End of training

README.md

@@ -17,16 +17,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [sentence-transformers/paraphrase-MiniLM-L3-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L3-v2) on the nyt_ingredients dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.2590
-- Comment: {'precision': 0.03657262277951933, 'recall': 0.0264750378214826, 'f1': 0.030715225976305396, 'number': 1322}
-- Name: {'precision': 0.5238095238095238, 'recall': 0.01245753114382786, 'f1': 0.024336283185840708, 'number': 1766}
-- Qty: {'precision': 0.0234375, 'recall': 0.0020920502092050207, 'f1': 0.003841229193341869, 'number': 1434}
-- Range End: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17}
-- Unit: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1166}
-- Overall Precision: 0.0419
-- Overall Recall: 0.0105
-- Overall F1: 0.0168
-- Overall Accuracy: 0.1284
+- Loss: 11.3870
+- Comment: {'precision': 0.018842530282637954, 'recall': 0.010174418604651164, 'f1': 0.01321378008494573, 'number': 1376}
+- Name: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1758}
+- Qty: {'precision': 0.1499119991717569, 'recall': 0.9986206896551724, 'f1': 0.26068953101089204, 'number': 1450}
+- Range End: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 14}
+- Unit: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1163}
+- Overall Precision: 0.1405
+- Overall Recall: 0.2538
+- Overall F1: 0.1809
+- Overall Accuracy: 0.1528
 
 ## Model description
 
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Comment                                                                                                      | Name                                                                                                          | Qty                                                                                                   | Range End                                                  | Unit                                                         | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------:|:----------------------------------------------------------:|:------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| No log        | 1.0   | 54   | 11.5992         | {'precision': 0.03826530612244898, 'recall': 0.0340393343419062, 'f1': 0.036028823058446756, 'number': 1322} | {'precision': 0.9047619047619048, 'recall': 0.010758776896942242, 'f1': 0.021264689423614997, 'number': 1766} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1434}                                          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1166} | 0.0526            | 0.0112         | 0.0185     | 0.1319           |
-| No log        | 2.0   | 108  | 10.2590         | {'precision': 0.03657262277951933, 'recall': 0.0264750378214826, 'f1': 0.030715225976305396, 'number': 1322} | {'precision': 0.5238095238095238, 'recall': 0.01245753114382786, 'f1': 0.024336283185840708, 'number': 1766}  | {'precision': 0.0234375, 'recall': 0.0020920502092050207, 'f1': 0.003841229193341869, 'number': 1434} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1166} | 0.0419            | 0.0105         | 0.0168     | 0.1284           |
+| Training Loss | Epoch | Step | Validation Loss | Comment                                                                                                          | Name                                                         | Qty                                                                                                        | Range End                                                  | Unit                                                         | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------:|:------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| No log        | 1.0   | 54   | 13.0360         | {'precision': 0.003246753246753247, 'recall': 0.0007267441860465116, 'f1': 0.001187648456057007, 'number': 1376} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1758} | {'precision': 0.142309205350118, 'recall': 0.9979310344827587, 'f1': 0.24909622998794975, 'number': 1450}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 14} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1163} | 0.1382            | 0.2513         | 0.1784     | 0.1432           |
+| No log        | 2.0   | 108  | 11.3870         | {'precision': 0.018842530282637954, 'recall': 0.010174418604651164, 'f1': 0.01321378008494573, 'number': 1376}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1758} | {'precision': 0.1499119991717569, 'recall': 0.9986206896551724, 'f1': 0.26068953101089204, 'number': 1450} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 14} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1163} | 0.1405            | 0.2538         | 0.1809     | 0.1528           |
 
 
 ### Framework versions

all_results.json

@@ -1,41 +1,41 @@
 {
     "epoch": 2.0,
     "eval_COMMENT": {
-        "f1": 0.030715225976305396,
-        "number": 1322,
-        "precision": 0.03657262277951933,
-        "recall": 0.0264750378214826
+        "f1": 0.01321378008494573,
+        "number": 1376,
+        "precision": 0.018842530282637954,
+        "recall": 0.010174418604651164
     },
     "eval_NAME": {
-        "f1": 0.024336283185840708,
-        "number": 1766,
-        "precision": 0.5238095238095238,
-        "recall": 0.01245753114382786
+        "f1": 0.0,
+        "number": 1758,
+        "precision": 0.0,
+        "recall": 0.0
     },
     "eval_QTY": {
-        "f1": 0.003841229193341869,
-        "number": 1434,
-        "precision": 0.0234375,
-        "recall": 0.0020920502092050207
+        "f1": 0.26068953101089204,
+        "number": 1450,
+        "precision": 0.1499119991717569,
+        "recall": 0.9986206896551724
     },
     "eval_RANGE_END": {
         "f1": 0.0,
-        "number": 17,
+        "number": 14,
         "precision": 0.0,
         "recall": 0.0
     },
     "eval_UNIT": {
         "f1": 0.0,
-        "number": 1166,
+        "number": 1163,
         "precision": 0.0,
         "recall": 0.0
     },
-    "eval_loss": 10.259025573730469,
-    "eval_overall_accuracy": 0.12838815472171314,
-    "eval_overall_f1": 0.016813787305590584,
-    "eval_overall_precision": 0.04189944134078212,
-    "eval_overall_recall": 0.010517090271691499,
-    "eval_runtime": 15.7061,
-    "eval_samples_per_second": 108.365,
-    "eval_steps_per_second": 3.438
+    "eval_loss": 11.38698959350586,
+    "eval_overall_accuracy": 0.15278303672851193,
+    "eval_overall_f1": 0.1809070098372827,
+    "eval_overall_precision": 0.14054989425110556,
+    "eval_overall_recall": 0.25377538621767054,
+    "eval_runtime": 15.4103,
+    "eval_samples_per_second": 110.445,
+    "eval_steps_per_second": 3.504
 }

config.json

@@ -4,9 +4,6 @@
     "PretrainedCRFModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "auto_map": {
-    "AutoModel": "crf_model.PretrainedCRFModel"
-  },
   "classifier_dropout": null,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957a43de6de74f7ecd4ba71f7c05807847718572ae4a3af8cd70c7f799baf978
+oid sha256:1bc0aa155e841d43ed8fb5a8293f148b0505c438f359a802417121f401313821
 size 69004255

trainer_state.json

@@ -11,102 +11,102 @@
     {
       "epoch": 1.0,
       "eval_COMMENT": {
-        "f1": 0.036028823058446756,
-        "number": 1322,
-        "precision": 0.03826530612244898,
-        "recall": 0.0340393343419062
+        "f1": 0.001187648456057007,
+        "number": 1376,
+        "precision": 0.003246753246753247,
+        "recall": 0.0007267441860465116
       },
       "eval_NAME": {
-        "f1": 0.021264689423614997,
-        "number": 1766,
-        "precision": 0.9047619047619048,
-        "recall": 0.010758776896942242
-      },
-      "eval_QTY": {
         "f1": 0.0,
-        "number": 1434,
+        "number": 1758,
         "precision": 0.0,
         "recall": 0.0
       },
+      "eval_QTY": {
+        "f1": 0.24909622998794975,
+        "number": 1450,
+        "precision": 0.142309205350118,
+        "recall": 0.9979310344827587
+      },
       "eval_RANGE_END": {
         "f1": 0.0,
-        "number": 17,
+        "number": 14,
         "precision": 0.0,
         "recall": 0.0
       },
       "eval_UNIT": {
         "f1": 0.0,
-        "number": 1166,
+        "number": 1163,
         "precision": 0.0,
         "recall": 0.0
       },
-      "eval_loss": 11.59915828704834,
-      "eval_overall_accuracy": 0.13186071187421627,
-      "eval_overall_f1": 0.018494437220054907,
-      "eval_overall_precision": 0.05263157894736842,
-      "eval_overall_recall": 0.011218229623137599,
-      "eval_runtime": 14.249,
-      "eval_samples_per_second": 119.447,
-      "eval_steps_per_second": 3.79,
+      "eval_loss": 13.036046981811523,
+      "eval_overall_accuracy": 0.1432222642938281,
+      "eval_overall_f1": 0.17835807107224239,
+      "eval_overall_precision": 0.13822069492172584,
+      "eval_overall_recall": 0.25134525256031937,
+      "eval_runtime": 14.6529,
+      "eval_samples_per_second": 116.155,
+      "eval_steps_per_second": 3.685,
       "step": 54
     },
     {
       "epoch": 2.0,
       "eval_COMMENT": {
-        "f1": 0.030715225976305396,
-        "number": 1322,
-        "precision": 0.03657262277951933,
-        "recall": 0.0264750378214826
+        "f1": 0.01321378008494573,
+        "number": 1376,
+        "precision": 0.018842530282637954,
+        "recall": 0.010174418604651164
       },
       "eval_NAME": {
-        "f1": 0.024336283185840708,
-        "number": 1766,
-        "precision": 0.5238095238095238,
-        "recall": 0.01245753114382786
+        "f1": 0.0,
+        "number": 1758,
+        "precision": 0.0,
+        "recall": 0.0
       },
       "eval_QTY": {
-        "f1": 0.003841229193341869,
-        "number": 1434,
-        "precision": 0.0234375,
-        "recall": 0.0020920502092050207
+        "f1": 0.26068953101089204,
+        "number": 1450,
+        "precision": 0.1499119991717569,
+        "recall": 0.9986206896551724
       },
       "eval_RANGE_END": {
         "f1": 0.0,
-        "number": 17,
+        "number": 14,
         "precision": 0.0,
         "recall": 0.0
       },
       "eval_UNIT": {
         "f1": 0.0,
-        "number": 1166,
+        "number": 1163,
         "precision": 0.0,
         "recall": 0.0
       },
-      "eval_loss": 10.259025573730469,
-      "eval_overall_accuracy": 0.12838815472171314,
-      "eval_overall_f1": 0.016813787305590584,
-      "eval_overall_precision": 0.04189944134078212,
-      "eval_overall_recall": 0.010517090271691499,
-      "eval_runtime": 15.3099,
-      "eval_samples_per_second": 111.17,
-      "eval_steps_per_second": 3.527,
+      "eval_loss": 11.38698959350586,
+      "eval_overall_accuracy": 0.15278303672851193,
+      "eval_overall_f1": 0.1809070098372827,
+      "eval_overall_precision": 0.14054989425110556,
+      "eval_overall_recall": 0.25377538621767054,
+      "eval_runtime": 17.2137,
+      "eval_samples_per_second": 98.875,
+      "eval_steps_per_second": 3.137,
       "step": 108
     },
     {
       "epoch": 2.0,
       "step": 108,
-      "total_flos": 3334407253032.0,
-      "train_loss": 12.8824462890625,
-      "train_runtime": 151.3626,
-      "train_samples_per_second": 22.489,
-      "train_steps_per_second": 0.714
+      "total_flos": 3333512058648.0,
+      "train_loss": 14.639327437789351,
+      "train_runtime": 158.5609,
+      "train_samples_per_second": 21.468,
+      "train_steps_per_second": 0.681
     }
   ],
   "logging_steps": 500,
   "max_steps": 108,
   "num_train_epochs": 2,
   "save_steps": 500,
-  "total_flos": 3334407253032.0,
+  "total_flos": 3333512058648.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5254dbe381bcf40ffb21d73c66be21031100bd1243da923a4f4347812cc60c
+oid sha256:96c214e97b6f20cd8938a61602e67132038a6f6d693fd46193ea1ba0693eda35
 size 4155

validation_results.json

@@ -1,41 +1,41 @@
 {
     "epoch": 2.0,
     "eval_COMMENT": {
-        "f1": 0.030715225976305396,
-        "number": 1322,
-        "precision": 0.03657262277951933,
-        "recall": 0.0264750378214826
+        "f1": 0.01321378008494573,
+        "number": 1376,
+        "precision": 0.018842530282637954,
+        "recall": 0.010174418604651164
     },
     "eval_NAME": {
-        "f1": 0.024336283185840708,
-        "number": 1766,
-        "precision": 0.5238095238095238,
-        "recall": 0.01245753114382786
+        "f1": 0.0,
+        "number": 1758,
+        "precision": 0.0,
+        "recall": 0.0
     },
     "eval_QTY": {
-        "f1": 0.003841229193341869,
-        "number": 1434,
-        "precision": 0.0234375,
-        "recall": 0.0020920502092050207
+        "f1": 0.26068953101089204,
+        "number": 1450,
+        "precision": 0.1499119991717569,
+        "recall": 0.9986206896551724
     },
     "eval_RANGE_END": {
         "f1": 0.0,
-        "number": 17,
+        "number": 14,
         "precision": 0.0,
         "recall": 0.0
     },
     "eval_UNIT": {
         "f1": 0.0,
-        "number": 1166,
+        "number": 1163,
         "precision": 0.0,
         "recall": 0.0
     },
-    "eval_loss": 10.259025573730469,
-    "eval_overall_accuracy": 0.12838815472171314,
-    "eval_overall_f1": 0.016813787305590584,
-    "eval_overall_precision": 0.04189944134078212,
-    "eval_overall_recall": 0.010517090271691499,
-    "eval_runtime": 15.7061,
-    "eval_samples_per_second": 108.365,
-    "eval_steps_per_second": 3.438
+    "eval_loss": 11.38698959350586,
+    "eval_overall_accuracy": 0.15278303672851193,
+    "eval_overall_f1": 0.1809070098372827,
+    "eval_overall_precision": 0.14054989425110556,
+    "eval_overall_recall": 0.25377538621767054,
+    "eval_runtime": 15.4103,
+    "eval_samples_per_second": 110.445,
+    "eval_steps_per_second": 3.504
 }