Training in progress, step 100

README.md

@@ -0,0 +1,124 @@
+---
+license: other
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: taide/TAIDE-LX-7B-Chat
+model-index:
+- name: ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V5
+  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. -->
+
+# ROE_QA_TAIDE-LX-7B-Chat_Q100_80_20_V5
+
+This model is a fine-tuned version of [taide/TAIDE-LX-7B-Chat](https://huggingface.co/taide/TAIDE-LX-7B-Chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3726
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.8629        | 0.0321 | 100  | 3.4698          |
+| 4.6474        | 0.0643 | 200  | 3.2343          |
+| 3.8261        | 0.0964 | 300  | 2.8205          |
+| 3.2992        | 0.1285 | 400  | 2.5034          |
+| 2.9369        | 0.1607 | 500  | 2.2639          |
+| 2.2674        | 0.1928 | 600  | 1.9493          |
+| 2.1393        | 0.2249 | 700  | 1.7888          |
+| 1.8195        | 0.2571 | 800  | 1.6285          |
+| 1.678         | 0.2892 | 900  | 1.4983          |
+| 1.6242        | 0.3213 | 1000 | 1.4013          |
+| 1.344         | 0.3535 | 1100 | 1.1522          |
+| 1.0894        | 0.3856 | 1200 | 1.0704          |
+| 1.2033        | 0.4177 | 1300 | 1.0537          |
+| 0.9503        | 0.4499 | 1400 | 0.9160          |
+| 0.9901        | 0.4820 | 1500 | 0.8751          |
+| 1.0363        | 0.5141 | 1600 | 0.7942          |
+| 0.9986        | 0.5463 | 1700 | 0.7668          |
+| 0.9407        | 0.5784 | 1800 | 0.6912          |
+| 0.9347        | 0.6105 | 1900 | 0.6543          |
+| 0.8109        | 0.6427 | 2000 | 0.6498          |
+| 0.8848        | 0.6748 | 2100 | 0.6077          |
+| 0.8937        | 0.7069 | 2200 | 0.5865          |
+| 0.7895        | 0.7391 | 2300 | 0.5780          |
+| 0.8044        | 0.7712 | 2400 | 0.5646          |
+| 0.8317        | 0.8033 | 2500 | 0.5449          |
+| 0.858         | 0.8355 | 2600 | 0.5132          |
+| 0.8519        | 0.8676 | 2700 | 0.4940          |
+| 0.7554        | 0.8997 | 2800 | 0.4972          |
+| 0.758         | 0.9319 | 2900 | 0.4809          |
+| 0.8866        | 0.9640 | 3000 | 0.4714          |
+| 0.7028        | 0.9961 | 3100 | 0.4608          |
+| 0.7031        | 1.0283 | 3200 | 0.4458          |
+| 0.6623        | 1.0604 | 3300 | 0.4427          |
+| 0.671         | 1.0925 | 3400 | 0.4366          |
+| 0.6588        | 1.1247 | 3500 | 0.4327          |
+| 0.6422        | 1.1568 | 3600 | 0.4239          |
+| 0.643         | 1.1889 | 3700 | 0.4235          |
+| 0.6747        | 1.2211 | 3800 | 0.4204          |
+| 0.6911        | 1.2532 | 3900 | 0.4130          |
+| 0.7354        | 1.2853 | 4000 | 0.4092          |
+| 0.6233        | 1.3175 | 4100 | 0.4070          |
+| 0.6005        | 1.3496 | 4200 | 0.4055          |
+| 0.624         | 1.3817 | 4300 | 0.4033          |
+| 0.623         | 1.4139 | 4400 | 0.3976          |
+| 0.6419        | 1.4460 | 4500 | 0.3966          |
+| 0.6329        | 1.4781 | 4600 | 0.3914          |
+| 0.6395        | 1.5103 | 4700 | 0.3934          |
+| 0.6541        | 1.5424 | 4800 | 0.3916          |
+| 0.6538        | 1.5746 | 4900 | 0.3917          |
+| 0.6214        | 1.6067 | 5000 | 0.3840          |
+| 0.6303        | 1.6388 | 5100 | 0.3844          |
+| 0.6547        | 1.6710 | 5200 | 0.3816          |
+| 0.6264        | 1.7031 | 5300 | 0.3844          |
+| 0.5896        | 1.7352 | 5400 | 0.3801          |
+| 0.6082        | 1.7674 | 5500 | 0.3786          |
+| 0.5772        | 1.7995 | 5600 | 0.3737          |
+| 0.5839        | 1.8316 | 5700 | 0.3745          |
+| 0.6201        | 1.8638 | 5800 | 0.3737          |
+| 0.5643        | 1.8959 | 5900 | 0.3717          |
+| 0.6258        | 1.9280 | 6000 | 0.3726          |
+
+
+### Framework versions
+
+- PEFT 0.12.1.dev0
+- Transformers 4.44.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "taide/TAIDE-LX-7B-Chat",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_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:bafad72e9a2d74b7343e09db8ae9ff8c78ae93c00ade1b3b0dd44b79431f3b4c
+size 16794200

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<EOD>": 61873,
+  "<PAD>": 61874
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5ae3c94ec47bca0ac39941c245df5dfc913feebe2d806bc89365af560e4524
+size 813044

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}\n    {% set loop_messages = messages[1:] %}\n    {% set system_message = messages[0]['content'] %}\n{% else %}\n    {% set loop_messages = messages %}\n    {% set system_message = false %}\n{% endif %}\n{% for message in loop_messages %}\n    {% if loop.index0 == 0 and system_message != false %}\n        {% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}\n    {% else %}\n        {% set content = message['content'] %}\n    {% endif %}\n    {% if message['role'] == 'user' %}\n        {{- bos_token + '[INST] ' + content.strip() + ' [/INST]' -}}\n    {% elif message['role'] == 'system' %}\n        {{- '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' -}}\n    {% elif message['role'] == 'assistant' %}\n        {{- ' '  + content.strip() + ' ' + eos_token -}}\n    {% endif %}\n{% endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "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 sha256:97c238627727ccea6afc17d945546c8b8462dea273d929e6577c929ad23e8ac9
+size 5432