Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilgpt2
+base_model: bert-base-uncased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # node-py/my_awesome_eli5_clm-model
 
-This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.2212
-- Validation Loss: 5.1350
-- Epoch: 9
+- Train Loss: 7.4278
+- Validation Loss: 6.1153
+- Epoch: 0
 
 ## Model description
 
@@ -43,16 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 7.9915     | 6.1584          | 0     |
-| 6.0733     | 5.8991          | 1     |
-| 5.9048     | 5.7918          | 2     |
-| 5.7975     | 5.6991          | 3     |
-| 5.7077     | 5.6058          | 4     |
-| 5.6085     | 5.5014          | 5     |
-| 5.5086     | 5.4011          | 6     |
-| 5.4100     | 5.3107          | 7     |
-| 5.3142     | 5.2220          | 8     |
-| 5.2212     | 5.1350          | 9     |
+| 7.4278     | 6.1153          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,45 +1,26 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "GPT2LMHeadModel"
+    "BertLMHeadModel"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "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
-    }
-  },
+  "intermediate_size": 3072,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "transformers_version": "4.44.0",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 30522
 }

generation_config.json

@@ -1,6 +1,5 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "pad_token_id": 0,
   "transformers_version": "4.44.0"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355baad3df548530b23cae5cc635cf03e531bc87edc100f88b19dd324863ef7b
-size 327745472
+oid sha256:d12e8534ea4b65b4e1ab43d991fdad385ca0338fbd005b1c5160af0a650d4c4f
+size 533687616