End of training

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # codeparrot-ds
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.1599
 
 ## Model description
 
@@ -34,19 +36,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.001
 - 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: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.4743        | 0.2   | 30   | 5.0870          |
+| 4.6204        | 0.4   | 60   | 4.1067          |
+| 3.6208        | 0.6   | 90   | 3.3209          |
+| 2.8321        | 0.79  | 120  | 3.0225          |
+| 2.5107        | 0.99  | 150  | 2.7852          |
+| 2.1614        | 1.19  | 180  | 2.7309          |
+| 1.868         | 1.39  | 210  | 2.8328          |
+| 1.7025        | 1.59  | 240  | 2.9077          |
+| 1.4511        | 1.79  | 270  | 3.0556          |
+| 1.1884        | 1.99  | 300  | 3.3297          |
+| 1.0243        | 2.19  | 330  | 3.4177          |
+| 0.9155        | 2.38  | 360  | 3.4031          |
+| 0.7844        | 2.58  | 390  | 3.6728          |
+| 0.688         | 2.78  | 420  | 4.0511          |
+| 0.7049        | 2.98  | 450  | 4.1599          |
 
 
 ### Framework versions

config.json

@@ -5,9 +5,9 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 0,
+  "bos_token_id": 50256,
   "embd_pdrop": 0.1,
-  "eos_token_id": 0,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -35,5 +35,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.2",
   "use_cache": true,
-  "vocab_size": 50000
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.39.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e347552ae0fa14b0c190c57174ec7f6c5cc7500d649e8851d6a409f1821f5962
-size 496984704
+oid sha256:9f6fea8a372c276b0050fa6cab5b2a59c13227f8eb56f5ad3abc04d67dace0b3
+size 497774208

special_tokens_map.json

@@ -1,24 +1,6 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
   "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,10 +1,10 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
+    "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a60674b93aa70bd27de4ff74e7c125918e2f28c695d0f7a6a2478089f9580e5
+oid sha256:2a67471d99e04b122a0424665902402901414547571a07ad8f9be55d6169f9cc
 size 4856