ai-maker-space/mistral-instruct-generation

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-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/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3338
+
+## 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4954        | 0.0   | 20   | 1.3620          |
+| 1.4476        | 0.01  | 40   | 1.3493          |
+| 1.4787        | 0.01  | 60   | 1.3418          |
+| 1.4646        | 0.02  | 80   | 1.3396          |
+| 1.4857        | 0.02  | 100  | 1.3338          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a382a26afbda1c48bf3c19537e7aeea175f7323b8c26e9b3a0c393ba100959
+size 109069176

runs/Dec15_23-33-32_b412f39db13d/events.out.tfevents.1702683239.b412f39db13d.568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca9601d50602703c7ffbc433e2740fd60f213781e761ba9308802053fc3c6b7
+size 4783

runs/Dec15_23-37-04_b412f39db13d/events.out.tfevents.1702683433.b412f39db13d.568.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f076c89a275214b96c3aeb55b9870c0ed5e53f6bf23dfcc28b49ec20d1553e1
+size 4782

runs/Dec15_23-37-47_b412f39db13d/events.out.tfevents.1702683476.b412f39db13d.568.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7645e6909c262bb8485ee94280e7d72964e3827adbbe1127e1d5cc0fb22826f
+size 4783

runs/Dec15_23-42-30_b412f39db13d/events.out.tfevents.1702683759.b412f39db13d.568.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaa5d20149e5e46ebd6ea658e34e2b68e2ffe3aa2b350f05f402c049c50e930
+size 5091

runs/Dec15_23-44-23_b412f39db13d/events.out.tfevents.1702683869.b412f39db13d.568.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eac0e9528e24f50837b47edc5d1c68deae48ccfe1d8255829a11f7af42734b4
+size 5091

runs/Dec15_23-47-00_b412f39db13d/events.out.tfevents.1702684033.b412f39db13d.568.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0e67f338ba482431744b4e164ebb3e09d9481ccfe209fd0917a79392d06182
+size 5090

runs/Dec15_23-48-40_b412f39db13d/events.out.tfevents.1702684128.b412f39db13d.568.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc3006df15ce9c673fc4228033d6e8300b0b07d5729c867b3a88540a2a9ae45
+size 8001

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 sha256:724805ed4a95b009197108879cb9600e2247aa6f40849f94804451976ce2dc4c
+size 4728