End of training

README.md

@@ -0,0 +1,112 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- generator
+model-index:
+- name: lc_full_packing
+  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. -->
+
+# lc_full_packing
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6843
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.658         | 1.0   | 80   | 1.6224          |
+| 1.5504        | 2.0   | 160  | 1.5658          |
+| 1.5401        | 3.0   | 240  | 1.5452          |
+| 1.5012        | 4.0   | 320  | 1.5356          |
+| 1.5873        | 5.0   | 400  | 1.5318          |
+| 1.4235        | 6.0   | 480  | 1.5295          |
+| 1.4938        | 7.0   | 560  | 1.5312          |
+| 1.4809        | 8.0   | 640  | 1.5340          |
+| 1.3717        | 9.0   | 720  | 1.5361          |
+| 1.5824        | 10.0  | 800  | 1.5430          |
+| 1.4478        | 11.0  | 880  | 1.5456          |
+| 1.4124        | 12.0  | 960  | 1.5535          |
+| 1.3804        | 13.0  | 1040 | 1.5635          |
+| 1.3416        | 14.0  | 1120 | 1.5694          |
+| 1.3678        | 15.0  | 1200 | 1.5820          |
+| 1.3439        | 16.0  | 1280 | 1.5922          |
+| 1.2532        | 17.0  | 1360 | 1.6031          |
+| 1.2628        | 18.0  | 1440 | 1.5963          |
+| 1.4167        | 19.0  | 1520 | 1.6095          |
+| 1.2727        | 20.0  | 1600 | 1.6200          |
+| 1.3244        | 21.0  | 1680 | 1.6197          |
+| 1.2597        | 22.0  | 1760 | 1.6325          |
+| 1.2578        | 23.0  | 1840 | 1.6415          |
+| 1.3411        | 24.0  | 1920 | 1.6453          |
+| 1.2795        | 25.0  | 2000 | 1.6495          |
+| 1.2928        | 26.0  | 2080 | 1.6509          |
+| 1.2235        | 27.0  | 2160 | 1.6586          |
+| 1.2335        | 28.0  | 2240 | 1.6604          |
+| 1.1769        | 29.0  | 2320 | 1.6701          |
+| 1.2284        | 30.0  | 2400 | 1.6681          |
+| 1.2416        | 31.0  | 2480 | 1.6704          |
+| 1.3158        | 32.0  | 2560 | 1.6737          |
+| 1.2734        | 33.0  | 2640 | 1.6806          |
+| 1.2803        | 34.0  | 2720 | 1.6815          |
+| 1.1976        | 35.0  | 2800 | 1.6803          |
+| 1.2457        | 36.0  | 2880 | 1.6801          |
+| 1.2039        | 37.0  | 2960 | 1.6831          |
+| 1.1931        | 38.0  | 3040 | 1.6824          |
+| 1.2337        | 39.0  | 3120 | 1.6841          |
+| 1.2167        | 40.0  | 3200 | 1.6833          |
+| 1.1514        | 41.0  | 3280 | 1.6847          |
+| 1.2817        | 42.0  | 3360 | 1.6841          |
+| 1.1658        | 43.0  | 3440 | 1.6837          |
+| 1.2635        | 44.0  | 3520 | 1.6841          |
+| 1.0984        | 45.0  | 3600 | 1.6842          |
+| 1.2229        | 46.0  | 3680 | 1.6843          |
+| 1.26          | 47.0  | 3760 | 1.6840          |
+| 1.1621        | 48.0  | 3840 | 1.6844          |
+| 1.2998        | 49.0  | 3920 | 1.6848          |
+| 1.2054        | 50.0  | 4000 | 1.6843          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c5bd8a2087076e54b7a9c98de2bcaaa9b1ddbf9a8e5aeced1b5122e2e9413a
+size 109086672

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f5a66dece855889a10b77edfa2effe38f23b5822afd45bcc3170802c5a7d6c
+size 5112