Training in progress, step 110

README.md

@@ -4,6 +4,7 @@ library_name: transformers
 model_name: lfm2-24b-sft-finetuned
 tags:
 - generated_from_trainer
+- unsloth
 - sft
 - trl
 licence: license
@@ -27,18 +28,17 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/thomas-gauthier-c/local-roma/runs/qqol9irg) 
-
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/thomas-gauthier-c/local-roma/runs/gmywbyzg) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.29.0
+- TRL: 0.24.0
 - Transformers: 5.2.0
 - Pytorch: 2.10.0
-- Datasets: 4.6.0
+- Datasets: 4.3.0
 - Tokenizers: 0.22.2
 
 ## Citations
@@ -48,11 +48,12 @@ This model was trained with SFT.
 Cite TRL as:
     
 ```bibtex
-@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}
+@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}}
 }
 ```

adapter_config.json

@@ -2,7 +2,11 @@
   "alora_invocation_tokens": null,
   "alpha_pattern": {},
   "arrow_config": null,
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "Lfm2MoeForCausalLM",
+    "parent_library": "transformers.models.lfm2_moe.modeling_lfm2_moe",
+    "unsloth_fixed": true
+  },
   "base_model_name_or_path": "LiquidAI/LFM2-24B-A2B",
   "bias": "none",
   "corda_config": null,
@@ -16,16 +20,16 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 256,
   "lora_bias": false,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
@@ -33,7 +37,6 @@
     "v_proj",
     "k_proj",
     "in_proj",
-    "gate",
     "w3",
     "w2",
     "out_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b1502de916ba9a799af50d4cb2c448c968c22fa8dac054d4571116aeef6f9f
-size 21317184
+oid sha256:fc80968391e16d4827f411a755b4e69a5646b7930842c49aec16079b88986dcd
+size 299397152

tokenizer_config.json

@@ -13,6 +13,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "model_specific_special_tokens": {},
   "pad_token": "<|pad|>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c205adbb17370c3c4041d2cbcf7030526af2fd091b1af64dd814d0f525650e
-size 5649
+oid sha256:5d1c5064807c64b5de05383cab06c0f95192408d5cf37e232cf3381c6b774f51
+size 5777