Hugging Face's logo

ChrisZeng
/
electra-large-discriminator-nli-efl-tweeteval

Text Classification
Transformers
PyTorch
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
1
ChrisZeng commited on
Commit
3268cc0
•
1 Parent(s): eb7485e

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. checkpoint-163/optimizer.pt +1 -1
  2. checkpoint-163/pytorch_model.bin +1 -1
  3. checkpoint-163/scheduler.pt +1 -1
  4. checkpoint-163/trainer_state.json +11 -11
  5. checkpoint-163/training_args.bin +1 -1
  6. config.json +1 -0
  7. pytorch_model.bin +1 -1
  8. training_args.bin +1 -1
checkpoint-163/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8728bab2bcdc5e3334cf2c3fe1a0bc7074f04cfd163bf0aaac91f08ef6c66b80
3
  size 2681485310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6173eb77564ae639dbc1512d53056915365c2ccee54ecf94f6db0acbe5f19cca
3
  size 2681485310
checkpoint-163/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14b4ec5568a4ea5a2a6e8bb5651b0a178b89c7f36e4cb0ad65616ef313550349
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1980969c1f3293a2dbe8ae316314026931095e140a3abba991a9d5833692cf31
3
  size 1340743917
checkpoint-163/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26b5822fb7e9aeeec3687d7aab0d1c76d55ca1c14e5b0eceb9c6e6a15b5aa1cc
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edde095725bb89b632814ef17cc5ff9858ec3ff9b892f220af84373987ae02e9
3
  size 623
checkpoint-163/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.39615127444267273,
3
  "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-163",
4
  "epoch": 0.9973231357552581,
5
  "global_step": 163,
@@ -9,23 +9,23 @@
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "learning_rate": 9.499999999999999e-07,
13
- "loss": 0.4384,
14
  "step": 163
15
  },
16
  {
17
  "epoch": 1.0,
18
- "eval_accuracy": 0.7444061962134251,
19
- "eval_f1": 0.7308261375858633,
20
- "eval_loss": 0.39615127444267273,
21
- "eval_runtime": 9.0599,
22
- "eval_samples_per_second": 256.514,
23
- "eval_steps_per_second": 32.119,
24
  "step": 163
25
  }
26
  ],
27
- "max_steps": 3260,
28
- "num_train_epochs": 20,
29
  "total_flos": 3050804117265024.0,
30
  "trial_name": null,
31
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3982622027397156,
3
  "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-163",
4
  "epoch": 0.9973231357552581,
5
  "global_step": 163,
 
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "learning_rate": 9e-07,
13
+ "loss": 0.439,
14
  "step": 163
15
  },
16
  {
17
  "epoch": 1.0,
18
+ "eval_accuracy": 0.745697074010327,
19
+ "eval_f1": 0.732240056847258,
20
+ "eval_loss": 0.3982622027397156,
21
+ "eval_runtime": 8.9237,
22
+ "eval_samples_per_second": 260.431,
23
+ "eval_steps_per_second": 32.61,
24
  "step": 163
25
  }
26
  ],
27
+ "max_steps": 1630,
28
+ "num_train_epochs": 10,
29
  "total_flos": 3050804117265024.0,
30
  "trial_name": null,
31
  "trial_params": null
checkpoint-163/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82126e010e751131ea0bffbc21275298a6bdbc244157fe27eed5dd4b7b0d6e0f
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd48e93c542d5f8f840918341d20dc98e6dbd60ec7052cf9f5610075d1655eaf
3
  size 3119
config.json CHANGED
@@ -28,6 +28,7 @@
28
  "num_hidden_layers": 24,
29
  "pad_token_id": 0,
30
  "position_embedding_type": "absolute",
 
31
  "summary_activation": "gelu",
32
  "summary_last_dropout": 0.1,
33
  "summary_type": "first",
 
28
  "num_hidden_layers": 24,
29
  "pad_token_id": 0,
30
  "position_embedding_type": "absolute",
31
+ "problem_type": "multi_label_classification",
32
  "summary_activation": "gelu",
33
  "summary_last_dropout": 0.1,
34
  "summary_type": "first",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1017cd7d6d785c901c6c1b5a7c8a543da183235f0b9932da80f8f3cd0484598b
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1980969c1f3293a2dbe8ae316314026931095e140a3abba991a9d5833692cf31
3
  size 1340743917
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9526e9a0f0e96e2411bffc2a4724295f9fc0a47e201347c1bbb5464f8837e532
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd48e93c542d5f8f840918341d20dc98e6dbd60ec7052cf9f5610075d1655eaf
3
  size 3119