amazon_helpfulness_classification_seqbn_tapt_full_train

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: amazon_helpfulness_classification_seqbn_tapt_full_train
+  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. -->
+
+# amazon_helpfulness_classification_seqbn_tapt_full_train
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3077
+- Accuracy: 0.8776
+- F1 Macro: 0.7027
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.06
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Macro |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
+| 0.3264        | 1.0   | 7204  | 0.3133          | 0.8658   | 0.5988   |
+| 0.3255        | 2.0   | 14408 | 0.3263          | 0.8668   | 0.5816   |
+| 0.3123        | 3.0   | 21612 | 0.3075          | 0.873    | 0.6920   |
+| 0.3098        | 4.0   | 28816 | 0.3100          | 0.8728   | 0.6726   |
+| 0.2613        | 5.0   | 36020 | 0.3124          | 0.8734   | 0.6992   |
+| 0.2496        | 6.0   | 43224 | 0.3123          | 0.8758   | 0.7014   |
+| 0.2484        | 7.0   | 50428 | 0.3164          | 0.8728   | 0.6936   |
+| 0.2296        | 8.0   | 57632 | 0.3310          | 0.8722   | 0.6849   |
+| 0.2885        | 9.0   | 64836 | 0.3307          | 0.873    | 0.6911   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

default/head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 50265
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "default",
+  "version": "0.1.2"
+}

default/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdff7928366b173ef2d74fcdf04581a7c98c13c3bd11623203f922ffcc7248c5
+size 156986358

runs/Apr21_02-36-48_54232f561a01/events.out.tfevents.1713667010.54232f561a01.469.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03eec8cc8b0f593bf8414d85e479cf64518eba434228057e387ae729347b25bf
-size 88008
+oid sha256:4546cc4c2495c9423418cd446d98fd185670e980240548e246143bee2909456e
+size 112172

runs/Apr21_02-36-48_54232f561a01/events.out.tfevents.1713687342.54232f561a01.469.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b359101bccce6e13da051fa81ad8c5ae0201d62639585bb51fc1c22dfea8efe1
+size 470

tapt_seq_bn/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "9076f36a74755ac4",
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "tapt_seq_bn",
+  "version": "0.1.2"
+}

tapt_seq_bn/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "helpful": 1,
+      "unhelpful": 0
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "RobertaAdapterModel",
+  "model_name": "roberta-base",
+  "model_type": "roberta",
+  "name": "tapt_seq_bn",
+  "version": "0.1.2"
+}

tapt_seq_bn/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e7ebdaa78a4a12c7ef851fb05e18aa90662e2e91ea303ddc517b34647d19c6
+size 3595878

tapt_seq_bn/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac90e628f7209b119381ff798242ba9b22a44c1d6f6f325a5377469cf7b300d8
+size 2370664