Model save
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: smolm-autoreg-bpe-counterfactual_babylm_naans_new-seed_211-1e-4
|
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 |
+
# smolm-autoreg-bpe-counterfactual_babylm_naans_new-seed_211-1e-4
|
15 |
+
|
16 |
+
This model was trained from scratch on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.4159
|
19 |
+
- Accuracy: 0.4060
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 32
|
40 |
+
- eval_batch_size: 64
|
41 |
+
- seed: 211
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 32000
|
45 |
+
- num_epochs: 20.0
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
52 |
+
| 4.0574 | 1.0 | 18595 | 4.2668 | 0.3095 |
|
53 |
+
| 3.574 | 2.0 | 37190 | 3.7340 | 0.3638 |
|
54 |
+
| 3.3998 | 3.0 | 55785 | 3.5946 | 0.3793 |
|
55 |
+
| 3.2908 | 4.0 | 74380 | 3.5169 | 0.3871 |
|
56 |
+
| 3.2244 | 5.0 | 92975 | 3.4843 | 0.3919 |
|
57 |
+
| 3.1723 | 6.0 | 111570 | 3.4423 | 0.3955 |
|
58 |
+
| 3.1287 | 7.0 | 130165 | 3.4224 | 0.3987 |
|
59 |
+
| 3.0995 | 8.0 | 148760 | 3.4119 | 0.4001 |
|
60 |
+
| 3.0666 | 9.0 | 167355 | 3.4093 | 0.4014 |
|
61 |
+
| 3.0395 | 10.0 | 185950 | 3.3993 | 0.4024 |
|
62 |
+
| 3.0097 | 11.0 | 204545 | 3.4087 | 0.4031 |
|
63 |
+
| 2.9923 | 12.0 | 223140 | 3.4030 | 0.4042 |
|
64 |
+
| 2.9703 | 13.0 | 241735 | 3.3938 | 0.4047 |
|
65 |
+
| 2.9483 | 14.0 | 260330 | 3.4000 | 0.4051 |
|
66 |
+
| 2.9286 | 15.0 | 278925 | 3.4069 | 0.4048 |
|
67 |
+
| 2.9143 | 16.0 | 297520 | 3.4020 | 0.4056 |
|
68 |
+
| 2.8935 | 17.0 | 316115 | 3.4100 | 0.4055 |
|
69 |
+
| 2.8782 | 18.0 | 334710 | 3.4071 | 0.4058 |
|
70 |
+
| 2.8613 | 19.0 | 353305 | 3.4123 | 0.4062 |
|
71 |
+
| 2.8439 | 20.0 | 371900 | 3.4159 | 0.4060 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.38.0
|
77 |
+
- Pytorch 2.3.1+cu121
|
78 |
+
- Datasets 2.16.1
|
79 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.38.0"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 391376736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:335877d43331c6f5c23e7a7863f9ccf31dad850dd73a6945e57b76848521367d
|
3 |
size 391376736
|
runs/Jun17_22-31-03_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1718681821.phyl-ling-p01.la.utexas.edu.556175.0
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:eb18f5bbd5f706486e041db168ceb7a8704dd525b58fca8174eefc39f6d59999
|
3 |
+
size 91600
|