End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: cc-by-4.0
-base_model: deepset/deberta-v3-large-squad2
+license: mit
+base_model: microsoft/deberta-v3-large
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deberta-tweetqa-5ep
 
-This model is a fine-tuned version of [deepset/deberta-v3-large-squad2](https://huggingface.co/deepset/deberta-v3-large-squad2) on the None dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1915
+- Loss: 3.0879
 
 ## Model description
 
@@ -44,16 +44,18 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.5817        | 1.0   | 1    | 2.5048          |
-| 1.5733        | 2.0   | 2    | 2.5048          |
-| 1.3207        | 3.0   | 3    | 2.1915          |
+| 2.8792        | 1.0   | 1    | 3.2915          |
+| 2.7794        | 2.0   | 2    | 3.2915          |
+| 2.7593        | 3.0   | 3    | 3.2778          |
+| 2.8457        | 4.0   | 4    | 3.2051          |
+| 2.5938        | 5.0   | 5    | 3.0879          |
 
 
 ### Framework versions

config.json

@@ -8,13 +8,11 @@
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
-  "language": "english",
   "layer_norm_eps": 1e-07,
   "legacy": true,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
-  "name": "DebertaV2",
   "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
@@ -30,10 +28,6 @@
   "position_buckets": 256,
   "relative_attention": true,
   "share_att_key": true,
-  "summary_activation": "tanh",
-  "summary_last_dropout": 0,
-  "summary_type": "first",
-  "summary_use_proj": false,
   "torch_dtype": "float32",
   "transformers_version": "4.52.2",
   "type_vocab_size": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619f209981cec39e3576694251e2b9d0358774588eb65a51371ff0b405fbc0d5
+oid sha256:79b54a5a604a93014b46ecaaebd024d4d138e76a0b15dc55c1ba45420b656359
 size 1736105880

runs/Jun03_09-16-52_dec77067a4b2/events.out.tfevents.1748942216.dec77067a4b2.1091.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbd8a121d96c430fd6a9054a5c45cd081844d0551931f8d0af68183cfca1c7d
+size 7799

special_tokens_map.json

@@ -1,50 +1,14 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -27,7 +27,7 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -48,7 +48,7 @@
   "eos_token": "[SEP]",
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34b44a7a1b4023b5dada58ea252b33edc399fc0571ecb4d2b0662d81c2ce753
+oid sha256:de8574030b10ca1735f243a9e293217a8602dcb31e58b12a4c6f15e2b0432ab5
 size 5304