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
d6cdca8
•
1 Parent(s): 746d096

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. logs/events.out.tfevents.1719316225.49cbd00d2005.382.0 +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 +14 -14
  7. run-0/checkpoint-527/training_args.bin +1 -1
  8. training_args.bin +1 -1
logs/events.out.tfevents.1719316225.49cbd00d2005.382.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298724a4bb557672c166bc1e25254912866c59cdddf96831c2184896ca9bdd45
3
+ size 5427
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4db5ce53872114bd04603e9f4cf8a2c9fff8b5eba2e6c35fa6175cd08190265
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4101e13540b9ca54dbd8ddf761e2b1b8af8108fb9147967fcd9ee7dd0b7ff1
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 sha256:3ae20a202c55d96dbc7a99eb68b3c49d5f2889c97c0f7b7581a4369c38393b73
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4101e13540b9ca54dbd8ddf761e2b1b8af8108fb9147967fcd9ee7dd0b7ff1
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 sha256:53a8520796ad50f6ff85e7e87d2a41102c44b1f2273e6444ae31344537166243
3
  size 35123898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e154f8de5d1ef22d68e299790c35d542007a54f497034b3baf80de7e6bc91a6
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:e5d8781fb59c88c7bad07954373a93237cb20c6820b8da7eae26083a78c3d342
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79638116c39075972d1c173f673dfdcd1943140b9d4d46a92b6cd0538475b05
3
  size 1064
run-0/checkpoint-527/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7672018348623854,
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": 12.377176284790039,
14
- "learning_rate": 1.5980854192157344e-05,
15
- "loss": 3.0218,
16
  "step": 527
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.7672018348623854,
21
- "eval_loss": 2.191861391067505,
22
- "eval_runtime": 2.5906,
23
- "eval_samples_per_second": 336.603,
24
- "eval_steps_per_second": 2.702,
25
  "step": 527
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 3162,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 6,
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": 0.275210688972374,
50
- "learning_rate": 1.9177025030588814e-05,
51
- "num_train_epochs": 6,
52
  "temperature": 6
53
  }
54
  }
 
1
  {
2
+ "best_metric": 0.8176605504587156,
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": 15.690781593322754,
14
+ "learning_rate": 0.0004329892843734803,
15
+ "loss": 1.29,
16
  "step": 527
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.8176605504587156,
21
+ "eval_loss": 1.5847134590148926,
22
+ "eval_runtime": 2.4131,
23
+ "eval_samples_per_second": 361.36,
24
+ "eval_steps_per_second": 2.901,
25
  "step": 527
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 2108,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 128,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "alpha": 0.19981548442581198,
50
+ "learning_rate": 0.000577319045831307,
51
+ "num_train_epochs": 4,
52
  "temperature": 6
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 sha256:15e7b4feae857373f91378a3d0efc15d0ec396bfba71e74c965086843aa6acf4
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b553ab9101fed6c5a9e75fca4cb81df81514d2d3f8ff94edc0c546949c119f9
3
  size 5176
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee9990afd96f204321e9e33fc4071f73d76355111015fd2ec723f4a4e4849ce7
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b553ab9101fed6c5a9e75fca4cb81df81514d2d3f8ff94edc0c546949c119f9
3
  size 5176