SharedGPT/mistral-generate-instruction

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: mistralai/Mixtral-8x7B-v0.1
+model-index:
+- name: Mixtral_dolly_reverse_Inst
+  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_dolly_reverse_Inst
+
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4407
+
+## 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: 32
+- 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8058        | 0.05  | 10   | 1.9081          |
+| 1.7565        | 0.1   | 20   | 1.8383          |
+| 1.7155        | 0.15  | 30   | 1.7551          |
+| 1.6477        | 0.2   | 40   | 1.7002          |
+| 1.5887        | 0.25  | 50   | 1.6647          |
+| 1.5521        | 0.3   | 60   | 1.6351          |
+| 1.5184        | 0.35  | 70   | 1.6105          |
+| 1.5338        | 0.4   | 80   | 1.5860          |
+| 1.4718        | 0.45  | 90   | 1.5600          |
+| 1.4739        | 0.5   | 100  | 1.5341          |
+| 1.4525        | 0.55  | 110  | 1.5110          |
+| 1.4125        | 0.6   | 120  | 1.4896          |
+| 1.4118        | 0.65  | 130  | 1.4735          |
+| 1.3921        | 0.7   | 140  | 1.4631          |
+| 1.3861        | 0.75  | 150  | 1.4553          |
+| 1.3765        | 0.8   | 160  | 1.4497          |
+| 1.3664        | 0.85  | 170  | 1.4460          |
+| 1.3783        | 0.9   | 180  | 1.4429          |
+| 1.3544        | 0.95  | 190  | 1.4413          |
+| 1.3743        | 1.0   | 200  | 1.4407          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "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": [
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "lm_head",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48bf361f5bfe4227d7ca8008d2d118485e003bcdfd5e05062cb5b5d0e255ee5b
+size 751667752

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 sha256:7951fbb1dbfc5825204e977ef87951f6b2929ac268feff7de7e291d84a806194
+size 4728