Promptengineering/mistral-instruct-generation-small

README.md

@@ -0,0 +1,65 @@
+---
+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: 1.5741
+
+## 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: 4
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.03  | 50   | 1.5982          |
+| 1.5364        | 0.06  | 100  | 1.5741          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 4,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "lm_head",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "down_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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

runs/Mar01_11-21-22_4c88f154dd36/events.out.tfevents.1709292087.4c88f154dd36.1289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4459e80f9463eaa6a39e386308044919910011df8da36ee7f2a9f34e47c099a
+size 5132

runs/Mar01_11-23-01_4c88f154dd36/events.out.tfevents.1709292201.4c88f154dd36.1289.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926375510ec9bdf99c2d542ca6f600cd23a4b325e98618e71a9a02a37f19663f
+size 5132

runs/Mar01_11-24-24_4c88f154dd36/events.out.tfevents.1709292269.4c88f154dd36.1289.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8950b589c587736829bd727ccbdecca46b3a82004f298638e9a70c16dd18691
+size 5132

runs/Mar01_11-27-47_4c88f154dd36/events.out.tfevents.1709292475.4c88f154dd36.1289.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa83b507984c91cea907eb807d252101895a82201947960e0f4fab5dc2c58fd
+size 5131

runs/Mar01_11-27-47_4c88f154dd36/events.out.tfevents.1709292496.4c88f154dd36.1289.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919d2e8ab7c5e1389f0fd37463a1ed1367a2052d16b0d1ce2dfeeb4e4921c88d
+size 10854

runs/Mar01_11-35-36_4c88f154dd36/events.out.tfevents.1709292943.4c88f154dd36.1289.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c77e747a5cf79920873746864b166a84052261abd947c5eca1fc79468e166ca
+size 5133

runs/Mar01_11-35-59_4c88f154dd36/events.out.tfevents.1709292964.4c88f154dd36.1289.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ff4000dce88be35ab01618a2f0b59d58cf8269f6de6fe242ef989b220b142a
+size 5132

runs/Mar01_11-36-17_4c88f154dd36/events.out.tfevents.1709292984.4c88f154dd36.1289.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6318dedec3b1667492071df8c39c193e79bd429ceb298dfc54210cb2bcf0ff2
+size 5132

runs/Mar01_11-38-15_4c88f154dd36/events.out.tfevents.1709293106.4c88f154dd36.1289.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c6fb25fbdd895a302623e0cc5690e0c74fa6d4a20b528b1229b081cdb80112
+size 5131

runs/Mar01_11-45-13_4c88f154dd36/events.out.tfevents.1709293522.4c88f154dd36.1289.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649ba45650b21968f6bb6c884fba4c62a53b9fb651d9a26fe6fc4743e3fa718d
+size 6220

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.model

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

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 sha256:1fa3fade9164d2c533771f15c055cbe3e9c8fdfc0c4a1611e1574285974440d4
+size 4920