Hugging Face's logo

JeremiahZ
/
bert-base-uncased-stsb

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
English
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Jeremiah Zhou commited on
Commit
a64de90
•
1 Parent(s): 18c7aff

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +16 -0
  2. eval_results.json +11 -0
  3. runs/Jun21_14-51-58_mewtwo/events.out.tfevents.1655823707.mewtwo +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +64 -0
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_combined_score": 0.8859105179324802,
4
+ "eval_loss": 0.5143781900405884,
5
+ "eval_pearson": 0.887504063385115,
6
+ "eval_runtime": 6.6344,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 226.095,
9
+ "eval_spearmanr": 0.8843169724798454,
10
+ "eval_steps_per_second": 28.337,
11
+ "train_loss": 0.7539703951941596,
12
+ "train_runtime": 279.0486,
13
+ "train_samples": 5749,
14
+ "train_samples_per_second": 61.806,
15
+ "train_steps_per_second": 1.935
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_combined_score": 0.8859105179324802,
4
+ "eval_loss": 0.5143781900405884,
5
+ "eval_pearson": 0.887504063385115,
6
+ "eval_runtime": 6.6344,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 226.095,
9
+ "eval_spearmanr": 0.8843169724798454,
10
+ "eval_steps_per_second": 28.337
11
+ }
runs/Jun21_14-51-58_mewtwo/events.out.tfevents.1655823707.mewtwo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7655044496d222bba858d9720949cc887cee328f703570a1c2a45edb35aebde6
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.7539703951941596,
4
+ "train_runtime": 279.0486,
5
+ "train_samples": 5749,
6
+ "train_samples_per_second": 61.806,
7
+ "train_steps_per_second": 1.935
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8843169724798454,
3
+ "best_model_checkpoint": "./fine-tune/bert-base-uncased/stsb/checkpoint-540",
4
+ "epoch": 3.0,
5
+ "global_step": 540,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_combined_score": 0.8770512336585177,
13
+ "eval_loss": 0.517871081829071,
14
+ "eval_pearson": 0.8805737478242902,
15
+ "eval_runtime": 6.6982,
16
+ "eval_samples_per_second": 223.94,
17
+ "eval_spearmanr": 0.873528719492745,
18
+ "eval_steps_per_second": 28.067,
19
+ "step": 180
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_combined_score": 0.8834893774364951,
24
+ "eval_loss": 0.5145099759101868,
25
+ "eval_pearson": 0.8850209566170038,
26
+ "eval_runtime": 6.9391,
27
+ "eval_samples_per_second": 216.167,
28
+ "eval_spearmanr": 0.8819577982559864,
29
+ "eval_steps_per_second": 27.093,
30
+ "step": 360
31
+ },
32
+ {
33
+ "epoch": 2.78,
34
+ "learning_rate": 1.4814814814814815e-06,
35
+ "loss": 0.7868,
36
+ "step": 500
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_combined_score": 0.8859105179324802,
41
+ "eval_loss": 0.5143781900405884,
42
+ "eval_pearson": 0.887504063385115,
43
+ "eval_runtime": 7.1241,
44
+ "eval_samples_per_second": 210.554,
45
+ "eval_spearmanr": 0.8843169724798454,
46
+ "eval_steps_per_second": 26.389,
47
+ "step": 540
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "step": 540,
52
+ "total_flos": 1134458907008256.0,
53
+ "train_loss": 0.7539703951941596,
54
+ "train_runtime": 279.0486,
55
+ "train_samples_per_second": 61.806,
56
+ "train_steps_per_second": 1.935
57
+ }
58
+ ],
59
+ "max_steps": 540,
60
+ "num_train_epochs": 3,
61
+ "total_flos": 1134458907008256.0,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }