NiallRooney
commited on
Commit
•
a0a5b02
1
Parent(s):
cd39181
End of training
Browse files- README.md +59 -0
- all_results.json +8 -0
- config.json +57 -0
- events.out.tfevents.1697533824.8a5184fc606e.198.0 +3 -0
- pytorch_model.bin +3 -0
- train_results.json +8 -0
- trainer_state.json +42 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: clefourrier/graphormer-base-pcqm4mv2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: graph-classification
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# graph-classification
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [clefourrier/graphormer-base-pcqm4mv2](https://huggingface.co/clefourrier/graphormer-base-pcqm4mv2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.5091
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 16
|
42 |
+
- total_train_batch_size: 64
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 1
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 0.7483 | 0.64 | 1 | 0.5091 |
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.34.0
|
57 |
+
- Pytorch 2.0.1+cu118
|
58 |
+
- Datasets 2.14.5
|
59 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.64,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.7483066916465759,
|
5 |
+
"train_runtime": 90.8934,
|
6 |
+
"train_samples_per_second": 1.1,
|
7 |
+
"train_steps_per_second": 0.011
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "clefourrier/graphormer-base-pcqm4mv2",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_fn": "gelu",
|
5 |
+
"apply_graphormer_init": true,
|
6 |
+
"architectures": [
|
7 |
+
"GraphormerForGraphClassification"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.1,
|
10 |
+
"bias": true,
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"dropout": 0.0,
|
13 |
+
"edge_type": "multi_hop",
|
14 |
+
"embed_scale": null,
|
15 |
+
"embedding_dim": 768,
|
16 |
+
"encoder_normalize_before": true,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"export": false,
|
19 |
+
"ffn_embedding_dim": 768,
|
20 |
+
"freeze_embeddings": false,
|
21 |
+
"hidden_size": 768,
|
22 |
+
"id2label": {
|
23 |
+
"0": "LABEL_0"
|
24 |
+
},
|
25 |
+
"init_fn": null,
|
26 |
+
"kdim": null,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0
|
29 |
+
},
|
30 |
+
"layerdrop": 0.0,
|
31 |
+
"max_nodes": 512,
|
32 |
+
"model_type": "graphormer",
|
33 |
+
"multi_hop_max_dist": 5,
|
34 |
+
"no_token_positional_embeddings": false,
|
35 |
+
"num_atoms": 4608,
|
36 |
+
"num_attention_heads": 32,
|
37 |
+
"num_classes": 2,
|
38 |
+
"num_edge_dis": 128,
|
39 |
+
"num_edges": 1536,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"num_in_degree": 512,
|
42 |
+
"num_layers": 12,
|
43 |
+
"num_out_degree": 512,
|
44 |
+
"num_spatial": 512,
|
45 |
+
"num_trans_layers_to_freeze": 0,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"pre_layernorm": false,
|
48 |
+
"q_noise": 0.0,
|
49 |
+
"qn_block_size": 8,
|
50 |
+
"self_attention": true,
|
51 |
+
"share_input_output_embed": false,
|
52 |
+
"spatial_pos_max": 1024,
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"traceable": false,
|
55 |
+
"transformers_version": "4.34.0",
|
56 |
+
"vdim": null
|
57 |
+
}
|
events.out.tfevents.1697533824.8a5184fc606e.198.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12e178e5401e51426faf65bb3b53225b3e336b6ae0cd380d14e08215c158aeb5
|
3 |
+
size 5565
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0543f51c87b9ce5c2d28cdf8d0e04d582409f468341968a20f7c6184bf066286
|
3 |
+
size 190784909
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.64,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.7483066916465759,
|
5 |
+
"train_runtime": 90.8934,
|
6 |
+
"train_samples_per_second": 1.1,
|
7 |
+
"train_steps_per_second": 0.011
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.64,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.64,
|
13 |
+
"learning_rate": 0.0,
|
14 |
+
"loss": 0.7483,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.64,
|
19 |
+
"eval_loss": 0.5090742707252502,
|
20 |
+
"eval_runtime": 55.595,
|
21 |
+
"eval_samples_per_second": 1.799,
|
22 |
+
"eval_steps_per_second": 0.45,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.64,
|
27 |
+
"step": 1,
|
28 |
+
"total_flos": 0.0,
|
29 |
+
"train_loss": 0.7483066916465759,
|
30 |
+
"train_runtime": 90.8934,
|
31 |
+
"train_samples_per_second": 1.1,
|
32 |
+
"train_steps_per_second": 0.011
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"logging_steps": 500,
|
36 |
+
"max_steps": 1,
|
37 |
+
"num_train_epochs": 1,
|
38 |
+
"save_steps": 500,
|
39 |
+
"total_flos": 0.0,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": null
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9671d94b9c9b529cedc4147f15afa89b063c74bb0eaa2c96b10e0187cca1a600
|
3 |
+
size 4027
|