add model

README.md

@@ -3,22 +3,18 @@ license: mit
 tags:
 - generated_from_keras_callback
 model-index:
-- name: jonaskoenig/xtremedistil-l6-h384-uncased-future-time-references
+- name: xtremedistil-l6-h384-uncased-future-time-references
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# jonaskoenig/xtremedistil-l6-h384-uncased-future-time-references
+# xtremedistil-l6-h384-uncased-future-time-references
 
-This model is a fine-tuned version of [microsoft/xtremedistil-l6-h384-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h384-uncased) on an unknown dataset.
+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: 0.0125
-- Train Sparse Categorical Accuracy: 0.9962
-- Validation Loss: 0.0144
-- Validation Sparse Categorical Accuracy: 0.9955
-- Epoch: 2
+
 
 ## Model description
 
@@ -42,11 +38,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
-|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
-| 0.0447     | 0.9870                            | 0.0225          | 0.9932                                 | 0     |
-| 0.0182     | 0.9947                            | 0.0169          | 0.9950                                 | 1     |
-| 0.0125     | 0.9962                            | 0.0144          | 0.9955                                 | 2     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/xtremedistil-l6-h384-uncased",
+  "_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,13 +8,73 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 256,
+  "id2label": {
+    "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": 1536,
+  "intermediate_size": 1024,
+  "label2id": {
+    "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",
-  "num_attention_heads": 12,
+  "num_attention_heads": 8,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42fd71c341ecdb842c98cf3c4009b94828d4659a0b042f9eabf205ae1f10bcd1
-size 91013368
+oid sha256:956a620cafc0e96032203a009a792e1f404e8ab0e95c33f423fc353583c1ebaa
+size 51177784