daze-unlv commited on
Commit
d2c2086
1 Parent(s): 912bf79

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uw-madison/yoso-4096",
3
+ "architectures": [
4
+ "YosoForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "conv_window": null,
9
+ "eos_token_id": 2,
10
+ "hash_code_len": 9,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-12,
17
+ "lsh_backward": true,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "yoso",
20
+ "num_attention_heads": 12,
21
+ "num_hash": 64,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "tokenizer_class": "AlbertTokenizer",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.39.0.dev0",
28
+ "type_vocab_size": 1,
29
+ "use_expectation": true,
30
+ "use_fast_hash": true,
31
+ "vocab_size": 50265
32
+ }
log.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ [1/4] /home/ludaze/usr/local/cuda/cuda-11.8/bin/nvcc --generate-dependencies-with-compile --dependency-output fast_lsh_cumulation_cuda.cuda.o.d -DTORCH_EXTENSION_NAME=fast_lsh_cumulation -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/TH -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/THC -isystem /home/ludaze/usr/local/cuda/cuda-11.8/include -isystem /home/ludaze/.conda/envs/axolotl/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++17 -c /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/transformers/kernels/yoso/fast_lsh_cumulation_cuda.cu -o fast_lsh_cumulation_cuda.cuda.o
2
+ [2/4] c++ -MMD -MF fast_lsh_cumulation_torch.o.d -DTORCH_EXTENSION_NAME=fast_lsh_cumulation -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/TH -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/THC -isystem /home/ludaze/usr/local/cuda/cuda-11.8/include -isystem /home/ludaze/.conda/envs/axolotl/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -c /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/transformers/kernels/yoso/fast_lsh_cumulation_torch.cpp -o fast_lsh_cumulation_torch.o
3
+ [3/4] /home/ludaze/usr/local/cuda/cuda-11.8/bin/nvcc --generate-dependencies-with-compile --dependency-output fast_lsh_cumulation.cuda.o.d -DTORCH_EXTENSION_NAME=fast_lsh_cumulation -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/TH -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/THC -isystem /home/ludaze/usr/local/cuda/cuda-11.8/include -isystem /home/ludaze/.conda/envs/axolotl/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++17 -c /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/transformers/kernels/yoso/fast_lsh_cumulation.cu -o fast_lsh_cumulation.cuda.o
4
+ [4/4] c++ fast_lsh_cumulation_torch.o fast_lsh_cumulation.cuda.o fast_lsh_cumulation_cuda.cuda.o -shared -L/home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/home/ludaze/usr/local/cuda/cuda-11.8/lib64 -lcudart -o fast_lsh_cumulation.so
5
+ {'loss': 1.3875, 'grad_norm': 0.290032297372818, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
6
+ {'loss': 1.387, 'grad_norm': 0.24705088138580322, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
7
+ {'loss': 1.387, 'grad_norm': 0.2913823425769806, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
8
+ {'loss': 1.3867, 'grad_norm': 0.2294648140668869, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
9
+ {'loss': 1.3868, 'grad_norm': 0.25805965065956116, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c1e52f9a3606b166333f65d696a3aa6724be199025da91d8b3ecc092550652
3
+ size 509619172
runs/Mar13_10-51-07_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710352269.cehsc-app-001.ad.unlv.edu.2985100.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb81185d7f756e1bec10b8d2accf8c710d80db11def9d501623caf2a3945903d
3
+ size 6151
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7ea0d9c64fc59dd649552dd9900385ad550a2f37beed7e40b9a68601284e2c
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff