2368.448,
+      "eval_steps_per_second": 11.354,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5597137212753296,
+      "learning_rate": 0.0009333333333333333,
+      "loss": 0.6115,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6193765997886658,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4407,
+      "eval_samples_per_second": 2366.891,
+      "eval_steps_per_second": 11.347,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7766118049621582,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6088,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6194814443588257,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4349,
+      "eval_samples_per_second": 2398.477,
+      "eval_steps_per_second": 11.498,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8668702244758606,
+      "learning_rate": 0.0008666666666666667,
+      "loss": 0.6101,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6185395121574402,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4327,
+      "eval_samples_per_second": 2410.294,
+      "eval_steps_per_second": 11.555,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5907299518585205,
+      "learning_rate": 0.0008333333333333334,
+      "loss": 0.6111,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6182230710983276,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4385,
+      "eval_samples_per_second": 2378.59,
+      "eval_steps_per_second": 11.403,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.3894692361354828,
+      "learning_rate": 0.0008,
+      "loss": 0.6081,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6194814443588257,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4421,
+      "eval_samples_per_second": 2359.366,
+      "eval_steps_per_second": 11.31,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1135684251785278,
+      "learning_rate": 0.0007666666666666667,
+      "loss": 0.6104,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6196780800819397,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4356,
+      "eval_samples_per_second": 2394.611,
+      "eval_steps_per_second": 11.479,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.4684953987598419,
+      "learning_rate": 0.0007333333333333333,
+      "loss": 0.6105,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6251610517501831,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4391,
+      "eval_samples_per_second": 2375.1,
+      "eval_steps_per_second": 11.386,
+      "step": 272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.3079698979854584,
+      "learning_rate": 0.0007,
+      "loss": 0.6093,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6256685256958008,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4337,
+      "eval_samples_per_second": 2405.045,
+      "eval_steps_per_second": 11.529,
+      "step": 306
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.6555743217468262,
+      "learning_rate": 0.0006666666666666666,
+      "loss": 0.6107,
+      "step": 340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6184196472167969,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4414,
+      "eval_samples_per_second": 2362.798,
+      "eval_steps_per_second": 11.327,
+      "step": 340
+    },
+    {
+      "epoch": 10.0,
+      "step": 340,
+      "total_flos": 5663643629537280.0,
+      "train_loss": 0.6425062516156365,
+      "train_runtime": 95.8918,
+      "train_samples_per_second": 2675.203,
+      "train_steps_per_second": 10.637
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1020,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "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": 5663643629537280.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}