voxmenthe/openhermes-mistral-2.5-7b-dpo-test

Browse files

Files changed (9) hide show

README.md +85 -0
adapter_config.json +23 -0
adapter_model.bin +3 -0
added_tokens.json +4 -0
special_tokens_map.json +24 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +61 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,85 @@

+---
+license: apache-2.0
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: openhermes-mistral-2.5-7b-dpo-test
+  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-2.5-7b-dpo-test
+This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4487
+- Rewards/chosen: -0.2951
+- Rewards/rejected: -2.2421
+- Rewards/accuracies: 0.875
+- Rewards/margins: 1.9470
+- Logps/rejected: -257.4751
+- Logps/chosen: -204.3027
+- Logits/rejected: -3.0752
+- Logits/chosen: -3.0485
+## 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: 0.0001
+- 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: 200
+### Training results
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.1645        | 0.01  | 10   | 0.5339          | 0.3993         | -0.1483          | 0.6875             | 0.5476          | -236.5374      | -197.3593    | -3.1575         | -3.1872       |
+| 0.0519        | 0.01  | 20   | 0.5521          | 0.2239         | -0.4486          | 0.625              | 0.6725          | -239.5405      | -199.1127    | -3.1969         | -3.2456       |
+| 0.1618        | 0.01  | 30   | 0.5866          | -0.0538        | -0.8893          | 0.5625             | 0.8355          | -243.9472      | -201.8902    | -3.2286         | -3.2525       |
+| 0.1752        | 0.02  | 40   | 0.5943          | -0.2184        | -1.2057          | 0.5                | 0.9873          | -247.1112      | -203.5360    | -3.2201         | -3.2477       |
+| 0.3811        | 0.03  | 50   | 0.6973          | -0.6180        | -1.8146          | 0.5                | 1.1966          | -253.2001      | -207.5316    | -3.1943         | -3.2034       |
+| 1.158         | 0.03  | 60   | 0.6347          | -0.4710        | -1.7363          | 0.5625             | 1.2653          | -252.4173      | -206.0622    | -3.1655         | -3.1197       |
+| 0.8751        | 0.04  | 70   | 0.6103          | -0.4061        | -1.5966          | 0.5625             | 1.1905          | -251.0201      | -205.4132    | -3.1360         | -3.0544       |
+| 0.7811        | 0.04  | 80   | 0.6405          | -0.4774        | -1.6574          | 0.5625             | 1.1799          | -251.6278      | -206.1260    | -3.1337         | -3.0492       |
+| 1.4305        | 0.04  | 90   | 0.6257          | -0.4784        | -1.6184          | 0.5625             | 1.1399          | -251.2379      | -206.1361    | -3.1251         | -3.0489       |
+| 0.5478        | 0.05  | 100  | 0.6191          | -0.5317        | -1.7067          | 0.5625             | 1.1750          | -252.1214      | -206.6691    | -3.1207         | -3.0753       |
+| 0.6344        | 0.06  | 110  | 0.5691          | -0.4827        | -1.7734          | 0.5625             | 1.2907          | -252.7882      | -206.1789    | -3.1075         | -3.0806       |
+| 0.5405        | 0.06  | 120  | 0.5337          | -0.4681        | -2.1739          | 0.8125             | 1.7058          | -256.7935      | -206.0332    | -3.1124         | -3.0733       |
+| 0.7848        | 0.07  | 130  | 0.5390          | -0.5288        | -2.3789          | 0.8125             | 1.8501          | -258.8436      | -206.6404    | -3.1019         | -3.0628       |
+| 1.3119        | 0.07  | 140  | 0.4753          | -0.3276        | -2.0907          | 0.875              | 1.7631          | -255.9614      | -204.6279    | -3.0904         | -3.0648       |
+| 0.3636        | 0.07  | 150  | 0.4555          | -0.2566        | -2.0064          | 0.625              | 1.7498          | -255.1179      | -203.9175    | -3.0804         | -3.0640       |
+| 0.427         | 0.08  | 160  | 0.4614          | -0.2900        | -2.0804          | 0.625              | 1.7904          | -255.8585      | -204.2518    | -3.0721         | -3.0518       |
+| 0.8971        | 0.09  | 170  | 0.4629          | -0.3117        | -2.1791          | 0.875              | 1.8673          | -256.8448      | -204.4694    | -3.0711         | -3.0468       |
+| 0.6219        | 0.09  | 180  | 0.4560          | -0.3042        | -2.2114          | 0.875              | 1.9073          | -257.1686      | -204.3934    | -3.0743         | -3.0485       |
+| 0.7551        | 0.1   | 190  | 0.4520          | -0.3007        | -2.2400          | 0.875              | 1.9392          | -257.4540      | -204.3593    | -3.0755         | -3.0481       |
+| 1.0917        | 0.1   | 200  | 0.4487          | -0.2951        | -2.2421          | 0.875              | 1.9470          | -257.4751      | -204.3027    | -3.0752         | -3.0485       |
+### Framework versions
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json ADDED Viewed

	@@ -0,0 +1,23 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e356ff3e1a0ab39bca8d63c1843b13ebc27babc235a79da70b276ae2b2300e
+size 13677706

added_tokens.json ADDED Viewed

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

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

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "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": "<unk>",
+  "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 +1,61 @@

+{
+  "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": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "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:ab7e13067d162f501ad67cc1bdb77957c23b3656408857a6f1ce53bafc6018af
+size 4536