Training in progress, step 1600

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -1,9 +1,9 @@
 {
-  "_name_or_path": "/data/dvitel/semParse/result/h0",
+  "_name_or_path": "distilgpt2",
   "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
-    "GPT2Model"
+    "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230a11d08d05f8a9dc9f1d5402a5c41cc5b281231686025c32dc530ba72532bd
-size 333967801
+oid sha256:879d6ab264071cb65b143d31d3f0d54cfdd9c99966ad9bdb0b92f96a19c89a6d
+size 333970169

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "distilgpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d2dbf5a68d995675e59c40531b101575c81835fd0f0d7b7773b34e29ffe968
+size 3387