KEITA21/rebel-large

README.md

@@ -0,0 +1,53 @@
+---
+license: cc-by-nc-sa-4.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Babelscape/rebel-large
+model-index:
+- name: rebel
+  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. -->
+
+# rebel
+
+This model is a fine-tuned version of [Babelscape/rebel-large](https://huggingface.co/Babelscape/rebel-large) on the None dataset.
+
+## 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-08
+- train_batch_size: 10
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 100
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Babelscape/rebel-large",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 180,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.encoder.layers.11.self_attn.q_proj",
+    "model.decoder.layers.11.encoder_attn.q_proj",
+    "model.encoder.layers.11.self_attn.k_proj",
+    "model.encoder.layers.10.self_attn.q_proj",
+    "model.decoder.layers.10.encoder_attn.q_proj",
+    "model.decoder.layers.11.self_attn.q_proj",
+    "model.decoder.layers.10.self_attn.k_proj",
+    "model.encoder.layers.10.self_attn.v_proj",
+    "model.decoder.layers.10.encoder_attn.v_proj",
+    "model.decoder.layers.10.self_attn.q_proj",
+    "model.encoder.layers.11.self_attn.v_proj",
+    "model.decoder.layers.10.self_attn.v_proj",
+    "model.encoder.layers.10.self_attn.k_proj",
+    "model.decoder.layers.11.self_attn.v_proj",
+    "model.decoder.layers.11.encoder_attn.k_proj",
+    "model.decoder.layers.10.encoder_attn.k_proj",
+    "model.decoder.layers.11.encoder_attn.v_proj",
+    "model.decoder.layers.11.self_attn.k_proj"
+  ],
+  "task_type": "text2text-generation",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470e7cca413a1f98fd979d414d264c40194c15e88efee06cbde9137a1527ce18
+size 26547312

epoch_losses.csv

@@ -0,0 +1,4 @@
+,epoch_loss
+0,0.0
+1,0.0
+2,0.0

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e236bee96e8a583d06831047d6f187170448367fac38a0a68e6197d9723823
+size 4920

training_losses.csv

@@ -0,0 +1 @@
+,loss