Ai-Marshal/mistral_12.5k_A100_5epoch_adapter

README.md

@@ -0,0 +1,87 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+datasets:
+- generator
+library_name: peft
+license: apache-2.0
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Mistral_Sentiment_Classification_2024-08-19
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Mistral_Sentiment_Classification_2024-08-19
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1144
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2.5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.1264        | 0.2048 | 500   | 0.1188          |
+| 0.1096        | 0.4097 | 1000  | 0.1146          |
+| 0.1289        | 0.6145 | 1500  | 0.1123          |
+| 0.1089        | 0.8193 | 2000  | 0.1106          |
+| 0.1218        | 1.0242 | 2500  | 0.1083          |
+| 0.0987        | 1.2290 | 3000  | 0.1079          |
+| 0.1074        | 1.4338 | 3500  | 0.1069          |
+| 0.0906        | 1.6387 | 4000  | 0.1062          |
+| 0.1094        | 1.8435 | 4500  | 0.1053          |
+| 0.0951        | 2.0483 | 5000  | 0.1068          |
+| 0.1           | 2.2532 | 5500  | 0.1068          |
+| 0.0799        | 2.4580 | 6000  | 0.1062          |
+| 0.0767        | 2.6628 | 6500  | 0.1058          |
+| 0.1046        | 2.8677 | 7000  | 0.1054          |
+| 0.0727        | 3.0725 | 7500  | 0.1091          |
+| 0.0737        | 3.2773 | 8000  | 0.1092          |
+| 0.0967        | 3.4822 | 8500  | 0.1092          |
+| 0.0726        | 3.6870 | 9000  | 0.1091          |
+| 0.0909        | 3.8918 | 9500  | 0.1085          |
+| 0.074         | 4.0967 | 10000 | 0.1141          |
+| 0.0777        | 4.3015 | 10500 | 0.1143          |
+| 0.0695        | 4.5063 | 11000 | 0.1145          |
+| 0.0604        | 4.7112 | 11500 | 0.1142          |
+| 0.0612        | 4.9160 | 12000 | 0.1144          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595448a5f9d1c9a111b3b9b1f41edaea600c08b32210ab00c0b9e3ba68fa1e12
+size 671149168

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_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3f310a9a600c3100b01d881ffa1f459f1870ee1918f12a3872f7fa506657e3
+size 5432