Model save
Browse files
README.md
CHANGED
@@ -6,6 +6,7 @@ metrics:
|
|
6 |
model-index:
|
7 |
- name: lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3__home_aiops_zhuty_lm_indexer_data_tyzhu_
|
8 |
results: []
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model was trained from scratch on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
-
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,12 +37,12 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0001
|
39 |
-
- train_batch_size:
|
40 |
- eval_batch_size: 2
|
41 |
- seed: 42
|
42 |
- distributed_type: multi-GPU
|
43 |
- num_devices: 4
|
44 |
-
- gradient_accumulation_steps:
|
45 |
- total_train_batch_size: 32
|
46 |
- total_eval_batch_size: 8
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -51,33 +52,34 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch
|
55 |
-
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
|
77 |
|
78 |
### Framework versions
|
79 |
|
80 |
-
-
|
81 |
-
-
|
82 |
-
-
|
83 |
-
-
|
|
|
|
6 |
model-index:
|
7 |
- name: lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3__home_aiops_zhuty_lm_indexer_data_tyzhu_
|
8 |
results: []
|
9 |
+
library_name: peft
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
16 |
|
17 |
This model was trained from scratch on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0955
|
20 |
+
- Accuracy: 0.7196
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 0.0001
|
40 |
+
- train_batch_size: 1
|
41 |
- eval_batch_size: 2
|
42 |
- seed: 42
|
43 |
- distributed_type: multi-GPU
|
44 |
- num_devices: 4
|
45 |
+
- gradient_accumulation_steps: 8
|
46 |
- total_train_batch_size: 32
|
47 |
- total_eval_batch_size: 8
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
57 |
+
| 0.7054 | 0.9973 | 187 | 0.5535 | 0.7686 |
|
58 |
+
| 0.4975 | 2.0 | 375 | 0.5416 | 0.7693 |
|
59 |
+
| 0.422 | 2.9973 | 562 | 0.5611 | 0.7645 |
|
60 |
+
| 0.3527 | 4.0 | 750 | 0.6100 | 0.7573 |
|
61 |
+
| 0.2941 | 4.9973 | 937 | 0.6599 | 0.7522 |
|
62 |
+
| 0.2518 | 6.0 | 1125 | 0.7200 | 0.7458 |
|
63 |
+
| 0.2138 | 6.9973 | 1312 | 0.7651 | 0.7421 |
|
64 |
+
| 0.1824 | 8.0 | 1500 | 0.8280 | 0.7379 |
|
65 |
+
| 0.1481 | 8.9973 | 1687 | 0.8700 | 0.7355 |
|
66 |
+
| 0.1298 | 10.0 | 1875 | 0.9146 | 0.7329 |
|
67 |
+
| 0.1167 | 10.9973 | 2062 | 0.9337 | 0.7309 |
|
68 |
+
| 0.1094 | 12.0 | 2250 | 0.9733 | 0.7281 |
|
69 |
+
| 0.1052 | 12.9973 | 2437 | 0.9980 | 0.7266 |
|
70 |
+
| 0.1007 | 14.0 | 2625 | 1.0022 | 0.7256 |
|
71 |
+
| 0.0971 | 14.9973 | 2812 | 1.0422 | 0.7234 |
|
72 |
+
| 0.0954 | 16.0 | 3000 | 1.0441 | 0.7236 |
|
73 |
+
| 0.0888 | 16.9973 | 3187 | 1.0574 | 0.7223 |
|
74 |
+
| 0.0879 | 18.0 | 3375 | 1.0728 | 0.7216 |
|
75 |
+
| 0.0879 | 18.9973 | 3562 | 1.0768 | 0.7200 |
|
76 |
+
| 0.0883 | 19.9467 | 3740 | 1.0955 | 0.7196 |
|
77 |
|
78 |
|
79 |
### Framework versions
|
80 |
|
81 |
+
- PEFT 0.5.0
|
82 |
+
- Transformers 4.40.2
|
83 |
+
- Pytorch 2.3.0
|
84 |
+
- Datasets 2.19.1
|
85 |
+
- Tokenizers 0.19.1
|