Hugging Face's logo

Kira-Floris
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Kira-Floris commited on
Commit
d771467
•
1 Parent(s): 85d3291

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. logs/events.out.tfevents.1719305887.852b1e905a9a.223.0 +3 -0
  2. model.safetensors +1 -1
  3. run-0/checkpoint-527/model.safetensors +1 -1
  4. run-0/checkpoint-527/optimizer.pt +1 -1
  5. run-0/checkpoint-527/scheduler.pt +1 -1
  6. run-0/checkpoint-527/trainer_state.json +15 -15
  7. run-0/checkpoint-527/training_args.bin +1 -1
  8. training_args.bin +1 -1
logs/events.out.tfevents.1719305887.852b1e905a9a.223.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99959e7256c57c0a7615a75a705d0c04ea51d6768974b0ec0a62b7fc9de73dfc
3
+ size 5430
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a04314b749d4acea219b75473b7159304fd15abbb0749b74b9a72dc41ad508ee
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa21ae55c664d183ed99418fbb9247b4b7ee6800ae3d0ed0500451e8a3bebc7d
3
  size 17549312
run-0/checkpoint-527/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7788cab7841f4a2f3693dc0c0ee6f814742ac5ce16528a51f55dad86befccf
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa21ae55c664d183ed99418fbb9247b4b7ee6800ae3d0ed0500451e8a3bebc7d
3
  size 17549312
run-0/checkpoint-527/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f84bb8008e162dd46d32fa4ebb51a54d7b995433819da88db2eaf40d2b42793
3
  size 35123898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e506fba24486a7972abbb52ec5ae9c62885914bc48d0e441ab7b5e31648df8f9
3
  size 35123898
run-0/checkpoint-527/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5456c00e41cc97e97f791dcd94d7d9bfdced990f7de7a36119b3adedfff1dc
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4bcffeec60c929d14a9cd81e26902c97bfab40e5297db923c2b617e690f8bb
3
  size 1064
run-0/checkpoint-527/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.8061926605504587,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,25 +10,25 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 16.55626678466797,
14
- "learning_rate": 5.1383294230414005e-05,
15
- "loss": 1.5907,
16
  "step": 527
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.8061926605504587,
21
- "eval_loss": 1.2464169263839722,
22
- "eval_runtime": 2.4007,
23
- "eval_samples_per_second": 363.232,
24
- "eval_steps_per_second": 2.916,
25
  "step": 527
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 4216,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 8,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
@@ -46,9 +46,9 @@
46
  "train_batch_size": 128,
47
  "trial_name": null,
48
  "trial_params": {
49
- "alpha": 0.5167874928728581,
50
- "learning_rate": 5.872376483475886e-05,
51
- "num_train_epochs": 8,
52
- "temperature": 5
53
  }
54
  }
 
1
  {
2
+ "best_metric": 0.7339449541284404,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 5.95961856842041,
14
+ "learning_rate": 9.55389368279823e-06,
15
+ "loss": 1.5369,
16
  "step": 527
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7339449541284404,
21
+ "eval_loss": 1.2773902416229248,
22
+ "eval_runtime": 2.5957,
23
+ "eval_samples_per_second": 335.939,
24
+ "eval_steps_per_second": 2.697,
25
  "step": 527
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 5270,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 10,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 128,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "alpha": 0.27608826195592573,
50
+ "learning_rate": 1.0615437425331367e-05,
51
+ "num_train_epochs": 10,
52
+ "temperature": 2
53
  }
54
  }
run-0/checkpoint-527/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f28149fe21091b257234d7cbe1611ee6ca88e3a7cef675e40e6d90410e6fc1a6
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8b6a60f7b85b38fa45cddf1a417ee51250fe5822237403416bf2406ff2cdb84
3
  size 5176
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa6a7f7b16042aa90d6a482b54cde9c8a264f21ae121942f35d43fb01c1ae0eb
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8b6a60f7b85b38fa45cddf1a417ee51250fe5822237403416bf2406ff2cdb84
3
  size 5176