Training in progress, step 10

added_tokens.json

@@ -1,5 +1,3 @@
 {
-  "<PAD>": 32002,
-  "<|im_end|>": 32000,
-  "<|im_start|>": 32001
+  "<PAD>": 50265
 }

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7496a6ddf08604ea5174beb8a582745eff2f61498682cdbd23cc9efe0d5129
+size 662437776

special_tokens_map.json

@@ -1,15 +1,15 @@
 {
   "bos_token": {
-    "content": "<s>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
@@ -21,10 +21,10 @@
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
     "single_word": false
   }
 }

tokenizer_config.json

@@ -1,48 +1,24 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
     "1": {
-      "content": "<s>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
-      "content": "<|im_end|>",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
+    "50265": {
       "content": "<PAD>",
       "lstrip": false,
       "normalized": false,
@@ -51,19 +27,12 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "legacy": true,
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<PAD>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true,
-  "use_fast": true
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007b0dd6ea451ef8ae59385d81928e475684ce5b7a0d9349be54e9dee85f14cf
-size 4600
+oid sha256:d921c21ba6ef10b96cae53be6210c933c7b8fa2c2e0e7efe33cd36827fd89376
+size 4920