Training in progress epoch 0

README.md

@@ -12,13 +12,13 @@ probably proofread and complete it, then remove this comment. -->
 
 # jonaskoenig/xtremedistil-l6-h256-uncased-go-emotion
 
-This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on [go_emotions](https://huggingface.co/datasets/go_emotions).
+This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0246
-- Train Binary Crossentropy: 0.4128
-- Validation Loss: 0.0231
-- Validation Binary Crossentropy: 0.3821
-- Epoch: 5
+- Train Loss: 0.0669
+- Train Binary Crossentropy: 0.6193
+- Validation Loss: 0.0415
+- Validation Binary Crossentropy: 0.6178
+- Epoch: 0
 
 ## Model description
 
@@ -44,12 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Binary Crossentropy | Validation Loss | Validation Binary Crossentropy | Epoch |
 |:----------:|:-------------------------:|:---------------:|:------------------------------:|:-----:|
-| 0.0663     | 0.6202                    | 0.0417          | 0.6178                         | 0     |
-| 0.0399     | 0.6222                    | 0.0359          | 0.6178                         | 1     |
-| 0.0336     | 0.5852                    | 0.0303          | 0.5096                         | 2     |
-| 0.0295     | 0.5047                    | 0.0275          | 0.4647                         | 3     |
-| 0.0268     | 0.4564                    | 0.0250          | 0.4179                         | 4     |
-| 0.0246     | 0.4128                    | 0.0231          | 0.3821                         | 5     |
+| 0.0669     | 0.6193                    | 0.0415          | 0.6178                         | 0     |
 
 
 ### Framework versions

config.json

@@ -10,68 +10,67 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
   "id2label": {
-  "0": "admiration",
-  "1": "amusement",
-  "10": "disapproval",
-  "11": "disgust",
-  "12": "embarrassment",
-  "13": "excitement",
-  "14": "fear",
-  "15": "gratitude",
-  "16": "grief",
-  "17": "joy",
-  "18": "love",
-  "19": "nervousness",
-  "2": "anger",
-  "20": "optimism",
-  "21": "pride",
-  "22": "realization",
-  "23": "relief",
-  "24": "remorse",
-  "25": "sadness",
-  "26": "surprise",
-  "27": "neutral",
-  "3": "annoyance",
-  "4": "approval",
-  "5": "caring",
-  "6": "confusion",
-  "7": "curiosity",
-  "8": "desire",
-  "9": "disappointment"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27"
   },
   "initializer_range": 0.02,
   "intermediate_size": 1024,
   "label2id": {
-    "admiration": 0,
-   "amusement": 1,
-   "anger": 2,
-   "annoyance": 3,
-   "approval": 4,
-   "caring": 5,
-   "confusion": 6,
-   "curiosity": 7,
-   "desire": 8,
-   "disappointment": 9,
-   "disapproval": 10,
-   "disgust": 11,
-   "embarrassment": 12,
-   "excitement": 13,
-   "fear": 14,
-   "gratitude": 15,
-   "grief": 16,
-   "joy": 17,
-   "love": 18,
-   "nervousness": 19,
-   "neutral": 27,
-   "optimism": 20,
-   "pride": 21,
-   "realization": 22,
-   "relief": 23,
-   "remorse": 24,
-   "sadness": 25,
-   "surprise": 26,
-   "neutral": 27
-   },
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "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_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b0dfd5a7a0fd5886a168384de27beb105f0a26acde41ec6e90a4d14ff69847
+oid sha256:cfc9f5175d9424edfaa7873b95cc2bf038442f7fe6086d65cb72b952307aca3a
 size 51177784