abhiGOAT/DPO

Browse files

Files changed (10) hide show

README.md +95 -0
adapter_config.json +27 -0
adapter_model.safetensors +3 -0
added_tokens.json +4 -0
runs/Feb14_06-57-05_4980eb37d5b1/events.out.tfevents.1707893901.4980eb37d5b1.34.0 +3 -0
special_tokens_map.json +35 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +64 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,95 @@

+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
+model-index:
+- name: mistral-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. -->
+# mistral-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: 0.7572
+- Rewards/chosen: 1.2167
+- Rewards/rejected: 1.0623
+- Rewards/accuracies: 0.5096
+- Rewards/margins: 0.1544
+- Logps/rejected: -175.8600
+- Logps/chosen: -185.2850
+- Logits/rejected: -2.4403
+- Logits/chosen: -2.5187
+## 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: 250
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.7021        | 0.0   | 10   | 0.6890          | 0.1146         | 0.0999           | 0.5192             | 0.0147          | -185.4845      | -196.3061    | -2.3759         | -2.4612       |
+| 0.6841        | 0.0   | 20   | 0.7001          | 0.0160         | 0.0098           | 0.5                | 0.0062          | -186.3854      | -197.2926    | -2.3872         | -2.4717       |
+| 0.8876        | 0.0   | 30   | 0.7302          | -0.1955        | -0.1884          | 0.5385             | -0.0071         | -188.3676      | -199.4075    | -2.4070         | -2.4917       |
+| 0.8433        | 0.0   | 40   | 0.7276          | -0.0970        | -0.0927          | 0.5288             | -0.0043         | -187.4101      | -198.4224    | -2.4156         | -2.4975       |
+| 0.8355        | 0.0   | 50   | 0.7405          | 0.3519         | 0.3619           | 0.4808             | -0.0100         | -182.8643      | -193.9333    | -2.4256         | -2.5051       |
+| 0.7391        | 0.0   | 60   | 0.7472          | 0.5734         | 0.5592           | 0.5481             | 0.0142          | -180.8914      | -191.7185    | -2.4426         | -2.5190       |
+| 0.5922        | 0.01  | 70   | 0.7534          | 0.8179         | 0.7898           | 0.5192             | 0.0281          | -178.5854      | -189.2730    | -2.4396         | -2.5167       |
+| 0.6762        | 0.01  | 80   | 0.7436          | 0.7843         | 0.7179           | 0.5385             | 0.0664          | -179.3046      | -189.6097    | -2.4306         | -2.5082       |
+| 0.5934        | 0.01  | 90   | 0.7474          | 0.8646         | 0.7935           | 0.5192             | 0.0711          | -178.5482      | -188.8059    | -2.4360         | -2.5117       |
+| 0.5773        | 0.01  | 100  | 0.7527          | 0.8864         | 0.8060           | 0.5481             | 0.0804          | -178.4233      | -188.5887    | -2.4363         | -2.5114       |
+| 1.159         | 0.01  | 110  | 0.7513          | 0.7767         | 0.6900           | 0.5385             | 0.0867          | -179.5837      | -189.6852    | -2.4325         | -2.5061       |
+| 0.5871        | 0.01  | 120  | 0.7514          | 0.6924         | 0.6190           | 0.5385             | 0.0733          | -180.2931      | -190.5286    | -2.4307         | -2.5040       |
+| 0.6655        | 0.01  | 130  | 0.7515          | 0.5617         | 0.4862           | 0.5385             | 0.0755          | -181.6214      | -191.8357    | -2.4293         | -2.5029       |
+| 0.5963        | 0.01  | 140  | 0.7489          | 0.4748         | 0.3917           | 0.5481             | 0.0831          | -182.5665      | -192.7043    | -2.4326         | -2.5072       |
+| 0.7817        | 0.01  | 150  | 0.7466          | 0.5389         | 0.4527           | 0.5288             | 0.0862          | -181.9568      | -192.0635    | -2.4306         | -2.5059       |
+| 0.7836        | 0.01  | 160  | 0.7399          | 0.5166         | 0.4148           | 0.5288             | 0.1017          | -182.3349      | -192.2867    | -2.4256         | -2.5014       |
+| 0.6246        | 0.01  | 170  | 0.7478          | 0.9222         | 0.8063           | 0.5                | 0.1159          | -178.4202      | -188.2300    | -2.4449         | -2.5218       |
+| 0.6159        | 0.01  | 180  | 0.7637          | 1.1539         | 1.0352           | 0.5                | 0.1187          | -176.1314      | -185.9132    | -2.4491         | -2.5259       |
+| 0.9218        | 0.02  | 190  | 0.7670          | 1.1914         | 1.0684           | 0.4808             | 0.1230          | -175.7993      | -185.5382    | -2.4471         | -2.5233       |
+| 0.8469        | 0.02  | 200  | 0.7670          | 1.2246         | 1.0991           | 0.5096             | 0.1255          | -175.4922      | -185.2060    | -2.4455         | -2.5220       |
+| 0.5824        | 0.02  | 210  | 0.7601          | 1.2119         | 1.0773           | 0.5096             | 0.1346          | -175.7105      | -185.3338    | -2.4418         | -2.5188       |
+| 0.5718        | 0.02  | 220  | 0.7590          | 1.2120         | 1.0736           | 0.5096             | 0.1384          | -175.7473      | -185.3322    | -2.4392         | -2.5168       |
+| 0.7219        | 0.02  | 230  | 0.7578          | 1.2033         | 1.0583           | 0.4904             | 0.1450          | -175.9007      | -185.4198    | -2.4385         | -2.5165       |
+| 2.6464        | 0.02  | 240  | 0.7570          | 1.2096         | 1.0575           | 0.5                | 0.1520          | -175.9079      | -185.3567    | -2.4392         | -2.5175       |
+| 0.8964        | 0.02  | 250  | 0.7572          | 1.2167         | 1.0623           | 0.5096             | 0.1544          | -175.8600      | -185.2850    | -2.4403         | -2.5187       |
+### Framework versions
+- PEFT 0.8.2
+- Transformers 4.37.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.1

adapter_config.json ADDED Viewed

	@@ -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": 6,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5880079c35bb58b2ec88fe21db37bb561970c0bde289d8e9a0290ed43b78c788
+size 6832600

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

runs/Feb14_06-57-05_4980eb37d5b1/events.out.tfevents.1707893901.4980eb37d5b1.34.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f29934f0dc08fed34ca7afe2212b3772c1e36a04d6dc8e6862fa4e108a3883d8
+size 40089

special_tokens_map.json ADDED Viewed

	@@ -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.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:da80bad236a74f2a70a455dbc801ee413eda02f564728639c71288f4a6528298
+size 4219