Training in progress, step 500

README.md

@@ -33,15 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 5.0
+- num_epochs: 3.0
 
 ### Training results
 

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd2f1842e1f0b796a39dc7678d279e3db8d52e83e0e46703c2249e7d4f94721
-size 497807197
+oid sha256:9f1e331759a5a24e01debd4dfabdf81179dbb28c1dc3fb62231f98b276cdf1ed
+size 497807706

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -8,10 +8,9 @@
       "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
@@ -19,6 +18,5 @@
   "model_max_length": 1024,
   "pad_token": null,
   "tokenizer_class": "GPT2Tokenizer",
-  "tokenizer_file": "/root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/tokenizer.json",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac03eec5be2371b78888ea6135607b667c85b17577ebd880a5c4e5adf5bd296
-size 4155
+oid sha256:a64b3c3d91f9078d061a2ccc52205d247334c0f9daad30130b5a74b45d0bd2f9
+size 4600