LLM-Alchemy-Chamber/mistral-instruct-generation

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mixtral-8x7B-v0.1
+model-index:
+- name: Mixtral_Alpace_v3
+  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. -->
+
+# Mixtral_Alpace_v3
+
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8556
+
+## 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: 16
+- 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
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1522        | 0.03  | 10   | 1.1246          |
+| 1.0849        | 0.07  | 20   | 1.0571          |
+| 1.0144        | 0.1   | 30   | 0.9943          |
+| 0.9654        | 0.13  | 40   | 0.9525          |
+| 0.9383        | 0.16  | 50   | 0.9212          |
+| 0.8954        | 0.2   | 60   | 0.8979          |
+| 0.8671        | 0.23  | 70   | 0.8798          |
+| 0.9088        | 0.26  | 80   | 0.8664          |
+| 0.8696        | 0.3   | 90   | 0.8584          |
+| 0.8281        | 0.33  | 100  | 0.8556          |
+
+
+### Framework versions
+
+- PEFT 0.9.1.dev0
+- Transformers 4.36.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "lm_head",
+    "up_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:ef037664ff1f241c9f05dbc8529a74c4b3f73f84043e90d3ed3dab3fdf3797f5
+size 751667752

runs/Mar15_14-46-00_llm-back-project-workbench-0/events.out.tfevents.1710513961.llm-back-project-workbench-0.314.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31460eba24aed3ffb494d24a71b7fc80c600467adcabea92b6216191c4b02211
+size 4883

runs/Mar15_15-20-02_llm-back-project-workbench-0/events.out.tfevents.1710516003.llm-back-project-workbench-0.882.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a469aa0d952923ac1514932818e987b5859e348cc7d6b582a08d3898c59ec021
+size 4883

runs/Mar16_02-35-22_llm-back-project-workbench-0/events.out.tfevents.1710556522.llm-back-project-workbench-0.344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b024a57ede898026072f98eea43cd7efdc302721a6185c445f95d06c52bcdb15
+size 4883

runs/Mar16_04-08-55_llm-back-project-workbench-0/events.out.tfevents.1710562135.llm-back-project-workbench-0.138.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46eb23144126ac21d4ffa44e4209f5fa80cc5f4fdd0f165f1510dcafb3efac4
+size 4883

runs/Mar16_08-37-07_llm-back-project-workbench-0/events.out.tfevents.1710578228.llm-back-project-workbench-0.395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630f77c91b3c67761882696254b0864d05d09f9702836290ae1708059ff0bfb8
+size 9431

runs/Mar16_13-32-45_llm-back-project-workbench-0/events.out.tfevents.1710595966.llm-back-project-workbench-0.377.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39d626b2ebf408740be1b596d43e7f041b5ddafd38a5741ac5b77aa6d806c89
+size 6297

runs/Mar16_15-30-20_llm-back-project-workbench-0/events.out.tfevents.1710603021.llm-back-project-workbench-0.563.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3c39a873736048fe63f2be6d74cbc2be21be0f50ad459c68a3b81e7f857a16
+size 9431

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 +1,42 @@
+{
+  "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>",
+  "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 sha256:6bbec64aaf2fa220f49f1f4d5180dd6a7e764015a902bf93f9475b73fcce36fa
+size 4283