sft_model_rlaif

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-alpha
+tags:
+- generated_from_trainer
+model-index:
+- name: sft_zephyr
+  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. -->
+
+# sft_zephyr
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) on an unknown dataset.
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-alpha",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d038325d8d2f6680ee8c9302ec74107cca8a185bbecfd421cd6fc7017639eba0
+size 109069176

runs/Nov21_23-50-46_9bb2bbaa3c9b/events.out.tfevents.1700610657.9bb2bbaa3c9b.4368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08793b80322af7420f462c536cf634d07713bbcbb927bf5d64e9b4e35c8b3df
+size 4575

runs/Nov21_23-51-56_9bb2bbaa3c9b/events.out.tfevents.1700610719.9bb2bbaa3c9b.4368.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69fdda01ea88132136aef03b494db23e8530bf80351fe268b0bab2a7f6f4d07
+size 4572

runs/Nov21_23-52-45_9bb2bbaa3c9b/events.out.tfevents.1700610768.9bb2bbaa3c9b.4368.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eded8943930ffd2b476d1d33608e954feb300280d96ffdff6a3568d6a67e13f
+size 4572

runs/Nov21_23-52-57_9bb2bbaa3c9b/events.out.tfevents.1700610797.9bb2bbaa3c9b.4368.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020f56f3ce6ef1c0f717e5f9fdaeed56174b5c96035a5a72186a936393af9ce8
+size 4572

runs/Nov21_23-54-23_9bb2bbaa3c9b/events.out.tfevents.1700610865.9bb2bbaa3c9b.4368.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e925d0764e952b919ab157f26721fd550314ff17504863f8db19052f93180057
+size 4572

runs/Nov21_23-55-22_9bb2bbaa3c9b/events.out.tfevents.1700610925.9bb2bbaa3c9b.4368.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f683df3babf148248ba86fc0012ae0c5f41f450d5a956c8a71c7a4b74ffe760
+size 4572

runs/Nov21_23-55-43_9bb2bbaa3c9b/events.out.tfevents.1700610945.9bb2bbaa3c9b.4368.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330aa0d3e8e6f8ea3b0c27ce1eb8ad4a487d1625ca94de13cbf747e1ed40bbb0
+size 4573

runs/Nov21_23-57-33_9bb2bbaa3c9b/events.out.tfevents.1700611056.9bb2bbaa3c9b.4368.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8646712a6320f1407d08f31d18dda4cbbcc81b3d1cfd3ad24df7288137e89802
+size 4184

runs/Nov22_00-03-45_9bb2bbaa3c9b/events.out.tfevents.1700611428.9bb2bbaa3c9b.27232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd81416c5a7625280ecf9254d102360f030af4511210ad8881425e7b385060fe
+size 4184

runs/Nov22_00-04-44_9bb2bbaa3c9b/events.out.tfevents.1700611487.9bb2bbaa3c9b.27232.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233f7c72663a7db01ad209269f29909a2a9f5438d13531206a7e9749b9618094
+size 4184

runs/Nov22_00-12-42_9bb2bbaa3c9b/events.out.tfevents.1700611965.9bb2bbaa3c9b.30686.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76cecf3a46a24375cf863ec07a871d4b5693594dfc7d14e44a63263a544d091a
+size 4922

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": "</s>",
+    "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_config.json

@@ -0,0 +1,46 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095fc8eb570c7821109b5b43891161aeeef89ce935874d90a044aba098bf50f7
+size 4600