Model save

README.md

@@ -3,10 +3,7 @@ library_name: peft
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
-- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
-- lora
-- transformers
-pipeline_tag: text-generation
+- generated_from_trainer
 model-index:
 - name: tinyllama-1.1b-sft-test3
   results: []
@@ -19,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2319
+- Loss: 0.2259
 
 ## Model description
 
@@ -42,7 +39,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 10
 - seed: 4234
-- optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1
@@ -51,24 +48,24 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.3307        | 0.0778 | 20   | 0.3030          |
-| 0.3519        | 0.1556 | 40   | 0.2559          |
-| 0.2853        | 0.2335 | 60   | 0.2719          |
-| 0.2972        | 0.3113 | 80   | 0.2569          |
-| 0.3116        | 0.3891 | 100  | 0.2501          |
-| 0.3691        | 0.4669 | 120  | 0.2374          |
-| 0.349         | 0.5447 | 140  | 0.2387          |
-| 0.2605        | 0.6226 | 160  | 0.2395          |
-| 0.3281        | 0.7004 | 180  | 0.2297          |
-| 0.278         | 0.7782 | 200  | 0.2314          |
-| 0.2592        | 0.8560 | 220  | 0.2334          |
-| 0.2562        | 0.9339 | 240  | 0.2319          |
+| 0.3312        | 0.0778 | 20   | 0.2974          |
+| 0.3523        | 0.1556 | 40   | 0.2538          |
+| 0.2853        | 0.2335 | 60   | 0.2694          |
+| 0.2953        | 0.3113 | 80   | 0.2519          |
+| 0.3104        | 0.3891 | 100  | 0.2379          |
+| 0.3664        | 0.4669 | 120  | 0.2325          |
+| 0.3484        | 0.5447 | 140  | 0.2302          |
+| 0.2604        | 0.6226 | 160  | 0.2322          |
+| 0.3282        | 0.7004 | 180  | 0.2232          |
+| 0.2788        | 0.7782 | 200  | 0.2250          |
+| 0.2589        | 0.8560 | 220  | 0.2260          |
+| 0.2551        | 0.9339 | 240  | 0.2259          |
 
 
 ### Framework versions
 
-- PEFT 0.17.1
-- Transformers 4.56.2
-- Pytorch 2.8.0+cu128
-- Datasets 4.1.1
-- Tokenizers 0.22.1
+- PEFT 0.15.2
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu128
+- Datasets 3.5.0
+- Tokenizers 0.21.1

final/README.md

@@ -1,11 +1,6 @@
 ---
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
-- lora
-- transformers
 ---
 
 # Model Card for Model ID
@@ -204,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.17.1
+- PEFT 0.15.2

final/adapter_config.json

@@ -20,20 +20,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "v_proj",
+    "o_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

final/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f68aa2c3a723712896c17effd9c0378c3898d193c09461c45b1334b903cf0a
+oid sha256:965759863b0b55d9d3434a43b226797a448e2d8d47a2000276e763796ec61bba
 size 9034304

final/tokenizer_config.json

@@ -29,6 +29,7 @@
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},

final/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3844ec01a7e5428375f5fa422945a281479583f95ab1b3f54a9ed7709b63560
-size 5777
+oid sha256:6c5efdf6a4d7499ebc0905143bebac35a1ff8dbc498e16a33ecdd81a101ec6f6
+size 5713