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:
 - accuracy
 - f1
 model-index:
 - name: distilbert_lda_100_v1_book_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6911764705882353
+    - name: F1
+      type: f1
+      value: 0.8061538461538461
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_lda_100_v1_book_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9396
-- Accuracy: 0.7328
-- F1: 0.8239
-- Combined Score: 0.7784
+- Loss: 0.5726
+- Accuracy: 0.6912
+- F1: 0.8062
+- Combined Score: 0.7487
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6911764705882353,
+    "eval_combined_score": 0.7486651583710406,
+    "eval_f1": 0.8061538461538461,
+    "eval_loss": 0.5726402401924133,
+    "eval_runtime": 0.1289,
+    "eval_samples": 408,
+    "eval_samples_per_second": 3165.173,
+    "eval_steps_per_second": 15.516,
+    "total_flos": 1700616463945728.0,
+    "train_loss": 0.3905606224423363,
+    "train_runtime": 26.103,
+    "train_samples": 3668,
+    "train_samples_per_second": 7026.021,
+    "train_steps_per_second": 28.732
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6911764705882353,
+    "eval_combined_score": 0.7486651583710406,
+    "eval_f1": 0.8061538461538461,
+    "eval_loss": 0.5726402401924133,
+    "eval_runtime": 0.1289,
+    "eval_samples": 408,
+    "eval_samples_per_second": 3165.173,
+    "eval_steps_per_second": 15.516
+}

logs/events.out.tfevents.1733764631.ki-g0009.1845686.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66995ba76b385d7feb9e0f03c55c677070f7a5fd978d1ede15b687c7df8cd812
+size 507

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1700616463945728.0,
+    "train_loss": 0.3905606224423363,
+    "train_runtime": 26.103,
+    "train_samples": 3668,
+    "train_samples_per_second": 7026.021,
+    "train_steps_per_second": 28.732
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.5726402401924133,
+  "best_model_checkpoint": "distilbert_lda_100_v1_book_mrpc/checkpoint-30",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7415820956230164,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6251,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7446266968325792,
+      "eval_f1": 0.8054298642533937,
+      "eval_loss": 0.5960478186607361,
+      "eval_runtime": 0.1245,
+      "eval_samples_per_second": 3277.967,
+      "eval_steps_per_second": 16.068,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4281333684921265,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5807,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7486651583710406,
+      "eval_f1": 0.8061538461538461,
+      "eval_loss": 0.5726402401924133,
+      "eval_runtime": 0.1277,
+      "eval_samples_per_second": 3194.819,
+      "eval_steps_per_second": 15.661,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.218419075012207,
+      "learning_rate": 4.7e-05,
+      "loss": 0.516,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7181372549019608,
+      "eval_combined_score": 0.7701969118404703,
+      "eval_f1": 0.8222565687789799,
+      "eval_loss": 0.5825024247169495,
+      "eval_runtime": 0.1389,
+      "eval_samples_per_second": 2937.889,
+      "eval_steps_per_second": 14.401,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.748422145843506,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4062,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7254901960784313,
+      "eval_combined_score": 0.7681505034446211,
+      "eval_f1": 0.8108108108108109,
+      "eval_loss": 0.5987961888313293,
+      "eval_runtime": 0.1456,
+      "eval_samples_per_second": 2802.21,
+      "eval_steps_per_second": 13.736,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.064699649810791,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2808,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7524509803921569,
+      "eval_combined_score": 0.7901948258008484,
+      "eval_f1": 0.82793867120954,
+      "eval_loss": 0.6600034832954407,
+      "eval_runtime": 0.1718,
+      "eval_samples_per_second": 2375.519,
+      "eval_steps_per_second": 11.645,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.583449840545654,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1683,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7352941176470589,
+      "eval_combined_score": 0.782741398446171,
+      "eval_f1": 0.8301886792452831,
+      "eval_loss": 0.9784038662910461,
+      "eval_runtime": 0.1441,
+      "eval_samples_per_second": 2831.593,
+      "eval_steps_per_second": 13.88,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 11.45016860961914,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1568,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7328431372549019,
+      "eval_combined_score": 0.7783763343786626,
+      "eval_f1": 0.8239095315024233,
+      "eval_loss": 0.9396167993545532,
+      "eval_runtime": 0.1329,
+      "eval_samples_per_second": 3070.258,
+      "eval_steps_per_second": 15.05,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 1700616463945728.0,
+      "train_loss": 0.3905606224423363,
+      "train_runtime": 26.103,
+      "train_samples_per_second": 7026.021,
+      "train_steps_per_second": 28.732
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "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": 1700616463945728.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}