Promptengineering/mistral-instruct-generation

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mixtral-8x7B-v0.1
+model-index:
+- name: mistral_instruct_generation
+  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_instruct_generation
+
+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: 0.7326
+
+## 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: 0.0002
+- 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: constant
+- lr_scheduler_warmup_steps: 0.03
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6174        | 0.0078 | 20   | 0.7952          |
+| 0.7153        | 0.0156 | 40   | 0.7565          |
+| 0.7903        | 0.0235 | 60   | 0.7447          |
+| 0.7175        | 0.0313 | 80   | 0.7377          |
+| 0.7081        | 0.0391 | 100  | 0.7326          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "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",
+    "o_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:a5090272f6ba0b7f747174386ffb351afc624af84845e4dc526571735720d96b
+size 218138576

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

runs/Apr20_18-35-11_8124952fcca7/events.out.tfevents.1713638128.8124952fcca7.985.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36dc6efc1fea5268c623e2106ce41613869a34b0b5cc816c2868b2ca8d9a1b3c
+size 18709

runs/Apr20_18-35-11_8124952fcca7/events.out.tfevents.1713639124.8124952fcca7.985.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad2d137aa224ece31a7e11598897789e39eb30ada738b1af882339b3af1343d
+size 5753

runs/Apr20_18-53-31_8124952fcca7/events.out.tfevents.1713639218.8124952fcca7.985.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb11bca21e8579051a4877553d22670c50950ff5c56a1e764003f7b8db120f8
+size 5753

runs/Apr20_18-56-02_8124952fcca7/events.out.tfevents.1713639371.8124952fcca7.985.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186b5099555dd739191d8480a6f76a250f12ca24b4629ff6e5cb3557a694e5b6
+size 10998

runs/Apr20_18-59-02_8124952fcca7/events.out.tfevents.1713639547.8124952fcca7.985.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2096b13eeb60080382ca8bd3b2bbd10b5ddb133a6b4e247c630c20f30ddccd55
+size 14752

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "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.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "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": "[PAD]",
+  "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:f00aaf31f79a6a347952262466011af816c2b3f4dbdc6f1cbae28f7ce096457c
+size 5048