mgh6 commited on
Commit
bc8892b
·
1 Parent(s): 06d7aa0

Training in progress, step 1000

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2d17a5dcc48ed6bac71945622b81fa0af241c8a9e41865e5a7b4e137fe41d97
3
  size 135998360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf2821ec4fb3eb0500b53b53f079f8851426a237088ccb64385e582f5444d71
3
  size 135998360
run-bad69_00000/checkpoint-1000/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mgh6/esm_cluster_35M_linear",
3
+ "architectures": [
4
+ "EsmForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout": 0.18727005942368125,
8
+ "emb_layer_norm_before": false,
9
+ "esmfold_config": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 480,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1920,
18
+ "is_folding_model": false,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "mask_token_id": 32,
24
+ "max_position_embeddings": 1026,
25
+ "model_type": "esm",
26
+ "num_attention_heads": 20,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "rotary",
30
+ "problem_type": "regression",
31
+ "token_dropout": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "use_cache": true,
35
+ "vocab_list": null,
36
+ "vocab_size": 33
37
+ }
run-bad69_00000/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf2821ec4fb3eb0500b53b53f079f8851426a237088ccb64385e582f5444d71
3
+ size 135998360
run-bad69_00000/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76e7895faa30a8d34008418bde011e0ab24957524f22f37ad3b5e5f950e2c9e
3
+ size 268171578
run-bad69_00000/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f077b2f5a1c369ee4a3f74c2424dab29dce328d101e98bc5ebef831752ab14bd
3
+ size 14244
run-bad69_00000/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e89f32228978a23808dd09d425de7e6edac3ad1f25eb33af4d9c65a11152219
3
+ size 1064
run-bad69_00000/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.19461262226104736,
3
+ "best_model_checkpoint": "mgh6/TCS_Pair/run-bad69_00000/checkpoint-1000",
4
+ "epoch": 0.26892564205997044,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "learning_rate": 0.00079158678443389,
14
+ "loss": 0.1584,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.13,
19
+ "eval_loss": 0.2451040893793106,
20
+ "eval_runtime": 21.3792,
21
+ "eval_samples_per_second": 224.096,
22
+ "eval_steps_per_second": 28.018,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.27,
27
+ "learning_rate": 0.000786228087003387,
28
+ "loss": 0.1285,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.27,
33
+ "eval_loss": 0.19461262226104736,
34
+ "eval_runtime": 21.0052,
35
+ "eval_samples_per_second": 228.086,
36
+ "eval_steps_per_second": 28.517,
37
+ "step": 1000
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 74360,
42
+ "num_train_epochs": 20,
43
+ "save_steps": 500,
44
+ "total_flos": 1015802234112000.0,
45
+ "trial_name": null,
46
+ "trial_params": {
47
+ "classifier_dropout": 0.18727005942368125,
48
+ "gradient_accumulation_steps": 2,
49
+ "learning_rate": 0.0007969454818643929,
50
+ "weight_decay": 0.029106359131330688
51
+ }
52
+ }
run-bad69_00000/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6824f9fe4d5530bdfbcda9b94035c681cade4710ef178c7fb69dcfe7e47c4df
3
+ size 4600