End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_olda_book_10_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_olda_book_10_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: 0.8428899082568807
 ---
 
 <!-- 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_olda_book_10_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_olda_book_10_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_olda_book_10_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_olda_book_10_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_olda_book_10_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4670
-- Accuracy: 0.8681
+- Loss: 0.3667
+- Accuracy: 0.8429
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8428899082568807,
+    "eval_loss": 0.36667394638061523,
+    "eval_runtime": 0.2215,
+    "eval_samples": 872,
+    "eval_samples_per_second": 3936.131,
+    "eval_steps_per_second": 18.056,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.16315942340426975,
+    "train_runtime": 159.4333,
+    "train_samples": 67349,
+    "train_samples_per_second": 21121.369,
+    "train_steps_per_second": 82.793
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8428899082568807,
+    "eval_loss": 0.36667394638061523,
+    "eval_runtime": 0.2215,
+    "eval_samples": 872,
+    "eval_samples_per_second": 3936.131,
+    "eval_steps_per_second": 18.056
+}

logs/events.out.tfevents.1739306588.ki-g0009.35827.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66861c173ccc80aaa27eb4dc138ed896bb74e5bc025a9be01d496a725d33f68e
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.16315942340426975,
+    "train_runtime": 159.4333,
+    "train_samples": 67349,
+    "train_samples_per_second": 21121.369,
+    "train_steps_per_second": 82.793
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.36667394638061523,
+  "best_model_checkpoint": "bert_tiny_olda_book_10_v1_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": 10.010531425476074,
+      "learning_rate": 4.9e-05,
+      "loss": 0.3588,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8428899082568807,
+      "eval_loss": 0.36667394638061523,
+      "eval_runtime": 0.1936,
+      "eval_samples_per_second": 4505.249,
+      "eval_steps_per_second": 20.666,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.7793607711792,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2083,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8669724770642202,
+      "eval_loss": 0.3749483823776245,
+      "eval_runtime": 0.1948,
+      "eval_samples_per_second": 4475.736,
+      "eval_steps_per_second": 20.531,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5934884548187256,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1452,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8623853211009175,
+      "eval_loss": 0.4112560749053955,
+      "eval_runtime": 0.1975,
+      "eval_samples_per_second": 4414.337,
+      "eval_steps_per_second": 20.249,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.6194257736206055,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1111,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8612385321100917,
+      "eval_loss": 0.43897953629493713,
+      "eval_runtime": 0.1946,
+      "eval_samples_per_second": 4480.457,
+      "eval_steps_per_second": 20.553,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.797027111053467,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0861,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8635321100917431,
+      "eval_loss": 0.4392467439174652,
+      "eval_runtime": 0.1962,
+      "eval_samples_per_second": 4445.468,
+      "eval_steps_per_second": 20.392,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.172165036201477,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0695,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8681192660550459,
+      "eval_loss": 0.4669587016105652,
+      "eval_runtime": 0.1939,
+      "eval_samples_per_second": 4496.055,
+      "eval_steps_per_second": 20.624,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 1.0596790573590528e+16,
+      "train_loss": 0.16315942340426975,
+      "train_runtime": 159.4333,
+      "train_samples_per_second": 21121.369,
+      "train_steps_per_second": 82.793
+    }
+  ],
+  "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
+}