End of training

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: Paper_Imp_Data_Augmented_1
+  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. -->
+
+# Paper_Imp_Data_Augmented_1
+
+This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8094
+
+## 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: cosine
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.0944        | 0.08  | 30   | 1.6167          |
+| 1.5308        | 0.16  | 60   | 1.0254          |
+| 0.9718        | 0.23  | 90   | 0.8645          |
+| 1.0394        | 0.31  | 120  | 0.8575          |
+| 0.9591        | 0.39  | 150  | 0.8520          |
+| 0.7642        | 0.47  | 180  | 0.8452          |
+| 0.7454        | 0.54  | 210  | 0.8407          |
+| 0.7823        | 0.62  | 240  | 0.8461          |
+| 0.8669        | 0.7   | 270  | 0.8369          |
+| 0.8827        | 0.78  | 300  | 0.8305          |
+| 0.7243        | 0.85  | 330  | 0.8267          |
+| 0.9427        | 0.93  | 360  | 0.8180          |
+| 0.7446        | 1.01  | 390  | 0.8181          |
+| 0.6774        | 1.09  | 420  | 0.8248          |
+| 0.7981        | 1.16  | 450  | 0.8191          |
+| 0.868         | 1.24  | 480  | 0.8147          |
+| 0.7947        | 1.32  | 510  | 0.8140          |
+| 0.7324        | 1.4   | 540  | 0.8122          |
+| 0.8008        | 1.47  | 570  | 0.8114          |
+| 0.749         | 1.55  | 600  | 0.8114          |
+| 0.8133        | 1.63  | 630  | 0.8113          |
+| 0.7606        | 1.71  | 660  | 0.8118          |
+| 0.7209        | 1.78  | 690  | 0.8103          |
+| 0.7236        | 1.86  | 720  | 0.8096          |
+| 0.6766        | 1.94  | 750  | 0.8094          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "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,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.7,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "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:ef7d09420f1575fdf1a1ffc31f68744075e7a60e83f1075e47c5b9f6ad640150
+size 37774528

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

runs/Jan10_21-49-46_49362e16fc35/events.out.tfevents.1704923387.49362e16fc35.1589.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667ca32d79c93e605ae0cf3f5b3e6695075f2562c421b472596e869a454b5c34
+size 7241

runs/Jan10_21-52-13_49362e16fc35/events.out.tfevents.1704923534.49362e16fc35.1589.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0189a0fecfd3c2374e5047990a62a58a1c2b177e3d94c8c4e0fa69622f4d83c
+size 4931

runs/Jan10_21-52-29_49362e16fc35/events.out.tfevents.1704923550.49362e16fc35.1589.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79f473b5154aa5890488c0c85cffc1e1eb7f17835483cf5659c48202aac703d
+size 4931

runs/Jan10_21-56-29_49362e16fc35/events.out.tfevents.1704923790.49362e16fc35.5455.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e041f71c9df7d35807dff9ae73329a6e4b2ee256aa1a826f7d26f09abd78a86
+size 33612

runs/Jan10_22-06-35_49362e16fc35/events.out.tfevents.1704924396.49362e16fc35.5455.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a38cf759fcb766585d3aed7020eeb3f3f2583a443bade2d1b4d760bf9221c4
+size 4777

runs/Jan10_22-08-26_49362e16fc35/events.out.tfevents.1704924507.49362e16fc35.9413.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d325e17ac0ea64f1bd6344ecb3a90943a58c23c59cee767133f91a2bccf9eb7
+size 17126

runs/Jan10_22-17-27_49362e16fc35/events.out.tfevents.1704925049.49362e16fc35.11882.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f7233d12b7d2c17794e1d0b483aae50401e6db8c6954e7a4d225af4082bc52
+size 24559

runs/Jan10_22-28-32_49362e16fc35/events.out.tfevents.1704925713.49362e16fc35.14845.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadf81dc3c14eda2c2dd8bbbf969650c9297b6f2091d5108dfe58e7e5bef5838
+size 11167

runs/Jan10_22-34-09_49362e16fc35/events.out.tfevents.1704926050.49362e16fc35.16484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626658fec29ad821d05aa72552520283dfd151936a4aa4605c6be1518d4ae177
+size 12023

runs/Jan10_22-43-27_49362e16fc35/events.out.tfevents.1704926608.49362e16fc35.19010.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6b801facb12cd19e220e00f587362d0abbe30268437765a66c2f039643e94b
+size 15822

special_tokens_map.json

@@ -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": "<|im_end|>",
+  "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 +1,61 @@
+{
+  "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": "<|im_end|>",
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc30dfabeb312ce988d7c48d71ae76816f76c1c8a5010e442f40a3a23ae73154
+size 4728