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
04f0c9c
•
1 Parent(s): 3268cc0

Training in progress, epoch 2

Browse files
Files changed (11) hide show
  1. checkpoint-326/optimizer.pt +1 -1
  2. checkpoint-326/pytorch_model.bin +1 -1
  3. checkpoint-326/scheduler.pt +1 -1
  4. checkpoint-326/trainer_state.json +19 -19
  5. checkpoint-326/training_args.bin +1 -1
  6. checkpoint-489/optimizer.pt +1 -1
  7. checkpoint-489/pytorch_model.bin +1 -1
  8. checkpoint-489/scheduler.pt +1 -1
  9. checkpoint-489/trainer_state.json +27 -27
  10. checkpoint-489/training_args.bin +1 -1
  11. pytorch_model.bin +1 -1
checkpoint-326/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b81e4851c2881dcef711af4697ef50a6462ba5c7e1c5b5e3b8378d35e8f383f
3
  size 2681485310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846c91eb3ce6c8b8df4a87a39bbdab9e22e02d3ad4ea3b46c10ad79049633467
3
  size 2681485310
checkpoint-326/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86cdd59d0a81eadb0634ce6bcc916feadce861da8cc4cc3451ee185ad4eaa4ac
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0813eae5262c9e47e39b6a350fabb7110ad6e66e437462b11fdd090423e953dc
3
  size 1340743917
checkpoint-326/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aae1bb5b445401f65c6949bbf3e6ceb826aa702ac8501d27afc0137be597724
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dac437143279069839405ba95a7bb1de11c328df082ef97316b1483a0272f88a
3
  size 623
checkpoint-326/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.3409559428691864,
3
  "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-326",
4
  "epoch": 1.997323135755258,
5
  "global_step": 326,
@@ -9,39 +9,39 @@
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
  "epoch": 2.0,
28
- "learning_rate": 9e-07,
29
- "loss": 0.3447,
30
  "step": 326
31
  },
32
  {
33
  "epoch": 2.0,
34
- "eval_accuracy": 0.76592082616179,
35
- "eval_f1": 0.7552159046464709,
36
- "eval_loss": 0.3409559428691864,
37
- "eval_runtime": 9.4378,
38
- "eval_samples_per_second": 246.244,
39
- "eval_steps_per_second": 30.833,
40
  "step": 326
41
  }
42
  ],
43
- "max_steps": 3260,
44
- "num_train_epochs": 20,
45
  "total_flos": 6097705758760512.0,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3448249399662018,
3
  "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-326",
4
  "epoch": 1.997323135755258,
5
  "global_step": 326,
 
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
  "epoch": 2.0,
28
+ "learning_rate": 8e-07,
29
+ "loss": 0.3465,
30
  "step": 326
31
  },
32
  {
33
  "epoch": 2.0,
34
+ "eval_accuracy": 0.7620481927710844,
35
+ "eval_f1": 0.750740067157349,
36
+ "eval_loss": 0.3448249399662018,
37
+ "eval_runtime": 9.0059,
38
+ "eval_samples_per_second": 258.053,
39
+ "eval_steps_per_second": 32.312,
40
  "step": 326
41
  }
42
  ],
43
+ "max_steps": 1630,
44
+ "num_train_epochs": 10,
45
  "total_flos": 6097705758760512.0,
46
  "trial_name": null,
47
  "trial_params": null
checkpoint-326/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
checkpoint-489/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d82fcecb740add996bf5ee0fb32b520102097d0504c5103e7a5e8dd20cb1fa7
3
  size 2681485310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6935a0481a58586f0e257a283ee30ff81be3ed3e121c9943f767c4c44a780c
3
  size 2681485310
checkpoint-489/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8cc6e01615d9fbc03a612a6299c16196268fe2e23e228d881f2f3bfa6b3ee9c
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0974d1d7e3c00ca3ef5b4f10e74487753227c1cf0a5211b14949a292a65de3
3
  size 1340743917
checkpoint-489/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08df44e0bd4d8b64139acfaf9c03eb9e41cbfb7bc1e64291bfc485d827865a29
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a92f2559882aa13b500495cd2e18cde31c42e2c5b2db64031b0d594c0edb530
3
  size 623
checkpoint-489/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.32338443398475647,
3
  "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-489",
4
  "epoch": 2.9973231357552583,
5
  "global_step": 489,
@@ -9,55 +9,55 @@
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
  "epoch": 2.0,
28
- "learning_rate": 9e-07,
29
- "loss": 0.3447,
30
  "step": 326
31
  },
32
  {
33
  "epoch": 2.0,
34
- "eval_accuracy": 0.76592082616179,
35
- "eval_f1": 0.7552159046464709,
36
- "eval_loss": 0.3409559428691864,
37
- "eval_runtime": 9.4378,
38
- "eval_samples_per_second": 246.244,
39
- "eval_steps_per_second": 30.833,
40
  "step": 326
41
  },
42
  {
43
  "epoch": 3.0,
44
- "learning_rate": 8.499999999999999e-07,
45
- "loss": 0.3057,
46
  "step": 489
47
  },
48
  {
49
  "epoch": 3.0,
50
- "eval_accuracy": 0.7749569707401033,
51
- "eval_f1": 0.768808341108185,
52
- "eval_loss": 0.32338443398475647,
53
- "eval_runtime": 9.0418,
54
- "eval_samples_per_second": 257.028,
55
- "eval_steps_per_second": 32.184,
56
  "step": 489
57
  }
58
  ],
59
- "max_steps": 3260,
60
- "num_train_epochs": 20,
61
  "total_flos": 9143325990301824.0,
62
  "trial_name": null,
63
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3303545117378235,
3
  "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-489",
4
  "epoch": 2.9973231357552583,
5
  "global_step": 489,
 
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
  "epoch": 2.0,
28
+ "learning_rate": 8e-07,
29
+ "loss": 0.3465,
30
  "step": 326
31
  },
32
  {
33
  "epoch": 2.0,
34
+ "eval_accuracy": 0.7620481927710844,
35
+ "eval_f1": 0.750740067157349,
36
+ "eval_loss": 0.3448249399662018,
37
+ "eval_runtime": 9.0059,
38
+ "eval_samples_per_second": 258.053,
39
+ "eval_steps_per_second": 32.312,
40
  "step": 326
41
  },
42
  {
43
  "epoch": 3.0,
44
+ "learning_rate": 7e-07,
45
+ "loss": 0.3089,
46
  "step": 489
47
  },
48
  {
49
  "epoch": 3.0,
50
+ "eval_accuracy": 0.7693631669535284,
51
+ "eval_f1": 0.7633651185887134,
52
+ "eval_loss": 0.3303545117378235,
53
+ "eval_runtime": 9.3737,
54
+ "eval_samples_per_second": 247.927,
55
+ "eval_steps_per_second": 31.044,
56
  "step": 489
57
  }
58
  ],
59
+ "max_steps": 1630,
60
+ "num_train_epochs": 10,
61
  "total_flos": 9143325990301824.0,
62
  "trial_name": null,
63
  "trial_params": null
checkpoint-489/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
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1980969c1f3293a2dbe8ae316314026931095e140a3abba991a9d5833692cf31
3
  size 1340743917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0974d1d7e3c00ca3ef5b4f10e74487753227c1cf0a5211b14949a292a65de3
3
  size 1340743917