upload checkpoint

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "save/iqlearn/250114_143059/iter1_meta-llama-Llama-3.2-3B-Instruct//checkpoint-500",
+  "_name_or_path": "rl-llm-agent/Llama-3.2-3B-Instruct-online-dpo-alfworld-iqlearn-iter0",
   "architectures": [
-    "LlamaForSequenceClassification"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -14,14 +14,8 @@
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 3072,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 8192,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
@@ -41,6 +35,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.1"
+}

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e910e5565a2ac0f108bc7bd410d2778983c95a7b68dd8e06f5ed9ba8747def6e
+oid sha256:5d0dd76b00345d23331d8e0f62431fa34ac8d795c36f47ffe8114501f3cf22ae
 size 4965841415

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b65246382a3c2003f7b85abbdd6b366a1b9730986fbf405d9933192eaf99d78
-size 1459751666
+oid sha256:ad778ecd5db56dfdbefeca17f5c7ff9b67c4ed8d1ece2b6330a1f073c9f4a772
+size 2247750386

pytorch_model.bin.index.json

@@ -1,8 +1,9 @@
 {
   "metadata": {
-    "total_size": 6425505792
+    "total_size": 7213504512
   },
   "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
     "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -256,7 +257,6 @@
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.norm.weight": "pytorch_model-00002-of-00002.bin",
-    "score.weight": "pytorch_model-00002-of-00002.bin"
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
   }
 }

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
-size 17210102
+oid sha256:a4e61cf9383a37398dfd3322799286181b91dedc6a4947393255f5efca1ea6da
+size 17210018

tokenizer_config.json

@@ -2047,14 +2047,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "128256": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",
@@ -2062,12 +2054,17 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
+  "max_length": 8000,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "[PAD]",
-  "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "pad_token": "<|eot_id|>",
+  "padding": true,
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation": true,
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first"
 }