End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: gpt2
 tags:
 - generated_from_trainer
 datasets:
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2_finetuned
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wiki_qa dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the wiki_qa dataset.
 
 ## Model description
 
@@ -34,13 +32,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 8
+- learning_rate: 0.0005
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+
+### Training results
+
+
 
 ### Framework versions
 

config.json

@@ -1,8 +1,7 @@
 {
-  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPT2ForSequenceClassification"
+    "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
@@ -11,7 +10,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
+  "n_ctx": 128,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,

generation_config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2718165d237d5c93ffe15a2ef9414b7339f52b555e287274706734b2c9f402
-size 497780432
+oid sha256:11abab5381374b6a7f4fe4143701b8f855fa72c5fcdaf1ad0ea1ba8f94642605
+size 497774208

runs/Dec05_22-48-46_e3ee4ba9a99f/events.out.tfevents.1701816548.e3ee4ba9a99f.133.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ccc7d4143fcd81a28eb0e50955aa389a12d585c60e0c9aee55b866f1b6dd7f
+size 4771

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a60eb205017f7d434ebd2b96bcac38d2932586e8a2610bcfb4f24f45c158555
+oid sha256:41495aa8b0a59bc691f04df068ff8de12bbbc1cea58706d9f7ea667ac13a1d4c
 size 4536