Upload with huggingface_hub
Browse files- checkpoint-49400/config.json +33 -0
- checkpoint-49400/optimizer.pt +3 -0
- checkpoint-49400/pytorch_model.bin +3 -0
- checkpoint-49400/rng_state.pth +3 -0
- checkpoint-49400/scheduler.pt +3 -0
- checkpoint-49400/trainer_state.json +1154 -0
- checkpoint-49400/training_args.bin +3 -0
- config.json +33 -0
- pdbbindfull.out +528 -0
- pytorch_model.bin +3 -0
- runs/Apr09_14-56-31_lotan/1649516197.1034896/events.out.tfevents.1649516197.lotan.2910198.1 +3 -0
- runs/Apr09_14-56-31_lotan/events.out.tfevents.1649516197.lotan.2910198.0 +3 -0
- training_args.bin +3 -0
checkpoint-49400/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "data/saved_models/our_90epochs_saved_model",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSelfiesClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "roberta",
|
24 |
+
"num_attention_heads": 4,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 1,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.15.0",
|
30 |
+
"type_vocab_size": 1,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 800
|
33 |
+
}
|
checkpoint-49400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d169e334a17b7ce3cf10931e1802ac211875216b186c2bfc17471a3349d5bc5
|
3 |
+
size 693374749
|
checkpoint-49400/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06f8fbd3d483a40043dfc4ed03d1d7f9d1c7387420b6f553e384b6d7e93d2f13
|
3 |
+
size 349077673
|
checkpoint-49400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0774dfa0312cea23978c476d3a4aa3d7be5eefe120a864c972c1d64a8ddfd4f6
|
3 |
+
size 14503
|
checkpoint-49400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:023ca11131eae1c7b31b63b372141621a6d26eb9246062a4b4d206ee0840f748
|
3 |
+
size 623
|
checkpoint-49400/trainer_state.json
ADDED
@@ -0,0 +1,1154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 50.0,
|
5 |
+
"global_step": 49400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.51,
|
12 |
+
"learning_rate": 9.898785425101214e-06,
|
13 |
+
"loss": 4.6519,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.3328564167022705,
|
19 |
+
"eval_mae": 1.2115871906280518,
|
20 |
+
"eval_mse": 2.3328561782836914,
|
21 |
+
"eval_rmse": 1.5273690223693848,
|
22 |
+
"eval_runtime": 2.139,
|
23 |
+
"eval_samples_per_second": 460.504,
|
24 |
+
"eval_steps_per_second": 57.972,
|
25 |
+
"step": 988
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.01,
|
29 |
+
"learning_rate": 9.79757085020243e-06,
|
30 |
+
"loss": 1.9813,
|
31 |
+
"step": 1000
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 1.52,
|
35 |
+
"learning_rate": 9.696356275303645e-06,
|
36 |
+
"loss": 1.7364,
|
37 |
+
"step": 1500
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.0,
|
41 |
+
"eval_loss": 2.25815749168396,
|
42 |
+
"eval_mae": 1.1845210790634155,
|
43 |
+
"eval_mse": 2.25815749168396,
|
44 |
+
"eval_rmse": 1.5027166604995728,
|
45 |
+
"eval_runtime": 2.2991,
|
46 |
+
"eval_samples_per_second": 428.436,
|
47 |
+
"eval_steps_per_second": 53.935,
|
48 |
+
"step": 1976
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.02,
|
52 |
+
"learning_rate": 9.595141700404859e-06,
|
53 |
+
"loss": 1.6471,
|
54 |
+
"step": 2000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 2.53,
|
58 |
+
"learning_rate": 9.493927125506074e-06,
|
59 |
+
"loss": 1.4318,
|
60 |
+
"step": 2500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 3.0,
|
64 |
+
"eval_loss": 2.2711498737335205,
|
65 |
+
"eval_mae": 1.195154070854187,
|
66 |
+
"eval_mse": 2.2711498737335205,
|
67 |
+
"eval_rmse": 1.5070334672927856,
|
68 |
+
"eval_runtime": 1.9177,
|
69 |
+
"eval_samples_per_second": 513.633,
|
70 |
+
"eval_steps_per_second": 64.66,
|
71 |
+
"step": 2964
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 3.04,
|
75 |
+
"learning_rate": 9.392712550607288e-06,
|
76 |
+
"loss": 1.3929,
|
77 |
+
"step": 3000
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 3.54,
|
81 |
+
"learning_rate": 9.291497975708503e-06,
|
82 |
+
"loss": 1.2099,
|
83 |
+
"step": 3500
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 4.0,
|
87 |
+
"eval_loss": 2.5615780353546143,
|
88 |
+
"eval_mae": 1.2618587017059326,
|
89 |
+
"eval_mse": 2.5615780353546143,
|
90 |
+
"eval_rmse": 1.60049307346344,
|
91 |
+
"eval_runtime": 2.4694,
|
92 |
+
"eval_samples_per_second": 398.879,
|
93 |
+
"eval_steps_per_second": 50.214,
|
94 |
+
"step": 3952
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 4.05,
|
98 |
+
"learning_rate": 9.190283400809717e-06,
|
99 |
+
"loss": 1.1585,
|
100 |
+
"step": 4000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 4.55,
|
104 |
+
"learning_rate": 9.089068825910932e-06,
|
105 |
+
"loss": 0.9984,
|
106 |
+
"step": 4500
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 5.0,
|
110 |
+
"eval_loss": 2.386498212814331,
|
111 |
+
"eval_mae": 1.2156014442443848,
|
112 |
+
"eval_mse": 2.386498212814331,
|
113 |
+
"eval_rmse": 1.5448294878005981,
|
114 |
+
"eval_runtime": 2.1201,
|
115 |
+
"eval_samples_per_second": 464.611,
|
116 |
+
"eval_steps_per_second": 58.489,
|
117 |
+
"step": 4940
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 5.06,
|
121 |
+
"learning_rate": 8.987854251012147e-06,
|
122 |
+
"loss": 1.0114,
|
123 |
+
"step": 5000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 5.57,
|
127 |
+
"learning_rate": 8.886639676113361e-06,
|
128 |
+
"loss": 0.897,
|
129 |
+
"step": 5500
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 6.0,
|
133 |
+
"eval_loss": 2.3048605918884277,
|
134 |
+
"eval_mae": 1.186144471168518,
|
135 |
+
"eval_mse": 2.3048605918884277,
|
136 |
+
"eval_rmse": 1.5181766748428345,
|
137 |
+
"eval_runtime": 2.4807,
|
138 |
+
"eval_samples_per_second": 397.063,
|
139 |
+
"eval_steps_per_second": 49.986,
|
140 |
+
"step": 5928
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 6.07,
|
144 |
+
"learning_rate": 8.785425101214575e-06,
|
145 |
+
"loss": 0.912,
|
146 |
+
"step": 6000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 6.58,
|
150 |
+
"learning_rate": 8.68421052631579e-06,
|
151 |
+
"loss": 0.7973,
|
152 |
+
"step": 6500
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 7.0,
|
156 |
+
"eval_loss": 2.423027992248535,
|
157 |
+
"eval_mae": 1.223141074180603,
|
158 |
+
"eval_mse": 2.4230284690856934,
|
159 |
+
"eval_rmse": 1.556607961654663,
|
160 |
+
"eval_runtime": 2.3801,
|
161 |
+
"eval_samples_per_second": 413.851,
|
162 |
+
"eval_steps_per_second": 52.099,
|
163 |
+
"step": 6916
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 7.09,
|
167 |
+
"learning_rate": 8.582995951417005e-06,
|
168 |
+
"loss": 0.8141,
|
169 |
+
"step": 7000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 7.59,
|
173 |
+
"learning_rate": 8.481781376518219e-06,
|
174 |
+
"loss": 0.7115,
|
175 |
+
"step": 7500
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 8.0,
|
179 |
+
"eval_loss": 2.51936936378479,
|
180 |
+
"eval_mae": 1.2446390390396118,
|
181 |
+
"eval_mse": 2.51936936378479,
|
182 |
+
"eval_rmse": 1.587252140045166,
|
183 |
+
"eval_runtime": 2.2497,
|
184 |
+
"eval_samples_per_second": 437.844,
|
185 |
+
"eval_steps_per_second": 55.119,
|
186 |
+
"step": 7904
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 8.1,
|
190 |
+
"learning_rate": 8.380566801619434e-06,
|
191 |
+
"loss": 0.7455,
|
192 |
+
"step": 8000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 8.6,
|
196 |
+
"learning_rate": 8.279352226720648e-06,
|
197 |
+
"loss": 0.6548,
|
198 |
+
"step": 8500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 9.0,
|
202 |
+
"eval_loss": 2.3894152641296387,
|
203 |
+
"eval_mae": 1.20915687084198,
|
204 |
+
"eval_mse": 2.3894152641296387,
|
205 |
+
"eval_rmse": 1.5457733869552612,
|
206 |
+
"eval_runtime": 2.012,
|
207 |
+
"eval_samples_per_second": 489.572,
|
208 |
+
"eval_steps_per_second": 61.631,
|
209 |
+
"step": 8892
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 9.11,
|
213 |
+
"learning_rate": 8.178137651821862e-06,
|
214 |
+
"loss": 0.6625,
|
215 |
+
"step": 9000
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 9.62,
|
219 |
+
"learning_rate": 8.076923076923077e-06,
|
220 |
+
"loss": 0.6466,
|
221 |
+
"step": 9500
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 10.0,
|
225 |
+
"eval_loss": 2.3797826766967773,
|
226 |
+
"eval_mae": 1.209175944328308,
|
227 |
+
"eval_mse": 2.3797826766967773,
|
228 |
+
"eval_rmse": 1.5426543951034546,
|
229 |
+
"eval_runtime": 1.9282,
|
230 |
+
"eval_samples_per_second": 510.852,
|
231 |
+
"eval_steps_per_second": 64.31,
|
232 |
+
"step": 9880
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 10.12,
|
236 |
+
"learning_rate": 7.975708502024292e-06,
|
237 |
+
"loss": 0.6429,
|
238 |
+
"step": 10000
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 10.63,
|
242 |
+
"learning_rate": 7.874493927125508e-06,
|
243 |
+
"loss": 0.6218,
|
244 |
+
"step": 10500
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 11.0,
|
248 |
+
"eval_loss": 2.325528383255005,
|
249 |
+
"eval_mae": 1.197866678237915,
|
250 |
+
"eval_mse": 2.325528383255005,
|
251 |
+
"eval_rmse": 1.5249682664871216,
|
252 |
+
"eval_runtime": 2.2819,
|
253 |
+
"eval_samples_per_second": 431.658,
|
254 |
+
"eval_steps_per_second": 54.341,
|
255 |
+
"step": 10868
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 11.13,
|
259 |
+
"learning_rate": 7.773279352226721e-06,
|
260 |
+
"loss": 0.596,
|
261 |
+
"step": 11000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 11.64,
|
265 |
+
"learning_rate": 7.672064777327935e-06,
|
266 |
+
"loss": 0.5498,
|
267 |
+
"step": 11500
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 12.0,
|
271 |
+
"eval_loss": 2.391416072845459,
|
272 |
+
"eval_mae": 1.2055319547653198,
|
273 |
+
"eval_mse": 2.391416072845459,
|
274 |
+
"eval_rmse": 1.5464204549789429,
|
275 |
+
"eval_runtime": 2.3484,
|
276 |
+
"eval_samples_per_second": 419.443,
|
277 |
+
"eval_steps_per_second": 52.803,
|
278 |
+
"step": 11856
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 12.15,
|
282 |
+
"learning_rate": 7.570850202429151e-06,
|
283 |
+
"loss": 0.5617,
|
284 |
+
"step": 12000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 12.65,
|
288 |
+
"learning_rate": 7.469635627530365e-06,
|
289 |
+
"loss": 0.5403,
|
290 |
+
"step": 12500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 13.0,
|
294 |
+
"eval_loss": 2.4148483276367188,
|
295 |
+
"eval_mae": 1.2168691158294678,
|
296 |
+
"eval_mse": 2.4148483276367188,
|
297 |
+
"eval_rmse": 1.5539782047271729,
|
298 |
+
"eval_runtime": 2.3371,
|
299 |
+
"eval_samples_per_second": 421.463,
|
300 |
+
"eval_steps_per_second": 53.057,
|
301 |
+
"step": 12844
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 13.16,
|
305 |
+
"learning_rate": 7.368421052631579e-06,
|
306 |
+
"loss": 0.5424,
|
307 |
+
"step": 13000
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 13.66,
|
311 |
+
"learning_rate": 7.267206477732795e-06,
|
312 |
+
"loss": 0.5392,
|
313 |
+
"step": 13500
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 14.0,
|
317 |
+
"eval_loss": 2.429582357406616,
|
318 |
+
"eval_mae": 1.2232253551483154,
|
319 |
+
"eval_mse": 2.429582357406616,
|
320 |
+
"eval_rmse": 1.5587117671966553,
|
321 |
+
"eval_runtime": 1.971,
|
322 |
+
"eval_samples_per_second": 499.752,
|
323 |
+
"eval_steps_per_second": 62.913,
|
324 |
+
"step": 13832
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 14.17,
|
328 |
+
"learning_rate": 7.165991902834008e-06,
|
329 |
+
"loss": 0.5105,
|
330 |
+
"step": 14000
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 14.68,
|
334 |
+
"learning_rate": 7.064777327935223e-06,
|
335 |
+
"loss": 0.5224,
|
336 |
+
"step": 14500
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 15.0,
|
340 |
+
"eval_loss": 2.279872417449951,
|
341 |
+
"eval_mae": 1.1799190044403076,
|
342 |
+
"eval_mse": 2.279872417449951,
|
343 |
+
"eval_rmse": 1.5099246501922607,
|
344 |
+
"eval_runtime": 2.2712,
|
345 |
+
"eval_samples_per_second": 433.694,
|
346 |
+
"eval_steps_per_second": 54.597,
|
347 |
+
"step": 14820
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 15.18,
|
351 |
+
"learning_rate": 6.963562753036438e-06,
|
352 |
+
"loss": 0.5082,
|
353 |
+
"step": 15000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 15.69,
|
357 |
+
"learning_rate": 6.862348178137653e-06,
|
358 |
+
"loss": 0.4868,
|
359 |
+
"step": 15500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 16.0,
|
363 |
+
"eval_loss": 2.309877634048462,
|
364 |
+
"eval_mae": 1.1822220087051392,
|
365 |
+
"eval_mse": 2.309877634048462,
|
366 |
+
"eval_rmse": 1.519828200340271,
|
367 |
+
"eval_runtime": 1.9368,
|
368 |
+
"eval_samples_per_second": 508.564,
|
369 |
+
"eval_steps_per_second": 64.022,
|
370 |
+
"step": 15808
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 16.19,
|
374 |
+
"learning_rate": 6.761133603238867e-06,
|
375 |
+
"loss": 0.5021,
|
376 |
+
"step": 16000
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 16.7,
|
380 |
+
"learning_rate": 6.6599190283400816e-06,
|
381 |
+
"loss": 0.4702,
|
382 |
+
"step": 16500
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 17.0,
|
386 |
+
"eval_loss": 2.205157518386841,
|
387 |
+
"eval_mae": 1.1669542789459229,
|
388 |
+
"eval_mse": 2.205157518386841,
|
389 |
+
"eval_rmse": 1.4849772453308105,
|
390 |
+
"eval_runtime": 2.2927,
|
391 |
+
"eval_samples_per_second": 429.627,
|
392 |
+
"eval_steps_per_second": 54.085,
|
393 |
+
"step": 16796
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 17.21,
|
397 |
+
"learning_rate": 6.558704453441296e-06,
|
398 |
+
"loss": 0.4905,
|
399 |
+
"step": 17000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 17.71,
|
403 |
+
"learning_rate": 6.457489878542511e-06,
|
404 |
+
"loss": 0.4665,
|
405 |
+
"step": 17500
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 18.0,
|
409 |
+
"eval_loss": 2.323201894760132,
|
410 |
+
"eval_mae": 1.1936134099960327,
|
411 |
+
"eval_mse": 2.323201894760132,
|
412 |
+
"eval_rmse": 1.5242053270339966,
|
413 |
+
"eval_runtime": 2.1851,
|
414 |
+
"eval_samples_per_second": 450.772,
|
415 |
+
"eval_steps_per_second": 56.747,
|
416 |
+
"step": 17784
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 18.22,
|
420 |
+
"learning_rate": 6.356275303643725e-06,
|
421 |
+
"loss": 0.4431,
|
422 |
+
"step": 18000
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 18.72,
|
426 |
+
"learning_rate": 6.2550607287449395e-06,
|
427 |
+
"loss": 0.483,
|
428 |
+
"step": 18500
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 19.0,
|
432 |
+
"eval_loss": 2.3569979667663574,
|
433 |
+
"eval_mae": 1.2059428691864014,
|
434 |
+
"eval_mse": 2.3569979667663574,
|
435 |
+
"eval_rmse": 1.5352517366409302,
|
436 |
+
"eval_runtime": 6.1451,
|
437 |
+
"eval_samples_per_second": 160.29,
|
438 |
+
"eval_steps_per_second": 20.179,
|
439 |
+
"step": 18772
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 19.23,
|
443 |
+
"learning_rate": 6.153846153846155e-06,
|
444 |
+
"loss": 0.4433,
|
445 |
+
"step": 19000
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 19.74,
|
449 |
+
"learning_rate": 6.0526315789473685e-06,
|
450 |
+
"loss": 0.4561,
|
451 |
+
"step": 19500
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 20.0,
|
455 |
+
"eval_loss": 2.313786268234253,
|
456 |
+
"eval_mae": 1.190987229347229,
|
457 |
+
"eval_mse": 2.313786268234253,
|
458 |
+
"eval_rmse": 1.5211135149002075,
|
459 |
+
"eval_runtime": 6.1814,
|
460 |
+
"eval_samples_per_second": 159.348,
|
461 |
+
"eval_steps_per_second": 20.06,
|
462 |
+
"step": 19760
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 20.24,
|
466 |
+
"learning_rate": 5.951417004048583e-06,
|
467 |
+
"loss": 0.4688,
|
468 |
+
"step": 20000
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 20.75,
|
472 |
+
"learning_rate": 5.850202429149798e-06,
|
473 |
+
"loss": 0.4577,
|
474 |
+
"step": 20500
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 21.0,
|
478 |
+
"eval_loss": 2.2783560752868652,
|
479 |
+
"eval_mae": 1.1627191305160522,
|
480 |
+
"eval_mse": 2.2783560752868652,
|
481 |
+
"eval_rmse": 1.5094224214553833,
|
482 |
+
"eval_runtime": 6.5272,
|
483 |
+
"eval_samples_per_second": 150.907,
|
484 |
+
"eval_steps_per_second": 18.997,
|
485 |
+
"step": 20748
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 21.26,
|
489 |
+
"learning_rate": 5.748987854251013e-06,
|
490 |
+
"loss": 0.4261,
|
491 |
+
"step": 21000
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 21.76,
|
495 |
+
"learning_rate": 5.6477732793522265e-06,
|
496 |
+
"loss": 0.4251,
|
497 |
+
"step": 21500
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 22.0,
|
501 |
+
"eval_loss": 2.3060412406921387,
|
502 |
+
"eval_mae": 1.176581621170044,
|
503 |
+
"eval_mse": 2.3060412406921387,
|
504 |
+
"eval_rmse": 1.5185655355453491,
|
505 |
+
"eval_runtime": 6.411,
|
506 |
+
"eval_samples_per_second": 153.641,
|
507 |
+
"eval_steps_per_second": 19.342,
|
508 |
+
"step": 21736
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 22.27,
|
512 |
+
"learning_rate": 5.546558704453442e-06,
|
513 |
+
"loss": 0.4235,
|
514 |
+
"step": 22000
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 22.77,
|
518 |
+
"learning_rate": 5.445344129554656e-06,
|
519 |
+
"loss": 0.4477,
|
520 |
+
"step": 22500
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 23.0,
|
524 |
+
"eval_loss": 2.3399007320404053,
|
525 |
+
"eval_mae": 1.1934117078781128,
|
526 |
+
"eval_mse": 2.339900493621826,
|
527 |
+
"eval_rmse": 1.5296733379364014,
|
528 |
+
"eval_runtime": 6.5358,
|
529 |
+
"eval_samples_per_second": 150.708,
|
530 |
+
"eval_steps_per_second": 18.972,
|
531 |
+
"step": 22724
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 23.28,
|
535 |
+
"learning_rate": 5.344129554655872e-06,
|
536 |
+
"loss": 0.3849,
|
537 |
+
"step": 23000
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 23.79,
|
541 |
+
"learning_rate": 5.242914979757085e-06,
|
542 |
+
"loss": 0.4274,
|
543 |
+
"step": 23500
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 24.0,
|
547 |
+
"eval_loss": 2.2604634761810303,
|
548 |
+
"eval_mae": 1.1710097789764404,
|
549 |
+
"eval_mse": 2.2604634761810303,
|
550 |
+
"eval_rmse": 1.503483772277832,
|
551 |
+
"eval_runtime": 6.4581,
|
552 |
+
"eval_samples_per_second": 152.522,
|
553 |
+
"eval_steps_per_second": 19.201,
|
554 |
+
"step": 23712
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 24.29,
|
558 |
+
"learning_rate": 5.1417004048583e-06,
|
559 |
+
"loss": 0.402,
|
560 |
+
"step": 24000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 24.8,
|
564 |
+
"learning_rate": 5.040485829959515e-06,
|
565 |
+
"loss": 0.4176,
|
566 |
+
"step": 24500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 25.0,
|
570 |
+
"eval_loss": 2.277299165725708,
|
571 |
+
"eval_mae": 1.1737443208694458,
|
572 |
+
"eval_mse": 2.277299404144287,
|
573 |
+
"eval_rmse": 1.5090724229812622,
|
574 |
+
"eval_runtime": 6.5489,
|
575 |
+
"eval_samples_per_second": 150.407,
|
576 |
+
"eval_steps_per_second": 18.935,
|
577 |
+
"step": 24700
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 25.3,
|
581 |
+
"learning_rate": 4.939271255060729e-06,
|
582 |
+
"loss": 0.4278,
|
583 |
+
"step": 25000
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 25.81,
|
587 |
+
"learning_rate": 4.838056680161944e-06,
|
588 |
+
"loss": 0.4105,
|
589 |
+
"step": 25500
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 26.0,
|
593 |
+
"eval_loss": 2.3140110969543457,
|
594 |
+
"eval_mae": 1.1842072010040283,
|
595 |
+
"eval_mse": 2.3140110969543457,
|
596 |
+
"eval_rmse": 1.521187424659729,
|
597 |
+
"eval_runtime": 6.5703,
|
598 |
+
"eval_samples_per_second": 149.918,
|
599 |
+
"eval_steps_per_second": 18.873,
|
600 |
+
"step": 25688
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 26.32,
|
604 |
+
"learning_rate": 4.736842105263158e-06,
|
605 |
+
"loss": 0.404,
|
606 |
+
"step": 26000
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 26.82,
|
610 |
+
"learning_rate": 4.635627530364373e-06,
|
611 |
+
"loss": 0.3843,
|
612 |
+
"step": 26500
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 27.0,
|
616 |
+
"eval_loss": 2.2196788787841797,
|
617 |
+
"eval_mae": 1.1630769968032837,
|
618 |
+
"eval_mse": 2.2196786403656006,
|
619 |
+
"eval_rmse": 1.489858627319336,
|
620 |
+
"eval_runtime": 4.2474,
|
621 |
+
"eval_samples_per_second": 231.905,
|
622 |
+
"eval_steps_per_second": 29.194,
|
623 |
+
"step": 26676
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 27.33,
|
627 |
+
"learning_rate": 4.534412955465588e-06,
|
628 |
+
"loss": 0.4395,
|
629 |
+
"step": 27000
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 27.83,
|
633 |
+
"learning_rate": 4.433198380566802e-06,
|
634 |
+
"loss": 0.3985,
|
635 |
+
"step": 27500
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 28.0,
|
639 |
+
"eval_loss": 2.2451844215393066,
|
640 |
+
"eval_mae": 1.1653474569320679,
|
641 |
+
"eval_mse": 2.2451844215393066,
|
642 |
+
"eval_rmse": 1.4983938932418823,
|
643 |
+
"eval_runtime": 4.5968,
|
644 |
+
"eval_samples_per_second": 214.279,
|
645 |
+
"eval_steps_per_second": 26.975,
|
646 |
+
"step": 27664
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 28.34,
|
650 |
+
"learning_rate": 4.3319838056680166e-06,
|
651 |
+
"loss": 0.3633,
|
652 |
+
"step": 28000
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"epoch": 28.85,
|
656 |
+
"learning_rate": 4.230769230769231e-06,
|
657 |
+
"loss": 0.4055,
|
658 |
+
"step": 28500
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 29.0,
|
662 |
+
"eval_loss": 2.1678428649902344,
|
663 |
+
"eval_mae": 1.1424471139907837,
|
664 |
+
"eval_mse": 2.1678428649902344,
|
665 |
+
"eval_rmse": 1.4723596572875977,
|
666 |
+
"eval_runtime": 3.4579,
|
667 |
+
"eval_samples_per_second": 284.854,
|
668 |
+
"eval_steps_per_second": 35.86,
|
669 |
+
"step": 28652
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 29.35,
|
673 |
+
"learning_rate": 4.1295546558704455e-06,
|
674 |
+
"loss": 0.4101,
|
675 |
+
"step": 29000
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 29.86,
|
679 |
+
"learning_rate": 4.028340080971661e-06,
|
680 |
+
"loss": 0.3916,
|
681 |
+
"step": 29500
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 30.0,
|
685 |
+
"eval_loss": 2.2453699111938477,
|
686 |
+
"eval_mae": 1.166300654411316,
|
687 |
+
"eval_mse": 2.2453699111938477,
|
688 |
+
"eval_rmse": 1.4984558820724487,
|
689 |
+
"eval_runtime": 2.9933,
|
690 |
+
"eval_samples_per_second": 329.066,
|
691 |
+
"eval_steps_per_second": 41.426,
|
692 |
+
"step": 29640
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 30.36,
|
696 |
+
"learning_rate": 3.9271255060728745e-06,
|
697 |
+
"loss": 0.3769,
|
698 |
+
"step": 30000
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 30.87,
|
702 |
+
"learning_rate": 3.825910931174089e-06,
|
703 |
+
"loss": 0.3905,
|
704 |
+
"step": 30500
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 31.0,
|
708 |
+
"eval_loss": 2.278787136077881,
|
709 |
+
"eval_mae": 1.170925259590149,
|
710 |
+
"eval_mse": 2.278787136077881,
|
711 |
+
"eval_rmse": 1.5095652341842651,
|
712 |
+
"eval_runtime": 2.1743,
|
713 |
+
"eval_samples_per_second": 453.018,
|
714 |
+
"eval_steps_per_second": 57.03,
|
715 |
+
"step": 30628
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 31.38,
|
719 |
+
"learning_rate": 3.724696356275304e-06,
|
720 |
+
"loss": 0.3638,
|
721 |
+
"step": 31000
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 31.88,
|
725 |
+
"learning_rate": 3.6234817813765184e-06,
|
726 |
+
"loss": 0.4033,
|
727 |
+
"step": 31500
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 32.0,
|
731 |
+
"eval_loss": 2.218869686126709,
|
732 |
+
"eval_mae": 1.1555440425872803,
|
733 |
+
"eval_mse": 2.218869686126709,
|
734 |
+
"eval_rmse": 1.4895870685577393,
|
735 |
+
"eval_runtime": 2.8668,
|
736 |
+
"eval_samples_per_second": 343.59,
|
737 |
+
"eval_steps_per_second": 43.254,
|
738 |
+
"step": 31616
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 32.39,
|
742 |
+
"learning_rate": 3.522267206477733e-06,
|
743 |
+
"loss": 0.3432,
|
744 |
+
"step": 32000
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 32.89,
|
748 |
+
"learning_rate": 3.421052631578948e-06,
|
749 |
+
"loss": 0.3603,
|
750 |
+
"step": 32500
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 33.0,
|
754 |
+
"eval_loss": 2.2483489513397217,
|
755 |
+
"eval_mae": 1.1578136682510376,
|
756 |
+
"eval_mse": 2.2483489513397217,
|
757 |
+
"eval_rmse": 1.4994494915008545,
|
758 |
+
"eval_runtime": 2.7175,
|
759 |
+
"eval_samples_per_second": 362.47,
|
760 |
+
"eval_steps_per_second": 45.631,
|
761 |
+
"step": 32604
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 33.4,
|
765 |
+
"learning_rate": 3.3198380566801623e-06,
|
766 |
+
"loss": 0.3832,
|
767 |
+
"step": 33000
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 33.91,
|
771 |
+
"learning_rate": 3.218623481781377e-06,
|
772 |
+
"loss": 0.3955,
|
773 |
+
"step": 33500
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 34.0,
|
777 |
+
"eval_loss": 2.2034738063812256,
|
778 |
+
"eval_mae": 1.148417353630066,
|
779 |
+
"eval_mse": 2.2034738063812256,
|
780 |
+
"eval_rmse": 1.484410285949707,
|
781 |
+
"eval_runtime": 2.6975,
|
782 |
+
"eval_samples_per_second": 365.15,
|
783 |
+
"eval_steps_per_second": 45.968,
|
784 |
+
"step": 33592
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 34.41,
|
788 |
+
"learning_rate": 3.1174089068825913e-06,
|
789 |
+
"loss": 0.3517,
|
790 |
+
"step": 34000
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 34.92,
|
794 |
+
"learning_rate": 3.0161943319838062e-06,
|
795 |
+
"loss": 0.3802,
|
796 |
+
"step": 34500
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 35.0,
|
800 |
+
"eval_loss": 2.2388076782226562,
|
801 |
+
"eval_mae": 1.1580203771591187,
|
802 |
+
"eval_mse": 2.238807201385498,
|
803 |
+
"eval_rmse": 1.4962644577026367,
|
804 |
+
"eval_runtime": 2.781,
|
805 |
+
"eval_samples_per_second": 354.184,
|
806 |
+
"eval_steps_per_second": 44.588,
|
807 |
+
"step": 34580
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 35.43,
|
811 |
+
"learning_rate": 2.9149797570850203e-06,
|
812 |
+
"loss": 0.3543,
|
813 |
+
"step": 35000
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 35.93,
|
817 |
+
"learning_rate": 2.8137651821862348e-06,
|
818 |
+
"loss": 0.3818,
|
819 |
+
"step": 35500
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 36.0,
|
823 |
+
"eval_loss": 2.3153350353240967,
|
824 |
+
"eval_mae": 1.178168773651123,
|
825 |
+
"eval_mse": 2.3153350353240967,
|
826 |
+
"eval_rmse": 1.5216225385665894,
|
827 |
+
"eval_runtime": 2.7673,
|
828 |
+
"eval_samples_per_second": 355.946,
|
829 |
+
"eval_steps_per_second": 44.81,
|
830 |
+
"step": 35568
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 36.44,
|
834 |
+
"learning_rate": 2.7125506072874497e-06,
|
835 |
+
"loss": 0.3451,
|
836 |
+
"step": 36000
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 36.94,
|
840 |
+
"learning_rate": 2.6113360323886646e-06,
|
841 |
+
"loss": 0.3837,
|
842 |
+
"step": 36500
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 37.0,
|
846 |
+
"eval_loss": 2.2114505767822266,
|
847 |
+
"eval_mae": 1.1500502824783325,
|
848 |
+
"eval_mse": 2.2114510536193848,
|
849 |
+
"eval_rmse": 1.4870948791503906,
|
850 |
+
"eval_runtime": 4.6473,
|
851 |
+
"eval_samples_per_second": 211.95,
|
852 |
+
"eval_steps_per_second": 26.682,
|
853 |
+
"step": 36556
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 37.45,
|
857 |
+
"learning_rate": 2.5101214574898787e-06,
|
858 |
+
"loss": 0.3335,
|
859 |
+
"step": 37000
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 37.96,
|
863 |
+
"learning_rate": 2.408906882591093e-06,
|
864 |
+
"loss": 0.3724,
|
865 |
+
"step": 37500
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 38.0,
|
869 |
+
"eval_loss": 2.190290927886963,
|
870 |
+
"eval_mae": 1.1481947898864746,
|
871 |
+
"eval_mse": 2.190290689468384,
|
872 |
+
"eval_rmse": 1.4799630641937256,
|
873 |
+
"eval_runtime": 4.4593,
|
874 |
+
"eval_samples_per_second": 220.888,
|
875 |
+
"eval_steps_per_second": 27.807,
|
876 |
+
"step": 37544
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 38.46,
|
880 |
+
"learning_rate": 2.307692307692308e-06,
|
881 |
+
"loss": 0.3631,
|
882 |
+
"step": 38000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 38.97,
|
886 |
+
"learning_rate": 2.2064777327935226e-06,
|
887 |
+
"loss": 0.3525,
|
888 |
+
"step": 38500
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 39.0,
|
892 |
+
"eval_loss": 2.208022117614746,
|
893 |
+
"eval_mae": 1.1508959531784058,
|
894 |
+
"eval_mse": 2.208022117614746,
|
895 |
+
"eval_rmse": 1.4859415292739868,
|
896 |
+
"eval_runtime": 4.5419,
|
897 |
+
"eval_samples_per_second": 216.868,
|
898 |
+
"eval_steps_per_second": 27.301,
|
899 |
+
"step": 38532
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 39.47,
|
903 |
+
"learning_rate": 2.105263157894737e-06,
|
904 |
+
"loss": 0.3589,
|
905 |
+
"step": 39000
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 39.98,
|
909 |
+
"learning_rate": 2.0040485829959516e-06,
|
910 |
+
"loss": 0.3477,
|
911 |
+
"step": 39500
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 40.0,
|
915 |
+
"eval_loss": 2.2591028213500977,
|
916 |
+
"eval_mae": 1.1669268608093262,
|
917 |
+
"eval_mse": 2.2591030597686768,
|
918 |
+
"eval_rmse": 1.5030312538146973,
|
919 |
+
"eval_runtime": 4.628,
|
920 |
+
"eval_samples_per_second": 212.837,
|
921 |
+
"eval_steps_per_second": 26.794,
|
922 |
+
"step": 39520
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 40.49,
|
926 |
+
"learning_rate": 1.902834008097166e-06,
|
927 |
+
"loss": 0.3239,
|
928 |
+
"step": 40000
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 40.99,
|
932 |
+
"learning_rate": 1.8016194331983807e-06,
|
933 |
+
"loss": 0.3891,
|
934 |
+
"step": 40500
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 41.0,
|
938 |
+
"eval_loss": 2.2003180980682373,
|
939 |
+
"eval_mae": 1.1513614654541016,
|
940 |
+
"eval_mse": 2.2003180980682373,
|
941 |
+
"eval_rmse": 1.483346939086914,
|
942 |
+
"eval_runtime": 4.722,
|
943 |
+
"eval_samples_per_second": 208.597,
|
944 |
+
"eval_steps_per_second": 26.26,
|
945 |
+
"step": 40508
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 41.5,
|
949 |
+
"learning_rate": 1.7004048582995952e-06,
|
950 |
+
"loss": 0.3474,
|
951 |
+
"step": 41000
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 42.0,
|
955 |
+
"eval_loss": 2.2396390438079834,
|
956 |
+
"eval_mae": 1.1607612371444702,
|
957 |
+
"eval_mse": 2.2396390438079834,
|
958 |
+
"eval_rmse": 1.4965423345565796,
|
959 |
+
"eval_runtime": 4.5927,
|
960 |
+
"eval_samples_per_second": 214.471,
|
961 |
+
"eval_steps_per_second": 26.999,
|
962 |
+
"step": 41496
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 42.0,
|
966 |
+
"learning_rate": 1.59919028340081e-06,
|
967 |
+
"loss": 0.347,
|
968 |
+
"step": 41500
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 42.51,
|
972 |
+
"learning_rate": 1.4979757085020244e-06,
|
973 |
+
"loss": 0.3173,
|
974 |
+
"step": 42000
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 43.0,
|
978 |
+
"eval_loss": 2.2095425128936768,
|
979 |
+
"eval_mae": 1.151437520980835,
|
980 |
+
"eval_mse": 2.2095425128936768,
|
981 |
+
"eval_rmse": 1.4864530563354492,
|
982 |
+
"eval_runtime": 4.6099,
|
983 |
+
"eval_samples_per_second": 213.67,
|
984 |
+
"eval_steps_per_second": 26.899,
|
985 |
+
"step": 42484
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 43.02,
|
989 |
+
"learning_rate": 1.3967611336032391e-06,
|
990 |
+
"loss": 0.3691,
|
991 |
+
"step": 42500
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 43.52,
|
995 |
+
"learning_rate": 1.2955465587044536e-06,
|
996 |
+
"loss": 0.335,
|
997 |
+
"step": 43000
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 44.0,
|
1001 |
+
"eval_loss": 2.1894824504852295,
|
1002 |
+
"eval_mae": 1.146257758140564,
|
1003 |
+
"eval_mse": 2.1894824504852295,
|
1004 |
+
"eval_rmse": 1.4796899557113647,
|
1005 |
+
"eval_runtime": 4.6282,
|
1006 |
+
"eval_samples_per_second": 212.828,
|
1007 |
+
"eval_steps_per_second": 26.793,
|
1008 |
+
"step": 43472
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 44.03,
|
1012 |
+
"learning_rate": 1.1943319838056681e-06,
|
1013 |
+
"loss": 0.3441,
|
1014 |
+
"step": 43500
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 44.53,
|
1018 |
+
"learning_rate": 1.0931174089068828e-06,
|
1019 |
+
"loss": 0.3443,
|
1020 |
+
"step": 44000
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 45.0,
|
1024 |
+
"eval_loss": 2.2246272563934326,
|
1025 |
+
"eval_mae": 1.1584477424621582,
|
1026 |
+
"eval_mse": 2.2246272563934326,
|
1027 |
+
"eval_rmse": 1.491518497467041,
|
1028 |
+
"eval_runtime": 4.7245,
|
1029 |
+
"eval_samples_per_second": 208.487,
|
1030 |
+
"eval_steps_per_second": 26.246,
|
1031 |
+
"step": 44460
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 45.04,
|
1035 |
+
"learning_rate": 9.919028340080973e-07,
|
1036 |
+
"loss": 0.3242,
|
1037 |
+
"step": 44500
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 45.55,
|
1041 |
+
"learning_rate": 8.906882591093118e-07,
|
1042 |
+
"loss": 0.3604,
|
1043 |
+
"step": 45000
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 46.0,
|
1047 |
+
"eval_loss": 2.2161009311676025,
|
1048 |
+
"eval_mae": 1.1535395383834839,
|
1049 |
+
"eval_mse": 2.2161009311676025,
|
1050 |
+
"eval_rmse": 1.4886574745178223,
|
1051 |
+
"eval_runtime": 4.6251,
|
1052 |
+
"eval_samples_per_second": 212.97,
|
1053 |
+
"eval_steps_per_second": 26.81,
|
1054 |
+
"step": 45448
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 46.05,
|
1058 |
+
"learning_rate": 7.894736842105263e-07,
|
1059 |
+
"loss": 0.3321,
|
1060 |
+
"step": 45500
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 46.56,
|
1064 |
+
"learning_rate": 6.882591093117409e-07,
|
1065 |
+
"loss": 0.3422,
|
1066 |
+
"step": 46000
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 47.0,
|
1070 |
+
"eval_loss": 2.2106308937072754,
|
1071 |
+
"eval_mae": 1.1536109447479248,
|
1072 |
+
"eval_mse": 2.2106311321258545,
|
1073 |
+
"eval_rmse": 1.4868191480636597,
|
1074 |
+
"eval_runtime": 4.7086,
|
1075 |
+
"eval_samples_per_second": 209.193,
|
1076 |
+
"eval_steps_per_second": 26.335,
|
1077 |
+
"step": 46436
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 47.06,
|
1081 |
+
"learning_rate": 5.870445344129555e-07,
|
1082 |
+
"loss": 0.3223,
|
1083 |
+
"step": 46500
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 47.57,
|
1087 |
+
"learning_rate": 4.858299595141701e-07,
|
1088 |
+
"loss": 0.3253,
|
1089 |
+
"step": 47000
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 48.0,
|
1093 |
+
"eval_loss": 2.2084391117095947,
|
1094 |
+
"eval_mae": 1.1512514352798462,
|
1095 |
+
"eval_mse": 2.2084388732910156,
|
1096 |
+
"eval_rmse": 1.4860817193984985,
|
1097 |
+
"eval_runtime": 4.6784,
|
1098 |
+
"eval_samples_per_second": 210.541,
|
1099 |
+
"eval_steps_per_second": 26.505,
|
1100 |
+
"step": 47424
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 48.08,
|
1104 |
+
"learning_rate": 3.846153846153847e-07,
|
1105 |
+
"loss": 0.3418,
|
1106 |
+
"step": 47500
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 48.58,
|
1110 |
+
"learning_rate": 2.834008097165992e-07,
|
1111 |
+
"loss": 0.3309,
|
1112 |
+
"step": 48000
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 49.0,
|
1116 |
+
"eval_loss": 2.2103824615478516,
|
1117 |
+
"eval_mae": 1.1521849632263184,
|
1118 |
+
"eval_mse": 2.2103824615478516,
|
1119 |
+
"eval_rmse": 1.486735463142395,
|
1120 |
+
"eval_runtime": 3.2286,
|
1121 |
+
"eval_samples_per_second": 305.083,
|
1122 |
+
"eval_steps_per_second": 38.406,
|
1123 |
+
"step": 48412
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 49.09,
|
1127 |
+
"learning_rate": 1.8218623481781377e-07,
|
1128 |
+
"loss": 0.3491,
|
1129 |
+
"step": 48500
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 49.6,
|
1133 |
+
"learning_rate": 8.097165991902835e-08,
|
1134 |
+
"loss": 0.3148,
|
1135 |
+
"step": 49000
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 50.0,
|
1139 |
+
"eval_loss": 2.2166781425476074,
|
1140 |
+
"eval_mae": 1.1540616750717163,
|
1141 |
+
"eval_mse": 2.2166783809661865,
|
1142 |
+
"eval_rmse": 1.4888513088226318,
|
1143 |
+
"eval_runtime": 4.5752,
|
1144 |
+
"eval_samples_per_second": 215.291,
|
1145 |
+
"eval_steps_per_second": 27.103,
|
1146 |
+
"step": 49400
|
1147 |
+
}
|
1148 |
+
],
|
1149 |
+
"max_steps": 49400,
|
1150 |
+
"num_train_epochs": 50,
|
1151 |
+
"total_flos": 2.61545223472896e+16,
|
1152 |
+
"trial_name": null,
|
1153 |
+
"trial_params": null
|
1154 |
+
}
|
checkpoint-49400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c20e300fc0f89a9cbc3f36d83d87f965a132958a9f96addf740aaf2a30cea4
|
3 |
+
size 2927
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "data/saved_models/our_90epochs_saved_model",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSelfiesClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "roberta",
|
24 |
+
"num_attention_heads": 4,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 1,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.15.0",
|
30 |
+
"type_vocab_size": 1,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 800
|
33 |
+
}
|
pdbbindfull.out
ADDED
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Some weights of the model checkpoint at data/saved_models/our_90epochs_saved_model were not used when initializing RobertaForSelfiesClassification: ['lm_head.dense.bias', 'lm_head.bias', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight', 'lm_head.dense.weight']
|
2 |
+
- This IS expected if you are initializing RobertaForSelfiesClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
|
3 |
+
- This IS NOT expected if you are initializing RobertaForSelfiesClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
|
4 |
+
Some weights of RobertaForSelfiesClassification were not initialized from the model checkpoint at data/saved_models/our_90epochs_saved_model and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.weight', 'classifier.out_proj.bias', 'roberta.pooler.dense.bias', 'roberta.pooler.dense.weight']
|
5 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
6 |
+
Not using a scaler.
|
7 |
+
***** Running training *****
|
8 |
+
Num examples = 7898
|
9 |
+
Num Epochs = 50
|
10 |
+
Instantaneous batch size per device = 8
|
11 |
+
Total train batch size (w. parallel, distributed & accumulation) = 8
|
12 |
+
Gradient Accumulation steps = 1
|
13 |
+
Total optimization steps = 49400
|
14 |
+
{'loss': 4.6519, 'learning_rate': 9.898785425101214e-06, 'epoch': 0.51}
|
15 |
+
***** Running Evaluation *****
|
16 |
+
Num examples = 985
|
17 |
+
Batch size = 8
|
18 |
+
{'eval_loss': 2.3328564167022705, 'eval_mse': 2.3328561782836914, 'eval_rmse': 1.5273690223693848, 'eval_mae': 1.2115871906280518, 'eval_runtime': 2.139, 'eval_samples_per_second': 460.504, 'eval_steps_per_second': 57.972, 'epoch': 1.0}
|
19 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-988
|
20 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-988/config.json
|
21 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-988/pytorch_model.bin
|
22 |
+
{'loss': 1.9813, 'learning_rate': 9.79757085020243e-06, 'epoch': 1.01}
|
23 |
+
{'loss': 1.7364, 'learning_rate': 9.696356275303645e-06, 'epoch': 1.52}
|
24 |
+
***** Running Evaluation *****
|
25 |
+
Num examples = 985
|
26 |
+
Batch size = 8
|
27 |
+
{'eval_loss': 2.25815749168396, 'eval_mse': 2.25815749168396, 'eval_rmse': 1.5027166604995728, 'eval_mae': 1.1845210790634155, 'eval_runtime': 2.2991, 'eval_samples_per_second': 428.436, 'eval_steps_per_second': 53.935, 'epoch': 2.0}
|
28 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-1976
|
29 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-1976/config.json
|
30 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-1976/pytorch_model.bin
|
31 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-988] due to args.save_total_limit
|
32 |
+
{'loss': 1.6471, 'learning_rate': 9.595141700404859e-06, 'epoch': 2.02}
|
33 |
+
{'loss': 1.4318, 'learning_rate': 9.493927125506074e-06, 'epoch': 2.53}
|
34 |
+
***** Running Evaluation *****
|
35 |
+
Num examples = 985
|
36 |
+
Batch size = 8
|
37 |
+
{'eval_loss': 2.2711498737335205, 'eval_mse': 2.2711498737335205, 'eval_rmse': 1.5070334672927856, 'eval_mae': 1.195154070854187, 'eval_runtime': 1.9177, 'eval_samples_per_second': 513.633, 'eval_steps_per_second': 64.66, 'epoch': 3.0}
|
38 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-2964
|
39 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-2964/config.json
|
40 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-2964/pytorch_model.bin
|
41 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-1976] due to args.save_total_limit
|
42 |
+
{'loss': 1.3929, 'learning_rate': 9.392712550607288e-06, 'epoch': 3.04}
|
43 |
+
{'loss': 1.2099, 'learning_rate': 9.291497975708503e-06, 'epoch': 3.54}
|
44 |
+
***** Running Evaluation *****
|
45 |
+
Num examples = 985
|
46 |
+
Batch size = 8
|
47 |
+
{'eval_loss': 2.5615780353546143, 'eval_mse': 2.5615780353546143, 'eval_rmse': 1.60049307346344, 'eval_mae': 1.2618587017059326, 'eval_runtime': 2.4694, 'eval_samples_per_second': 398.879, 'eval_steps_per_second': 50.214, 'epoch': 4.0}
|
48 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-3952
|
49 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-3952/config.json
|
50 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-3952/pytorch_model.bin
|
51 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-2964] due to args.save_total_limit
|
52 |
+
{'loss': 1.1585, 'learning_rate': 9.190283400809717e-06, 'epoch': 4.05}
|
53 |
+
{'loss': 0.9984, 'learning_rate': 9.089068825910932e-06, 'epoch': 4.55}
|
54 |
+
***** Running Evaluation *****
|
55 |
+
Num examples = 985
|
56 |
+
Batch size = 8
|
57 |
+
{'eval_loss': 2.386498212814331, 'eval_mse': 2.386498212814331, 'eval_rmse': 1.5448294878005981, 'eval_mae': 1.2156014442443848, 'eval_runtime': 2.1201, 'eval_samples_per_second': 464.611, 'eval_steps_per_second': 58.489, 'epoch': 5.0}
|
58 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-4940
|
59 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-4940/config.json
|
60 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-4940/pytorch_model.bin
|
61 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-3952] due to args.save_total_limit
|
62 |
+
{'loss': 1.0114, 'learning_rate': 8.987854251012147e-06, 'epoch': 5.06}
|
63 |
+
{'loss': 0.897, 'learning_rate': 8.886639676113361e-06, 'epoch': 5.57}
|
64 |
+
***** Running Evaluation *****
|
65 |
+
Num examples = 985
|
66 |
+
Batch size = 8
|
67 |
+
{'eval_loss': 2.3048605918884277, 'eval_mse': 2.3048605918884277, 'eval_rmse': 1.5181766748428345, 'eval_mae': 1.186144471168518, 'eval_runtime': 2.4807, 'eval_samples_per_second': 397.063, 'eval_steps_per_second': 49.986, 'epoch': 6.0}
|
68 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-5928
|
69 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-5928/config.json
|
70 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-5928/pytorch_model.bin
|
71 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-4940] due to args.save_total_limit
|
72 |
+
{'loss': 0.912, 'learning_rate': 8.785425101214575e-06, 'epoch': 6.07}
|
73 |
+
{'loss': 0.7973, 'learning_rate': 8.68421052631579e-06, 'epoch': 6.58}
|
74 |
+
***** Running Evaluation *****
|
75 |
+
Num examples = 985
|
76 |
+
Batch size = 8
|
77 |
+
{'eval_loss': 2.423027992248535, 'eval_mse': 2.4230284690856934, 'eval_rmse': 1.556607961654663, 'eval_mae': 1.223141074180603, 'eval_runtime': 2.3801, 'eval_samples_per_second': 413.851, 'eval_steps_per_second': 52.099, 'epoch': 7.0}
|
78 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-6916
|
79 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-6916/config.json
|
80 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-6916/pytorch_model.bin
|
81 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-5928] due to args.save_total_limit
|
82 |
+
{'loss': 0.8141, 'learning_rate': 8.582995951417005e-06, 'epoch': 7.09}
|
83 |
+
{'loss': 0.7115, 'learning_rate': 8.481781376518219e-06, 'epoch': 7.59}
|
84 |
+
***** Running Evaluation *****
|
85 |
+
Num examples = 985
|
86 |
+
Batch size = 8
|
87 |
+
{'eval_loss': 2.51936936378479, 'eval_mse': 2.51936936378479, 'eval_rmse': 1.587252140045166, 'eval_mae': 1.2446390390396118, 'eval_runtime': 2.2497, 'eval_samples_per_second': 437.844, 'eval_steps_per_second': 55.119, 'epoch': 8.0}
|
88 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-7904
|
89 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-7904/config.json
|
90 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-7904/pytorch_model.bin
|
91 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-6916] due to args.save_total_limit
|
92 |
+
{'loss': 0.7455, 'learning_rate': 8.380566801619434e-06, 'epoch': 8.1}
|
93 |
+
{'loss': 0.6548, 'learning_rate': 8.279352226720648e-06, 'epoch': 8.6}
|
94 |
+
***** Running Evaluation *****
|
95 |
+
Num examples = 985
|
96 |
+
Batch size = 8
|
97 |
+
{'eval_loss': 2.3894152641296387, 'eval_mse': 2.3894152641296387, 'eval_rmse': 1.5457733869552612, 'eval_mae': 1.20915687084198, 'eval_runtime': 2.012, 'eval_samples_per_second': 489.572, 'eval_steps_per_second': 61.631, 'epoch': 9.0}
|
98 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-8892
|
99 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-8892/config.json
|
100 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-8892/pytorch_model.bin
|
101 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-7904] due to args.save_total_limit
|
102 |
+
{'loss': 0.6625, 'learning_rate': 8.178137651821862e-06, 'epoch': 9.11}
|
103 |
+
{'loss': 0.6466, 'learning_rate': 8.076923076923077e-06, 'epoch': 9.62}
|
104 |
+
***** Running Evaluation *****
|
105 |
+
Num examples = 985
|
106 |
+
Batch size = 8
|
107 |
+
{'eval_loss': 2.3797826766967773, 'eval_mse': 2.3797826766967773, 'eval_rmse': 1.5426543951034546, 'eval_mae': 1.209175944328308, 'eval_runtime': 1.9282, 'eval_samples_per_second': 510.852, 'eval_steps_per_second': 64.31, 'epoch': 10.0}
|
108 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-9880
|
109 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-9880/config.json
|
110 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-9880/pytorch_model.bin
|
111 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-8892] due to args.save_total_limit
|
112 |
+
{'loss': 0.6429, 'learning_rate': 7.975708502024292e-06, 'epoch': 10.12}
|
113 |
+
{'loss': 0.6218, 'learning_rate': 7.874493927125508e-06, 'epoch': 10.63}
|
114 |
+
***** Running Evaluation *****
|
115 |
+
Num examples = 985
|
116 |
+
Batch size = 8
|
117 |
+
{'eval_loss': 2.325528383255005, 'eval_mse': 2.325528383255005, 'eval_rmse': 1.5249682664871216, 'eval_mae': 1.197866678237915, 'eval_runtime': 2.2819, 'eval_samples_per_second': 431.658, 'eval_steps_per_second': 54.341, 'epoch': 11.0}
|
118 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-10868
|
119 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-10868/config.json
|
120 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-10868/pytorch_model.bin
|
121 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-9880] due to args.save_total_limit
|
122 |
+
{'loss': 0.596, 'learning_rate': 7.773279352226721e-06, 'epoch': 11.13}
|
123 |
+
{'loss': 0.5498, 'learning_rate': 7.672064777327935e-06, 'epoch': 11.64}
|
124 |
+
***** Running Evaluation *****
|
125 |
+
Num examples = 985
|
126 |
+
Batch size = 8
|
127 |
+
{'eval_loss': 2.391416072845459, 'eval_mse': 2.391416072845459, 'eval_rmse': 1.5464204549789429, 'eval_mae': 1.2055319547653198, 'eval_runtime': 2.3484, 'eval_samples_per_second': 419.443, 'eval_steps_per_second': 52.803, 'epoch': 12.0}
|
128 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-11856
|
129 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-11856/config.json
|
130 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-11856/pytorch_model.bin
|
131 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-10868] due to args.save_total_limit
|
132 |
+
{'loss': 0.5617, 'learning_rate': 7.570850202429151e-06, 'epoch': 12.15}
|
133 |
+
{'loss': 0.5403, 'learning_rate': 7.469635627530365e-06, 'epoch': 12.65}
|
134 |
+
***** Running Evaluation *****
|
135 |
+
Num examples = 985
|
136 |
+
Batch size = 8
|
137 |
+
{'eval_loss': 2.4148483276367188, 'eval_mse': 2.4148483276367188, 'eval_rmse': 1.5539782047271729, 'eval_mae': 1.2168691158294678, 'eval_runtime': 2.3371, 'eval_samples_per_second': 421.463, 'eval_steps_per_second': 53.057, 'epoch': 13.0}
|
138 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-12844
|
139 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-12844/config.json
|
140 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-12844/pytorch_model.bin
|
141 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-11856] due to args.save_total_limit
|
142 |
+
{'loss': 0.5424, 'learning_rate': 7.368421052631579e-06, 'epoch': 13.16}
|
143 |
+
{'loss': 0.5392, 'learning_rate': 7.267206477732795e-06, 'epoch': 13.66}
|
144 |
+
***** Running Evaluation *****
|
145 |
+
Num examples = 985
|
146 |
+
Batch size = 8
|
147 |
+
{'eval_loss': 2.429582357406616, 'eval_mse': 2.429582357406616, 'eval_rmse': 1.5587117671966553, 'eval_mae': 1.2232253551483154, 'eval_runtime': 1.971, 'eval_samples_per_second': 499.752, 'eval_steps_per_second': 62.913, 'epoch': 14.0}
|
148 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-13832
|
149 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-13832/config.json
|
150 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-13832/pytorch_model.bin
|
151 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-12844] due to args.save_total_limit
|
152 |
+
{'loss': 0.5105, 'learning_rate': 7.165991902834008e-06, 'epoch': 14.17}
|
153 |
+
{'loss': 0.5224, 'learning_rate': 7.064777327935223e-06, 'epoch': 14.68}
|
154 |
+
***** Running Evaluation *****
|
155 |
+
Num examples = 985
|
156 |
+
Batch size = 8
|
157 |
+
{'eval_loss': 2.279872417449951, 'eval_mse': 2.279872417449951, 'eval_rmse': 1.5099246501922607, 'eval_mae': 1.1799190044403076, 'eval_runtime': 2.2712, 'eval_samples_per_second': 433.694, 'eval_steps_per_second': 54.597, 'epoch': 15.0}
|
158 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-14820
|
159 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-14820/config.json
|
160 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-14820/pytorch_model.bin
|
161 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-13832] due to args.save_total_limit
|
162 |
+
{'loss': 0.5082, 'learning_rate': 6.963562753036438e-06, 'epoch': 15.18}
|
163 |
+
{'loss': 0.4868, 'learning_rate': 6.862348178137653e-06, 'epoch': 15.69}
|
164 |
+
***** Running Evaluation *****
|
165 |
+
Num examples = 985
|
166 |
+
Batch size = 8
|
167 |
+
{'eval_loss': 2.309877634048462, 'eval_mse': 2.309877634048462, 'eval_rmse': 1.519828200340271, 'eval_mae': 1.1822220087051392, 'eval_runtime': 1.9368, 'eval_samples_per_second': 508.564, 'eval_steps_per_second': 64.022, 'epoch': 16.0}
|
168 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-15808
|
169 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-15808/config.json
|
170 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-15808/pytorch_model.bin
|
171 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-14820] due to args.save_total_limit
|
172 |
+
{'loss': 0.5021, 'learning_rate': 6.761133603238867e-06, 'epoch': 16.19}
|
173 |
+
{'loss': 0.4702, 'learning_rate': 6.6599190283400816e-06, 'epoch': 16.7}
|
174 |
+
***** Running Evaluation *****
|
175 |
+
Num examples = 985
|
176 |
+
Batch size = 8
|
177 |
+
{'eval_loss': 2.205157518386841, 'eval_mse': 2.205157518386841, 'eval_rmse': 1.4849772453308105, 'eval_mae': 1.1669542789459229, 'eval_runtime': 2.2927, 'eval_samples_per_second': 429.627, 'eval_steps_per_second': 54.085, 'epoch': 17.0}
|
178 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-16796
|
179 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-16796/config.json
|
180 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-16796/pytorch_model.bin
|
181 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-15808] due to args.save_total_limit
|
182 |
+
{'loss': 0.4905, 'learning_rate': 6.558704453441296e-06, 'epoch': 17.21}
|
183 |
+
{'loss': 0.4665, 'learning_rate': 6.457489878542511e-06, 'epoch': 17.71}
|
184 |
+
***** Running Evaluation *****
|
185 |
+
Num examples = 985
|
186 |
+
Batch size = 8
|
187 |
+
{'eval_loss': 2.323201894760132, 'eval_mse': 2.323201894760132, 'eval_rmse': 1.5242053270339966, 'eval_mae': 1.1936134099960327, 'eval_runtime': 2.1851, 'eval_samples_per_second': 450.772, 'eval_steps_per_second': 56.747, 'epoch': 18.0}
|
188 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-17784
|
189 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-17784/config.json
|
190 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-17784/pytorch_model.bin
|
191 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-16796] due to args.save_total_limit
|
192 |
+
{'loss': 0.4431, 'learning_rate': 6.356275303643725e-06, 'epoch': 18.22}
|
193 |
+
{'loss': 0.483, 'learning_rate': 6.2550607287449395e-06, 'epoch': 18.72}
|
194 |
+
***** Running Evaluation *****
|
195 |
+
Num examples = 985
|
196 |
+
Batch size = 8
|
197 |
+
{'eval_loss': 2.3569979667663574, 'eval_mse': 2.3569979667663574, 'eval_rmse': 1.5352517366409302, 'eval_mae': 1.2059428691864014, 'eval_runtime': 6.1451, 'eval_samples_per_second': 160.29, 'eval_steps_per_second': 20.179, 'epoch': 19.0}
|
198 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-18772
|
199 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-18772/config.json
|
200 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-18772/pytorch_model.bin
|
201 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-17784] due to args.save_total_limit
|
202 |
+
{'loss': 0.4433, 'learning_rate': 6.153846153846155e-06, 'epoch': 19.23}
|
203 |
+
{'loss': 0.4561, 'learning_rate': 6.0526315789473685e-06, 'epoch': 19.74}
|
204 |
+
***** Running Evaluation *****
|
205 |
+
Num examples = 985
|
206 |
+
Batch size = 8
|
207 |
+
{'eval_loss': 2.313786268234253, 'eval_mse': 2.313786268234253, 'eval_rmse': 1.5211135149002075, 'eval_mae': 1.190987229347229, 'eval_runtime': 6.1814, 'eval_samples_per_second': 159.348, 'eval_steps_per_second': 20.06, 'epoch': 20.0}
|
208 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-19760
|
209 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-19760/config.json
|
210 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-19760/pytorch_model.bin
|
211 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-18772] due to args.save_total_limit
|
212 |
+
{'loss': 0.4688, 'learning_rate': 5.951417004048583e-06, 'epoch': 20.24}
|
213 |
+
{'loss': 0.4577, 'learning_rate': 5.850202429149798e-06, 'epoch': 20.75}
|
214 |
+
***** Running Evaluation *****
|
215 |
+
Num examples = 985
|
216 |
+
Batch size = 8
|
217 |
+
{'eval_loss': 2.2783560752868652, 'eval_mse': 2.2783560752868652, 'eval_rmse': 1.5094224214553833, 'eval_mae': 1.1627191305160522, 'eval_runtime': 6.5272, 'eval_samples_per_second': 150.907, 'eval_steps_per_second': 18.997, 'epoch': 21.0}
|
218 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-20748
|
219 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-20748/config.json
|
220 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-20748/pytorch_model.bin
|
221 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-19760] due to args.save_total_limit
|
222 |
+
{'loss': 0.4261, 'learning_rate': 5.748987854251013e-06, 'epoch': 21.26}
|
223 |
+
{'loss': 0.4251, 'learning_rate': 5.6477732793522265e-06, 'epoch': 21.76}
|
224 |
+
***** Running Evaluation *****
|
225 |
+
Num examples = 985
|
226 |
+
Batch size = 8
|
227 |
+
{'eval_loss': 2.3060412406921387, 'eval_mse': 2.3060412406921387, 'eval_rmse': 1.5185655355453491, 'eval_mae': 1.176581621170044, 'eval_runtime': 6.411, 'eval_samples_per_second': 153.641, 'eval_steps_per_second': 19.342, 'epoch': 22.0}
|
228 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-21736
|
229 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-21736/config.json
|
230 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-21736/pytorch_model.bin
|
231 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-20748] due to args.save_total_limit
|
232 |
+
{'loss': 0.4235, 'learning_rate': 5.546558704453442e-06, 'epoch': 22.27}
|
233 |
+
{'loss': 0.4477, 'learning_rate': 5.445344129554656e-06, 'epoch': 22.77}
|
234 |
+
***** Running Evaluation *****
|
235 |
+
Num examples = 985
|
236 |
+
Batch size = 8
|
237 |
+
{'eval_loss': 2.3399007320404053, 'eval_mse': 2.339900493621826, 'eval_rmse': 1.5296733379364014, 'eval_mae': 1.1934117078781128, 'eval_runtime': 6.5358, 'eval_samples_per_second': 150.708, 'eval_steps_per_second': 18.972, 'epoch': 23.0}
|
238 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-22724
|
239 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-22724/config.json
|
240 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-22724/pytorch_model.bin
|
241 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-21736] due to args.save_total_limit
|
242 |
+
{'loss': 0.3849, 'learning_rate': 5.344129554655872e-06, 'epoch': 23.28}
|
243 |
+
{'loss': 0.4274, 'learning_rate': 5.242914979757085e-06, 'epoch': 23.79}
|
244 |
+
***** Running Evaluation *****
|
245 |
+
Num examples = 985
|
246 |
+
Batch size = 8
|
247 |
+
{'eval_loss': 2.2604634761810303, 'eval_mse': 2.2604634761810303, 'eval_rmse': 1.503483772277832, 'eval_mae': 1.1710097789764404, 'eval_runtime': 6.4581, 'eval_samples_per_second': 152.522, 'eval_steps_per_second': 19.201, 'epoch': 24.0}
|
248 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-23712
|
249 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-23712/config.json
|
250 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-23712/pytorch_model.bin
|
251 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-22724] due to args.save_total_limit
|
252 |
+
{'loss': 0.402, 'learning_rate': 5.1417004048583e-06, 'epoch': 24.29}
|
253 |
+
{'loss': 0.4176, 'learning_rate': 5.040485829959515e-06, 'epoch': 24.8}
|
254 |
+
***** Running Evaluation *****
|
255 |
+
Num examples = 985
|
256 |
+
Batch size = 8
|
257 |
+
{'eval_loss': 2.277299165725708, 'eval_mse': 2.277299404144287, 'eval_rmse': 1.5090724229812622, 'eval_mae': 1.1737443208694458, 'eval_runtime': 6.5489, 'eval_samples_per_second': 150.407, 'eval_steps_per_second': 18.935, 'epoch': 25.0}
|
258 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-24700
|
259 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-24700/config.json
|
260 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-24700/pytorch_model.bin
|
261 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-23712] due to args.save_total_limit
|
262 |
+
{'loss': 0.4278, 'learning_rate': 4.939271255060729e-06, 'epoch': 25.3}
|
263 |
+
{'loss': 0.4105, 'learning_rate': 4.838056680161944e-06, 'epoch': 25.81}
|
264 |
+
***** Running Evaluation *****
|
265 |
+
Num examples = 985
|
266 |
+
Batch size = 8
|
267 |
+
{'eval_loss': 2.3140110969543457, 'eval_mse': 2.3140110969543457, 'eval_rmse': 1.521187424659729, 'eval_mae': 1.1842072010040283, 'eval_runtime': 6.5703, 'eval_samples_per_second': 149.918, 'eval_steps_per_second': 18.873, 'epoch': 26.0}
|
268 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-25688
|
269 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-25688/config.json
|
270 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-25688/pytorch_model.bin
|
271 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-24700] due to args.save_total_limit
|
272 |
+
{'loss': 0.404, 'learning_rate': 4.736842105263158e-06, 'epoch': 26.32}
|
273 |
+
{'loss': 0.3843, 'learning_rate': 4.635627530364373e-06, 'epoch': 26.82}
|
274 |
+
***** Running Evaluation *****
|
275 |
+
Num examples = 985
|
276 |
+
Batch size = 8
|
277 |
+
{'eval_loss': 2.2196788787841797, 'eval_mse': 2.2196786403656006, 'eval_rmse': 1.489858627319336, 'eval_mae': 1.1630769968032837, 'eval_runtime': 4.2474, 'eval_samples_per_second': 231.905, 'eval_steps_per_second': 29.194, 'epoch': 27.0}
|
278 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-26676
|
279 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-26676/config.json
|
280 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-26676/pytorch_model.bin
|
281 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-25688] due to args.save_total_limit
|
282 |
+
{'loss': 0.4395, 'learning_rate': 4.534412955465588e-06, 'epoch': 27.33}
|
283 |
+
{'loss': 0.3985, 'learning_rate': 4.433198380566802e-06, 'epoch': 27.83}
|
284 |
+
***** Running Evaluation *****
|
285 |
+
Num examples = 985
|
286 |
+
Batch size = 8
|
287 |
+
{'eval_loss': 2.2451844215393066, 'eval_mse': 2.2451844215393066, 'eval_rmse': 1.4983938932418823, 'eval_mae': 1.1653474569320679, 'eval_runtime': 4.5968, 'eval_samples_per_second': 214.279, 'eval_steps_per_second': 26.975, 'epoch': 28.0}
|
288 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-27664
|
289 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-27664/config.json
|
290 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-27664/pytorch_model.bin
|
291 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-26676] due to args.save_total_limit
|
292 |
+
{'loss': 0.3633, 'learning_rate': 4.3319838056680166e-06, 'epoch': 28.34}
|
293 |
+
{'loss': 0.4055, 'learning_rate': 4.230769230769231e-06, 'epoch': 28.85}
|
294 |
+
***** Running Evaluation *****
|
295 |
+
Num examples = 985
|
296 |
+
Batch size = 8
|
297 |
+
{'eval_loss': 2.1678428649902344, 'eval_mse': 2.1678428649902344, 'eval_rmse': 1.4723596572875977, 'eval_mae': 1.1424471139907837, 'eval_runtime': 3.4579, 'eval_samples_per_second': 284.854, 'eval_steps_per_second': 35.86, 'epoch': 29.0}
|
298 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-28652
|
299 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-28652/config.json
|
300 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-28652/pytorch_model.bin
|
301 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-27664] due to args.save_total_limit
|
302 |
+
{'loss': 0.4101, 'learning_rate': 4.1295546558704455e-06, 'epoch': 29.35}
|
303 |
+
{'loss': 0.3916, 'learning_rate': 4.028340080971661e-06, 'epoch': 29.86}
|
304 |
+
***** Running Evaluation *****
|
305 |
+
Num examples = 985
|
306 |
+
Batch size = 8
|
307 |
+
{'eval_loss': 2.2453699111938477, 'eval_mse': 2.2453699111938477, 'eval_rmse': 1.4984558820724487, 'eval_mae': 1.166300654411316, 'eval_runtime': 2.9933, 'eval_samples_per_second': 329.066, 'eval_steps_per_second': 41.426, 'epoch': 30.0}
|
308 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-29640
|
309 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-29640/config.json
|
310 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-29640/pytorch_model.bin
|
311 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-28652] due to args.save_total_limit
|
312 |
+
{'loss': 0.3769, 'learning_rate': 3.9271255060728745e-06, 'epoch': 30.36}
|
313 |
+
{'loss': 0.3905, 'learning_rate': 3.825910931174089e-06, 'epoch': 30.87}
|
314 |
+
***** Running Evaluation *****
|
315 |
+
Num examples = 985
|
316 |
+
Batch size = 8
|
317 |
+
{'eval_loss': 2.278787136077881, 'eval_mse': 2.278787136077881, 'eval_rmse': 1.5095652341842651, 'eval_mae': 1.170925259590149, 'eval_runtime': 2.1743, 'eval_samples_per_second': 453.018, 'eval_steps_per_second': 57.03, 'epoch': 31.0}
|
318 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-30628
|
319 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-30628/config.json
|
320 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-30628/pytorch_model.bin
|
321 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-29640] due to args.save_total_limit
|
322 |
+
{'loss': 0.3638, 'learning_rate': 3.724696356275304e-06, 'epoch': 31.38}
|
323 |
+
{'loss': 0.4033, 'learning_rate': 3.6234817813765184e-06, 'epoch': 31.88}
|
324 |
+
***** Running Evaluation *****
|
325 |
+
Num examples = 985
|
326 |
+
Batch size = 8
|
327 |
+
{'eval_loss': 2.218869686126709, 'eval_mse': 2.218869686126709, 'eval_rmse': 1.4895870685577393, 'eval_mae': 1.1555440425872803, 'eval_runtime': 2.8668, 'eval_samples_per_second': 343.59, 'eval_steps_per_second': 43.254, 'epoch': 32.0}
|
328 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-31616
|
329 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-31616/config.json
|
330 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-31616/pytorch_model.bin
|
331 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-30628] due to args.save_total_limit
|
332 |
+
{'loss': 0.3432, 'learning_rate': 3.522267206477733e-06, 'epoch': 32.39}
|
333 |
+
{'loss': 0.3603, 'learning_rate': 3.421052631578948e-06, 'epoch': 32.89}
|
334 |
+
***** Running Evaluation *****
|
335 |
+
Num examples = 985
|
336 |
+
Batch size = 8
|
337 |
+
{'eval_loss': 2.2483489513397217, 'eval_mse': 2.2483489513397217, 'eval_rmse': 1.4994494915008545, 'eval_mae': 1.1578136682510376, 'eval_runtime': 2.7175, 'eval_samples_per_second': 362.47, 'eval_steps_per_second': 45.631, 'epoch': 33.0}
|
338 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-32604
|
339 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-32604/config.json
|
340 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-32604/pytorch_model.bin
|
341 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-31616] due to args.save_total_limit
|
342 |
+
{'loss': 0.3832, 'learning_rate': 3.3198380566801623e-06, 'epoch': 33.4}
|
343 |
+
{'loss': 0.3955, 'learning_rate': 3.218623481781377e-06, 'epoch': 33.91}
|
344 |
+
***** Running Evaluation *****
|
345 |
+
Num examples = 985
|
346 |
+
Batch size = 8
|
347 |
+
{'eval_loss': 2.2034738063812256, 'eval_mse': 2.2034738063812256, 'eval_rmse': 1.484410285949707, 'eval_mae': 1.148417353630066, 'eval_runtime': 2.6975, 'eval_samples_per_second': 365.15, 'eval_steps_per_second': 45.968, 'epoch': 34.0}
|
348 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-33592
|
349 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-33592/config.json
|
350 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-33592/pytorch_model.bin
|
351 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-32604] due to args.save_total_limit
|
352 |
+
{'loss': 0.3517, 'learning_rate': 3.1174089068825913e-06, 'epoch': 34.41}
|
353 |
+
{'loss': 0.3802, 'learning_rate': 3.0161943319838062e-06, 'epoch': 34.92}
|
354 |
+
***** Running Evaluation *****
|
355 |
+
Num examples = 985
|
356 |
+
Batch size = 8
|
357 |
+
{'eval_loss': 2.2388076782226562, 'eval_mse': 2.238807201385498, 'eval_rmse': 1.4962644577026367, 'eval_mae': 1.1580203771591187, 'eval_runtime': 2.781, 'eval_samples_per_second': 354.184, 'eval_steps_per_second': 44.588, 'epoch': 35.0}
|
358 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-34580
|
359 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-34580/config.json
|
360 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-34580/pytorch_model.bin
|
361 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-33592] due to args.save_total_limit
|
362 |
+
{'loss': 0.3543, 'learning_rate': 2.9149797570850203e-06, 'epoch': 35.43}
|
363 |
+
{'loss': 0.3818, 'learning_rate': 2.8137651821862348e-06, 'epoch': 35.93}
|
364 |
+
***** Running Evaluation *****
|
365 |
+
Num examples = 985
|
366 |
+
Batch size = 8
|
367 |
+
{'eval_loss': 2.3153350353240967, 'eval_mse': 2.3153350353240967, 'eval_rmse': 1.5216225385665894, 'eval_mae': 1.178168773651123, 'eval_runtime': 2.7673, 'eval_samples_per_second': 355.946, 'eval_steps_per_second': 44.81, 'epoch': 36.0}
|
368 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-35568
|
369 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-35568/config.json
|
370 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-35568/pytorch_model.bin
|
371 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-34580] due to args.save_total_limit
|
372 |
+
{'loss': 0.3451, 'learning_rate': 2.7125506072874497e-06, 'epoch': 36.44}
|
373 |
+
{'loss': 0.3837, 'learning_rate': 2.6113360323886646e-06, 'epoch': 36.94}
|
374 |
+
***** Running Evaluation *****
|
375 |
+
Num examples = 985
|
376 |
+
Batch size = 8
|
377 |
+
{'eval_loss': 2.2114505767822266, 'eval_mse': 2.2114510536193848, 'eval_rmse': 1.4870948791503906, 'eval_mae': 1.1500502824783325, 'eval_runtime': 4.6473, 'eval_samples_per_second': 211.95, 'eval_steps_per_second': 26.682, 'epoch': 37.0}
|
378 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-36556
|
379 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-36556/config.json
|
380 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-36556/pytorch_model.bin
|
381 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-35568] due to args.save_total_limit
|
382 |
+
{'loss': 0.3335, 'learning_rate': 2.5101214574898787e-06, 'epoch': 37.45}
|
383 |
+
{'loss': 0.3724, 'learning_rate': 2.408906882591093e-06, 'epoch': 37.96}
|
384 |
+
***** Running Evaluation *****
|
385 |
+
Num examples = 985
|
386 |
+
Batch size = 8
|
387 |
+
{'eval_loss': 2.190290927886963, 'eval_mse': 2.190290689468384, 'eval_rmse': 1.4799630641937256, 'eval_mae': 1.1481947898864746, 'eval_runtime': 4.4593, 'eval_samples_per_second': 220.888, 'eval_steps_per_second': 27.807, 'epoch': 38.0}
|
388 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-37544
|
389 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-37544/config.json
|
390 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-37544/pytorch_model.bin
|
391 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-36556] due to args.save_total_limit
|
392 |
+
{'loss': 0.3631, 'learning_rate': 2.307692307692308e-06, 'epoch': 38.46}
|
393 |
+
{'loss': 0.3525, 'learning_rate': 2.2064777327935226e-06, 'epoch': 38.97}
|
394 |
+
***** Running Evaluation *****
|
395 |
+
Num examples = 985
|
396 |
+
Batch size = 8
|
397 |
+
{'eval_loss': 2.208022117614746, 'eval_mse': 2.208022117614746, 'eval_rmse': 1.4859415292739868, 'eval_mae': 1.1508959531784058, 'eval_runtime': 4.5419, 'eval_samples_per_second': 216.868, 'eval_steps_per_second': 27.301, 'epoch': 39.0}
|
398 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-38532
|
399 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-38532/config.json
|
400 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-38532/pytorch_model.bin
|
401 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-37544] due to args.save_total_limit
|
402 |
+
{'loss': 0.3589, 'learning_rate': 2.105263157894737e-06, 'epoch': 39.47}
|
403 |
+
{'loss': 0.3477, 'learning_rate': 2.0040485829959516e-06, 'epoch': 39.98}
|
404 |
+
***** Running Evaluation *****
|
405 |
+
Num examples = 985
|
406 |
+
Batch size = 8
|
407 |
+
{'eval_loss': 2.2591028213500977, 'eval_mse': 2.2591030597686768, 'eval_rmse': 1.5030312538146973, 'eval_mae': 1.1669268608093262, 'eval_runtime': 4.628, 'eval_samples_per_second': 212.837, 'eval_steps_per_second': 26.794, 'epoch': 40.0}
|
408 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-39520
|
409 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-39520/config.json
|
410 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-39520/pytorch_model.bin
|
411 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-38532] due to args.save_total_limit
|
412 |
+
{'loss': 0.3239, 'learning_rate': 1.902834008097166e-06, 'epoch': 40.49}
|
413 |
+
{'loss': 0.3891, 'learning_rate': 1.8016194331983807e-06, 'epoch': 40.99}
|
414 |
+
***** Running Evaluation *****
|
415 |
+
Num examples = 985
|
416 |
+
Batch size = 8
|
417 |
+
{'eval_loss': 2.2003180980682373, 'eval_mse': 2.2003180980682373, 'eval_rmse': 1.483346939086914, 'eval_mae': 1.1513614654541016, 'eval_runtime': 4.722, 'eval_samples_per_second': 208.597, 'eval_steps_per_second': 26.26, 'epoch': 41.0}
|
418 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-40508
|
419 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-40508/config.json
|
420 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-40508/pytorch_model.bin
|
421 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-39520] due to args.save_total_limit
|
422 |
+
{'loss': 0.3474, 'learning_rate': 1.7004048582995952e-06, 'epoch': 41.5}
|
423 |
+
***** Running Evaluation *****
|
424 |
+
Num examples = 985
|
425 |
+
Batch size = 8
|
426 |
+
{'eval_loss': 2.2396390438079834, 'eval_mse': 2.2396390438079834, 'eval_rmse': 1.4965423345565796, 'eval_mae': 1.1607612371444702, 'eval_runtime': 4.5927, 'eval_samples_per_second': 214.471, 'eval_steps_per_second': 26.999, 'epoch': 42.0}
|
427 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-41496
|
428 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-41496/config.json
|
429 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-41496/pytorch_model.bin
|
430 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-40508] due to args.save_total_limit
|
431 |
+
{'loss': 0.347, 'learning_rate': 1.59919028340081e-06, 'epoch': 42.0}
|
432 |
+
{'loss': 0.3173, 'learning_rate': 1.4979757085020244e-06, 'epoch': 42.51}
|
433 |
+
***** Running Evaluation *****
|
434 |
+
Num examples = 985
|
435 |
+
Batch size = 8
|
436 |
+
{'eval_loss': 2.2095425128936768, 'eval_mse': 2.2095425128936768, 'eval_rmse': 1.4864530563354492, 'eval_mae': 1.151437520980835, 'eval_runtime': 4.6099, 'eval_samples_per_second': 213.67, 'eval_steps_per_second': 26.899, 'epoch': 43.0}
|
437 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-42484
|
438 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-42484/config.json
|
439 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-42484/pytorch_model.bin
|
440 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-41496] due to args.save_total_limit
|
441 |
+
{'loss': 0.3691, 'learning_rate': 1.3967611336032391e-06, 'epoch': 43.02}
|
442 |
+
{'loss': 0.335, 'learning_rate': 1.2955465587044536e-06, 'epoch': 43.52}
|
443 |
+
***** Running Evaluation *****
|
444 |
+
Num examples = 985
|
445 |
+
Batch size = 8
|
446 |
+
{'eval_loss': 2.1894824504852295, 'eval_mse': 2.1894824504852295, 'eval_rmse': 1.4796899557113647, 'eval_mae': 1.146257758140564, 'eval_runtime': 4.6282, 'eval_samples_per_second': 212.828, 'eval_steps_per_second': 26.793, 'epoch': 44.0}
|
447 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-43472
|
448 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-43472/config.json
|
449 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-43472/pytorch_model.bin
|
450 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-42484] due to args.save_total_limit
|
451 |
+
{'loss': 0.3441, 'learning_rate': 1.1943319838056681e-06, 'epoch': 44.03}
|
452 |
+
{'loss': 0.3443, 'learning_rate': 1.0931174089068828e-06, 'epoch': 44.53}
|
453 |
+
***** Running Evaluation *****
|
454 |
+
Num examples = 985
|
455 |
+
Batch size = 8
|
456 |
+
{'eval_loss': 2.2246272563934326, 'eval_mse': 2.2246272563934326, 'eval_rmse': 1.491518497467041, 'eval_mae': 1.1584477424621582, 'eval_runtime': 4.7245, 'eval_samples_per_second': 208.487, 'eval_steps_per_second': 26.246, 'epoch': 45.0}
|
457 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-44460
|
458 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-44460/config.json
|
459 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-44460/pytorch_model.bin
|
460 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-43472] due to args.save_total_limit
|
461 |
+
{'loss': 0.3242, 'learning_rate': 9.919028340080973e-07, 'epoch': 45.04}
|
462 |
+
{'loss': 0.3604, 'learning_rate': 8.906882591093118e-07, 'epoch': 45.55}
|
463 |
+
***** Running Evaluation *****
|
464 |
+
Num examples = 985
|
465 |
+
Batch size = 8
|
466 |
+
{'eval_loss': 2.2161009311676025, 'eval_mse': 2.2161009311676025, 'eval_rmse': 1.4886574745178223, 'eval_mae': 1.1535395383834839, 'eval_runtime': 4.6251, 'eval_samples_per_second': 212.97, 'eval_steps_per_second': 26.81, 'epoch': 46.0}
|
467 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-45448
|
468 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-45448/config.json
|
469 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-45448/pytorch_model.bin
|
470 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-44460] due to args.save_total_limit
|
471 |
+
{'loss': 0.3321, 'learning_rate': 7.894736842105263e-07, 'epoch': 46.05}
|
472 |
+
{'loss': 0.3422, 'learning_rate': 6.882591093117409e-07, 'epoch': 46.56}
|
473 |
+
***** Running Evaluation *****
|
474 |
+
Num examples = 985
|
475 |
+
Batch size = 8
|
476 |
+
{'eval_loss': 2.2106308937072754, 'eval_mse': 2.2106311321258545, 'eval_rmse': 1.4868191480636597, 'eval_mae': 1.1536109447479248, 'eval_runtime': 4.7086, 'eval_samples_per_second': 209.193, 'eval_steps_per_second': 26.335, 'epoch': 47.0}
|
477 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-46436
|
478 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-46436/config.json
|
479 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-46436/pytorch_model.bin
|
480 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-45448] due to args.save_total_limit
|
481 |
+
{'loss': 0.3223, 'learning_rate': 5.870445344129555e-07, 'epoch': 47.06}
|
482 |
+
{'loss': 0.3253, 'learning_rate': 4.858299595141701e-07, 'epoch': 47.57}
|
483 |
+
***** Running Evaluation *****
|
484 |
+
Num examples = 985
|
485 |
+
Batch size = 8
|
486 |
+
{'eval_loss': 2.2084391117095947, 'eval_mse': 2.2084388732910156, 'eval_rmse': 1.4860817193984985, 'eval_mae': 1.1512514352798462, 'eval_runtime': 4.6784, 'eval_samples_per_second': 210.541, 'eval_steps_per_second': 26.505, 'epoch': 48.0}
|
487 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-47424
|
488 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-47424/config.json
|
489 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-47424/pytorch_model.bin
|
490 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-46436] due to args.save_total_limit
|
491 |
+
{'loss': 0.3418, 'learning_rate': 3.846153846153847e-07, 'epoch': 48.08}
|
492 |
+
{'loss': 0.3309, 'learning_rate': 2.834008097165992e-07, 'epoch': 48.58}
|
493 |
+
***** Running Evaluation *****
|
494 |
+
Num examples = 985
|
495 |
+
Batch size = 8
|
496 |
+
{'eval_loss': 2.2103824615478516, 'eval_mse': 2.2103824615478516, 'eval_rmse': 1.486735463142395, 'eval_mae': 1.1521849632263184, 'eval_runtime': 3.2286, 'eval_samples_per_second': 305.083, 'eval_steps_per_second': 38.406, 'epoch': 49.0}
|
497 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-48412
|
498 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-48412/config.json
|
499 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-48412/pytorch_model.bin
|
500 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-47424] due to args.save_total_limit
|
501 |
+
{'loss': 0.3491, 'learning_rate': 1.8218623481781377e-07, 'epoch': 49.09}
|
502 |
+
{'loss': 0.3148, 'learning_rate': 8.097165991902835e-08, 'epoch': 49.6}
|
503 |
+
***** Running Evaluation *****
|
504 |
+
Num examples = 985
|
505 |
+
Batch size = 8
|
506 |
+
{'eval_loss': 2.2166781425476074, 'eval_mse': 2.2166783809661865, 'eval_rmse': 1.4888513088226318, 'eval_mae': 1.1540616750717163, 'eval_runtime': 4.5752, 'eval_samples_per_second': 215.291, 'eval_steps_per_second': 27.103, 'epoch': 50.0}
|
507 |
+
Saving model checkpoint to our_pdbbindfull_model/checkpoint-49400
|
508 |
+
Configuration saved in our_pdbbindfull_model/checkpoint-49400/config.json
|
509 |
+
Model weights saved in our_pdbbindfull_model/checkpoint-49400/pytorch_model.bin
|
510 |
+
Deleting older checkpoint [our_pdbbindfull_model/checkpoint-48412] due to args.save_total_limit
|
511 |
+
|
512 |
+
|
513 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
514 |
+
|
515 |
+
|
516 |
+
{'train_runtime': 6118.0305, 'train_samples_per_second': 64.547, 'train_steps_per_second': 8.074, 'train_loss': 0.5750620862829541, 'epoch': 50.0}
|
517 |
+
Metrics
|
518 |
+
TrainOutput(global_step=49400, training_loss=0.5750620862829541, metrics={'train_runtime': 6118.0305, 'train_samples_per_second': 64.547, 'train_steps_per_second': 8.074, 'train_loss': 0.5750620862829541, 'epoch': 50.0})
|
519 |
+
Saving model checkpoint to our_pdbbindfull_model
|
520 |
+
Configuration saved in our_pdbbindfull_model/config.json
|
521 |
+
Model weights saved in our_pdbbindfull_model/pytorch_model.bin
|
522 |
+
***** Running Prediction *****
|
523 |
+
Num examples = 988
|
524 |
+
Batch size = 8
|
525 |
+
|
526 |
+
Mean Squared Error (MSE): 2.2154239492054857
|
527 |
+
Root Mean Square Error (RMSE): 1.488430028320272
|
528 |
+
Mean Absolute Error (MAE): 1.1369174286276704
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06f8fbd3d483a40043dfc4ed03d1d7f9d1c7387420b6f553e384b6d7e93d2f13
|
3 |
+
size 349077673
|
runs/Apr09_14-56-31_lotan/1649516197.1034896/events.out.tfevents.1649516197.lotan.2910198.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9bbf1c11235f3eadde8eca56833bbcfc95a8f520827c1b37c2c22063e786afe
|
3 |
+
size 4736
|
runs/Apr09_14-56-31_lotan/events.out.tfevents.1649516197.lotan.2910198.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:571e8cc9d87e5bcaed6187d00f15b8fdff9134e85d48359bb2ec567997b7331b
|
3 |
+
size 40277
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c20e300fc0f89a9cbc3f36d83d87f965a132958a9f96addf740aaf2a30cea4
|
3 |
+
size 2927
|