Ai-Marshal/mistral_12.5k_A100_5epoch_adapter

README.md

@@ -0,0 +1,107 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+datasets:
+- generator
+model-index:
+- name: Mistral_Sentiment_Classification_2024-06-01
+  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_2024-06-01
+
+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: 0.2992
+
+## 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: 0.03
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4525        | 0.1126 | 100  | 0.3376          |
+| 0.3445        | 0.2252 | 200  | 0.3210          |
+| 0.3244        | 0.3378 | 300  | 0.3147          |
+| 0.3012        | 0.4505 | 400  | 0.3101          |
+| 0.3169        | 0.5631 | 500  | 0.3069          |
+| 0.3357        | 0.6757 | 600  | 0.3045          |
+| 0.31          | 0.7883 | 700  | 0.3027          |
+| 0.3146        | 0.9009 | 800  | 0.3008          |
+| 0.2868        | 1.0135 | 900  | 0.2988          |
+| 0.2881        | 1.1261 | 1000 | 0.2988          |
+| 0.3123        | 1.2387 | 1100 | 0.2972          |
+| 0.2796        | 1.3514 | 1200 | 0.2960          |
+| 0.2865        | 1.4640 | 1300 | 0.2943          |
+| 0.2906        | 1.5766 | 1400 | 0.2929          |
+| 0.2713        | 1.6892 | 1500 | 0.2919          |
+| 0.2751        | 1.8018 | 1600 | 0.2906          |
+| 0.2916        | 1.9144 | 1700 | 0.2895          |
+| 0.264         | 2.0270 | 1800 | 0.2917          |
+| 0.2603        | 2.1396 | 1900 | 0.2919          |
+| 0.2486        | 2.2523 | 2000 | 0.2917          |
+| 0.2583        | 2.3649 | 2100 | 0.2910          |
+| 0.2556        | 2.4775 | 2200 | 0.2905          |
+| 0.2629        | 2.5901 | 2300 | 0.2897          |
+| 0.2423        | 2.7027 | 2400 | 0.2894          |
+| 0.256         | 2.8153 | 2500 | 0.2889          |
+| 0.2664        | 2.9279 | 2600 | 0.2881          |
+| 0.2595        | 3.0405 | 2700 | 0.2933          |
+| 0.2297        | 3.1532 | 2800 | 0.2955          |
+| 0.239         | 3.2658 | 2900 | 0.2940          |
+| 0.2363        | 3.3784 | 3000 | 0.2929          |
+| 0.2295        | 3.4910 | 3100 | 0.2937          |
+| 0.2438        | 3.6036 | 3200 | 0.2923          |
+| 0.2226        | 3.7162 | 3300 | 0.2920          |
+| 0.2473        | 3.8288 | 3400 | 0.2924          |
+| 0.2314        | 3.9414 | 3500 | 0.2919          |
+| 0.2218        | 4.0541 | 3600 | 0.2985          |
+| 0.218         | 4.1667 | 3700 | 0.2994          |
+| 0.2154        | 4.2793 | 3800 | 0.2994          |
+| 0.2032        | 4.3919 | 3900 | 0.2994          |
+| 0.2234        | 4.5045 | 4000 | 0.2996          |
+| 0.224         | 4.6171 | 4100 | 0.2995          |
+| 0.1978        | 4.7297 | 4200 | 0.2997          |
+| 0.2204        | 4.8423 | 4300 | 0.3000          |
+| 0.2114        | 4.9550 | 4400 | 0.2992          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- 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": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_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:f0804dd92ca1bb693ef7d4e6b9ab27a018064414290911a1aa7d45f03afc71a3
+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 +1,43 @@
+{
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5783ee5ca1c5b21ca78c71c0b75a31543d69694eae7b7a03b29bb766f26e48f
+size 5112