Hugging Face's logo

edloginovad
/
tinybert

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
edloginovad commited on
Commit
112ec80
·
verified ·
1 Parent(s): 28a3ced

Model save

Browse files
Files changed (13) hide show
  1. README.md +12 -12
  2. evaluation_results_en/classification_report_goldset.json +13 -13
  3. evaluation_results_en/classification_report_goldset.png +2 -2
  4. evaluation_results_en/confusion_matrix_goldset.png +2 -2
  5. evaluation_results_en/prediction_scores_goldset.png +2 -2
  6. logs/events.out.tfevents.1760011956.02786a67844b.548.0 +2 -2
  7. model.safetensors +1 -1
  8. training_args.bin +2 -2
  9. training_artifacts/training_history.csv +11 -11
  10. training_artifacts/training_history.json +66 -66
  11. training_artifacts/training_loss.png +2 -2
  12. training_artifacts/training_metrics.png +2 -2
  13. training_artifacts/training_summary.json +3 -3
README.md CHANGED
@@ -21,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [DedalusHealthCare/tinybert-mlm-en](https://huggingface.co/DedalusHealthCare/tinybert-mlm-en) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.6019
25
  - Accuracy: 0.9816
26
  - F1: 0.0
27
  - Precision: 0.0
@@ -58,17 +58,17 @@ The following hyperparameters were used during training:
58
 
59
  ### Training results
60
 
61
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
62
- |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
63
- | 0.7327 | 0.2857 | 1 | 0.7513 | 0.0341 | 0.0366 | 0.0187 | 1.0 |
64
- | 0.7327 | 0.5714 | 2 | 0.7464 | 0.0525 | 0.0373 | 0.0190 | 1.0 |
65
- | 0.7327 | 0.8571 | 3 | 0.7368 | 0.0892 | 0.0388 | 0.0198 | 1.0 |
66
- | 0.7327 | 1.1429 | 4 | 0.7225 | 0.1916 | 0.0375 | 0.0192 | 0.8571 |
67
- | 0.7327 | 1.4286 | 5 | 0.7037 | 0.3885 | 0.0251 | 0.0129 | 0.4286 |
68
- | 0.7327 | 1.7143 | 6 | 0.6806 | 0.6325 | 0.0 | 0.0 | 0.0 |
69
- | 0.7327 | 2.0 | 7 | 0.6538 | 0.8688 | 0.0 | 0.0 | 0.0 |
70
- | 0.7327 | 2.2857 | 8 | 0.6274 | 0.9738 | 0.0 | 0.0 | 0.0 |
71
- | 0.7327 | 2.5714 | 9 | 0.6019 | 0.9816 | 0.0 | 0.0 | 0.0 |
72
 
73
 
74
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [DedalusHealthCare/tinybert-mlm-en](https://huggingface.co/DedalusHealthCare/tinybert-mlm-en) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.5237
25
  - Accuracy: 0.9816
26
  - F1: 0.0
27
  - Precision: 0.0
 
58
 
59
  ### Training results
60
 
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---:|:---------:|:------:|
63
+ | 0.6688 | 0.2857 | 1 | 0.6695 | 0.7690 | 0.0 | 0.0 | 0.0 |
64
+ | 0.6688 | 0.5714 | 2 | 0.6647 | 0.8110 | 0.0 | 0.0 | 0.0 |
65
+ | 0.6688 | 0.8571 | 3 | 0.6551 | 0.8635 | 0.0 | 0.0 | 0.0 |
66
+ | 0.6688 | 1.1429 | 4 | 0.6407 | 0.9344 | 0.0 | 0.0 | 0.0 |
67
+ | 0.6688 | 1.4286 | 5 | 0.6220 | 0.9659 | 0.0 | 0.0 | 0.0 |
68
+ | 0.6688 | 1.7143 | 6 | 0.5993 | 0.9764 | 0.0 | 0.0 | 0.0 |
69
+ | 0.6688 | 2.0 | 7 | 0.5731 | 0.9816 | 0.0 | 0.0 | 0.0 |
70
+ | 0.6688 | 2.2857 | 8 | 0.5478 | 0.9816 | 0.0 | 0.0 | 0.0 |
71
+ | 0.6688 | 2.5714 | 9 | 0.5237 | 0.9816 | 0.0 | 0.0 | 0.0 |
72
 
73
 
74
  ### Framework versions
evaluation_results_en/classification_report_goldset.json CHANGED
@@ -1,27 +1,27 @@
1
  {
2
  "NOT_FAMILY": {
3
- "precision": 1.0,
4
- "recall": 0.13212435233160622,
5
- "f1-score": 0.2334096109839817,
6
  "support": 386.0
7
  },
8
  "FAMILY": {
9
- "precision": 0.014705882352941176,
10
- "recall": 1.0,
11
- "f1-score": 0.028985507246376812,
12
  "support": 5.0
13
  },
14
- "accuracy": 0.1432225063938619,
15
  "macro avg": {
16
- "precision": 0.5073529411764706,
17
- "recall": 0.5660621761658031,
18
- "f1-score": 0.13119755911517925,
19
  "support": 391.0
20
  },
21
  "weighted avg": {
22
- "precision": 0.9874003309763802,
23
- "recall": 0.1432225063938619,
24
- "f1-score": 0.23079549201035504,
25
  "support": 391.0
26
  },
27
  "evaluation_metadata": {
 
1
  {
2
  "NOT_FAMILY": {
3
+ "precision": 0.9789029535864979,
4
+ "recall": 0.6010362694300518,
5
+ "f1-score": 0.7447833065810595,
6
  "support": 386.0
7
  },
8
  "FAMILY": {
9
+ "precision": 0.0,
10
+ "recall": 0.0,
11
+ "f1-score": 0.0,
12
  "support": 5.0
13
  },
14
+ "accuracy": 0.5933503836317136,
15
  "macro avg": {
16
+ "precision": 0.48945147679324896,
17
+ "recall": 0.3005181347150259,
18
+ "f1-score": 0.37239165329052976,
19
  "support": 391.0
20
  },
21
  "weighted avg": {
22
+ "precision": 0.9663850130035504,
23
+ "recall": 0.5933503836317136,
24
+ "f1-score": 0.7352592233766981,
25
  "support": 391.0
26
  },
27
  "evaluation_metadata": {
evaluation_results_en/classification_report_goldset.png CHANGED

Git LFS Details

  • SHA256: 95ebfa7c489dc7a4f56d1dc82a7355bc3ee842cef1125c496049780d376bb64c
  • Pointer size: 131 Bytes
  • Size of remote file: 225 kB

Git LFS Details

  • SHA256: 1e639f4a095985999b65a33330eb53063251fab7d013e055c14ceda2be45efd5
  • Pointer size: 131 Bytes
  • Size of remote file: 225 kB
evaluation_results_en/confusion_matrix_goldset.png CHANGED

Git LFS Details

  • SHA256: f3ceba989c8f8caf32215889d81b6b964c3642767f37f4171a3cbb89e1ad1ee3
  • Pointer size: 131 Bytes
  • Size of remote file: 135 kB

Git LFS Details

  • SHA256: 53a00a6fbbfd80443af25c04ebd5641ef0ae2ec26a81cad23cfbaf0a729edfa8
  • Pointer size: 131 Bytes
  • Size of remote file: 129 kB
evaluation_results_en/prediction_scores_goldset.png CHANGED

Git LFS Details

  • SHA256: d3bf012b8a8d3bee1661ce9a69f03d90fbec837dca91ecc923e893885aef18b4
  • Pointer size: 131 Bytes
  • Size of remote file: 289 kB

Git LFS Details

  • SHA256: 0c2e31263527709248fbce1809648e7e5a750dc186a6aca25b4bebfc47aac6a0
  • Pointer size: 131 Bytes
  • Size of remote file: 324 kB
logs/events.out.tfevents.1760011956.02786a67844b.548.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:266fcb31977cb9c341a06ae436aa254d76a3e3ab3124d8feaeab98c33fdb3f88
3
- size 7623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808c380a6488ec5ba9b734c42d2d31d4fd9d1b270404e45f74aa21568175d8b9
3
+ size 9823
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c270f4d5425845329b57b5a00429e669c0149bcf21a9e0c8303b71b8aa504852
3
  size 46634832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad234a2b33b93334794723105ac1864560d83f4af65d915679ffa594b1f7a4d
3
  size 46634832
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd6ab76cdb6290642263495ef9ccbac4bce2acbc40c68819c1dc3fde0b088978
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4cc4e9eff3450f9d5c31bd5bf3c299968002ed6b50bab6a7a9d4b76137fbc6
3
+ size 5176
training_artifacts/training_history.csv CHANGED
@@ -1,12 +1,12 @@
1
  loss;grad_norm;learning_rate;epoch;step;eval_loss;eval_accuracy;eval_f1;eval_precision;eval_recall;eval_runtime;eval_samples_per_second;eval_steps_per_second;train_runtime;train_samples_per_second;train_steps_per_second;total_flos;train_loss
2
- 0.7327;2.7726080417633057;3.3333333333333333e-06;0.2857142857142857;1;;;;;;;;;;;;;
3
- ;;;0.2857142857142857;1;0.7512667775154114;0.03412073490813648;0.03664921465968587;0.018666666666666668;1.0;5.3956;70.613;4.448;;;;;
4
- ;;;0.5714285714285714;2;0.7464109659194946;0.05249343832020997;0.037333333333333336;0.019021739130434784;1.0;5.5933;68.117;4.291;;;;;
5
- ;;;0.8571428571428571;3;0.7368069291114807;0.08923884514435695;0.038781163434903045;0.01977401129943503;1.0;5.5621;68.5;4.315;;;;;
6
- ;;;1.1428571428571428;4;0.7224730849266052;0.19160104986876642;0.03749999999999999;0.019169329073482427;0.8571428571428571;5.6279;67.698;4.264;;;;;
7
- ;;;1.4285714285714286;5;0.7036912441253662;0.3884514435695538;0.02510460251046025;0.01293103448275862;0.42857142857142855;5.703;66.807;4.208;;;;;
8
- ;;;1.7142857142857144;6;0.6806334853172302;0.6325459317585301;0.0;0.0;0.0;5.773;65.997;4.157;;;;;
9
- ;;;2.0;7;0.6538448929786682;0.868766404199475;0.0;0.0;0.0;5.6817;67.057;4.224;;;;;
10
- ;;;2.2857142857142856;8;0.6274169683456421;0.973753280839895;0.0;0.0;0.0;5.8624;64.991;4.094;;;;;
11
- ;;;2.571428571428571;9;0.6018883585929871;0.9816272965879265;0.0;0.0;0.0;5.644;67.505;4.252;;;;;
12
- ;;;2.571428571428571;9;;;;;;;;;101.6832;41.698;0.59;2156353020864.0;0.6984957986407809
 
1
  loss;grad_norm;learning_rate;epoch;step;eval_loss;eval_accuracy;eval_f1;eval_precision;eval_recall;eval_runtime;eval_samples_per_second;eval_steps_per_second;train_runtime;train_samples_per_second;train_steps_per_second;total_flos;train_loss
2
+ 0.6688;2.3227410316467285;3.3333333333333333e-06;0.2857142857142857;1;;;;;;;;;;;;;
3
+ ;;;0.2857142857142857;1;0.6694528460502625;0.7690288713910761;0.0;0.0;0.0;0.7051;540.382;34.04;;;;;
4
+ ;;;0.5714285714285714;2;0.6646609902381897;0.8110236220472441;0.0;0.0;0.0;0.7126;534.676;33.68;;;;;
5
+ ;;;0.8571428571428571;3;0.6550504565238953;0.863517060367454;0.0;0.0;0.0;2.6308;144.825;9.123;;;;;
6
+ ;;;1.1428571428571428;4;0.6407275199890137;0.9343832020997376;0.0;0.0;0.0;0.7121;535.065;33.705;;;;;
7
+ ;;;1.4285714285714286;5;0.6219562292098999;0.9658792650918635;0.0;0.0;0.0;0.7078;538.256;33.906;;;;;
8
+ ;;;1.7142857142857144;6;0.599317193031311;0.9763779527559056;0.0;0.0;0.0;1.1518;330.775;20.836;;;;;
9
+ ;;;2.0;7;0.5731121301651001;0.9816272965879265;0.0;0.0;0.0;0.7338;519.238;32.708;;;;;
10
+ ;;;2.2857142857142856;8;0.5478406548500061;0.9816272965879265;0.0;0.0;0.0;0.7067;539.157;33.963;;;;;
11
+ ;;;2.571428571428571;9;0.5236592292785645;0.9816272965879265;0.0;0.0;0.0;0.7083;537.937;33.886;;;;;
12
+ ;;;2.571428571428571;9;;;;;;;;;18.534;228.769;3.237;2148246430560.0;0.6554172303941515
training_artifacts/training_history.json CHANGED
@@ -1,125 +1,125 @@
1
  [
2
  {
3
- "loss": 0.7327,
4
- "grad_norm": 2.7726080417633057,
5
  "learning_rate": 3.3333333333333333e-06,
6
  "epoch": 0.2857142857142857,
7
  "step": 1
8
  },
9
  {
10
- "eval_loss": 0.7512667775154114,
11
- "eval_accuracy": 0.03412073490813648,
12
- "eval_f1": 0.03664921465968587,
13
- "eval_precision": 0.018666666666666668,
14
- "eval_recall": 1.0,
15
- "eval_runtime": 5.3956,
16
- "eval_samples_per_second": 70.613,
17
- "eval_steps_per_second": 4.448,
18
  "epoch": 0.2857142857142857,
19
  "step": 1
20
  },
21
  {
22
- "eval_loss": 0.7464109659194946,
23
- "eval_accuracy": 0.05249343832020997,
24
- "eval_f1": 0.037333333333333336,
25
- "eval_precision": 0.019021739130434784,
26
- "eval_recall": 1.0,
27
- "eval_runtime": 5.5933,
28
- "eval_samples_per_second": 68.117,
29
- "eval_steps_per_second": 4.291,
30
  "epoch": 0.5714285714285714,
31
  "step": 2
32
  },
33
  {
34
- "eval_loss": 0.7368069291114807,
35
- "eval_accuracy": 0.08923884514435695,
36
- "eval_f1": 0.038781163434903045,
37
- "eval_precision": 0.01977401129943503,
38
- "eval_recall": 1.0,
39
- "eval_runtime": 5.5621,
40
- "eval_samples_per_second": 68.5,
41
- "eval_steps_per_second": 4.315,
42
  "epoch": 0.8571428571428571,
43
  "step": 3
44
  },
45
  {
46
- "eval_loss": 0.7224730849266052,
47
- "eval_accuracy": 0.19160104986876642,
48
- "eval_f1": 0.03749999999999999,
49
- "eval_precision": 0.019169329073482427,
50
- "eval_recall": 0.8571428571428571,
51
- "eval_runtime": 5.6279,
52
- "eval_samples_per_second": 67.698,
53
- "eval_steps_per_second": 4.264,
54
  "epoch": 1.1428571428571428,
55
  "step": 4
56
  },
57
  {
58
- "eval_loss": 0.7036912441253662,
59
- "eval_accuracy": 0.3884514435695538,
60
- "eval_f1": 0.02510460251046025,
61
- "eval_precision": 0.01293103448275862,
62
- "eval_recall": 0.42857142857142855,
63
- "eval_runtime": 5.703,
64
- "eval_samples_per_second": 66.807,
65
- "eval_steps_per_second": 4.208,
66
  "epoch": 1.4285714285714286,
67
  "step": 5
68
  },
69
  {
70
- "eval_loss": 0.6806334853172302,
71
- "eval_accuracy": 0.6325459317585301,
72
  "eval_f1": 0.0,
73
  "eval_precision": 0.0,
74
  "eval_recall": 0.0,
75
- "eval_runtime": 5.773,
76
- "eval_samples_per_second": 65.997,
77
- "eval_steps_per_second": 4.157,
78
  "epoch": 1.7142857142857144,
79
  "step": 6
80
  },
81
  {
82
- "eval_loss": 0.6538448929786682,
83
- "eval_accuracy": 0.868766404199475,
84
  "eval_f1": 0.0,
85
  "eval_precision": 0.0,
86
  "eval_recall": 0.0,
87
- "eval_runtime": 5.6817,
88
- "eval_samples_per_second": 67.057,
89
- "eval_steps_per_second": 4.224,
90
  "epoch": 2.0,
91
  "step": 7
92
  },
93
  {
94
- "eval_loss": 0.6274169683456421,
95
- "eval_accuracy": 0.973753280839895,
96
  "eval_f1": 0.0,
97
  "eval_precision": 0.0,
98
  "eval_recall": 0.0,
99
- "eval_runtime": 5.8624,
100
- "eval_samples_per_second": 64.991,
101
- "eval_steps_per_second": 4.094,
102
  "epoch": 2.2857142857142856,
103
  "step": 8
104
  },
105
  {
106
- "eval_loss": 0.6018883585929871,
107
  "eval_accuracy": 0.9816272965879265,
108
  "eval_f1": 0.0,
109
  "eval_precision": 0.0,
110
  "eval_recall": 0.0,
111
- "eval_runtime": 5.644,
112
- "eval_samples_per_second": 67.505,
113
- "eval_steps_per_second": 4.252,
114
  "epoch": 2.571428571428571,
115
  "step": 9
116
  },
117
  {
118
- "train_runtime": 101.6832,
119
- "train_samples_per_second": 41.698,
120
- "train_steps_per_second": 0.59,
121
- "total_flos": 2156353020864.0,
122
- "train_loss": 0.6984957986407809,
123
  "epoch": 2.571428571428571,
124
  "step": 9
125
  }
 
1
  [
2
  {
3
+ "loss": 0.6688,
4
+ "grad_norm": 2.3227410316467285,
5
  "learning_rate": 3.3333333333333333e-06,
6
  "epoch": 0.2857142857142857,
7
  "step": 1
8
  },
9
  {
10
+ "eval_loss": 0.6694528460502625,
11
+ "eval_accuracy": 0.7690288713910761,
12
+ "eval_f1": 0.0,
13
+ "eval_precision": 0.0,
14
+ "eval_recall": 0.0,
15
+ "eval_runtime": 0.7051,
16
+ "eval_samples_per_second": 540.382,
17
+ "eval_steps_per_second": 34.04,
18
  "epoch": 0.2857142857142857,
19
  "step": 1
20
  },
21
  {
22
+ "eval_loss": 0.6646609902381897,
23
+ "eval_accuracy": 0.8110236220472441,
24
+ "eval_f1": 0.0,
25
+ "eval_precision": 0.0,
26
+ "eval_recall": 0.0,
27
+ "eval_runtime": 0.7126,
28
+ "eval_samples_per_second": 534.676,
29
+ "eval_steps_per_second": 33.68,
30
  "epoch": 0.5714285714285714,
31
  "step": 2
32
  },
33
  {
34
+ "eval_loss": 0.6550504565238953,
35
+ "eval_accuracy": 0.863517060367454,
36
+ "eval_f1": 0.0,
37
+ "eval_precision": 0.0,
38
+ "eval_recall": 0.0,
39
+ "eval_runtime": 2.6308,
40
+ "eval_samples_per_second": 144.825,
41
+ "eval_steps_per_second": 9.123,
42
  "epoch": 0.8571428571428571,
43
  "step": 3
44
  },
45
  {
46
+ "eval_loss": 0.6407275199890137,
47
+ "eval_accuracy": 0.9343832020997376,
48
+ "eval_f1": 0.0,
49
+ "eval_precision": 0.0,
50
+ "eval_recall": 0.0,
51
+ "eval_runtime": 0.7121,
52
+ "eval_samples_per_second": 535.065,
53
+ "eval_steps_per_second": 33.705,
54
  "epoch": 1.1428571428571428,
55
  "step": 4
56
  },
57
  {
58
+ "eval_loss": 0.6219562292098999,
59
+ "eval_accuracy": 0.9658792650918635,
60
+ "eval_f1": 0.0,
61
+ "eval_precision": 0.0,
62
+ "eval_recall": 0.0,
63
+ "eval_runtime": 0.7078,
64
+ "eval_samples_per_second": 538.256,
65
+ "eval_steps_per_second": 33.906,
66
  "epoch": 1.4285714285714286,
67
  "step": 5
68
  },
69
  {
70
+ "eval_loss": 0.599317193031311,
71
+ "eval_accuracy": 0.9763779527559056,
72
  "eval_f1": 0.0,
73
  "eval_precision": 0.0,
74
  "eval_recall": 0.0,
75
+ "eval_runtime": 1.1518,
76
+ "eval_samples_per_second": 330.775,
77
+ "eval_steps_per_second": 20.836,
78
  "epoch": 1.7142857142857144,
79
  "step": 6
80
  },
81
  {
82
+ "eval_loss": 0.5731121301651001,
83
+ "eval_accuracy": 0.9816272965879265,
84
  "eval_f1": 0.0,
85
  "eval_precision": 0.0,
86
  "eval_recall": 0.0,
87
+ "eval_runtime": 0.7338,
88
+ "eval_samples_per_second": 519.238,
89
+ "eval_steps_per_second": 32.708,
90
  "epoch": 2.0,
91
  "step": 7
92
  },
93
  {
94
+ "eval_loss": 0.5478406548500061,
95
+ "eval_accuracy": 0.9816272965879265,
96
  "eval_f1": 0.0,
97
  "eval_precision": 0.0,
98
  "eval_recall": 0.0,
99
+ "eval_runtime": 0.7067,
100
+ "eval_samples_per_second": 539.157,
101
+ "eval_steps_per_second": 33.963,
102
  "epoch": 2.2857142857142856,
103
  "step": 8
104
  },
105
  {
106
+ "eval_loss": 0.5236592292785645,
107
  "eval_accuracy": 0.9816272965879265,
108
  "eval_f1": 0.0,
109
  "eval_precision": 0.0,
110
  "eval_recall": 0.0,
111
+ "eval_runtime": 0.7083,
112
+ "eval_samples_per_second": 537.937,
113
+ "eval_steps_per_second": 33.886,
114
  "epoch": 2.571428571428571,
115
  "step": 9
116
  },
117
  {
118
+ "train_runtime": 18.534,
119
+ "train_samples_per_second": 228.769,
120
+ "train_steps_per_second": 3.237,
121
+ "total_flos": 2148246430560.0,
122
+ "train_loss": 0.6554172303941515,
123
  "epoch": 2.571428571428571,
124
  "step": 9
125
  }
training_artifacts/training_loss.png CHANGED

Git LFS Details

  • SHA256: 2442a6dfb2b6e233c954ed8baa916fc80416d0df3dad826dd04a67185674fd3f
  • Pointer size: 131 Bytes
  • Size of remote file: 181 kB

Git LFS Details

  • SHA256: c8de62a9b09da200f4f15b537ef7764460a1863b5a37524bf8c6c69dc403b544
  • Pointer size: 131 Bytes
  • Size of remote file: 181 kB
training_artifacts/training_metrics.png CHANGED

Git LFS Details

  • SHA256: 8fdaf612382fde5a85de85e053554c899ec7aad819b7ce3dca3dd632d3964b1c
  • Pointer size: 131 Bytes
  • Size of remote file: 186 kB

Git LFS Details

  • SHA256: f8d21d6e36234333edf90d5c61ef63b900fdc92fa5fd5fc2c100337807bd04e5
  • Pointer size: 131 Bytes
  • Size of remote file: 102 kB
training_artifacts/training_summary.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "total_epochs": 2.571428571428571,
3
  "total_steps": "9",
4
- "final_train_loss": 0.7327,
5
- "final_eval_loss": 0.6018883585929871,
6
- "best_eval_loss": 0.6018883585929871
7
  }
 
1
  {
2
  "total_epochs": 2.571428571428571,
3
  "total_steps": "9",
4
+ "final_train_loss": 0.6688,
5
+ "final_eval_loss": 0.5236592292785645,
6
+ "best_eval_loss": 0.5236592292785645
7
  }