End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_5_v1_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5091743119266054
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_5_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7005
+- Loss: 0.6928
 - Accuracy: 0.5092
 
 ## Model description

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6927546262741089,
+    "eval_runtime": 0.2812,
+    "eval_samples": 872,
+    "eval_samples_per_second": 3101.546,
+    "eval_steps_per_second": 14.227,
+    "total_flos": 1.2362922335855616e+16,
+    "train_loss": 0.6844654330959568,
+    "train_runtime": 261.6721,
+    "train_samples": 67349,
+    "train_samples_per_second": 12868.97,
+    "train_steps_per_second": 50.445
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6927546262741089,
+    "eval_runtime": 0.2812,
+    "eval_samples": 872,
+    "eval_samples_per_second": 3101.546,
+    "eval_steps_per_second": 14.227
+}

logs/events.out.tfevents.1732655527.ki-g0008.2136607.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5bcb46c78e44ac1da6c18fffd0aae071316749d70de7b091038fb9dcbea330
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1.2362922335855616e+16,
+    "train_loss": 0.6844654330959568,
+    "train_runtime": 261.6721,
+    "train_samples": 67349,
+    "train_samples_per_second": 12868.97,
+    "train_steps_per_second": 50.445
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.6927546262741089,
+  "best_model_checkpoint": "bert_tiny_lda_5_v1_sst2/checkpoint-528",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1848,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4769257307052612,
+      "learning_rate": 0.00098,
+      "loss": 0.6805,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.533256880733945,
+      "eval_loss": 0.694188117980957,
+      "eval_runtime": 0.2722,
+      "eval_samples_per_second": 3203.363,
+      "eval_steps_per_second": 14.694,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.41901111602783203,
+      "learning_rate": 0.00096,
+      "loss": 0.6795,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6927546262741089,
+      "eval_runtime": 0.2751,
+      "eval_samples_per_second": 3169.792,
+      "eval_steps_per_second": 14.54,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19532398879528046,
+      "learning_rate": 0.00094,
+      "loss": 0.6848,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6971402168273926,
+      "eval_runtime": 0.2751,
+      "eval_samples_per_second": 3169.886,
+      "eval_steps_per_second": 14.541,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3345678448677063,
+      "learning_rate": 0.00092,
+      "loss": 0.6868,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.695724606513977,
+      "eval_runtime": 0.2812,
+      "eval_samples_per_second": 3101.48,
+      "eval_steps_per_second": 14.227,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.1190953329205513,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6866,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6954379081726074,
+      "eval_runtime": 0.2865,
+      "eval_samples_per_second": 3043.347,
+      "eval_steps_per_second": 13.96,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.08549844473600388,
+      "learning_rate": 0.00088,
+      "loss": 0.6865,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6989858150482178,
+      "eval_runtime": 0.285,
+      "eval_samples_per_second": 3059.492,
+      "eval_steps_per_second": 14.034,
+      "step": 1584
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5443962216377258,
+      "learning_rate": 0.00086,
+      "loss": 0.6866,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7005447149276733,
+      "eval_runtime": 0.2848,
+      "eval_samples_per_second": 3061.81,
+      "eval_steps_per_second": 14.045,
+      "step": 1848
+    },
+    {
+      "epoch": 7.0,
+      "step": 1848,
+      "total_flos": 1.2362922335855616e+16,
+      "train_loss": 0.6844654330959568,
+      "train_runtime": 261.6721,
+      "train_samples_per_second": 12868.97,
+      "train_steps_per_second": 50.445
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 13200,
+  "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": 1.2362922335855616e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}