Fawazzx/Saul-instruct-1keg

README.md

@@ -1,9 +1,10 @@
 ---
-license: mit
 library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
-base_model: Equall/Saul-Instruct-v1
+base_model: Fawazzx/Saul-Instruct-v1_sharded
 model-index:
 - name: outputs
   results: []
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1) on an unknown dataset.
+This model is a fine-tuned version of [Fawazzx/Saul-Instruct-v1_sharded](https://huggingface.co/Fawazzx/Saul-Instruct-v1_sharded) on an unknown dataset.
 
 ## Model description
 
@@ -35,14 +36,14 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
 - train_batch_size: 2
-- eval_batch_size: 16
-- seed: 42
+- eval_batch_size: 8
+- seed: 3407
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2
-- training_steps: 10
+- lr_scheduler_warmup_steps: 5
+- training_steps: 120
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -52,7 +53,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.39.3
+- Transformers 4.40.1
 - Pytorch 2.1.0+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Equall/Saul-Instruct-v1",
+  "base_model_name_or_path": "Fawazzx/Saul-Instruct-v1_sharded",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56bc6b96d763fc80988d7699cb8ea6074760efaf320e36808accaca3f5f134a5
+oid sha256:11be58aec1d77fbaf3367ce4dd15c35908c7cd3ddb5cc10651d033d952be590e
 size 8397056

runs/May03_17-58-30_e5ac710b52d5/events.out.tfevents.1714759132.e5ac710b52d5.6044.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fb1f21f0e390eedbde2682ef7be357b7f864db6542b643c0732871989af160
+size 30315

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47263fcc9a2a58db48d3b5b4f8c2b9b0f2dee6f4168d928e7b68327d816a9f15
-size 4920
+oid sha256:39b32405be8744502090c652a562d08e4b88758c84e0279be0d6ed5e939e83db
+size 4984