gemma2B-Medical-Finetune-test-2epochs

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
+license: other
 library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
-base_model: alexsherstinsky/Mistral-7B-v0.1-sharded
+base_model: google/gemma-2b-it
 model-index:
 - name: outputs
   results: []
@@ -14,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [alexsherstinsky/Mistral-7B-v0.1-sharded](https://huggingface.co/alexsherstinsky/Mistral-7B-v0.1-sharded) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5527
+This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
 
 ## Model description
 
@@ -35,30 +35,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2
-- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.6694        | 0.59  | 50   | 0.6315          |
-| 0.5594        | 1.18  | 100  | 0.5652          |
-| 0.5449        | 1.77  | 150  | 0.5527          |
 
 
 ### Framework versions
 
 - PEFT 0.8.2
-- Transformers 4.38.0.dev0
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Transformers 4.38.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
+  "base_model_name_or_path": "google/gemma-2b-it",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -15,16 +15,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "k_proj",
-    "gate_proj",
+    "down_proj",
     "q_proj",
     "up_proj",
+    "gate_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:373c1740a4ebeecd9a64a117520268f80d09c0019263148af0c840262915662a
-size 167832240
+oid sha256:934c9dc96cbcbdf7a0291059d54fad03ea27608fa06c284ed0be9e650bc1b8c3
+size 156926880

runs/Mar17_13-32-52_3ac06cdcb29d/events.out.tfevents.1710682377.3ac06cdcb29d.351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e51b55fcd42ce600d442a6957c2015141e233ea9bc8d2136a42b8d167bf0505
+size 10579

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce19157ce6b457736a0015a2a4fb06c966c6ff252ec9d1950777eec6598abf6d
+size 17478028

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e18a7b207f7d9ac514a5fa0cfd341351e677d4b43925275ac6bd867267f3d4
-size 4728
+oid sha256:77c7ac08fea4403b0d9beed0ef5095552d19edd85f199fb8f60683b4c33202f6
+size 4920