mcamara/gemma-7b-es-spanishbillionwords

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,94 @@
+---
+license: other
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-7b
+model-index:
+- name: gemma-7b-spanishbillionwords
+  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. -->
+
+# gemma-7b-spanishbillionwords
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 12.1686
+
+## 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
+- 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_steps: 2
+- training_steps: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.7924        | 0.0   | 1    | 12.2361         |
+| 4.4499        | 0.0   | 2    | 12.1524         |
+| 3.9217        | 0.0   | 3    | 12.0710         |
+| 4.3292        | 0.0   | 4    | 12.1710         |
+| 6.6619        | 0.0   | 5    | 12.1710         |
+| 4.4917        | 0.0   | 6    | 12.2628         |
+| 4.8346        | 0.0   | 7    | 12.3997         |
+| 3.6987        | 0.0   | 8    | 12.4212         |
+| 6.0457        | 0.0   | 9    | 12.4049         |
+| 3.7882        | 0.0   | 10   | 12.4228         |
+| 3.9878        | 0.0   | 11   | 12.4168         |
+| 5.1707        | 0.0   | 12   | 12.3961         |
+| 3.7024        | 0.0   | 13   | 12.3430         |
+| 5.8496        | 0.0   | 14   | 12.3009         |
+| 5.1708        | 0.0   | 15   | 12.2863         |
+| 4.9796        | 0.0   | 16   | 12.2789         |
+| 4.3754        | 0.0   | 17   | 12.2600         |
+| 4.8339        | 0.0   | 18   | 12.2371         |
+| 4.0352        | 0.0   | 19   | 12.2284         |
+| 3.9643        | 0.0   | 20   | 12.2266         |
+| 3.6923        | 0.0   | 21   | 12.2103         |
+| 4.8213        | 0.0   | 22   | 12.2015         |
+| 3.8048        | 0.0   | 23   | 12.1901         |
+| 4.3145        | 0.0   | 24   | 12.1837         |
+| 3.6633        | 0.0   | 25   | 12.1811         |
+| 4.2401        | 0.0   | 26   | 12.1775         |
+| 3.3954        | 0.0   | 27   | 12.1757         |
+| 5.631         | 0.0   | 28   | 12.1720         |
+| 3.8886        | 0.0   | 29   | 12.1714         |
+| 4.3891        | 0.0   | 30   | 12.1686         |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d78b5d8d24040f8fd9a7a54f55dc907858cbd3c6cd638c0026838ddfe657df
+size 100059752

runs/Mar11_22-19-31_byo-WS5/events.out.tfevents.1710192034.byo-WS5.260663.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194cbc70f75a0dfa2ea9686a2bee39681a567a1327a23eb91080b5dc355d8235
+size 19589

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7e592b7314175501c7fc56b904d581de569169ac90e5aa2ec11a860c2cbbaa
+size 17477652

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f54d7f5fc9d746c213a0c8d83b95b5b23c8bf71b3ec9460823edc50bdf8aff2
+size 4920