End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_5_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_5_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: 0.7181372549019608
+    - name: F1
+      type: f1
+      value: 0.8200312989045383
 ---
 
 <!-- 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. -->
 
 # bert_tiny_lda_5_v1_book_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1_book) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9086
-- Accuracy: 0.7328
-- F1: 0.8310
-- Combined Score: 0.7819
+- Loss: 0.5735
+- Accuracy: 0.7181
+- F1: 0.8200
+- Combined Score: 0.7691
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.7181372549019608,
+    "eval_combined_score": 0.7690842769032495,
+    "eval_f1": 0.8200312989045383,
+    "eval_loss": 0.5734569430351257,
+    "eval_runtime": 0.1649,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2473.865,
+    "eval_steps_per_second": 12.127,
+    "total_flos": 865692760633344.0,
+    "train_loss": 0.4036285700621428,
+    "train_runtime": 29.1514,
+    "train_samples": 3668,
+    "train_samples_per_second": 6291.284,
+    "train_steps_per_second": 25.728
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.7181372549019608,
+    "eval_combined_score": 0.7690842769032495,
+    "eval_f1": 0.8200312989045383,
+    "eval_loss": 0.5734569430351257,
+    "eval_runtime": 0.1649,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2473.865,
+    "eval_steps_per_second": 12.127
+}

logs/events.out.tfevents.1733835562.ki-g0008.683966.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7d226afd00ccdf3ab8ef0415cdbfd87cc0777f66c18b2cdbaa11ff3b3470f5
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 865692760633344.0,
+    "train_loss": 0.4036285700621428,
+    "train_runtime": 29.1514,
+    "train_samples": 3668,
+    "train_samples_per_second": 6291.284,
+    "train_steps_per_second": 25.728
+}

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": 0.5734569430351257,
+  "best_model_checkpoint": "bert_tiny_lda_5_v1_book_mrpc/checkpoint-60",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8096499443054199,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6264,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.7428237752781364,
+      "eval_f1": 0.7993730407523512,
+      "eval_loss": 0.6012465357780457,
+      "eval_runtime": 0.135,
+      "eval_samples_per_second": 3022.911,
+      "eval_steps_per_second": 14.818,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1260656118392944,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5868,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7495888549909429,
+      "eval_f1": 0.8006482982171799,
+      "eval_loss": 0.5820479989051819,
+      "eval_runtime": 0.1386,
+      "eval_samples_per_second": 2943.25,
+      "eval_steps_per_second": 14.428,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1880303621292114,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5558,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7552248444287895,
+      "eval_f1": 0.8143712574850299,
+      "eval_loss": 0.6051216721534729,
+      "eval_runtime": 0.1361,
+      "eval_samples_per_second": 2997.149,
+      "eval_steps_per_second": 14.692,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1416378021240234,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5036,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7181372549019608,
+      "eval_combined_score": 0.7690842769032495,
+      "eval_f1": 0.8200312989045383,
+      "eval_loss": 0.5734569430351257,
+      "eval_runtime": 0.1382,
+      "eval_samples_per_second": 2951.305,
+      "eval_steps_per_second": 14.467,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.060704231262207,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4117,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7083333333333334,
+      "eval_combined_score": 0.7531479909451047,
+      "eval_f1": 0.797962648556876,
+      "eval_loss": 0.596909761428833,
+      "eval_runtime": 0.1346,
+      "eval_samples_per_second": 3030.953,
+      "eval_steps_per_second": 14.858,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.873413562774658,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.32,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7328431372549019,
+      "eval_combined_score": 0.779221568627451,
+      "eval_f1": 0.8256,
+      "eval_loss": 0.6339625716209412,
+      "eval_runtime": 0.1476,
+      "eval_samples_per_second": 2765.136,
+      "eval_steps_per_second": 13.555,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 12.927068710327148,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2656,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7181372549019608,
+      "eval_combined_score": 0.7726024620374465,
+      "eval_f1": 0.8270676691729323,
+      "eval_loss": 0.9136943221092224,
+      "eval_runtime": 0.1371,
+      "eval_samples_per_second": 2975.304,
+      "eval_steps_per_second": 14.585,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 10.023394584655762,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2023,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7230392156862745,
+      "eval_combined_score": 0.7744625970573129,
+      "eval_f1": 0.8258859784283514,
+      "eval_loss": 0.8610660433769226,
+      "eval_runtime": 0.1675,
+      "eval_samples_per_second": 2435.62,
+      "eval_steps_per_second": 11.939,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 8.822165489196777,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1604,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7328431372549019,
+      "eval_combined_score": 0.7819254445964432,
+      "eval_f1": 0.8310077519379845,
+      "eval_loss": 0.908581018447876,
+      "eval_runtime": 0.136,
+      "eval_samples_per_second": 2999.176,
+      "eval_steps_per_second": 14.702,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "step": 135,
+      "total_flos": 865692760633344.0,
+      "train_loss": 0.4036285700621428,
+      "train_runtime": 29.1514,
+      "train_samples_per_second": 6291.284,
+      "train_steps_per_second": 25.728
+    }
+  ],
+  "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": 865692760633344.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}