Training in progress, step 40

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: google/functiongemma-270m-it
 library_name: transformers
 model_name: functiongemma-270m-it-simple-tool-calling
 tags:
@@ -11,7 +10,7 @@ licence: license
 
 # Model Card for functiongemma-270m-it-simple-tool-calling
 
-This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -30,15 +29,16 @@ print(output["generated_text"])
  
 
 
+
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.26.2
-- Transformers: 4.57.3
-- Pytorch: 2.9.0+cu126
+- TRL: 0.29.0
+- Transformers: 5.0.0
+- Pytorch: 2.10.0+cu128
 - Datasets: 4.0.0
-- Tokenizers: 0.22.1
+- Tokenizers: 0.22.2
 
 ## Citations
 
@@ -47,12 +47,11 @@ This model was trained with SFT.
 Cite TRL as:
     
 ```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
 }
 ```

config.json

@@ -43,12 +43,20 @@
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000.0,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
   "sliding_window": 512,
-  "transformers_version": "4.57.3",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
   "use_bidirectional_attention": false,
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 262144
 }

generation_config.json

@@ -10,5 +10,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.57.3"
+  "transformers_version": "5.0.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d31c9a228dd7c4a988af29bf8da2d6ff072bcf64073b44fd65f81c1fce34871
+oid sha256:b72823a73feceb25868da1db7a6aa1b2e7caaa457a303daf1d12f90a9c64c6e3
 size 536223056

runs/Feb28_08-00-10_742caaa5b789/events.out.tfevents.1772265610.742caaa5b789.391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc603ff5934ad197fabf6f77cd397635757179a076b6ddc679b47618af441e16
+size 24476

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
-size 33384899
+oid sha256:e3655797f9d732b7dc08b4225200697af8e37d94b74711d9b1d8166feb953578
+size 33384774

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43b5c65669241fd72ed69d57e500eeb2f0e7f99a7b35ae9d13d471effe33c91
-size 6353
+oid sha256:e7e62cfb706287057356d240fea739c2aed3842d9777a9d44f5ae25716b92617
+size 5649