Hugging Face's logo

ipeksnmz
/
bert-base-uncased-finetuned-rte-run_3

Text Classification
Transformers
TensorBoard
Safetensors
bert
glue
rte
max_length_128
dropout_0.4
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
ipeksnmz commited on
Commit
b1ded72
·
verified ·
1 Parent(s): 5322d51

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-156/model.safetensors +1 -1
  3. run-6/checkpoint-156/optimizer.pt +1 -1
  4. run-6/checkpoint-156/rng_state.pth +1 -1
  5. run-6/checkpoint-156/scheduler.pt +1 -1
  6. run-6/checkpoint-156/trainer_state.json +22 -40
  7. run-6/checkpoint-156/training_args.bin +1 -1
  8. runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048507.7bb8169db539.937.9 +3 -0
  9. runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048522.7bb8169db539.937.10 +3 -0
  10. runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048536.7bb8169db539.937.11 +3 -0
  11. runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048550.7bb8169db539.937.12 +3 -0
  12. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e22353dff37b637241c76ecbe7008845d8d6cd0d372d916b653d2bdd8347e9f2
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca46fba069a09ac6fb41575c7caebc4777e335c36f53bbdc76ce8eda823c924
3
  size 437958648
run-6/checkpoint-156/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a79054409b7f5e520ca33b577f276dbad52782fdce5db059aaea39b643f8c203
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c31b54736d18d9d993de95dd9825ae261a4ba80b10af9fb212c26596f0cde1
3
  size 437958648
run-6/checkpoint-156/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4631479b96bafec4fa1af94a5aec9e85b4cd0446b1fb631f350568086ff203a7
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bf80d852fd55c6cd930cf8562caa4e30e8a866a047c212b43ef9ae66103f48
3
  size 876038394
run-6/checkpoint-156/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d60a11c2570e4f4dcd3b0d8e0823b5f74c0a337374c5c14747c4176f53063dcc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf55ba021d2ab0b1c833e29f9931dd901a0d951d01051cb520710fec2f7666a1
3
  size 14244
run-6/checkpoint-156/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95dd43a02a1122b30f51d5cecf899e8bea4a04abef2c849498fdbc278632d337
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd405caa0e65456a9f28f5f3296c58338c02ce0deeb39ca478dd3f20039c3d6f
3
  size 1064
run-6/checkpoint-156/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_global_step": 156,
3
- "best_metric": 0.6425992779783394,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-156",
5
- "epoch": 4.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
8
  "is_hyper_param_search": true,
@@ -11,45 +11,27 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.5703971119133574,
15
- "eval_loss": 0.6812458634376526,
16
- "eval_runtime": 2.0392,
17
- "eval_samples_per_second": 135.837,
18
- "eval_steps_per_second": 1.471,
19
- "step": 39
20
- },
21
- {
22
- "epoch": 2.0,
23
- "eval_accuracy": 0.5992779783393501,
24
- "eval_loss": 0.6685588359832764,
25
- "eval_runtime": 2.046,
26
- "eval_samples_per_second": 135.383,
27
- "eval_steps_per_second": 1.466,
28
  "step": 78
29
  },
30
  {
31
- "epoch": 3.0,
32
- "eval_accuracy": 0.6209386281588448,
33
- "eval_loss": 0.6961658000946045,
34
- "eval_runtime": 1.9909,
35
- "eval_samples_per_second": 139.131,
36
- "eval_steps_per_second": 1.507,
37
- "step": 117
38
- },
39
- {
40
- "epoch": 4.0,
41
- "eval_accuracy": 0.6425992779783394,
42
- "eval_loss": 0.6747164130210876,
43
- "eval_runtime": 2.079,
44
- "eval_samples_per_second": 133.237,
45
- "eval_steps_per_second": 1.443,
46
  "step": 156
47
  }
48
  ],
49
  "logging_steps": 500,
50
  "max_steps": 156,
51
  "num_input_tokens_seen": 0,
52
- "num_train_epochs": 4,
53
  "save_steps": 500,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
@@ -64,13 +46,13 @@
64
  }
65
  },
66
  "total_flos": 0,
67
- "train_batch_size": 64,
68
  "trial_name": null,
69
  "trial_params": {
70
- "dropout": 0.1,
71
- "learning_rate": 2.821492361481216e-05,
72
- "max_length": 512,
73
- "num_train_epochs": 4,
74
- "per_device_train_batch_size": 64
75
  }
76
  }
 
1
  {
2
+ "best_global_step": 78,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-78",
5
+ "epoch": 2.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
8
  "is_hyper_param_search": true,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.5270758122743683,
15
+ "eval_loss": 0.6928369402885437,
16
+ "eval_runtime": 0.4634,
17
+ "eval_samples_per_second": 597.785,
18
+ "eval_steps_per_second": 19.423,
 
 
 
 
 
 
 
 
 
19
  "step": 78
20
  },
21
  {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5234657039711191,
24
+ "eval_loss": 0.6930994987487793,
25
+ "eval_runtime": 0.4655,
26
+ "eval_samples_per_second": 595.12,
27
+ "eval_steps_per_second": 19.336,
 
 
 
 
 
 
 
 
 
28
  "step": 156
29
  }
30
  ],
31
  "logging_steps": 500,
32
  "max_steps": 156,
33
  "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
  "save_steps": 500,
36
  "stateful_callbacks": {
37
  "TrainerControl": {
 
46
  }
47
  },
48
  "total_flos": 0,
49
+ "train_batch_size": 32,
50
  "trial_name": null,
51
  "trial_params": {
52
+ "dropout": 0.5,
53
+ "learning_rate": 6.296103579896171e-06,
54
+ "max_length": 256,
55
+ "num_train_epochs": 2,
56
+ "per_device_train_batch_size": 32
57
  }
58
  }
run-6/checkpoint-156/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c80f32d9cadf1ae74822613d53c554739b7bb24659244d6b85dbfac9583f451
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2a483ffac7b45a1a655e8b96513e75ca01665a0452bac0c21578e6d240630c
3
  size 5432
runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048507.7bb8169db539.937.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4180511197a6aec22c86fa5e71a9fc079081054b294f2a584c1ae8c49af2432
3
+ size 5418
runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048522.7bb8169db539.937.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda86df346b5690f4960cf9b0d1d4f97c35dcc717e4e70d7826e409c38f3bde1
3
+ size 5419
runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048536.7bb8169db539.937.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca89fb254630025d3dab2c535678c4450971c6d4f4562dc6990c339bf46aef6b
3
+ size 5418
runs/Apr07_17-38-31_7bb8169db539/events.out.tfevents.1744048550.7bb8169db539.937.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a445780c3c6d2936590bebc9ba1ebd3a86511d2bcefcb188f12e4bac19cc738a
3
+ size 6095
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e2a483ffac7b45a1a655e8b96513e75ca01665a0452bac0c21578e6d240630c
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4eb51e77ae12a9a82f0717c329a69d2d0bb6a4369dd7b192e3569db3d2e859
3
  size 5432