Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -3,14 +3,14 @@ base_model: huawei-noah/TinyBERT_General_4L_312D
 tags:
 - generated_from_trainer
 model-index:
-- name: result
+- name: TUDNLP4W
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# result
+# TUDNLP4W
 
 This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
 
@@ -46,6 +46,6 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - Transformers 4.38.0.dev0
-- Pytorch 2.1.0+cu121
+- Pytorch 2.2.0
 - Datasets 2.16.1
 - Tokenizers 0.15.0

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 2.0,
-    "eval_exact_match": 55.54993252361673,
-    "eval_f1": 67.43200197066156,
-    "eval_runtime": 20.5032,
+    "eval_exact_match": 58.04655870445344,
+    "eval_f1": 70.00816554397369,
+    "eval_runtime": 37.0671,
     "eval_samples": 6056,
-    "eval_samples_per_second": 295.368,
-    "eval_steps_per_second": 36.921,
-    "train_loss": 2.134629626242807,
-    "train_runtime": 1518.4117,
+    "eval_samples_per_second": 163.379,
+    "eval_steps_per_second": 20.422,
+    "train_loss": 0.013409816984013865,
+    "train_runtime": 36.1557,
     "train_samples": 87739,
-    "train_samples_per_second": 115.567,
-    "train_steps_per_second": 9.631
+    "train_samples_per_second": 4853.397,
+    "train_steps_per_second": 404.473
 }

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda9b172f98c9e9376f0df6c872fa698d46bbfd4d45b552f9d3a980ab1aa0a50
+size 28157111

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
-    "eval_exact_match": 55.54993252361673,
-    "eval_f1": 67.43200197066156,
-    "eval_runtime": 20.5032,
+    "eval_exact_match": 58.04655870445344,
+    "eval_f1": 70.00816554397369,
+    "eval_runtime": 37.0671,
     "eval_samples": 6056,
-    "eval_samples_per_second": 295.368,
-    "eval_steps_per_second": 36.921
+    "eval_samples_per_second": 163.379,
+    "eval_steps_per_second": 20.422
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb5e71a14c70818def6025d7b984487a38053815f7bf0da800eaaf80ae15690
+size 57020992

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 384,
-    "strategy": "OnlySecond",
-    "stride": 128
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 384
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
-    "train_loss": 2.134629626242807,
-    "train_runtime": 1518.4117,
+    "train_loss": 0.013409816984013865,
+    "train_runtime": 36.1557,
     "train_samples": 87739,
-    "train_samples_per_second": 115.567,
-    "train_steps_per_second": 9.631
+    "train_samples_per_second": 4853.397,
+    "train_steps_per_second": 404.473
 }

trainer_state.json

@@ -11,185 +11,185 @@
     {
       "epoch": 0.07,
       "learning_rate": 2.897428884026258e-05,
-      "loss": 3.8747,
+      "loss": 3.9021,
       "step": 500
     },
     {
       "epoch": 0.14,
       "learning_rate": 2.7948577680525165e-05,
-      "loss": 3.0141,
+      "loss": 3.0233,
       "step": 1000
     },
     {
       "epoch": 0.21,
       "learning_rate": 2.6922866520787748e-05,
-      "loss": 2.7867,
+      "loss": 2.7852,
       "step": 1500
     },
     {
       "epoch": 0.27,
       "learning_rate": 2.589715536105033e-05,
-      "loss": 2.6368,
+      "loss": 2.6301,
       "step": 2000
     },
     {
       "epoch": 0.34,
       "learning_rate": 2.4871444201312912e-05,
-      "loss": 2.556,
+      "loss": 2.4956,
       "step": 2500
     },
     {
       "epoch": 0.41,
       "learning_rate": 2.3845733041575492e-05,
-      "loss": 2.4478,
+      "loss": 2.2733,
       "step": 3000
     },
     {
       "epoch": 0.48,
       "learning_rate": 2.2820021881838072e-05,
-      "loss": 2.4204,
+      "loss": 2.2072,
       "step": 3500
     },
     {
       "epoch": 0.55,
       "learning_rate": 2.179431072210066e-05,
-      "loss": 2.381,
+      "loss": 2.1646,
       "step": 4000
     },
     {
       "epoch": 0.62,
       "learning_rate": 2.076859956236324e-05,
-      "loss": 2.2586,
+      "loss": 2.0685,
       "step": 4500
     },
     {
       "epoch": 0.68,
       "learning_rate": 1.9742888402625823e-05,
-      "loss": 2.1788,
+      "loss": 2.006,
       "step": 5000
     },
     {
       "epoch": 0.75,
       "learning_rate": 1.8717177242888403e-05,
-      "loss": 2.1679,
+      "loss": 2.0149,
       "step": 5500
     },
     {
       "epoch": 0.82,
       "learning_rate": 1.7691466083150983e-05,
-      "loss": 2.0685,
+      "loss": 1.9361,
       "step": 6000
     },
     {
       "epoch": 0.89,
       "learning_rate": 1.6665754923413567e-05,
-      "loss": 2.0419,
+      "loss": 1.9372,
       "step": 6500
     },
     {
       "epoch": 0.96,
       "learning_rate": 1.564004376367615e-05,
-      "loss": 2.0122,
+      "loss": 1.9043,
       "step": 7000
     },
     {
       "epoch": 1.03,
       "learning_rate": 1.4614332603938733e-05,
-      "loss": 1.9763,
+      "loss": 1.8555,
       "step": 7500
     },
     {
       "epoch": 1.09,
       "learning_rate": 1.3588621444201313e-05,
-      "loss": 1.8748,
+      "loss": 1.7623,
       "step": 8000
     },
     {
       "epoch": 1.16,
       "learning_rate": 1.2562910284463895e-05,
-      "loss": 1.8163,
+      "loss": 1.7307,
       "step": 8500
     },
     {
       "epoch": 1.23,
       "learning_rate": 1.1537199124726478e-05,
-      "loss": 1.8351,
+      "loss": 1.7475,
       "step": 9000
     },
     {
       "epoch": 1.3,
       "learning_rate": 1.0511487964989058e-05,
-      "loss": 1.8195,
+      "loss": 1.7261,
       "step": 9500
     },
     {
       "epoch": 1.37,
       "learning_rate": 9.485776805251642e-06,
-      "loss": 1.8151,
+      "loss": 1.7196,
       "step": 10000
     },
     {
       "epoch": 1.44,
       "learning_rate": 8.460065645514224e-06,
-      "loss": 1.8129,
+      "loss": 1.7055,
       "step": 10500
     },
     {
       "epoch": 1.5,
       "learning_rate": 7.434354485776806e-06,
-      "loss": 1.7618,
+      "loss": 1.6923,
       "step": 11000
     },
     {
       "epoch": 1.57,
       "learning_rate": 6.408643326039388e-06,
-      "loss": 1.7896,
+      "loss": 1.677,
       "step": 11500
     },
     {
       "epoch": 1.64,
       "learning_rate": 5.3829321663019695e-06,
-      "loss": 1.7948,
+      "loss": 1.7111,
       "step": 12000
     },
     {
       "epoch": 1.71,
       "learning_rate": 4.357221006564551e-06,
-      "loss": 1.789,
+      "loss": 1.701,
       "step": 12500
     },
     {
       "epoch": 1.78,
       "learning_rate": 3.3315098468271337e-06,
-      "loss": 1.7811,
+      "loss": 1.6748,
       "step": 13000
     },
     {
       "epoch": 1.85,
       "learning_rate": 2.3057986870897156e-06,
-      "loss": 1.757,
+      "loss": 1.6773,
       "step": 13500
     },
     {
       "epoch": 1.91,
       "learning_rate": 1.2800875273522977e-06,
-      "loss": 1.778,
+      "loss": 1.6973,
       "step": 14000
     },
     {
       "epoch": 1.98,
       "learning_rate": 2.543763676148797e-07,
-      "loss": 1.7596,
+      "loss": 1.6668,
       "step": 14500
     },
     {
       "epoch": 2.0,
       "step": 14624,
       "total_flos": 1847651335621632.0,
-      "train_loss": 2.134629626242807,
-      "train_runtime": 1518.4117,
-      "train_samples_per_second": 115.567,
-      "train_steps_per_second": 9.631
+      "train_loss": 0.013409816984013865,
+      "train_runtime": 36.1557,
+      "train_samples_per_second": 4853.397,
+      "train_steps_per_second": 404.473
     }
   ],
   "logging_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007f46ea94b8d67dc8cb3f6da65ee29923b99f42839fe274dd8111973c46e82a
-size 4728
+oid sha256:5fd73e0cd7777d4653116a4e00ee666d42b88fdcd22ca0f1763d2bae0feb85b9
+size 4792