Training with 90/10 Spanish dataset, 50 epochs, 3 Batch Size, reduce_lr_on_plateau

README.md

@@ -0,0 +1,109 @@
+---
+license: llama2
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-chat-hf
+model-index:
+- name: Llama-2-7b-chat-hf-finetune_90_10_SY_gold
+  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. -->
+
+# Llama-2-7b-chat-hf-finetune_90_10_SY_gold
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1470
+
+## 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: 0.0001
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: reduce_lr_on_plateau
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 0.5446        | 0.9937  | 157  | 0.7173          |
+| 0.0863        | 1.9873  | 314  | 0.8235          |
+| 0.1229        | 2.9810  | 471  | 0.8690          |
+| 0.0914        | 3.9747  | 628  | 0.9089          |
+| 0.0766        | 4.9684  | 785  | 0.9324          |
+| 0.0842        | 5.9620  | 942  | 0.9564          |
+| 0.0725        | 6.9557  | 1099 | 0.9903          |
+| 0.0584        | 7.9494  | 1256 | 1.0348          |
+| 0.0653        | 8.9430  | 1413 | 1.0468          |
+| 0.0601        | 9.9367  | 1570 | 1.0397          |
+| 0.0601        | 10.9304 | 1727 | 1.0622          |
+| 0.0595        | 11.9241 | 1884 | 1.0757          |
+| 0.0676        | 12.9177 | 2041 | 1.0911          |
+| 0.0513        | 13.9114 | 2198 | 1.0942          |
+| 0.0492        | 14.9051 | 2355 | 1.0980          |
+| 0.0489        | 15.8987 | 2512 | 1.1041          |
+| 0.05          | 16.8924 | 2669 | 1.1095          |
+| 0.0498        | 17.8861 | 2826 | 1.1136          |
+| 0.0494        | 18.8797 | 2983 | 1.1174          |
+| 0.0483        | 19.8734 | 3140 | 1.1220          |
+| 0.0476        | 20.8671 | 3297 | 1.1226          |
+| 0.0487        | 21.8608 | 3454 | 1.1250          |
+| 0.048         | 22.8544 | 3611 | 1.1297          |
+| 0.0445        | 23.8481 | 3768 | 1.1307          |
+| 0.0461        | 24.8418 | 3925 | 1.1321          |
+| 0.0456        | 25.8354 | 4082 | 1.1338          |
+| 0.0455        | 26.8291 | 4239 | 1.1355          |
+| 0.0437        | 27.8228 | 4396 | 1.1372          |
+| 0.0434        | 28.8165 | 4553 | 1.1390          |
+| 0.0442        | 29.8101 | 4710 | 1.1400          |
+| 0.0432        | 30.8038 | 4867 | 1.1417          |
+| 0.0433        | 31.7975 | 5024 | 1.1426          |
+| 0.0424        | 32.7911 | 5181 | 1.1437          |
+| 0.0415        | 33.7848 | 5338 | 1.1453          |
+| 0.0424        | 34.7785 | 5495 | 1.1453          |
+| 0.0399        | 35.7722 | 5652 | 1.1455          |
+| 0.04          | 36.7658 | 5809 | 1.1457          |
+| 0.0401        | 37.7595 | 5966 | 1.1458          |
+| 0.0394        | 38.7532 | 6123 | 1.1461          |
+| 0.0369        | 39.7468 | 6280 | 1.1462          |
+| 0.0515        | 40.7405 | 6437 | 1.1464          |
+| 0.0511        | 41.7342 | 6594 | 1.1465          |
+| 0.0483        | 42.7278 | 6751 | 1.1465          |
+| 0.0478        | 43.7215 | 6908 | 1.1468          |
+| 0.0492        | 44.7152 | 7065 | 1.1469          |
+| 0.0492        | 45.7089 | 7222 | 1.1469          |
+| 0.0473        | 46.7025 | 7379 | 1.1469          |
+| 0.0483        | 47.6962 | 7536 | 1.1470          |
+| 0.0474        | 48.6899 | 7693 | 1.1470          |
+| 0.0473        | 49.6835 | 7850 | 1.1470          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "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": 0.0001,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_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 sha256:4a2e98f9f8fa16c3f1d68305374b3ab8a85dffe51532b0bb9d1b500bc15957e4
+size 1688269144

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "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 sha256:5357ccc7d424a05bc2b6e78a0ec98eb782e4f82689419422741fa0330569fd33
+size 5048