Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
-license: cc-by-4.0
-base_model: ydshieh/bert-base-cased-squad2
+license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # MohamedAAK/my_awesome_eli5_clm-model
 
-This model is a fine-tuned version of [ydshieh/bert-base-cased-squad2](https://huggingface.co/ydshieh/bert-base-cased-squad2) on an unknown dataset.
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0294
-- Validation Loss: 0.0122
-- Epoch: 2
+- Train Loss: 4.8400
+- Validation Loss: 3.9280
+- Epoch: 0
 
 ## Model description
 
@@ -43,9 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.1925     | 0.0644          | 0     |
-| 0.0691     | 0.0213          | 1     |
-| 0.0294     | 0.0122          | 2     |
+| 4.8400     | 3.9280          | 0     |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -1,27 +1,45 @@
 {
-  "_name_or_path": "ydshieh/bert-base-cased-squad2",
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertLMHeadModel"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "language": "english",
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "name": "Bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "transformers_version": "4.35.2",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 50258
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
-  "pad_token_id": 0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.35.2"
 }

special_tokens_map.json

@@ -1,18 +1,6 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
   "pad_token": {
     "content": "[PAD]",
     "lstrip": false,
@@ -20,18 +8,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfbd61c3d6cfcec5cf435d8f885d29fec3462bcad62ecf617354a235247f0b29
-size 524305768
+oid sha256:6a76b064697dcd142f69578efd96dc80636c43e702c450642d5c1bdcb4cce93a
+size 327748552

tokenizer_config.json

@@ -1,39 +1,16 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
+    "50257": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,18 +18,11 @@
       "special": true
     }
   },
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "max_len": 512,
-  "model_max_length": 512,
-  "never_split": null,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
   "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }