joedonino/zephyr-7b-radia-html-events-v8

README.md

@@ -0,0 +1,100 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-beta
+tags:
+- generated_from_trainer
+model-index:
+- name: models
+  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. -->
+
+# models
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7368
+
+## 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: 0.0004
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 40
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9828        | 0.02  | 1    | 1.0330          |
+| 1.1538        | 0.03  | 2    | 1.0256          |
+| 0.9734        | 0.05  | 3    | 1.0120          |
+| 1.0574        | 0.07  | 4    | 0.9942          |
+| 0.9797        | 0.09  | 5    | 0.9755          |
+| 0.9399        | 0.1   | 6    | 0.9580          |
+| 1.0294        | 0.12  | 7    | 0.9434          |
+| 0.7965        | 0.14  | 8    | 0.9318          |
+| 0.7741        | 0.16  | 9    | 0.9236          |
+| 0.8252        | 0.17  | 10   | 0.9178          |
+| 0.8478        | 0.19  | 11   | 0.9135          |
+| 0.9641        | 0.21  | 12   | 0.9068          |
+| 0.9073        | 0.22  | 13   | 0.8980          |
+| 0.9682        | 0.24  | 14   | 0.8877          |
+| 0.8794        | 0.26  | 15   | 0.8774          |
+| 0.7602        | 0.28  | 16   | 0.8690          |
+| 0.9019        | 0.29  | 17   | 0.8611          |
+| 0.8619        | 0.31  | 18   | 0.8547          |
+| 0.8195        | 0.33  | 19   | 0.8484          |
+| 0.9562        | 0.34  | 20   | 0.8418          |
+| 0.7822        | 0.36  | 21   | 0.8366          |
+| 0.767         | 0.38  | 22   | 0.8308          |
+| 0.9024        | 0.4   | 23   | 0.8242          |
+| 0.8596        | 0.41  | 24   | 0.8183          |
+| 0.8424        | 0.43  | 25   | 0.8123          |
+| 0.7396        | 0.45  | 26   | 0.8059          |
+| 0.7742        | 0.47  | 27   | 0.7999          |
+| 0.7007        | 0.48  | 28   | 0.7943          |
+| 0.6915        | 0.5   | 29   | 0.7890          |
+| 0.7054        | 0.52  | 30   | 0.7836          |
+| 0.7622        | 0.53  | 31   | 0.7785          |
+| 0.6493        | 0.55  | 32   | 0.7720          |
+| 0.6106        | 0.57  | 33   | 0.7650          |
+| 0.7534        | 0.59  | 34   | 0.7583          |
+| 0.7065        | 0.6   | 35   | 0.7532          |
+| 0.8823        | 0.62  | 36   | 0.7472          |
+| 0.7082        | 0.64  | 37   | 0.7424          |
+| 0.7292        | 0.66  | 38   | 0.7405          |
+| 0.8142        | 0.67  | 39   | 0.7390          |
+| 0.6079        | 0.69  | 40   | 0.7368          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- 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-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 256,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "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:ff7dce7132c891ffbe67bab4637150f2060c2ee2c36a99daf0878768bbdd3866
+size 218121344

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "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": "</s>",
+  "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 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "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>",
+  "padding_side": "left",
+  "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 sha256:35c74119243eb67b7f4f38ac8ec07c8db0cbe159c5478dd6e0b3865b874c05b6
+size 4664