Rocketknight1 HF staff commited on
Commit
fc4b654
1 Parent(s): 1768227

Training in progress epoch 0

Browse files
README.md CHANGED
@@ -14,9 +14,13 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.9654
18
- - Validation Loss: 1.1050
19
- - Epoch: 1
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -40,15 +44,14 @@ The following hyperparameters were used during training:
40
 
41
  ### Training results
42
 
43
- | Train Loss | Validation Loss | Epoch |
44
- |:----------:|:---------------:|:-----:|
45
- | 1.5152 | 1.1427 | 0 |
46
- | 0.9654 | 1.1050 | 1 |
47
 
48
 
49
  ### Framework versions
50
 
51
- - Transformers 4.16.0.dev0
52
  - TensorFlow 2.8.0-rc0
53
- - Datasets 1.17.0
54
  - Tokenizers 0.11.0
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 1.4605
18
+ - Train End Logits Sparse Categorical Accuracy: 0.6170
19
+ - Train Start Logits Sparse Categorical Accuracy: 0.5768
20
+ - Validation Loss: 1.1588
21
+ - Validation End Logits Sparse Categorical Accuracy: 0.6840
22
+ - Validation Start Logits Sparse Categorical Accuracy: 0.6511
23
+ - Epoch: 0
24
 
25
  ## Model description
26
 
 
44
 
45
  ### Training results
46
 
47
+ | Train Loss | Train End Logits Sparse Categorical Accuracy | Train Start Logits Sparse Categorical Accuracy | Validation Loss | Validation End Logits Sparse Categorical Accuracy | Validation Start Logits Sparse Categorical Accuracy | Epoch |
48
+ |:----------:|:--------------------------------------------:|:----------------------------------------------:|:---------------:|:-------------------------------------------------:|:---------------------------------------------------:|:-----:|
49
+ | 1.4605 | 0.6170 | 0.5768 | 1.1588 | 0.6840 | 0.6511 | 0 |
 
50
 
51
 
52
  ### Framework versions
53
 
54
+ - Transformers 4.19.0.dev0
55
  - TensorFlow 2.8.0-rc0
56
+ - Datasets 2.1.1.dev0
57
  - Tokenizers 0.11.0
config.json CHANGED
@@ -18,6 +18,6 @@
18
  "seq_classif_dropout": 0.2,
19
  "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
- "transformers_version": "4.16.0.dev0",
22
  "vocab_size": 30522
23
  }
 
18
  "seq_classif_dropout": 0.2,
19
  "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
+ "transformers_version": "4.19.0.dev0",
22
  "vocab_size": 30522
23
  }
logs/train/events.out.tfevents.1651592683.matt-TRX40-AORUS-PRO-WIFI.72570.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5d7e6a13c4949403ac8f9be78e1566cf8e17be1d4e3e6c20446ec0c93ce875
3
+ size 914252
logs/train/events.out.tfevents.1651592730.matt-TRX40-AORUS-PRO-WIFI.72570.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558ceb88bf96f484fa07146bd122c1c0dcc81770dd3bdff5bb01eeb834ebd237
3
+ size 923721
logs/validation/events.out.tfevents.1651593574.matt-TRX40-AORUS-PRO-WIFI.72570.2.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d3b0078fac835e56fc3dbd79e957be2110f702d3e823f4e3f9eb64df527091
3
+ size 642
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:863a6c4531ebfc77df6656f61337c631ad9e50137edde2250b967f46a3d8415b
3
  size 265583688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60027f7bb66fa14194bd91a7a07ad533eac866b383bdede2026f5ad04177aca
3
  size 265583688