Add files using upload-large-folder tool

global_step_24/actor/chat_template.jinja

@@ -1,5 +1,5 @@
 {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
-You are a helpful assistant<|im_end|>
+You are a helpful assistant.<|im_end|>
 ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
 ' + message['content'] + '<|im_end|>' + '
 '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant

global_step_24/actor/config.json

@@ -4,7 +4,7 @@
   ],
   "attention_dropout": 0.0,
   "dtype": "float32",
-  "eos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "initializer_range": 0.02,
@@ -48,7 +48,7 @@
   "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
+  "rope_theta": 10000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",

global_step_24/actor/generation_config.json

@@ -1,6 +1,11 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.0,
   "transformers_version": "4.56.2"
 }

global_step_24/actor/huggingface/chat_template.jinja

@@ -1,5 +1,5 @@
 {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
-You are a helpful assistant<|im_end|>
+You are a helpful assistant.<|im_end|>
 ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
 ' + message['content'] + '<|im_end|>' + '
 '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant

global_step_24/actor/huggingface/config.json

@@ -4,7 +4,7 @@
   ],
   "attention_dropout": 0.0,
   "dtype": "float32",
-  "eos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "initializer_range": 0.02,
@@ -48,7 +48,7 @@
   "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
+  "rope_theta": 10000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",

global_step_24/actor/huggingface/special_tokens_map.json

@@ -4,7 +4,7 @@
     "<|im_end|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

global_step_24/actor/huggingface/tokenizer_config.json

@@ -32,7 +32,7 @@
   ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,

global_step_24/actor/special_tokens_map.json

@@ -4,7 +4,7 @@
     "<|im_end|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

global_step_24/actor/tokenizer_config.json

@@ -32,7 +32,7 @@
   ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,

global_step_24/data.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312e68b61863d8a09b2659671bc9e16cccd7f0061fa89c66a195a0e9a39d6630
-size 6943629
+oid sha256:b15695dc76b6fa86acca2d24560f12e612e39f0cc827633a24066475bd3cb4b7
+size 6943885

global_step_24/training_state.json

@@ -1 +1 @@
-{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.75, "7": 0.75, "8": 0.75, "9": 0.75, "10": 0.75, "11": 0.75, "12": 0.75, "13": 0.75, "14": 0.75, "15": 0.75, "16": 0.75, "17": 0.75, "18": 0.75, "19": 0.75, "20": 0.75, "21": 0.75, "22": 0.75, "23": 0.75}}, "validation_accuracy_by_source": {"math_quiz": {"0": 0.7283582086883374, "10": 0.8656716417910447, "20": 0.9253731343283582, "24": 0.9253731343283582}}}
+{"history_accuracy": {"null": [0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75]}, "history_accuracy_with_step": {"null": {"1": 0.75, "2": 0.75, "3": 0.75, "4": 0.75, "5": 0.75, "6": 0.75, "7": 0.75, "8": 0.75, "9": 0.75, "10": 0.75, "11": 0.75, "12": 0.75, "13": 0.75, "14": 0.75, "15": 0.75, "16": 0.75, "17": 0.75, "18": 0.75, "19": 0.75, "20": 0.75, "21": 0.75, "22": 0.75, "23": 0.75}}, "validation_accuracy_by_source": {"math_quiz": {"0": 0.855072463768116, "10": 0.8840579710144928, "20": 0.9420289855072463, "24": 0.8985507246376812}}}