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
4e5c0fb
·
verified ·
1 Parent(s): 8693e92

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-563/model.safetensors +1 -1
  3. run-1/checkpoint-563/optimizer.pt +1 -1
  4. run-1/checkpoint-563/scheduler.pt +1 -1
  5. run-1/checkpoint-563/trainer_state.json +14 -14
  6. run-1/checkpoint-563/training_args.bin +1 -1
  7. runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733696071.6ff5f1d99a72.23.1 +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 sha256:48e3134343bbdcbaa2d0e515e448ba031cd266949636f85cccb6bf345f14ac59
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec2e5250bedd266bfb35bf352696ec04e794cf8fe35f9366e93b673162645e3
3
  size 498625128
run-1/checkpoint-563/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2999c5c45ace354242376f2be90db4238a31117d3a08d6a1feb43fe0596f3f9e
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec2e5250bedd266bfb35bf352696ec04e794cf8fe35f9366e93b673162645e3
3
  size 498625128
run-1/checkpoint-563/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dca027a35397ca14b602cf38277bd2d0cf8431351e372bf1ed202e14cdb5cad9
3
  size 997370106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525af664db0555aeb47054eb84b08d8993d22bb5641f3e17cbe15b11e629537a
3
  size 997370106
run-1/checkpoint-563/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed49c5af3789e22fc643ddfa776a4e4d1dac2c8b6d694f36fa76f1a6d6a6b58
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67acb8c45f2a5267738ac2fa23235c72161e378ee00369b01362c2d3a0c9f636
3
  size 1064
run-1/checkpoint-563/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5438473456606133,
3
  "best_model_checkpoint": "students_scores_model/run-1/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": 16.69457244873047,
14
- "learning_rate": 1.3821787207411013e-05,
15
- "loss": 1.0782,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_f1": 0.5438473456606133,
21
- "eval_loss": 1.0308393239974976,
22
- "eval_runtime": 37.8021,
23
- "eval_samples_per_second": 59.52,
24
- "eval_steps_per_second": 7.46,
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": 1.9634145158382844e-05,
50
- "num_train_epochs": 3,
51
  "per_device_train_batch_size": 16,
52
- "weight_decay": 0.000263763325616835
53
  }
54
  }
 
1
  {
2
+ "best_metric": 0.5710981943306789,
3
  "best_model_checkpoint": "students_scores_model/run-1/checkpoint-563",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.8880994671403197,
13
+ "grad_norm": 33.513973236083984,
14
+ "learning_rate": 6.5983988623305475e-06,
15
+ "loss": 1.0854,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_f1": 0.5710981943306789,
21
+ "eval_loss": 0.9620336294174194,
22
+ "eval_runtime": 37.4093,
23
+ "eval_samples_per_second": 60.146,
24
+ "eval_steps_per_second": 7.538,
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": 1.1868685493584978e-05,
50
+ "num_train_epochs": 2,
51
  "per_device_train_batch_size": 16,
52
+ "weight_decay": 0.002134803775236508
53
  }
54
  }
run-1/checkpoint-563/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b1b930fb8e91788c965e2716a6235c673c8a487c662e9f94e1672503a85155c
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94ce251b73f8aadbf2d3b914945301b52341856da7ddaf4675709c9b25289a5
3
  size 5368
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733696071.6ff5f1d99a72.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6c12e65a830f35a3c3363d0253606b6431e0c8184affc765d0dc2742090f6b
3
+ size 5882
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b18f3514f71ccee1e74cafceb4cbd84c3f4bda80bd3c08496a257871a520e8eb
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94ce251b73f8aadbf2d3b914945301b52341856da7ddaf4675709c9b25289a5
3
  size 5368