End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_100_v1_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5633802816901409
 ---
 
 <!-- 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_base_lda_100_v1_wnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6907
+- Loss: 0.6856
 - Accuracy: 0.5634
 
 ## Model description

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 15.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6856295466423035,
+    "eval_runtime": 0.0576,
+    "eval_samples": 71,
+    "eval_samples_per_second": 1232.399,
+    "eval_steps_per_second": 17.358,
+    "total_flos": 1253066401152000.0,
+    "train_loss": 0.8670393943786621,
+    "train_runtime": 52.286,
+    "train_samples": 635,
+    "train_samples_per_second": 607.237,
+    "train_steps_per_second": 2.869
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6856295466423035,
+    "eval_runtime": 0.0576,
+    "eval_samples": 71,
+    "eval_samples_per_second": 1232.399,
+    "eval_steps_per_second": 17.358
+}

logs/events.out.tfevents.1732650930.ki-g0008.2137866.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b6acc7841b7c5641dee0df1c5b5a643803d526d4c8fd29b313c1841a00585a
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "total_flos": 1253066401152000.0,
+    "train_loss": 0.8670393943786621,
+    "train_runtime": 52.286,
+    "train_samples": 635,
+    "train_samples_per_second": 607.237,
+    "train_steps_per_second": 2.869
+}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": 0.6856295466423035,
+  "best_model_checkpoint": "bert_base_lda_100_v1_wnli/checkpoint-30",
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.07452392578125,
+      "learning_rate": 0.00098,
+      "loss": 0.9555,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 1.7839032411575317,
+      "eval_runtime": 0.0536,
+      "eval_samples_per_second": 1324.278,
+      "eval_steps_per_second": 18.652,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.76796817779541,
+      "learning_rate": 0.00096,
+      "loss": 1.287,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 1.9711134433746338,
+      "eval_runtime": 0.0533,
+      "eval_samples_per_second": 1331.507,
+      "eval_steps_per_second": 18.754,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 12.501447677612305,
+      "learning_rate": 0.00094,
+      "loss": 1.9411,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.7585827708244324,
+      "eval_runtime": 0.0551,
+      "eval_samples_per_second": 1289.404,
+      "eval_steps_per_second": 18.161,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.754487037658691,
+      "learning_rate": 0.00092,
+      "loss": 0.8928,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.9854752421379089,
+      "eval_runtime": 0.0538,
+      "eval_samples_per_second": 1320.402,
+      "eval_steps_per_second": 18.597,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.53428316116333,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.8147,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.7991858720779419,
+      "eval_runtime": 0.0554,
+      "eval_samples_per_second": 1282.584,
+      "eval_steps_per_second": 18.065,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.009016752243042,
+      "learning_rate": 0.00088,
+      "loss": 0.8064,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.6986685991287231,
+      "eval_runtime": 0.0546,
+      "eval_samples_per_second": 1299.668,
+      "eval_steps_per_second": 18.305,
+      "step": 18
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.4272738695144653,
+      "learning_rate": 0.00086,
+      "loss": 0.7033,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.69140625,
+      "eval_runtime": 0.0542,
+      "eval_samples_per_second": 1309.561,
+      "eval_steps_per_second": 18.445,
+      "step": 21
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.7512166500091553,
+      "learning_rate": 0.00084,
+      "loss": 0.7235,
+      "step": 24
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6867297291755676,
+      "eval_runtime": 0.0548,
+      "eval_samples_per_second": 1296.517,
+      "eval_steps_per_second": 18.261,
+      "step": 24
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.845127522945404,
+      "learning_rate": 0.00082,
+      "loss": 0.701,
+      "step": 27
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.720455527305603,
+      "eval_runtime": 0.0588,
+      "eval_samples_per_second": 1206.74,
+      "eval_steps_per_second": 16.996,
+      "step": 27
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.6040953993797302,
+      "learning_rate": 0.0008,
+      "loss": 0.6954,
+      "step": 30
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6856295466423035,
+      "eval_runtime": 0.0566,
+      "eval_samples_per_second": 1253.86,
+      "eval_steps_per_second": 17.66,
+      "step": 30
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.5374388098716736,
+      "learning_rate": 0.0007800000000000001,
+      "loss": 0.6999,
+      "step": 33
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6916264295578003,
+      "eval_runtime": 0.0546,
+      "eval_samples_per_second": 1301.224,
+      "eval_steps_per_second": 18.327,
+      "step": 33
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.1416128873825073,
+      "learning_rate": 0.00076,
+      "loss": 0.7008,
+      "step": 36
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.7042252421379089,
+      "eval_runtime": 0.0559,
+      "eval_samples_per_second": 1269.717,
+      "eval_steps_per_second": 17.883,
+      "step": 36
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.340388685464859,
+      "learning_rate": 0.00074,
+      "loss": 0.6948,
+      "step": 39
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6856295466423035,
+      "eval_runtime": 0.0552,
+      "eval_samples_per_second": 1286.391,
+      "eval_steps_per_second": 18.118,
+      "step": 39
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.5490344166755676,
+      "learning_rate": 0.0007199999999999999,
+      "loss": 0.6948,
+      "step": 42
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6863997578620911,
+      "eval_runtime": 0.0541,
+      "eval_samples_per_second": 1312.014,
+      "eval_steps_per_second": 18.479,
+      "step": 42
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.25031745433807373,
+      "learning_rate": 0.0007,
+      "loss": 0.6946,
+      "step": 45
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.690690815448761,
+      "eval_runtime": 0.0566,
+      "eval_samples_per_second": 1255.234,
+      "eval_steps_per_second": 17.679,
+      "step": 45
+    },
+    {
+      "epoch": 15.0,
+      "step": 45,
+      "total_flos": 1253066401152000.0,
+      "train_loss": 0.8670393943786621,
+      "train_runtime": 52.286,
+      "train_samples_per_second": 607.237,
+      "train_steps_per_second": 2.869
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "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": 1253066401152000.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}