init

peft_logs/events.out.tfevents.1744412793.nigpu.1908034.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec289b0759625e658ac27f7ae85681a70e9f65b287d453914f3a2dc9e237b34
+size 88

peft_logs/events.out.tfevents.1744413155.nigpu.1913698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d688b3737771589c4d0d8ee3bf3d47b4db70ad2345a2963e84fcd3511b8e24b
+size 10028

peft_models/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.5.0

peft_models/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "sintsh/AKPlbart",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM"
+}

peft_models/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f192ef21aee7271f37557abad28763d90e19c323c84bb29fc29b3ae0213f15f3
+size 2694074

peft_models/config.json

@@ -0,0 +1,39 @@
+{
+  "peft_type": "lora",
+  "model_name": "sintsh/AKPlbart",
+  "training_config": {
+    "model_name": "sintsh/AKPlbart",
+    "peft_type": "lora",
+    "lora_rank": 8,
+    "lora_alpha": 32,
+    "adapter_size": 128,
+    "learning_rate": 3e-05,
+    "batch_size": 32,
+    "max_length": 512,
+    "num_epochs": 8,
+    "early_stopping": 3,
+    "gradient_accumulation": 2,
+    "warmup_steps": 1000,
+    "weight_decay": 0.01,
+    "output_dir": "./peft_models/lora_20250411",
+    "logging_dir": "./peft_logs/lora_20250411",
+    "logging_steps": 500,
+    "quantization": null,
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj"
+    ],
+    "ddp_find_unused_parameters": false,
+    "sample_size": 780944,
+    "generation": {
+      "temperature": 0.7,
+      "top_k": 50,
+      "top_p": 0.95,
+      "repetition_penalty": 1.2,
+      "no_repeat_ngram_size": 2,
+      "num_beams": 5,
+      "max_new_tokens": 256
+    }
+  }
+}

peft_models/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80
+size 985833

peft_models/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "__java__",
+    "__python__",
+    "__en_XX__"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

peft_models/tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "language_codes": "base",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "sintsh/AKPlbart",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "PLBartTokenizer",
+  "unk_token": "<unk>"
+}