End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: clefourrier/graphormer-base-pcqm4mv2
+tags:
+- generated_from_trainer
+model-index:
+- name: graph-classification
+  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. -->
+
+# graph-classification
+
+This model is a fine-tuned version of [clefourrier/graphormer-base-pcqm4mv2](https://huggingface.co/clefourrier/graphormer-base-pcqm4mv2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4349
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.46          | 1.0   | 515  | 0.3197          |
+| 0.3875        | 2.0   | 1030 | 0.2661          |
+| 0.348         | 3.0   | 1545 | 0.2706          |
+| 0.3096        | 4.0   | 2060 | 0.2712          |
+| 0.2819        | 5.0   | 2575 | 0.2830          |
+| 0.2414        | 6.0   | 3090 | 0.3111          |
+| 0.2024        | 7.0   | 3605 | 0.3633          |
+| 0.1843        | 8.0   | 4120 | 0.4180          |
+| 0.1467        | 9.0   | 4635 | 0.4040          |
+| 0.1364        | 10.0  | 5150 | 0.4349          |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "clefourrier/graphormer-base-pcqm4mv2",
+  "activation_dropout": 0.1,
+  "activation_fn": "gelu",
+  "apply_graphormer_init": true,
+  "architectures": [
+    "GraphormerForGraphClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bias": true,
+  "bos_token_id": 1,
+  "dropout": 0.0,
+  "edge_type": "multi_hop",
+  "embed_scale": null,
+  "embedding_dim": 768,
+  "encoder_normalize_before": true,
+  "eos_token_id": 2,
+  "export": false,
+  "ffn_embedding_dim": 768,
+  "freeze_embeddings": false,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "init_fn": null,
+  "kdim": null,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layerdrop": 0.0,
+  "max_nodes": 512,
+  "model_type": "graphormer",
+  "multi_hop_max_dist": 5,
+  "no_token_positional_embeddings": false,
+  "num_atoms": 4608,
+  "num_attention_heads": 32,
+  "num_classes": 2,
+  "num_edge_dis": 128,
+  "num_edges": 1536,
+  "num_hidden_layers": 12,
+  "num_in_degree": 512,
+  "num_layers": 12,
+  "num_out_degree": 512,
+  "num_spatial": 512,
+  "num_trans_layers_to_freeze": 0,
+  "pad_token_id": 0,
+  "pre_layernorm": false,
+  "q_noise": 0.0,
+  "qn_block_size": 8,
+  "self_attention": true,
+  "share_input_output_embed": false,
+  "spatial_pos_max": 1024,
+  "torch_dtype": "float32",
+  "traceable": false,
+  "transformers_version": "4.43.3",
+  "vdim": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187d8aa3ca511a26de0cb8a2414b3567a8af914298c344effc8d14e340f82918
+size 190738260

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eeb6fe7a61c49e458464a413acdca3d573bd5c7773b9194affe18dc1594593e
+size 5176