mistral-instruct-generation-test

README.md

@@ -0,0 +1,88 @@
+---
+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_Alpace_v2
+  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_v2
+
+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: 1.4367
+
+## 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: 250
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9894        | 0.01  | 10   | 2.0548          |
+| 1.8953        | 0.03  | 20   | 1.9843          |
+| 1.8277        | 0.04  | 30   | 1.8909          |
+| 1.7951        | 0.05  | 40   | 1.8240          |
+| 1.7125        | 0.06  | 50   | 1.7710          |
+| 1.65          | 0.08  | 60   | 1.7196          |
+| 1.6006        | 0.09  | 70   | 1.6751          |
+| 1.5773        | 0.1   | 80   | 1.6351          |
+| 1.5904        | 0.11  | 90   | 1.5976          |
+| 1.5122        | 0.13  | 100  | 1.5603          |
+| 1.4715        | 0.14  | 110  | 1.5330          |
+| 1.481         | 0.15  | 120  | 1.5132          |
+| 1.4293        | 0.16  | 130  | 1.4993          |
+| 1.4464        | 0.18  | 140  | 1.4872          |
+| 1.4326        | 0.19  | 150  | 1.4764          |
+| 1.4018        | 0.2   | 160  | 1.4674          |
+| 1.3775        | 0.21  | 170  | 1.4611          |
+| 1.4324        | 0.23  | 180  | 1.4554          |
+| 1.3947        | 0.24  | 190  | 1.4506          |
+| 1.3759        | 0.25  | 200  | 1.4467          |
+| 1.3792        | 0.26  | 210  | 1.4429          |
+| 1.3784        | 0.28  | 220  | 1.4402          |
+| 1.3762        | 0.29  | 230  | 1.4383          |
+| 1.3918        | 0.3   | 240  | 1.4371          |
+| 1.3394        | 0.31  | 250  | 1.4367          |
+
+
+### 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": [
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "lm_head",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

runs/Jan21_20-32-52_f5b5b2cfe530/events.out.tfevents.1705869183.f5b5b2cfe530.4485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42487906808854136b9a9e5f5689326abb0647dcc866b924035eda95f351a8a
+size 4867

runs/Jan21_20-56-58_f5b5b2cfe530/events.out.tfevents.1705870630.f5b5b2cfe530.13025.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2e943aedd1267c033f4e15d88817a14a81dfd0420d3a6eab054685e14b05fa
+size 4867

runs/Jan21_21-18-03_f5b5b2cfe530/events.out.tfevents.1705871884.f5b5b2cfe530.18993.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ecd6cd49b0bcfc5fcb193e4df4434982df396b789987041229f2f2d7488dec
+size 15825

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 sha256:61d475c228645c8734b8c51f5803623fa6c4b04984c7eb91d0ac76d5dbb338c5
+size 4728