Upload 7 files
Browse files- config.json +31 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +40 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/esm2_t6_8M_UR50D",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 320,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 1280,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 32,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 6,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"token_dropout": true,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.25.0.dev0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_list": null,
|
30 |
+
"vocab_size": 33
|
31 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a34bf97373c05a675547856f6a6ff3c4171b4b8785283f2dbd919bbd63d26553
|
3 |
+
size 60156037
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:061faf49be5d1a619ce879bcfa7f77995588c853a45a5efbba89271c1a9e8c22
|
3 |
+
size 31406473
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e4a020859128898787016d8a34b3d6fb14153e2f7ea85230e231f97c71bb4fd
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8df026ec5c201bc50d1c20c73c641b1d5fac3ffcc8046bf98d39cb8e974e0191
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.982530890498509,
|
5 |
+
"global_step": 7000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.999289873597501e-05,
|
13 |
+
"loss": 0.4718,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.89,
|
19 |
+
"eval_loss": 0.23648260533809662,
|
20 |
+
"eval_runtime": 31.0846,
|
21 |
+
"eval_samples_per_second": 3.217,
|
22 |
+
"eval_steps_per_second": 0.418,
|
23 |
+
"step": 2347
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_accuracy": 0.9,
|
28 |
+
"eval_loss": 0.23966342210769653,
|
29 |
+
"eval_runtime": 4863.3895,
|
30 |
+
"eval_samples_per_second": 0.021,
|
31 |
+
"eval_steps_per_second": 0.003,
|
32 |
+
"step": 4694
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"max_steps": 7041,
|
36 |
+
"num_train_epochs": 3,
|
37 |
+
"total_flos": 2580901877465088.0,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": null
|
40 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0911c4ca9408415ed2920fa8d063f2146a004a447e2ed3fbffa1a64e41e9845
|
3 |
+
size 3387
|