nolo99/DPO-mistral-dpo-gptq

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: openhermes-mistral-dpo-gptq
+  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. -->
+
+# openhermes-mistral-dpo-gptq
+
+This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8471
+- Rewards/chosen: -0.2589
+- Rewards/rejected: -0.1510
+- Rewards/accuracies: 0.375
+- Rewards/margins: -0.1079
+- Logps/rejected: -116.0277
+- Logps/chosen: -111.7328
+- Logits/rejected: -2.2331
+- Logits/chosen: -2.3546
+
+## 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: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6755        | 0.1   | 10   | 0.7298          | -0.0301        | -0.0035          | 0.375              | -0.0266         | -114.5520      | -109.4439    | -2.2395         | -2.3722       |
+| 0.6379        | 0.2   | 20   | 0.7804          | -0.1600        | -0.1132          | 0.375              | -0.0468         | -115.6494      | -110.7433    | -2.2341         | -2.3621       |
+| 0.7061        | 0.3   | 30   | 0.8180          | -0.2242        | -0.1463          | 0.375              | -0.0779         | -115.9803      | -111.3849    | -2.2357         | -2.3577       |
+| 0.6503        | 0.4   | 40   | 0.8460          | -0.2548        | -0.1442          | 0.375              | -0.1106         | -115.9595      | -111.6915    | -2.2330         | -2.3554       |
+| 0.9618        | 0.5   | 50   | 0.8471          | -0.2589        | -0.1510          | 0.375              | -0.1079         | -116.0277      | -111.7328    | -2.2331         | -2.3546       |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/OpenHermes-2-Mistral-7B-GPTQ",
+  "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": 8,
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abe158e2ad3998712499113705f762cd50cd5eccae26df80dcbd72ea33993a5
+size 13648432

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

runs/Feb15_23-04-33_d28669ee3e9a/events.out.tfevents.1708038425.d28669ee3e9a.164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc580efbe736cf3623fbf1b5df3a8d1b5100c05986a69c878eca855ab9c24b7
+size 12594

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "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 +1,64 @@
+{
+  "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": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3615e08fbcd891ab3692f90b13cbc03bf1aff7ac3b2df0b00b24926542e07b
+size 4155