jamesliu23/openhermes-mistral-gptq-dpo

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
+tags:
+- generated_from_trainer
+model-index:
+- name: openhermes-mistral-gptq-dpo
+  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-gptq-dpo
+
+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: 0.8689
+- Rewards/chosen: -1.0765
+- Rewards/rejected: -0.9664
+- Rewards/accuracies: 0.4800
+- Rewards/margins: -0.1101
+- Logps/rejected: -139.8855
+- Logps/chosen: -135.5758
+- Logits/rejected: -2.2110
+- Logits/chosen: -2.2313
+
+## 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: 0.0003
+- 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
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6842        | 0.01  | 10   | 0.7768          | -0.4985        | -0.4411          | 0.5750             | -0.0574         | -134.6327      | -129.7961    | -2.2478         | -2.2667       |
+| 0.8539        | 0.02  | 20   | 2.0287          | -9.4492        | -8.7234          | 0.4800             | -0.7258         | -217.4559      | -219.3030    | -1.5781         | -1.5859       |
+| 0.9433        | 0.03  | 30   | 1.6915          | -7.3191        | -6.8845          | 0.5                | -0.4346         | -199.0667      | -198.0014    | -1.6865         | -1.6973       |
+| 0.6295        | 0.04  | 40   | 0.9729          | -1.6986        | -1.5214          | 0.5200             | -0.1772         | -145.4362      | -141.7968    | -2.1859         | -2.2057       |
+| 0.8681        | 0.05  | 50   | 0.8689          | -1.0765        | -0.9664          | 0.4800             | -0.1101         | -139.8855      | -135.5758    | -2.2110         | -2.2313       |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "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,
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283347dc17611be501dbb65b559d29c75bf84a37adaf3d20abccfcb41715dc76
+size 6861962

added_tokens.json

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

emissions.csv

@@ -0,0 +1,3 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2023-11-09T06:37:17,codecarbon,099668be-6d86-4a98-a229-f321fd327ec7,375.4025270938873,0.0079922137553183,2.1289717512528927e-05,82.5,222.151,47.05446195602417,0.0086026503706971,0.0254286187869067,0.0049040212218882,0.0389352903794922,United States,USA,california,,,Linux-5.4.0-166-generic-x86_64-with-glibc2.31,3.11.3,2.2.3,20,Intel(R) Core(TM) i9-9820X CPU @ 3.30GHz,1,1 x NVIDIA GeForce RTX 2080 Ti,-121.8595,37.374,125.47856521606444,machine,N,1.0
+2023-11-09T07:04:14,codecarbon,daefa877-7165-45e1-82b7-9eb53d8c4deb,373.4955837726593,0.00797799572814249,2.1360348220338173e-05,82.5,214.47400000000002,47.05446195602417,0.008558964617053667,0.025427699463984564,0.0048793610068009275,0.03886602508783918,United States,USA,california,,,Linux-5.4.0-166-generic-x86_64-with-glibc2.31,3.11.3,2.2.3,20,Intel(R) Core(TM) i9-9820X CPU @ 3.30GHz,1,1 x NVIDIA GeForce RTX 2080 Ti,-121.8595,37.374,125.47856521606445,machine,N,1.0

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:cbad7e9be1b578380f26069d8e96865b1944c733e5b1c7055f092482d0ef8d41
+size 4536