Hugging Face's logo

itsanastasiaminina
/
students_scores_model

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsanastasiaminina commited on
Commit
9f84478
·
verified ·
1 Parent(s): 521dd18

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-563/model.safetensors +1 -1
  3. run-0/checkpoint-563/optimizer.pt +1 -1
  4. run-0/checkpoint-563/scheduler.pt +1 -1
  5. run-0/checkpoint-563/trainer_state.json +14 -14
  6. run-0/checkpoint-563/training_args.bin +1 -1
  7. runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733694862.6ff5f1d99a72.23.0 +3 -0
  8. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e68e1c060b319ce9f7dd0e7ee1ee17d4629ae7d117a75334c50850723d49a56a
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa81e66f1e22f8c42ce00493a180958c1211c7b9164379b96b4ebc9dab28e641
3
  size 498625128
run-0/checkpoint-563/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20502fa59980a968de6a795910978158a6e7dc802fc30eb7b2a3e3cf80432e08
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa81e66f1e22f8c42ce00493a180958c1211c7b9164379b96b4ebc9dab28e641
3
  size 498625128
run-0/checkpoint-563/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f13a0c4827a5a7eadbcbbb919d572966eb15f877aa8fdf09d62f8ddd9728efb
3
  size 997370106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd98ec52dea6469ba1ae90fab44ac5383799224e1b0c672362ae1ed477f870d0
3
  size 997370106
run-0/checkpoint-563/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffa7f61800a2ce991449185f7abbad7b0b78a640352b56672360deef76d19cb6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2d865d07fdf2f700f9b60e889c990f7a867696b7f9d927c1e7a4c156d6300f
3
  size 1064
run-0/checkpoint-563/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.559496193541961,
3
  "best_model_checkpoint": "students_scores_model/run-0/checkpoint-563",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,25 +10,25 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.8880994671403197,
13
- "grad_norm": 9.486105918884277,
14
- "learning_rate": 1.6060239187203855e-05,
15
- "loss": 1.0687,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_f1": 0.559496193541961,
21
- "eval_loss": 1.0184900760650635,
22
- "eval_runtime": 37.7502,
23
- "eval_samples_per_second": 59.602,
24
- "eval_steps_per_second": 7.47,
25
  "step": 563
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 1689,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 3,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
@@ -46,9 +46,9 @@
46
  "train_batch_size": 16,
47
  "trial_name": null,
48
  "trial_params": {
49
- "learning_rate": 2.2813914202848873e-05,
50
- "num_train_epochs": 3,
51
  "per_device_train_batch_size": 16,
52
- "weight_decay": 0.0012064342197859815
53
  }
54
  }
 
1
  {
2
+ "best_metric": 0.568809428898138,
3
  "best_model_checkpoint": "students_scores_model/run-0/checkpoint-563",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.8880994671403197,
13
+ "grad_norm": 33.89450454711914,
14
+ "learning_rate": 7.71014137309043e-06,
15
+ "loss": 1.0858,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_f1": 0.568809428898138,
21
+ "eval_loss": 0.9511491060256958,
22
+ "eval_runtime": 37.4937,
23
+ "eval_samples_per_second": 60.01,
24
+ "eval_steps_per_second": 7.521,
25
  "step": 563
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 1126,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 2,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 16,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "learning_rate": 1.386840125575052e-05,
50
+ "num_train_epochs": 2,
51
  "per_device_train_batch_size": 16,
52
+ "weight_decay": 0.010177242974562553
53
  }
54
  }
run-0/checkpoint-563/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86e506878344e67934428f3176c568da4bb4fdfd8b8918c71494a2c9eb08433b
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18f3514f71ccee1e74cafceb4cbd84c3f4bda80bd3c08496a257871a520e8eb
3
  size 5368
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733694862.6ff5f1d99a72.23.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae4d45bd72b4cba87e8f635492bae932d6fc162479d4bf817569f99035e250d
3
+ size 5900
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07844380fb9421e367e0fe8c8cfeb6356de89708d1d3002c9565a87a48709fa1
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18f3514f71ccee1e74cafceb4cbd84c3f4bda80bd3c08496a257871a520e8eb
3
  size 5368