Training in progress, epoch 1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Sim4Rec/inter-play-sim-assistant-sft",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -18,7 +17,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 128001,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
@@ -31,7 +30,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.2",
-  "use_cache": true,
+  "transformers_version": "4.51.3",
+  "use_cache": false,
   "vocab_size": 128320
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1dca7caf67b0af32b1aa5c9c52ad02de5b54e84a8ec038bd74e3bc91b18d8c7
+oid sha256:153e9b2f9968cee7c24500b9db39043ef6774e83253ae1c5e9f0334989f34523
 size 4977222960

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f09aa5fdc5b3591ad4b03edba26dce3703417eba2a78ff25e3f469b3664a254
+oid sha256:0840f1cb9d760a5fe7cdf22d38bd1850143ce43ad67a9f237e72e62974a568c3
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6625e7a5cfcdd77627f26512cf498048fc24b6547e71e3ef4c3a71e41141d9
+oid sha256:9e0cbc723f505f812a453e788f1e4eca733497803384056017b633870d1cdf1e
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6115a28a38e67e9c28cd5db2742d2794509bfac5395d3a4d4f58a995d926ed67
+oid sha256:246dc7b1f34895bf90a6b0804a19d4ded9e8e98d711a3372086d2271bee3028b
 size 1168663096

runs/May07_15-46-50_w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-84pj9pb/events.out.tfevents.1746632959.w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-84pj9pb.15363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1159dea1e8aef4ef9c1581b1bd648f29fa0c5dba4e7f59f1d74ab5d8b845cb
+size 6312

runs/May07_18-58-10_w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-7bjk8jd/events.out.tfevents.1746644432.w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-7bjk8jd.16849.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367914b0c34f4d4fe626a3c404b5dad5a5c625a85d972bc89f18d111688a09fe
+size 203122

special_tokens_map.json

@@ -2,9 +2,16 @@
   "additional_special_tokens": [
     "<response>",
     "</response>",
-    "<answer>",
-    "</answer>",
-    "<inquire>"
+    "<action>",
+    "</action>",
+    "<inquire>",
+    "<recommend>",
+    "<greeting>",
+    "<disclose-goal>",
+    "<feedback>",
+    "<accept>",
+    "<movie_title>",
+    "</movie_title>"
   ],
   "bos_token": {
     "content": "<|im_start|>",
@@ -21,7 +28,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|finetune_right_pad_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ea5afcc70a5f73f9b545a5940b211fd23e2acd4d895a3ebc3144ca348a4633
-size 17211228
+oid sha256:1333f4772561fe7012579974661e97e8d5105c4a40fcaeca1fcaa35e2f1c72f7
+size 17212548

tokenizer_config.json

@@ -2081,7 +2081,7 @@
       "special": true
     },
     "128260": {
-      "content": "<answer>",
+      "content": "<action>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2089,7 +2089,7 @@
       "special": true
     },
     "128261": {
-      "content": "</answer>",
+      "content": "</action>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2103,29 +2103,88 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "128263": {
+      "content": "<recommend>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128264": {
+      "content": "<greeting>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128265": {
+      "content": "<disclose-goal>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128266": {
+      "content": "<feedback>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128267": {
+      "content": "<accept>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128268": {
+      "content": "<movie_title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128269": {
+      "content": "</movie_title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
     "<response>",
     "</response>",
-    "<answer>",
-    "</answer>",
-    "<inquire>"
+    "<action>",
+    "</action>",
+    "<inquire>",
+    "<recommend>",
+    "<greeting>",
+    "<disclose-goal>",
+    "<feedback>",
+    "<accept>",
+    "<movie_title>",
+    "</movie_title>"
   ],
   "bos_token": "<|im_start|>",
   "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": true,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "max_length": 2048,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|end_of_text|>",
-  "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first"
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizer"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31315ddeb7aa7465f2bd16d20b45c43e929c9c6b6b9f79d4646ff479ab0b680
+oid sha256:395fb48e7de57f282dbfbd55c1cdbbb8e8a6be71123f5d59c2730f53296e6c0e
 size 7800