rzr1331/nexi-mind-adapter

README.md

@@ -1,11 +1,11 @@
 ---
-license: mit
+base_model: microsoft/Phi-3-medium-128k-instruct
 library_name: peft
+license: mit
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: microsoft/Phi-3-mini-4k-instruct
 model-index:
 - name: phi-3-mini-LoRA
   results: []
@@ -16,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-3-mini-LoRA
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5733
+This model is a fine-tuned version of [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) on an unknown dataset.
 
 ## Model description
 
@@ -38,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -50,15 +48,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.8349        | 0.4   | 100  | 0.6078          |
-| 0.599         | 0.8   | 200  | 0.5819          |
-| 0.5878        | 1.2   | 300  | 0.5786          |
-| 0.5663        | 1.6   | 400  | 0.5757          |
-| 0.5656        | 2.0   | 500  | 0.5745          |
-| 0.5622        | 2.4   | 600  | 0.5741          |
-| 0.5471        | 2.8   | 700  | 0.5733          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "base_model_name_or_path": "microsoft/Phi-3-medium-128k-instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "q_proj",
-    "up_proj",
     "k_proj",
+    "down_proj",
+    "gate_proj",
     "o_proj",
     "v_proj",
-    "gate_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a7e7e631d51cc91de36bf9cb0318a769da56842299579c89171b1cea711cc3
-size 35668592
+oid sha256:593c7d46d0a5cde3abc3191ca9cccaf58c19e401eb0ec080fd1be5585518b881
+size 85218160

tokenizer_config.json

@@ -117,11 +117,11 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,
-  "model_max_length": 4096,
+  "model_max_length": 131072,
   "pad_token": "<unk>",
   "padding_side": "left",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cfadcf94600af31d86e74323371e7f24490b6386c2ec1e415dd3aa38cf483f
+oid sha256:771cfc8c89a1c8cb4fe68de7e82ec78e924b4898e294036099ffe4901411447a
 size 5432