End of training

README.md

@@ -0,0 +1,69 @@
+---
+base_model: google/gemma-2-2b
+library_name: peft
+license: gemma
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+tags:
+- generated_from_trainer
+model-index:
+- name: seqcls-mahasent
+  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. -->
+
+# seqcls-mahasent
+
+This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Accuracy: 0.3333
+- Precision: 0.1111
+- Recall: 0.3333
+- F1: 0.1667
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.0           | 1.0   | 3029 | nan             | 0.3333   | 0.1111    | 0.3333 | 0.1667 |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,213 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-2b",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.22.mlp.up_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.16.mlp.up_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.22.self_attn.o_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.21.self_attn.o_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.19.self_attn.o_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.16.mlp.gate_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.21.mlp.up_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.0.self_attn.o_proj",
+    "score",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.23.mlp.up_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.17.mlp.up_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.24.mlp.down_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.19.mlp.gate_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.18.self_attn.o_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.20.self_attn.o_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.24.mlp.up_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.23.mlp.gate_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.18.mlp.gate_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.24.mlp.gate_proj",
+    "model.layers.17.mlp.gate_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.21.mlp.gate_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.24.self_attn.o_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.22.mlp.down_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.22.mlp.gate_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.25.mlp.down_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.23.self_attn.k_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e931d99b2dc6f98f4f2e8e2f638ec238b81acf32b6dfcb52e1af5f36314a14
+size 41831288

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33b8f97f8a238a3c8ce2e91bda9201e17ab83bd27d79565e7d04549612fc6dc
+size 5176