nadahlberg
commited on
Commit
•
73bd912
1
Parent(s):
965f244
Model save
Browse files- README.md +16 -17
- eval_results.json +5 -5
- logs/events.out.tfevents.1722463228.nathan.173807.0 +3 -0
- logs/events.out.tfevents.1722465205.nathan.173807.1 +3 -0
- model.safetensors +1 -1
- run_config.json +4 -3
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [docketanalyzer/docket-lm-xs](https://huggingface.co/docketanalyzer/docket-lm-xs) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- F1: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,32 +38,31 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 16
|
43 |
- seed: 42
|
44 |
-
- gradient_accumulation_steps: 2
|
45 |
-
- total_train_batch_size: 16
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.02
|
49 |
- num_epochs: 1
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.0005 | 0.4 | 1900 | 0.
|
60 |
-
| 0.
|
61 |
-
| 0.0004 | 0.56 | 2660 | 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.0002 | 0.96 | 4560 | 0.
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [docketanalyzer/docket-lm-xs](https://huggingface.co/docketanalyzer/docket-lm-xs) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0015
|
21 |
+
- F1: 0.9995
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 16
|
42 |
- eval_batch_size: 16
|
43 |
- seed: 42
|
|
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_ratio: 0.02
|
47 |
- num_epochs: 1
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
+
| 0.0013 | 0.08 | 380 | 0.0054 | 0.9983 |
|
55 |
+
| 0.0007 | 0.16 | 760 | 0.0139 | 0.9976 |
|
56 |
+
| 0.0003 | 0.24 | 1140 | 0.0061 | 0.9985 |
|
57 |
+
| 0.0002 | 0.32 | 1520 | 0.0109 | 0.9981 |
|
58 |
+
| 0.0005 | 0.4 | 1900 | 0.0093 | 0.9985 |
|
59 |
+
| 0.0002 | 0.48 | 2280 | 0.0080 | 0.9988 |
|
60 |
+
| 0.0004 | 0.56 | 2660 | 0.0099 | 0.9978 |
|
61 |
+
| 0.0004 | 0.64 | 3040 | 0.0024 | 0.9990 |
|
62 |
+
| 0.0002 | 0.72 | 3420 | 0.0037 | 0.9988 |
|
63 |
+
| 0.0003 | 0.8 | 3800 | 0.0013 | 0.9998 |
|
64 |
+
| 0.0003 | 0.88 | 4180 | 0.0034 | 0.9993 |
|
65 |
+
| 0.0002 | 0.96 | 4560 | 0.0017 | 0.9993 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"eval_loss": 0.
|
3 |
-
"eval_f1": 0.
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second":
|
7 |
"epoch": 1.0
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"eval_loss": 0.0014596829423680902,
|
3 |
+
"eval_f1": 0.9995131450827653,
|
4 |
+
"eval_runtime": 8.2463,
|
5 |
+
"eval_samples_per_second": 485.069,
|
6 |
+
"eval_steps_per_second": 30.317,
|
7 |
"epoch": 1.0
|
8 |
}
|
logs/events.out.tfevents.1722463228.nathan.173807.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62e8708557de010a167899eb5d5e54a4960bf8ed5e9b084c3dffc66f4c703bf3
|
3 |
+
size 510331
|
logs/events.out.tfevents.1722465205.nathan.173807.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f985d34adea2e9a1d80da94c3239daa4d1945bbf531e2934080619656a049ae5
|
3 |
+
size 405
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 283347432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0566ceb185a37aceb7b77f0d65402f1449a3d7df5c6688cfc268627f2c4ab89b
|
3 |
size 283347432
|
run_config.json
CHANGED
@@ -5,16 +5,17 @@
|
|
5 |
},
|
6 |
"training_args": {
|
7 |
"num_train_epochs": 1,
|
8 |
-
"per_device_train_batch_size":
|
9 |
"per_device_eval_batch_size": 16,
|
10 |
-
"gradient_accumulation_steps":
|
11 |
"learning_rate": 5e-05,
|
12 |
"weight_decay": 0.1,
|
13 |
"warmup_ratio": 0.02,
|
14 |
"evaluation_strategy": "steps",
|
15 |
"eval_steps": 0.08,
|
16 |
"save_steps": 0.08,
|
17 |
-
"save_total_limit": 2
|
|
|
18 |
},
|
19 |
"run_name": "complaint",
|
20 |
"run_type": "ClassificationRoutine"
|
|
|
5 |
},
|
6 |
"training_args": {
|
7 |
"num_train_epochs": 1,
|
8 |
+
"per_device_train_batch_size": 16,
|
9 |
"per_device_eval_batch_size": 16,
|
10 |
+
"gradient_accumulation_steps": 1,
|
11 |
"learning_rate": 5e-05,
|
12 |
"weight_decay": 0.1,
|
13 |
"warmup_ratio": 0.02,
|
14 |
"evaluation_strategy": "steps",
|
15 |
"eval_steps": 0.08,
|
16 |
"save_steps": 0.08,
|
17 |
+
"save_total_limit": 2,
|
18 |
+
"fp16": true
|
19 |
},
|
20 |
"run_name": "complaint",
|
21 |
"run_type": "ClassificationRoutine"
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30d3579d075a2b7dcef799631a3bf63aed51391f5e3e930601890e8d9c6c88eb
|
3 |
size 5240
|