**kwargs

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: microsoft/Phi-3.5-mini-instruct
 library_name: peft
 license: mit
-base_model: microsoft/Phi-3.5-mini-instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9570
+- Loss: 0.7631
 - Exact Match Ratio: 0.0
 - Sequence Accuracy: 0.0
 
@@ -38,10 +38,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 3
 
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match Ratio | Sequence Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:-----------------:|
-| 11.7855       | 1.0   | 25   | 8.9031          | 0.0               | 0.0               |
-| 6.224         | 2.0   | 50   | 3.5512          | 0.0               | 0.0               |
-| 2.4789        | 3.0   | 75   | 1.9570          | 0.0               | 0.0               |
+| 8.1148        | 1.0   | 50   | 1.6942          | 0.0               | 0.0               |
+| 1.2769        | 2.0   | 100  | 0.8926          | 0.0               | 0.0               |
+| 0.8832        | 3.0   | 150  | 0.7631          | 0.0               | 0.0               |
 
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.3
-- Pytorch 2.4.0
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- PEFT 0.14.0
+- Transformers 4.47.0
+- Pytorch 2.3.1.post300
+- Datasets 2.2.1
+- Tokenizers 0.21.0

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,10 +26,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "qkv_proj",
-    "gate_up_proj",
     "down_proj",
-    "o_proj"
+    "qkv_proj",
+    "o_proj",
+    "gate_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 sha256:27a7cbcb66e6e504dbc358a729696bdab2dae4d22de840c2832cfdbc1c55e746
+oid sha256:f15bd442fe3e4d1b515b51f3d64667e033497c8f4e4a635f2a227d6d8078cec8
 size 888703384

runs/Dec06_21-54-03_default/events.out.tfevents.1733522044.default.1672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c4344e7c26553c5fd19bb007e2d0979beb5abc3a2e541dc386440cee72e924
+size 8620

runs/Dec06_22-01-43_default/events.out.tfevents.1733522503.default.1672.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bebf8de3902aafecf7fcdeeb25e7f517d0c9ca810950d4467191faf9013b897
+size 8407

runs/Dec06_22-02-36_default/events.out.tfevents.1733522557.default.1812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78ab36464de3c3c080e47d5d98735bb6e2764a9ba94d1f29badb6a5c52b23c5
+size 8407

runs/Dec06_22-03-48_default/events.out.tfevents.1733522628.default.1977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75754a447b08f5ada39fb6ae4e18a10c48be2bd011da25946472b520aa01b9cb
+size 8407

runs/Dec06_22-05-18_default/events.out.tfevents.1733522718.default.2104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e12ce4ad6722e80f88e9ae15680926035df7d9052cd9e40e7e9eba8d7a98e77
+size 10551

runs/Dec06_22-05-18_default/events.out.tfevents.1733522920.default.2104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec63876df9534d0b085749e3fc5074b79f4fb53ec11a428e5f6fe1b1c7d394a
+size 481

tokenizer_config.json

@@ -120,6 +120,7 @@
   "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9f41011fcf7ec3fe9753744e688c1d2abc7dbdbb48b0e9ea7b284cfb56b5f4
-size 5240
+oid sha256:fb9a6430bbb63abb7745d79404d46877785336574cf79a89fd40d253e0990ea9
+size 5304