Training in progress, step 500

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilroberta-base
+base_model: distilgpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # github_cybersecurity_READMEs
 
-This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) 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:
-- Loss: 1.9832
+- Loss: 2.8573
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.7395        | 1.0   | 1250 | 2.2302          |
-| 2.3054        | 2.0   | 2500 | 2.0325          |
-| 2.2275        | 3.0   | 3750 | 1.9858          |
+| 3.0489        | 1.0   | 1250 | 2.9234          |
+| 2.902         | 2.0   | 2500 | 2.8704          |
+| 2.8353        | 3.0   | 3750 | 2.8573          |
 
 
 ### Framework versions

config.json

@@ -1,27 +1,46 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "RobertaForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "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,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "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
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.40.0.dev0",
-  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.40.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81912bd7ede131cb98d81f5f40f6ab05f26936cf7ab8c7ce31a9901c66627522
-size 328693404
+oid sha256:b9672d37a68559da4599e03a6757028c4dbe768105cee90d437983b4c7bce319
+size 327657928

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110b3ba92e63a2ec1f5abe30288582284085ef1ab832bab1bc9c64479dd8e85d
+oid sha256:9b9703f9a83601a5eaa6ca6169a8b2c3b1614cb9881166962af9231d5ad645bf
 size 4984