End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_50_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_50_v1_book_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8532110091743119
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_50_v1_book_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4193
-- Accuracy: 0.8773
+- Loss: 0.3608
+- Accuracy: 0.8532
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8532110091743119,
+    "eval_loss": 0.3607921898365021,
+    "eval_runtime": 0.2803,
+    "eval_samples": 872,
+    "eval_samples_per_second": 3110.48,
+    "eval_steps_per_second": 14.268,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.1716307449822474,
+    "train_runtime": 226.4089,
+    "train_samples": 67349,
+    "train_samples_per_second": 14873.314,
+    "train_steps_per_second": 58.302
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8532110091743119,
+    "eval_loss": 0.3607921898365021,
+    "eval_runtime": 0.2803,
+    "eval_samples": 872,
+    "eval_samples_per_second": 3110.48,
+    "eval_steps_per_second": 14.268
+}

logs/events.out.tfevents.1733838364.ki-g0008.684565.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d87a430bf22b71a4345a92d14576ee44414f8aa89d5467ea747acc4090d306
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.1716307449822474,
+    "train_runtime": 226.4089,
+    "train_samples": 67349,
+    "train_samples_per_second": 14873.314,
+    "train_steps_per_second": 58.302
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.3607921898365021,
+  "best_model_checkpoint": "bert_tiny_lda_50_v1_book_sst2/checkpoint-264",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1584,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.187464714050293,
+      "learning_rate": 4.9e-05,
+      "loss": 0.3652,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8532110091743119,
+      "eval_loss": 0.3607921898365021,
+      "eval_runtime": 0.2732,
+      "eval_samples_per_second": 3191.99,
+      "eval_steps_per_second": 14.642,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.1309661865234375,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2205,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8635321100917431,
+      "eval_loss": 0.37138402462005615,
+      "eval_runtime": 0.2803,
+      "eval_samples_per_second": 3110.469,
+      "eval_steps_per_second": 14.268,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.429926872253418,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1577,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8497706422018348,
+      "eval_loss": 0.4074440002441406,
+      "eval_runtime": 0.291,
+      "eval_samples_per_second": 2996.383,
+      "eval_steps_per_second": 13.745,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.587671279907227,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1198,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8658256880733946,
+      "eval_loss": 0.38508209586143494,
+      "eval_runtime": 0.3002,
+      "eval_samples_per_second": 2904.627,
+      "eval_steps_per_second": 13.324,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.722463607788086,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0932,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8704128440366973,
+      "eval_loss": 0.4103902280330658,
+      "eval_runtime": 0.2754,
+      "eval_samples_per_second": 3166.269,
+      "eval_steps_per_second": 14.524,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.038421154022217,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0733,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8772935779816514,
+      "eval_loss": 0.419316828250885,
+      "eval_runtime": 0.3016,
+      "eval_samples_per_second": 2891.226,
+      "eval_steps_per_second": 13.263,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 1.0596790573590528e+16,
+      "train_loss": 0.1716307449822474,
+      "train_runtime": 226.4089,
+      "train_samples_per_second": 14873.314,
+      "train_steps_per_second": 58.302
+    }
+  ],
+  "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": 1.0596790573590528e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}