Hugging Face's logo

lapa-llm
/
alignment-score-model

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
robinhad commited on
Commit
d9d7f01
·
verified ·
1 Parent(s): aa1a181

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. README.md +14 -14
  2. final/model.safetensors +1 -1
  3. final/training_args.bin +1 -1
  4. model.safetensors +1 -1
  5. runs/Sep14_18-15-35_fs-cai-002/events.out.tfevents.1757873740.fs-cai-002.3614253.0 +2 -2
  6. runs/Sep14_18-17-49_fs-cai-002/events.out.tfevents.1757873873.fs-cai-002.3615295.0 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0969
24
- - Precision: 0.9388
25
- - Recall: 0.9275
26
- - F1 Macro: 0.9283
27
- - Accuracy: 0.9289
28
 
29
  ## Model description
30
 
@@ -44,12 +44,12 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 3e-05
47
- - train_batch_size: 256
48
  - eval_batch_size: 128
49
  - seed: 0
50
  - distributed_type: multi-GPU
51
  - num_devices: 8
52
- - total_train_batch_size: 2048
53
  - total_eval_batch_size: 1024
54
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
55
  - lr_scheduler_type: linear
@@ -59,13 +59,13 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
61
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
62
- | No log | 0 | 0 | 0.4846 | 0.2550 | 0.5 | 0.3377 | 0.5100 |
63
- | No log | 1.0 | 4 | 0.2132 | 0.7608 | 0.6895 | 0.6704 | 0.6947 |
64
- | No log | 2.0 | 8 | 0.1678 | 0.8813 | 0.8469 | 0.8458 | 0.8498 |
65
- | No log | 3.0 | 12 | 0.1488 | 0.8297 | 0.7313 | 0.7137 | 0.7367 |
66
- | No log | 4.0 | 16 | 0.1257 | 0.8693 | 0.8159 | 0.8121 | 0.8196 |
67
- | No log | 5.0 | 20 | 0.1047 | 0.9183 | 0.8984 | 0.8989 | 0.9004 |
68
- | No log | 6.0 | 24 | 0.0969 | 0.9388 | 0.9275 | 0.9283 | 0.9289 |
69
 
70
 
71
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0077
24
+ - Precision: 0.9995
25
+ - Recall: 0.9995
26
+ - F1 Macro: 0.9995
27
+ - Accuracy: 0.9995
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 3e-05
47
+ - train_batch_size: 32
48
  - eval_batch_size: 128
49
  - seed: 0
50
  - distributed_type: multi-GPU
51
  - num_devices: 8
52
+ - total_train_batch_size: 256
53
  - total_eval_batch_size: 1024
54
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
55
  - lr_scheduler_type: linear
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
61
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
62
+ | No log | 0 | 0 | 0.3800 | 0.2550 | 0.5 | 0.3377 | 0.5100 |
63
+ | No log | 1.0 | 31 | 0.0183 | 0.9963 | 0.9962 | 0.9962 | 0.9962 |
64
+ | No log | 2.0 | 62 | 0.0106 | 0.9995 | 0.9995 | 0.9995 | 0.9995 |
65
+ | No log | 3.0 | 93 | 0.0090 | 0.9995 | 0.9995 | 0.9995 | 0.9995 |
66
+ | 0.0339 | 4.0 | 124 | 0.0082 | 0.9995 | 0.9995 | 0.9995 | 0.9995 |
67
+ | 0.0339 | 5.0 | 155 | 0.0078 | 0.9995 | 0.9995 | 0.9995 | 0.9995 |
68
+ | 0.0339 | 6.0 | 186 | 0.0077 | 0.9995 | 0.9995 | 0.9995 | 0.9995 |
69
 
70
 
71
  ### Framework versions
final/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2d871c1c9db3bf703b69015678e7daae94d8a6464b6fe788cc481f9665748a2
3
  size 1112201932
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9e5ef6e60699b8a5c54d32d8a6b5e20ec5051519bbe823c03dadd770d36c34
3
  size 1112201932
final/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5685c8d944a8138d54ea8d9ac9bd7d9f7858cfa5fba16bf86c8fb5115d681ebd
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfeddccf810fad45336a0ec967fe155b99071d859db049cfcb4c4ec32b885d07
3
  size 5432
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0795a9050cc280a2a9d0739ec2bfc7e9f7aeadb88fda0bcf07dc786d4b881365
3
  size 1112201932
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e34a8a16c6b025c273cb72b84871d18baa965d0be495978988db430abe09cc24
3
  size 1112201932
runs/Sep14_18-15-35_fs-cai-002/events.out.tfevents.1757873740.fs-cai-002.3614253.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62a4a6ee154ddac260dc9607ab6eb156dcbecf1cbe7918e7f75410099af7466
3
- size 8613
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7586483b428e7d55257d75038ee01cfa1d74e8f3527c1645fef49294ae498249
3
+ size 8967
runs/Sep14_18-17-49_fs-cai-002/events.out.tfevents.1757873873.fs-cai-002.3615295.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a4383e419ed9c68f7843207f4c74b5475793753dd031cfda7377942db28524
3
+ size 6512
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfeddccf810fad45336a0ec967fe155b99071d859db049cfcb4c4ec32b885d07
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d32bf7c1e6d6196d6a5c398e875afe04cfa26acaf6fda29b7d730253b3a90e
3
  size 5432