Training in progress, epoch 1

README.md

@@ -3,11 +3,26 @@ license: apache-2.0
 base_model: allenai/longformer-base-4096
 tags:
 - generated_from_trainer
+datasets:
+- fancy_dataset
 metrics:
 - accuracy
 model-index:
 - name: longformer-one-step
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: fancy_dataset
+      type: fancy_dataset
+      config: full_labels
+      split: test
+      args: full_labels
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8161524956107349
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,16 +30,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # longformer-one-step
 
-This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the fancy_dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5640
-- Claim: {'precision': 0.5519765739385066, 'recall': 0.32811140121845084, 'f1-score': 0.41157205240174677, 'support': 2298.0}
-- Majorclaim: {'precision': 0.5541490857946554, 'recall': 0.701067615658363, 'f1-score': 0.6190102120974077, 'support': 1124.0}
-- O: {'precision': 0.8899137758171245, 'recall': 0.8831840796019901, 'f1-score': 0.8865361566120655, 'support': 5025.0}
-- Premise: {'precision': 0.830119375573921, 'recall': 0.9103726082578046, 'f1-score': 0.8683957732949088, 'support': 6951.0}
-- Accuracy: 0.7993
-- Macro avg: {'precision': 0.7065397027810518, 'recall': 0.7056839261841521, 'f1-score': 0.6963785486015321, 'support': 15398.0}
-- Weighted avg: {'precision': 0.7879778050681424, 'recall': 0.7993245876087803, 'f1-score': 0.7879350085702844, 'support': 15398.0}
+- Loss: 0.5164
+- Claim: {'precision': 0.5841029946823397, 'recall': 0.47910927456382, 'f1-score': 0.5264219952074664, 'support': 4356.0}
+- Majorclaim: {'precision': 0.663898774219059, 'recall': 0.7694775435380385, 'f1-score': 0.7127998301846742, 'support': 2182.0}
+- O: {'precision': 0.9219015280135824, 'recall': 0.8781671159029649, 'f1-score': 0.8995030369961348, 'support': 9275.0}
+- Premise: {'precision': 0.8377274128893001, 'recall': 0.8983961640211641, 'f1-score': 0.8670017552257859, 'support': 12096.0}
+- Accuracy: 0.8162
+- Macro avg: {'precision': 0.7519076774510703, 'recall': 0.7562875245064969, 'f1-score': 0.7514316544035153, 'support': 27909.0}
+- Weighted avg: {'precision': 0.8125252509519227, 'recall': 0.8161524956107349, 'f1-score': 0.8125897502575133, 'support': 27909.0}
 
 ## Model description
 
@@ -53,11 +68,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                                 | Majorclaim                                                                                                             | O                                                                                                                  | Premise                                                                                                            | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
-|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
-| No log        | 1.0   | 36   | 0.7525          | {'precision': 0.41766381766381766, 'recall': 0.31897302001740646, 'f1-score': 0.36170737725141877, 'support': 2298.0} | {'precision': 0.43548387096774194, 'recall': 0.02402135231316726, 'f1-score': 0.045531197301854974, 'support': 1124.0} | {'precision': 0.7476681394207167, 'recall': 0.9092537313432836, 'f1-score': 0.8205818965517241, 'support': 5025.0} | {'precision': 0.8187416331994646, 'recall': 0.8798733995108617, 'f1-score': 0.8482074752097636, 'support': 6951.0} | 0.7433   | {'precision': 0.6048893653129352, 'recall': 0.5330303757961797, 'f1-score': 0.5190069865786904, 'support': 15398.0} | {'precision': 0.707714041883217, 'recall': 0.7432783478373814, 'f1-score': 0.7079942076273884, 'support': 15398.0}  |
-| No log        | 2.0   | 72   | 0.6577          | {'precision': 0.4793814432989691, 'recall': 0.3237597911227154, 'f1-score': 0.38649350649350644, 'support': 2298.0}   | {'precision': 0.41677503250975295, 'recall': 0.5702846975088968, 'f1-score': 0.48159278737791134, 'support': 1124.0}   | {'precision': 0.7966573816155988, 'recall': 0.9106467661691542, 'f1-score': 0.849846782431052, 'support': 5025.0}  | {'precision': 0.8743144424131627, 'recall': 0.8256365990504964, 'f1-score': 0.8492785793562707, 'support': 6951.0} | 0.7598   | {'precision': 0.6417820749593709, 'recall': 0.6575819634628157, 'f1-score': 0.6418029139146851, 'support': 15398.0} | {'precision': 0.7566331163186304, 'recall': 0.7598389401220937, 'f1-score': 0.7535581151939423, 'support': 15398.0} |
-| No log        | 3.0   | 108  | 0.5640          | {'precision': 0.5519765739385066, 'recall': 0.32811140121845084, 'f1-score': 0.41157205240174677, 'support': 2298.0}  | {'precision': 0.5541490857946554, 'recall': 0.701067615658363, 'f1-score': 0.6190102120974077, 'support': 1124.0}      | {'precision': 0.8899137758171245, 'recall': 0.8831840796019901, 'f1-score': 0.8865361566120655, 'support': 5025.0} | {'precision': 0.830119375573921, 'recall': 0.9103726082578046, 'f1-score': 0.8683957732949088, 'support': 6951.0}  | 0.7993   | {'precision': 0.7065397027810518, 'recall': 0.7056839261841521, 'f1-score': 0.6963785486015321, 'support': 15398.0} | {'precision': 0.7879778050681424, 'recall': 0.7993245876087803, 'f1-score': 0.7879350085702844, 'support': 15398.0} |
+| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                                | Majorclaim                                                                                                           | O                                                                                                                  | Premise                                                                                                             | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
+| No log        | 1.0   | 41   | 0.7242          | {'precision': 0.4451114922813036, 'recall': 0.23829201101928374, 'f1-score': 0.3104066985645933, 'support': 4356.0}  | {'precision': 0.6888297872340425, 'recall': 0.11869844179651695, 'f1-score': 0.20250195465207194, 'support': 2182.0} | {'precision': 0.7629536017331648, 'recall': 0.9112668463611859, 'f1-score': 0.8305409521937798, 'support': 9275.0} | {'precision': 0.7774552148976847, 'recall': 0.9077380952380952, 'f1-score': 0.83756054769442, 'support': 12096.0}   | 0.7427   | {'precision': 0.6685875240365489, 'recall': 0.5439988486037705, 'f1-score': 0.5452525382762162, 'support': 27909.0} | {'precision': 0.7138351496506337, 'recall': 0.7427353183560859, 'f1-score': 0.7032996725252499, 'support': 27909.0} |
+| No log        | 2.0   | 82   | 0.5451          | {'precision': 0.5706823375775384, 'recall': 0.40128558310376494, 'f1-score': 0.47122253673001757, 'support': 4356.0} | {'precision': 0.6872317596566524, 'recall': 0.5870760769935839, 'f1-score': 0.6332179930795848, 'support': 2182.0}   | {'precision': 0.8817295464179737, 'recall': 0.8970350404312668, 'f1-score': 0.8893164448720005, 'support': 9275.0} | {'precision': 0.819134799940942, 'recall': 0.9173280423280423, 'f1-score': 0.8654551127057172, 'support': 12096.0}  | 0.8042   | {'precision': 0.7396946108982767, 'recall': 0.7006811857141645, 'f1-score': 0.71480302184683, 'support': 27909.0}   | {'precision': 0.7908462519320261, 'recall': 0.8042208606542692, 'f1-score': 0.7936967322502336, 'support': 27909.0} |
+| No log        | 3.0   | 123  | 0.5164          | {'precision': 0.5841029946823397, 'recall': 0.47910927456382, 'f1-score': 0.5264219952074664, 'support': 4356.0}     | {'precision': 0.663898774219059, 'recall': 0.7694775435380385, 'f1-score': 0.7127998301846742, 'support': 2182.0}    | {'precision': 0.9219015280135824, 'recall': 0.8781671159029649, 'f1-score': 0.8995030369961348, 'support': 9275.0} | {'precision': 0.8377274128893001, 'recall': 0.8983961640211641, 'f1-score': 0.8670017552257859, 'support': 12096.0} | 0.8162   | {'precision': 0.7519076774510703, 'recall': 0.7562875245064969, 'f1-score': 0.7514316544035153, 'support': 27909.0} | {'precision': 0.8125252509519227, 'recall': 0.8161524956107349, 'f1-score': 0.8125897502575133, 'support': 27909.0} |
 
 
 ### Framework versions

config.json

@@ -6,18 +6,18 @@
   "attention_mode": "longformer",
   "attention_probs_dropout_prob": 0.1,
   "attention_window": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700
   ],
   "bos_token_id": 0,
   "eos_token_id": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a9d66a6f610a23421ecae3c2af31fc5562c837143bb5fac933832c2ca2deeb
+oid sha256:32300cbf932e31f222044f90470759b1876373b427ccdd1a9aa67ec8cd263fcc
 size 592330980

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de4fffad50a10dc74fc6cce32fa2c5ba232abac8a9efcc8dc7fe55a0a63d993
+oid sha256:b255ea933fa019c0434165b15f04a6f6f1bcbebd5334f05444070af09508cd03
 size 4664