Training in progress, step 7

README.md

@@ -1,18 +1,17 @@
 ---
 base_model: Qwen/Qwen2-0.5B
-datasets: trl-lib/Capybara
 library_name: transformers
 model_name: Qwen2-0.5B-SFT
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for Qwen2-0.5B-SFT
 
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the [trl-lib/Capybara](https://huggingface.co/datasets/trl-lib/Capybara) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -36,8 +35,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.22.0.dev0
-- Transformers: 4.55.2
-- Pytorch: 2.8.0
+- Transformers: 4.56.0.dev0
+- Pytorch: 2.7.1
 - Datasets: 4.0.0
 - Tokenizers: 0.21.4
 

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee958146bebfd296e0a53f9078068b6cd935267a7e1598b43c12d5d52ae9f9f
+size 8663400

runs/Aug26_14-25-55_hf-dgx-01/events.out.tfevents.1756211165.hf-dgx-01.2087794.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37aee279608361ec56e2d6c35d6a5c3fd01fa37aa8b7b2b11a6e84218580553a
+size 6010

runs/Aug26_14-26-28_hf-dgx-01/events.out.tfevents.1756211197.hf-dgx-01.2088700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727a6fad6eb6be6cc250a55d0b2f2a85520b33f50af84146ce9173edb46f3895
+size 6474

special_tokens_map.json

@@ -3,13 +3,7 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|im_end|>",
   "pad_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ed0cfea9fd59d68e5b6790b60ebcb4bb047e2bd78861cf66535130ba7b086
+oid sha256:7118430e7d0e4c8e771cb24ae1d8ba5f35299ceae75d5b005a5e5bbbc31f8b1b
 size 6161