Training complete

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-base_model: cardiffnlp/twitter-roberta-base
+license: apache-2.0
+base_model: distilbert/distilroberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tweet-classifier
 
-This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base](https://huggingface.co/cardiffnlp/twitter-roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4290
-- Accuracy: 0.8926
+- Loss: 0.1510
+- Accuracy: 0.941
 
 ## Model description
 
@@ -49,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4808        | 1.0   | 1062 | 0.5176          | 0.8547   |
-| 0.3479        | 2.0   | 2124 | 0.4521          | 0.8737   |
-| 0.0921        | 3.0   | 3186 | 0.4290          | 0.8926   |
+| 0.2876        | 1.0   | 1000 | 0.1812          | 0.9325   |
+| 0.1441        | 2.0   | 2000 | 0.1583          | 0.9355   |
+| 0.1227        | 3.0   | 3000 | 0.1510          | 0.941    |
 
 
 ### Framework versions

config.json

@@ -6,61 +6,32 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "label_1",
-    "1": "label_2",
-    "2": "label_3",
-    "3": "label_4",
-    "4": "label_5",
-    "5": "label_6",
-    "6": "label_7",
-    "7": "label_8",
-    "8": "label_9",
-    "9": "label_10",
-    "10": "label_11",
-    "11": "label_12",
-    "12": "label_13",
-    "13": "label_14",
-    "14": "label_15",
-    "15": "label_16",
-    "16": "label_17",
-    "17": "label_18",
-    "18": "label_19",
-    "19": "label_20"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "label_1": 0,
-    "label_10": 9,
-    "label_11": 10,
-    "label_12": 11,
-    "label_13": 12,
-    "label_14": 13,
-    "label_15": 14,
-    "label_16": 15,
-    "label_17": 16,
-    "label_18": 17,
-    "label_19": 18,
-    "label_2": 1,
-    "label_20": 19,
-    "label_3": 2,
-    "label_4": 3,
-    "label_5": 4,
-    "label_6": 5,
-    "label_7": 6,
-    "label_8": 7,
-    "label_9": 8
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9245f04b70f05606f4a31644f35339b2364bf00043929269504a9693a08359d
-size 498668192
+oid sha256:381b6eedb4b048fd9de7ffe40f8af854de463c5b43948fa8fc01b6068730c6c8
+size 328504584

runs/Apr03_13-02-02_ed66a94a5026/events.out.tfevents.1743685326.ed66a94a5026.1783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e5c7b389f3a5c57da4e86679651cf5e609148e7843d952a8df3fa9de9a78f2
+size 69968

runs/Apr03_13-02-02_ed66a94a5026/events.out.tfevents.1743685532.ed66a94a5026.1783.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a05ada88227f4c0c93841ba9b876f19df23714d5025591eeecc9aff7d64d3be
+size 411

special_tokens_map.json

@@ -1,25 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -27,25 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -49,7 +49,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "RobertaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38dfe502f793fd79abfed36999a2f692b8fb7254faba43555edb4b406cd61c8a
+oid sha256:e6994dee4b5a40364ab008180ccccf9fdad27aade12f682ff07eeba1271ab5eb
 size 5368