enkhtogtokh/mistral-dpo

Browse files

Files changed (10) hide show

README.md +93 -0
adapter_config.json +26 -0
adapter_model.safetensors +3 -0
added_tokens.json +4 -0
runs/Jan15_08-21-38_2c69626c07f9/events.out.tfevents.1705307174.2c69626c07f9.144.0 +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 +1,93 @@

+---
+license: apache-2.0
+base_model: TheBloke/OpenHermes-2-Mistral-7B-GPTQ
+tags:
+- trl
+- dpo
+- generated_from_trainer
+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: 0.8386
+- Rewards/chosen: 1.3959
+- Rewards/rejected: 1.2944
+- Rewards/accuracies: 0.6635
+- Rewards/margins: 0.1015
+- Logps/rejected: -204.8275
+- Logps/chosen: -212.7901
+- Logits/rejected: -2.3737
+- Logits/chosen: -2.4043
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.7034        | 0.0   | 10   | 0.6881          | 0.0669         | 0.0544           | 0.6442             | 0.0125          | -217.2274      | -226.0799    | -2.3083         | -2.3446       |
+| 0.6817        | 0.0   | 20   | 0.7081          | -0.0529        | -0.0428          | 0.5096             | -0.0100         | -218.1994      | -227.2778    | -2.3270         | -2.3588       |
+| 0.8729        | 0.0   | 30   | 0.7720          | -0.3001        | -0.2331          | 0.5                | -0.0670         | -220.1020      | -229.7500    | -2.3539         | -2.3796       |
+| 0.8805        | 0.0   | 40   | 0.7841          | -0.2908        | -0.2089          | 0.4712             | -0.0819         | -219.8597      | -229.6567    | -2.3597         | -2.3866       |
+| 0.7656        | 0.0   | 50   | 0.7334          | 0.0924         | 0.1060           | 0.5288             | -0.0136         | -216.7109      | -225.8250    | -2.3542         | -2.3835       |
+| 0.7447        | 0.0   | 60   | 0.7034          | 0.4187         | 0.3651           | 0.5288             | 0.0536          | -214.1196      | -222.5618    | -2.3546         | -2.3821       |
+| 0.5761        | 0.01  | 70   | 0.6868          | 0.7922         | 0.6818           | 0.6635             | 0.1105          | -210.9534      | -218.8266    | -2.3600         | -2.3880       |
+| 0.6459        | 0.01  | 80   | 0.6960          | 0.9805         | 0.8607           | 0.6154             | 0.1198          | -209.1636      | -216.9435    | -2.3727         | -2.4040       |
+| 0.6212        | 0.01  | 90   | 0.7216          | 1.0026         | 0.9052           | 0.5962             | 0.0974          | -208.7185      | -216.7225    | -2.3769         | -2.4083       |
+| 0.5771        | 0.01  | 100  | 0.7343          | 1.2182         | 1.1107           | 0.625              | 0.1075          | -206.6636      | -214.5667    | -2.3794         | -2.4081       |
+| 1.105         | 0.01  | 110  | 0.7612          | 1.3164         | 1.2262           | 0.625              | 0.0901          | -205.5086      | -213.5851    | -2.3803         | -2.4103       |
+| 0.5704        | 0.01  | 120  | 0.7712          | 1.2350         | 1.1516           | 0.6154             | 0.0834          | -206.2548      | -214.3988    | -2.3789         | -2.4092       |
+| 0.651         | 0.01  | 130  | 0.7840          | 1.2433         | 1.1676           | 0.6058             | 0.0757          | -206.0951      | -214.3164    | -2.3799         | -2.4109       |
+| 0.5913        | 0.01  | 140  | 0.7916          | 1.1579         | 1.0827           | 0.6058             | 0.0752          | -206.9440      | -215.1704    | -2.3800         | -2.4116       |
+| 0.7816        | 0.01  | 150  | 0.7879          | 1.0975         | 1.0127           | 0.6058             | 0.0849          | -207.6444      | -215.7737    | -2.3767         | -2.4085       |
+| 0.7859        | 0.01  | 160  | 0.7833          | 0.9808         | 0.8809           | 0.6346             | 0.0999          | -208.9623      | -216.9414    | -2.3730         | -2.4050       |
+| 0.6368        | 0.01  | 170  | 0.8020          | 1.1103         | 1.0068           | 0.6538             | 0.1035          | -207.7034      | -215.6462    | -2.3739         | -2.4052       |
+| 0.7555        | 0.01  | 180  | 0.8232          | 1.3013         | 1.2030           | 0.6731             | 0.0983          | -205.7407      | -213.7359    | -2.3795         | -2.4099       |
+| 1.0436        | 0.02  | 190  | 0.8346          | 1.3330         | 1.2393           | 0.6635             | 0.0938          | -205.3784      | -213.4188    | -2.3772         | -2.4080       |
+| 0.8714        | 0.02  | 200  | 0.8394          | 1.4131         | 1.3150           | 0.6731             | 0.0980          | -204.6207      | -212.6184    | -2.3790         | -2.4098       |
+| 0.5898        | 0.02  | 210  | 0.8321          | 1.4170         | 1.3099           | 0.6731             | 0.1072          | -204.6723      | -212.5786    | -2.3751         | -2.4056       |
+| 0.5896        | 0.02  | 220  | 0.8264          | 1.4029         | 1.2923           | 0.6827             | 0.1106          | -204.8480      | -212.7195    | -2.3727         | -2.4031       |
+| 0.7008        | 0.02  | 230  | 0.8307          | 1.4009         | 1.2911           | 0.6731             | 0.1098          | -204.8596      | -212.7401    | -2.3724         | -2.4028       |
+| 2.6272        | 0.02  | 240  | 0.8366          | 1.3934         | 1.2906           | 0.6635             | 0.1028          | -204.8651      | -212.8147    | -2.3735         | -2.4039       |
+| 0.9059        | 0.02  | 250  | 0.8386          | 1.3959         | 1.2944           | 0.6635             | 0.1015          | -204.8275      | -212.7901    | -2.3737         | -2.4043       |
+### Framework versions
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "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"
+}

adapter_model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:42b1b58c214146e1ef7e4fba8f7e8372f453587e7537ae7fe1283b9fe29751ba
+size 6832600

added_tokens.json ADDED Viewed

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

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

runs/Jan15_08-21-38_2c69626c07f9/events.out.tfevents.1705307174.2c69626c07f9.144.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:321b47960c64c3b7a625d1f95eca78247dd898fccfd02f0e55e0a124bb2036e0
+size 39878

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 sha256:855d694fed9e062d72458809eb91cec0a8c065e1ae7665772773c22b3eb1c231
+size 4091