Model save
Browse files- README.md +98 -0
- generation_config.json +8 -0
README.md
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: allenai/led-base-16384
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: hf
|
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 |
+
# hf
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2202
|
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: 3e-05
|
38 |
+
- train_batch_size: 2
|
39 |
+
- eval_batch_size: 2
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: polynomial
|
43 |
+
- lr_scheduler_warmup_steps: 500
|
44 |
+
- training_steps: 20000
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
51 |
+
| 0.255 | 0.0 | 500 | 0.2798 |
|
52 |
+
| 0.211 | 0.01 | 1000 | 0.2655 |
|
53 |
+
| 0.2399 | 0.01 | 1500 | 0.2625 |
|
54 |
+
| 0.2183 | 0.01 | 2000 | 0.2533 |
|
55 |
+
| 0.2375 | 0.02 | 2500 | 0.2501 |
|
56 |
+
| 0.2452 | 0.02 | 3000 | 0.2477 |
|
57 |
+
| 0.2636 | 0.02 | 3500 | 0.2474 |
|
58 |
+
| 0.2289 | 0.03 | 4000 | 0.2476 |
|
59 |
+
| 0.2453 | 0.03 | 4500 | 0.2443 |
|
60 |
+
| 0.2081 | 0.03 | 5000 | 0.2441 |
|
61 |
+
| 0.1655 | 0.04 | 5500 | 0.2422 |
|
62 |
+
| 0.2765 | 0.04 | 6000 | 0.2386 |
|
63 |
+
| 0.2797 | 0.05 | 6500 | 0.2398 |
|
64 |
+
| 0.1902 | 0.05 | 7000 | 0.2393 |
|
65 |
+
| 0.1875 | 0.05 | 7500 | 0.2363 |
|
66 |
+
| 0.2048 | 0.06 | 8000 | 0.2371 |
|
67 |
+
| 0.1695 | 0.06 | 8500 | 0.2341 |
|
68 |
+
| 0.2121 | 0.06 | 9000 | 0.2348 |
|
69 |
+
| 0.2402 | 0.07 | 9500 | 0.2331 |
|
70 |
+
| 0.1865 | 0.07 | 10000 | 0.2324 |
|
71 |
+
| 0.1862 | 0.07 | 10500 | 0.2329 |
|
72 |
+
| 0.2382 | 0.08 | 11000 | 0.2323 |
|
73 |
+
| 0.2703 | 0.08 | 11500 | 0.2300 |
|
74 |
+
| 0.2303 | 0.08 | 12000 | 0.2297 |
|
75 |
+
| 0.2258 | 0.09 | 12500 | 0.2287 |
|
76 |
+
| 0.1924 | 0.09 | 13000 | 0.2271 |
|
77 |
+
| 0.1849 | 0.09 | 13500 | 0.2269 |
|
78 |
+
| 0.2288 | 0.1 | 14000 | 0.2257 |
|
79 |
+
| 0.2461 | 0.1 | 14500 | 0.2259 |
|
80 |
+
| 0.2509 | 0.1 | 15000 | 0.2241 |
|
81 |
+
| 0.2087 | 0.11 | 15500 | 0.2245 |
|
82 |
+
| 0.1707 | 0.11 | 16000 | 0.2243 |
|
83 |
+
| 0.2053 | 0.11 | 16500 | 0.2238 |
|
84 |
+
| 0.2157 | 0.12 | 17000 | 0.2225 |
|
85 |
+
| 0.1976 | 0.12 | 17500 | 0.2218 |
|
86 |
+
| 0.2626 | 0.13 | 18000 | 0.2213 |
|
87 |
+
| 0.2032 | 0.13 | 18500 | 0.2209 |
|
88 |
+
| 0.2928 | 0.13 | 19000 | 0.2207 |
|
89 |
+
| 0.2438 | 0.14 | 19500 | 0.2205 |
|
90 |
+
| 0.2028 | 0.14 | 20000 | 0.2202 |
|
91 |
+
|
92 |
+
|
93 |
+
### Framework versions
|
94 |
+
|
95 |
+
- Transformers 4.37.2
|
96 |
+
- Pytorch 2.2.2+cu121
|
97 |
+
- Datasets 2.18.0
|
98 |
+
- Tokenizers 0.15.1
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.37.2"
|
8 |
+
}
|