Model save
Browse files- README.md +145 -0
- best/config.json +17 -0
- best/model.safetensors +3 -0
- best/training_args.bin +3 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: results_model5
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# results_model5
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 230.4205
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0001
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 16
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- lr_scheduler_warmup_steps: 300
|
42 |
+
- num_epochs: 50
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-------:|:------:|:---------------:|
|
49 |
+
| 7.2107 | 0.5570 | 10000 | 7.1334 |
|
50 |
+
| 6.855 | 1.1141 | 20000 | 6.8933 |
|
51 |
+
| 6.7223 | 1.6711 | 30000 | 6.8169 |
|
52 |
+
| 6.5948 | 2.2282 | 40000 | 6.8059 |
|
53 |
+
| 6.5197 | 2.7852 | 50000 | 6.8322 |
|
54 |
+
| 6.3908 | 3.3422 | 60000 | 6.6924 |
|
55 |
+
| 6.3202 | 3.8993 | 70000 | 6.8986 |
|
56 |
+
| 6.2023 | 4.4563 | 80000 | 6.7110 |
|
57 |
+
| 6.1197 | 5.0134 | 90000 | 6.5662 |
|
58 |
+
| 6.1291 | 5.5704 | 100000 | 6.7865 |
|
59 |
+
| 6.0831 | 6.1275 | 110000 | 6.4560 |
|
60 |
+
| 6.0572 | 6.6845 | 120000 | 6.6910 |
|
61 |
+
| 5.9835 | 7.2415 | 130000 | 6.5923 |
|
62 |
+
| 5.9799 | 7.7986 | 140000 | 6.6270 |
|
63 |
+
| 5.889 | 8.3556 | 150000 | 6.5736 |
|
64 |
+
| 5.9385 | 8.9127 | 160000 | 6.5225 |
|
65 |
+
| 5.9399 | 9.4697 | 170000 | 6.4342 |
|
66 |
+
| 5.8455 | 10.0267 | 180000 | 6.7230 |
|
67 |
+
| 5.8304 | 10.5838 | 190000 | 6.6909 |
|
68 |
+
| 5.8024 | 11.1408 | 200000 | 6.5837 |
|
69 |
+
| 5.7549 | 11.6979 | 210000 | 6.6577 |
|
70 |
+
| 5.7796 | 12.2549 | 220000 | 6.4482 |
|
71 |
+
| 5.7656 | 12.8119 | 230000 | 6.4355 |
|
72 |
+
| 5.7265 | 13.3690 | 240000 | 6.8308 |
|
73 |
+
| 5.7496 | 13.9260 | 250000 | 6.5874 |
|
74 |
+
| 5.6837 | 14.4831 | 260000 | 6.4602 |
|
75 |
+
| 5.6449 | 15.0401 | 270000 | 6.8683 |
|
76 |
+
| 5.6522 | 15.5971 | 280000 | 6.7332 |
|
77 |
+
| 5.5971 | 16.1542 | 290000 | 7.0091 |
|
78 |
+
| 5.6177 | 16.7112 | 300000 | 6.9452 |
|
79 |
+
| 5.5726 | 17.2683 | 310000 | 7.1216 |
|
80 |
+
| 5.6119 | 17.8253 | 320000 | 7.3758 |
|
81 |
+
| 5.5656 | 18.3824 | 330000 | 6.7465 |
|
82 |
+
| 5.5463 | 18.9394 | 340000 | 6.4133 |
|
83 |
+
| 5.5375 | 19.4964 | 350000 | 6.7948 |
|
84 |
+
| 5.4745 | 20.0535 | 360000 | 7.1663 |
|
85 |
+
| 5.5345 | 20.6105 | 370000 | 6.9830 |
|
86 |
+
| 5.5127 | 21.1676 | 380000 | 7.1736 |
|
87 |
+
| 5.5163 | 21.7246 | 390000 | 6.9526 |
|
88 |
+
| 5.5085 | 22.2816 | 400000 | 7.1294 |
|
89 |
+
| 5.4868 | 22.8387 | 410000 | 7.2336 |
|
90 |
+
| 5.4954 | 23.3957 | 420000 | 7.3882 |
|
91 |
+
| 5.4534 | 23.9528 | 430000 | 7.4660 |
|
92 |
+
| 5.4636 | 24.5098 | 440000 | 7.7570 |
|
93 |
+
| 5.4572 | 25.0668 | 450000 | 7.2802 |
|
94 |
+
| 5.4501 | 25.6239 | 460000 | 7.0237 |
|
95 |
+
| 5.4259 | 26.1809 | 470000 | 7.2043 |
|
96 |
+
| 5.4205 | 26.7380 | 480000 | 7.4920 |
|
97 |
+
| 5.4388 | 27.2950 | 490000 | 7.6919 |
|
98 |
+
| 5.4461 | 27.8520 | 500000 | 7.2496 |
|
99 |
+
| 5.4505 | 28.4091 | 510000 | 8.0927 |
|
100 |
+
| 5.3868 | 28.9661 | 520000 | 7.9013 |
|
101 |
+
| 5.3955 | 29.5232 | 530000 | 7.3911 |
|
102 |
+
| 5.3767 | 30.0802 | 540000 | 7.5686 |
|
103 |
+
| 5.4033 | 30.6373 | 550000 | 7.6312 |
|
104 |
+
| 5.4766 | 31.1943 | 560000 | 7.4374 |
|
105 |
+
| 5.4446 | 31.7513 | 570000 | 8.5821 |
|
106 |
+
| 5.3709 | 32.3084 | 580000 | 8.1120 |
|
107 |
+
| 5.3984 | 32.8654 | 590000 | 7.8773 |
|
108 |
+
| 5.3645 | 33.4225 | 600000 | 7.4649 |
|
109 |
+
| 5.4198 | 33.9795 | 610000 | 8.5657 |
|
110 |
+
| 5.3058 | 34.5365 | 620000 | 7.8521 |
|
111 |
+
| 5.3206 | 35.0936 | 630000 | 7.7948 |
|
112 |
+
| 5.3565 | 35.6506 | 640000 | 8.0000 |
|
113 |
+
| 5.2853 | 36.2077 | 650000 | 7.2801 |
|
114 |
+
| 5.354 | 36.7647 | 660000 | 7.6050 |
|
115 |
+
| 5.3187 | 37.3217 | 670000 | 7.9883 |
|
116 |
+
| 5.3183 | 37.8788 | 680000 | 7.8469 |
|
117 |
+
| 5.4273 | 38.4358 | 690000 | 6.9470 |
|
118 |
+
| 5.5932 | 38.9929 | 700000 | 6.4775 |
|
119 |
+
| 6.8168 | 39.5499 | 710000 | 7.6621 |
|
120 |
+
| 7.9333 | 40.1070 | 720000 | 8.5982 |
|
121 |
+
| 10.8308 | 40.6640 | 730000 | 11.0965 |
|
122 |
+
| 25.3974 | 41.2210 | 740000 | 25.4061 |
|
123 |
+
| 13.526 | 41.7781 | 750000 | 13.1423 |
|
124 |
+
| 11.8513 | 42.3351 | 760000 | 11.7643 |
|
125 |
+
| 10.1776 | 42.8922 | 770000 | 9.8905 |
|
126 |
+
| 96.1114 | 43.4492 | 780000 | 97.4525 |
|
127 |
+
| 196.2914 | 44.0062 | 790000 | 199.1897 |
|
128 |
+
| 227.9711 | 44.5633 | 800000 | 230.4205 |
|
129 |
+
| 226.7711 | 45.1203 | 810000 | 230.4205 |
|
130 |
+
| 225.694 | 45.6774 | 820000 | 230.4205 |
|
131 |
+
| 226.7237 | 46.2344 | 830000 | 230.4205 |
|
132 |
+
| 226.6388 | 46.7914 | 840000 | 230.4205 |
|
133 |
+
| 225.8023 | 47.3485 | 850000 | 230.4205 |
|
134 |
+
| 226.7597 | 47.9055 | 860000 | 230.4205 |
|
135 |
+
| 226.232 | 48.4626 | 870000 | 230.4205 |
|
136 |
+
| 226.6263 | 49.0196 | 880000 | 230.4205 |
|
137 |
+
| 226.0536 | 49.5766 | 890000 | 230.4205 |
|
138 |
+
|
139 |
+
|
140 |
+
### Framework versions
|
141 |
+
|
142 |
+
- Transformers 4.40.2
|
143 |
+
- Pytorch 2.3.0
|
144 |
+
- Datasets 2.19.1
|
145 |
+
- Tokenizers 0.19.1
|
best/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"TransformerModel"
|
4 |
+
],
|
5 |
+
"d_model": 512,
|
6 |
+
"dim_feedforward": 1024,
|
7 |
+
"dropout": 0.1,
|
8 |
+
"input_dim": 30000,
|
9 |
+
"max_seq_len": 1024,
|
10 |
+
"model_type": "transformer",
|
11 |
+
"nhead": 8,
|
12 |
+
"num_decoder_layers": 6,
|
13 |
+
"num_encoder_layers": 6,
|
14 |
+
"output_dim": 30000,
|
15 |
+
"torch_dtype": "float32",
|
16 |
+
"transformers_version": "4.40.2"
|
17 |
+
}
|
best/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd7befb72b4a43439725b565c62c562c31e15a1a3e27aab34f8bb4523f27417
|
3 |
+
size 251300560
|
best/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d37b3f5d3a69e86ac3302cbc767bed886d067c692cbaf76c7999649648205c2d
|
3 |
+
size 5112
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 251300560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd7befb72b4a43439725b565c62c562c31e15a1a3e27aab34f8bb4523f27417
|
3 |
size 251300560
|