End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_100_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6838235294117647
+    - name: F1
+      type: f1
+      value: 0.8122270742358079
 ---
 
 <!-- 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. -->
 
 # bert_tiny_lda_100_v1_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6242
+- Loss: 0.6237
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6236787438392639,
+    "eval_runtime": 0.143,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2852.645,
+    "eval_steps_per_second": 13.984,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.6492394038609096,
+    "train_runtime": 20.0708,
+    "train_samples": 3668,
+    "train_samples_per_second": 9137.635,
+    "train_steps_per_second": 37.368
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6236787438392639,
+    "eval_runtime": 0.143,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2852.645,
+    "eval_steps_per_second": 13.984
+}

logs/events.out.tfevents.1732660110.ki-g0008.2137866.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3175517325542324363eeb68504f5e9ffc073068f383d12f18049f0708f9a74
+size 507

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.6492394038609096,
+    "train_runtime": 20.0708,
+    "train_samples": 3668,
+    "train_samples_per_second": 9137.635,
+    "train_steps_per_second": 37.368
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.6236787438392639,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_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": 0.2620401084423065,
+      "learning_rate": 0.00098,
+      "loss": 0.7449,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6298397183418274,
+      "eval_runtime": 0.14,
+      "eval_samples_per_second": 2913.559,
+      "eval_steps_per_second": 14.282,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1782532930374146,
+      "learning_rate": 0.00096,
+      "loss": 0.6364,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6236787438392639,
+      "eval_runtime": 0.1384,
+      "eval_samples_per_second": 2948.519,
+      "eval_steps_per_second": 14.454,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6571235656738281,
+      "learning_rate": 0.00094,
+      "loss": 0.6276,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6311466097831726,
+      "eval_runtime": 0.1335,
+      "eval_samples_per_second": 3055.228,
+      "eval_steps_per_second": 14.977,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7049502730369568,
+      "learning_rate": 0.00092,
+      "loss": 0.6363,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6257467865943909,
+      "eval_runtime": 0.138,
+      "eval_samples_per_second": 2956.659,
+      "eval_steps_per_second": 14.493,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.30875012278556824,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6345,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6274126768112183,
+      "eval_runtime": 0.1399,
+      "eval_samples_per_second": 2917.384,
+      "eval_steps_per_second": 14.301,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5072498321533203,
+      "learning_rate": 0.00088,
+      "loss": 0.6332,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6252154111862183,
+      "eval_runtime": 0.1373,
+      "eval_samples_per_second": 2971.961,
+      "eval_steps_per_second": 14.568,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.4643026888370514,
+      "learning_rate": 0.00086,
+      "loss": 0.6318,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241670250892639,
+      "eval_runtime": 0.135,
+      "eval_samples_per_second": 3022.719,
+      "eval_steps_per_second": 14.817,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.6492394038609096,
+      "train_runtime": 20.0708,
+      "train_samples_per_second": 9137.635,
+      "train_steps_per_second": 37.368
+    }
+  ],
+  "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": 673316591603712.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}