Hemanth-thunder/aimo-lora-deepseek-math

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: microsoft/Phi-3-mini-128k-instruct
+base_model: deepseek-ai/deepseek-math-7b-base
 library_name: peft
-license: mit
+license: other
 tags:
 - trl
 - sft
@@ -16,9 +16,9 @@ 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-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the None dataset.
+This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3525
+- Loss: 0.4014
 
 ## Model description
 
@@ -39,36 +39,31 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
 - train_batch_size: 1
-- eval_batch_size: 2
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3351        | 0.17  | 500  | 0.3755          |
-| 0.3312        | 0.34  | 1000 | 0.3644          |
-| 0.3079        | 0.51  | 1500 | 0.3597          |
-| 0.3195        | 0.68  | 2000 | 0.3577          |
-| 0.3218        | 0.85  | 2500 | 0.3557          |
-| 0.3034        | 1.02  | 3000 | 0.3553          |
-| 0.296         | 1.19  | 3500 | 0.3543          |
-| 0.3175        | 1.36  | 4000 | 0.3539          |
-| 0.3257        | 1.53  | 4500 | 0.3533          |
-| 0.3263        | 1.7   | 5000 | 0.3526          |
-| 0.3209        | 1.87  | 5500 | 0.3522          |
-| 0.3221        | 2.04  | 6000 | 0.3528          |
-| 0.2927        | 2.21  | 6500 | 0.3526          |
-| 0.2922        | 2.38  | 7000 | 0.3527          |
-| 0.2968        | 2.55  | 7500 | 0.3525          |
-| 0.2968        | 2.72  | 8000 | 0.3526          |
-| 0.3094        | 2.89  | 8500 | 0.3525          |
+| 0.4522        | 0.07  | 500  | 0.4533          |
+| 0.4512        | 0.14  | 1000 | 0.4301          |
+| 0.4386        | 0.21  | 1500 | 0.4199          |
+| 0.4268        | 0.28  | 2000 | 0.4144          |
+| 0.4167        | 0.35  | 2500 | 0.4104          |
+| 0.3955        | 0.42  | 3000 | 0.4092          |
+| 0.436         | 0.49  | 3500 | 0.4062          |
+| 0.3912        | 0.55  | 4000 | 0.4057          |
+| 0.425         | 0.62  | 4500 | 0.4036          |
+| 0.4066        | 0.69  | 5000 | 0.4026          |
+| 0.3963        | 0.76  | 5500 | 0.4016          |
+| 0.3862        | 0.83  | 6000 | 0.4019          |
+| 0.3902        | 0.9   | 6500 | 0.4015          |
+| 0.4364        | 0.97  | 7000 | 0.4014          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
     "o_proj",
-    "down_proj",
-    "k_proj",
-    "up_proj",
     "gate_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72cc8322717038ed30a3b43fb773df23d987343b384623f55d7f661f69356ab
-size 35668720
+oid sha256:55d4dd2d8f5dca57eb6f2d585953032833e9fb028643fdf5c2a12c0c661b190e
+size 299884176

special_tokens_map.json

@@ -1,21 +1,20 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<｜begin▁of▁sentence｜>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
-  "unk_token": {
-    "content": "<unk>",
+  "pad_token": {
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2,129 +2,39 @@
   "add_bos_token": true,
   "add_eos_token": true,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
+    "100002": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% 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 %}",
+  "bos_token": "<｜begin▁of▁sentence｜>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "legacy": false,
-  "model_max_length": 131072,
-  "pad_token": "<unk>",
-  "padding_side": "left",
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": null,
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f1163156a6e093294761f498ed7b169cc46914b0048e784e7b099836d24e5a
+oid sha256:07499305a79f43d712f931d36cda48241ab9bcdb9e62eca12ee76486978e406f
 size 4856