End of training
Browse files
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: BigTMiami/amazon_pretraining_5M_model_corrected
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: dapt_plus_tapt_helpfulness_base_pretraining_model
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# dapt_plus_tapt_helpfulness_base_pretraining_model
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [BigTMiami/amazon_pretraining_5M_model_corrected](https://huggingface.co/BigTMiami/amazon_pretraining_5M_model_corrected) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.4446
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0001
|
38 |
+
- train_batch_size: 21
|
39 |
+
- eval_batch_size: 21
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 2
|
42 |
+
- total_train_batch_size: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 100
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 1.6784 | 1.0 | 232 | 1.5304 |
|
52 |
+
| 1.6014 | 2.0 | 465 | 1.5186 |
|
53 |
+
| 1.5847 | 3.0 | 697 | 1.5100 |
|
54 |
+
| 1.5492 | 4.0 | 930 | 1.4959 |
|
55 |
+
| 1.5369 | 5.0 | 1162 | 1.5022 |
|
56 |
+
| 1.5086 | 6.0 | 1395 | 1.4919 |
|
57 |
+
| 1.4953 | 7.0 | 1627 | 1.4770 |
|
58 |
+
| 1.4729 | 8.0 | 1860 | 1.4840 |
|
59 |
+
| 1.4612 | 9.0 | 2092 | 1.4719 |
|
60 |
+
| 1.4502 | 10.0 | 2325 | 1.4595 |
|
61 |
+
| 1.436 | 11.0 | 2557 | 1.4670 |
|
62 |
+
| 1.4178 | 12.0 | 2790 | 1.4709 |
|
63 |
+
| 1.4055 | 13.0 | 3022 | 1.4514 |
|
64 |
+
| 1.3951 | 14.0 | 3255 | 1.4595 |
|
65 |
+
| 1.3848 | 15.0 | 3487 | 1.4585 |
|
66 |
+
| 1.3678 | 16.0 | 3720 | 1.4752 |
|
67 |
+
| 1.3659 | 17.0 | 3952 | 1.4636 |
|
68 |
+
| 1.3523 | 18.0 | 4185 | 1.4515 |
|
69 |
+
| 1.3443 | 19.0 | 4417 | 1.4609 |
|
70 |
+
| 1.3285 | 20.0 | 4650 | 1.4590 |
|
71 |
+
| 1.3283 | 21.0 | 4882 | 1.4595 |
|
72 |
+
| 1.3109 | 22.0 | 5115 | 1.4490 |
|
73 |
+
| 1.3111 | 23.0 | 5347 | 1.4457 |
|
74 |
+
| 1.2964 | 24.0 | 5580 | 1.4543 |
|
75 |
+
| 1.2945 | 25.0 | 5812 | 1.4500 |
|
76 |
+
| 1.2792 | 26.0 | 6045 | 1.4537 |
|
77 |
+
| 1.2741 | 27.0 | 6277 | 1.4428 |
|
78 |
+
| 1.2603 | 28.0 | 6510 | 1.4508 |
|
79 |
+
| 1.2609 | 29.0 | 6742 | 1.4473 |
|
80 |
+
| 1.246 | 30.0 | 6975 | 1.4458 |
|
81 |
+
| 1.2436 | 31.0 | 7207 | 1.4473 |
|
82 |
+
| 1.2324 | 32.0 | 7440 | 1.4384 |
|
83 |
+
| 1.2282 | 33.0 | 7672 | 1.4368 |
|
84 |
+
| 1.2164 | 34.0 | 7905 | 1.4466 |
|
85 |
+
| 1.2146 | 35.0 | 8137 | 1.4460 |
|
86 |
+
| 1.2022 | 36.0 | 8370 | 1.4520 |
|
87 |
+
| 1.1991 | 37.0 | 8602 | 1.4509 |
|
88 |
+
| 1.191 | 38.0 | 8835 | 1.4412 |
|
89 |
+
| 1.1909 | 39.0 | 9067 | 1.4449 |
|
90 |
+
| 1.1777 | 40.0 | 9300 | 1.4521 |
|
91 |
+
| 1.1762 | 41.0 | 9532 | 1.4582 |
|
92 |
+
| 1.166 | 42.0 | 9765 | 1.4403 |
|
93 |
+
| 1.1618 | 43.0 | 9997 | 1.4484 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.38.2
|
99 |
+
- Pytorch 2.2.1+cu121
|
100 |
+
- Datasets 2.18.0
|
101 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498813948
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f24dea3a056aeb662df938085aa5ace67b7c2c5d2144919c97363abaee6e4d62
|
3 |
size 498813948
|
runs/Apr16_20-21-06_ec2cbfe8c2a4/events.out.tfevents.1713298869.ec2cbfe8c2a4.385.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7fa10c8a1051fd95d83d34d3369534ada43f2f7fb0f5b3d317116fb1b11daec
|
3 |
+
size 25816
|
runs/Apr16_20-21-06_ec2cbfe8c2a4/events.out.tfevents.1713303791.ec2cbfe8c2a4.385.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a194b8022928dd169c7fd7441b4bcda320d6f504e09b40220781e7a956ad39f1
|
3 |
+
size 359
|