Upload task output 1

config.json

@@ -1,31 +1,30 @@
 {
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "LlamaForCausalLM"
+    "OPTForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
   "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 5632,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
   "max_position_embeddings": 2048,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 4,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "unsloth_version": "2024.9",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
-  "bos_token_id": 1,
+  "_from_model_config": true,
+  "bos_token_id": 2,
   "eos_token_id": 2,
-  "max_length": 2048,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "transformers_version": "4.51.3"
 }

loss.txt

@@ -1 +1 @@
-12,0.000252216326771304
+12432,0.39887547492980957

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70fb36287eeff1033963e3ae64e6406cd1e0fd4fc6148760d05b1479945e8539
-size 2200119864
+oid sha256:49441b876fd304e0b61051425bd6dfcf0cd62456863f2a940098c48e998dd422
+size 250501160

special_tokens_map.json

@@ -1,29 +1,29 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
+    "content": "<pad>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,20 +1,11 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "1": {
-      "content": "<s>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,23 +13,19 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "bos_token": "</s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "<unk>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:412cda4b1cc0fd6a694649992b0dd43266f84cba74f8f0140b2e1be7ef3dd743
+oid sha256:bcba3b3cf9b11713ce72b366ea0331734366b66173af6d17fe073becbb5df686
 size 5560