Hugging Face's logo

mrtuandao
/
dunono

Safetensors
Model card Files
xet
Community
mrtuandao commited on
Commit
de3bc6e
·
verified ·
1 Parent(s): e07e2d6

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/added_tokens.json +5 -0
  3. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/chat_template.jinja +6 -0
  4. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/config.json +39 -0
  5. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/generation_config.json +6 -0
  6. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/lr_scheduler.pt +3 -0
  7. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/merges.txt +0 -0
  8. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/model.safetensors +3 -0
  9. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/optimizer.pt +3 -0
  10. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_0.pt +3 -0
  11. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_1.pt +3 -0
  12. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_2.pt +3 -0
  13. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_3.pt +3 -0
  14. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_4.pt +3 -0
  15. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_5.pt +3 -0
  16. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_6.pt +3 -0
  17. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_7.pt +3 -0
  18. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/special_tokens_map.json +14 -0
  19. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/tokenizer.json +3 -0
  20. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/tokenizer_config.json +47 -0
  21. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/vocab.json +0 -0
  22. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/tuandao_qwen1.5-1.8b_to_gpt2-120m.log +48 -0
  23. experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/tuandao_qwen1.5-1.8b_to_gpt2-120m_metrics.jsonl +0 -0
.gitattributes CHANGED
@@ -146,3 +146,4 @@ experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_
146
  experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
147
  experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_17/tokenizer.json filter=lfs diff=lfs merge=lfs -text
148
  experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_18/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
146
  experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
147
  experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_17/tokenizer.json filter=lfs diff=lfs merge=lfs -text
148
  experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_18/tokenizer.json filter=lfs diff=lfs merge=lfs -text
149
+ experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/tokenizer.json filter=lfs diff=lfs merge=lfs -text
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful assistant<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50256,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.56.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.56.0"
6
+ }
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/lr_scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd12d1ba8559b15b6467eff107c00b9a21fd7e64d4653ab460d73f1e4ea9467
3
+ size 1483
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a29904bbe34a5e1426b821debb738d218e113f29d39e8e4a7b9bb093dff7c1
3
+ size 497774208
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e9e64aaea96d48de6480f44bc014be0cd20fa6537779df9af071d3f11576e9
3
+ size 1096368715
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff0a1b67645b44261ef49e5787de3ec9cf9b56663657ecd56f0ba3fdc15952b
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dea6d992f91c883d7185395bb16553f677abbb827705fad1c5fa7f307f966f7
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1f71d183a67517c5671aa2b4e2e83b8f21296f884ac53fa14675102c401862
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86637d792b6849ae808c4e3fbd3fa357a0243d3df11a3f99d9de086663390412
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3262b20802339e4d328f148bcc06b35c049ef8c94471d2f4e37fabf4adebcc75
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75d83f29a47d7a8f174819e690527d32654f1a6b1ce9ad9d886c0536b7aefaf
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daf055b5091cd4d357ac8f2efa32067f76fc561ac41d6d574bbaabb42a704e1
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/projector_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c53fde7a7b1f7d086ed5666c393e3ab5c26404388ca31bb1051f5964b538bc
3
+ size 6296517
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|endoftext|>"
14
+ }
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6f32fb0a832e7efb2c2de5e805c8aaaf43e933c191ffc8d7cb56b176e0f11b
3
+ size 11418364
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "<|endoftext|>",
36
+ "errors": "replace",
37
+ "extra_special_tokens": {},
38
+ "max_length": 256,
39
+ "model_max_length": 32768,
40
+ "pad_token": "<|endoftext|>",
41
+ "split_special_tokens": false,
42
+ "stride": 0,
43
+ "tokenizer_class": "Qwen2Tokenizer",
44
+ "truncation_side": "right",
45
+ "truncation_strategy": "longest_first",
46
+ "unk_token": null
47
+ }
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/checkpoints/epoch_19/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/tuandao_qwen1.5-1.8b_to_gpt2-120m.log CHANGED
@@ -1012,3 +1012,51 @@
1012
  2025-11-30 16:12:29,508 - absl - INFO - Using default tokenizer.
1013
  2025-11-30 16:12:30,027 - root - INFO - Step 27265/28600 train rougeL: 1.0
1014
  2025-11-30 16:12:30,090 - root - INFO - Step 27265/28600 loss: 0.6465226411819458, nll_loss: 0.006603807210922241, distill_loss: 0.3199594020843506
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1012
  2025-11-30 16:12:29,508 - absl - INFO - Using default tokenizer.
1013
  2025-11-30 16:12:30,027 - root - INFO - Step 27265/28600 train rougeL: 1.0
1014
  2025-11-30 16:12:30,090 - root - INFO - Step 27265/28600 loss: 0.6465226411819458, nll_loss: 0.006603807210922241, distill_loss: 0.3199594020843506
1015
+ 2025-11-30 16:13:11,040 - absl - INFO - Using default tokenizer.
1016
+ 2025-11-30 16:13:12,944 - root - INFO - Step 27393/28600 train rougeL: 0.9423669467787115
1017
+ 2025-11-30 16:13:13,007 - root - INFO - Step 27393/28600 loss: 0.7532645463943481, nll_loss: 0.016324713826179504, distill_loss: 0.3684699237346649
1018
+ 2025-11-30 16:13:54,498 - absl - INFO - Using default tokenizer.
1019
+ 2025-11-30 16:13:55,185 - root - INFO - Step 27521/28600 train rougeL: 1.0
1020
+ 2025-11-30 16:13:55,247 - root - INFO - Step 27521/28600 loss: 0.6677549481391907, nll_loss: 0.00863515306264162, distill_loss: 0.32955989241600037
1021
+ 2025-11-30 16:14:36,622 - absl - INFO - Using default tokenizer.
1022
+ 2025-11-30 16:14:37,835 - root - INFO - Step 27649/28600 train rougeL: 1.0
1023
+ 2025-11-30 16:14:37,897 - root - INFO - Step 27649/28600 loss: 0.6685707569122314, nll_loss: 0.021448642015457153, distill_loss: 0.32356104254722595
1024
+ 2025-11-30 16:15:18,918 - absl - INFO - Using default tokenizer.
1025
+ 2025-11-30 16:15:19,342 - root - INFO - Step 27777/28600 train rougeL: 1.0
1026
+ 2025-11-30 16:15:19,404 - root - INFO - Step 27777/28600 loss: 0.6504983901977539, nll_loss: 0.006399303674697876, distill_loss: 0.3220495283603668
1027
+ 2025-11-30 16:16:00,394 - absl - INFO - Using default tokenizer.
1028
+ 2025-11-30 16:16:02,356 - root - INFO - Step 27905/28600 train rougeL: 0.809881208171401
1029
+ 2025-11-30 16:16:02,420 - root - INFO - Step 27905/28600 loss: 0.7603797912597656, nll_loss: 0.02054585888981819, distill_loss: 0.36991697549819946
1030
+ 2025-11-30 16:16:43,365 - absl - INFO - Using default tokenizer.
1031
+ 2025-11-30 16:16:45,164 - root - INFO - Step 28033/28600 train rougeL: 0.9436945990517419
1032
+ 2025-11-30 16:16:45,226 - root - INFO - Step 28033/28600 loss: 0.7420259714126587, nll_loss: 0.017242711037397385, distill_loss: 0.3623916208744049
1033
+ 2025-11-30 16:17:26,568 - absl - INFO - Using default tokenizer.
1034
+ 2025-11-30 16:17:28,259 - root - INFO - Step 28161/28600 train rougeL: 1.0
1035
+ 2025-11-30 16:17:28,322 - root - INFO - Step 28161/28600 loss: 0.739902675151825, nll_loss: 0.02427525632083416, distill_loss: 0.3578137159347534
1036
+ 2025-11-30 16:18:09,262 - absl - INFO - Using default tokenizer.
1037
+ 2025-11-30 16:18:11,090 - root - INFO - Step 28289/28600 train rougeL: 0.9519543973941368
1038
+ 2025-11-30 16:18:11,153 - root - INFO - Step 28289/28600 loss: 0.7623029351234436, nll_loss: 0.014688455499708652, distill_loss: 0.37380725145339966
1039
+ 2025-11-30 16:18:52,249 - absl - INFO - Using default tokenizer.
1040
+ 2025-11-30 16:18:53,637 - root - INFO - Step 28417/28600 train rougeL: 1.0
1041
+ 2025-11-30 16:18:53,700 - root - INFO - Step 28417/28600 loss: 0.6988828182220459, nll_loss: 0.013126135803759098, distill_loss: 0.3428783416748047
1042
+ 2025-11-30 16:19:34,627 - absl - INFO - Using default tokenizer.
1043
+ 2025-11-30 16:19:35,562 - root - INFO - Step 28545/28600 train rougeL: 1.0
1044
+ 2025-11-30 16:19:35,624 - root - INFO - Step 28545/28600 loss: 0.6725203394889832, nll_loss: 0.014981920830905437, distill_loss: 0.3287692070007324
1045
+ 2025-11-30 16:19:52,933 - root - INFO - Epoch 20/20 finished
1046
+ 2025-11-30 16:19:52,951 - absl - INFO - Using default tokenizer.
1047
+ 2025-11-30 16:19:55,450 - absl - INFO - Using default tokenizer.
1048
+ 2025-11-30 16:19:57,953 - absl - INFO - Using default tokenizer.
1049
+ 2025-11-30 16:20:00,425 - absl - INFO - Using default tokenizer.
1050
+ 2025-11-30 16:20:02,916 - absl - INFO - Using default tokenizer.
1051
+ 2025-11-30 16:20:05,435 - absl - INFO - Using default tokenizer.
1052
+ 2025-11-30 16:20:07,859 - absl - INFO - Using default tokenizer.
1053
+ 2025-11-30 16:20:10,358 - absl - INFO - Using default tokenizer.
1054
+ 2025-11-30 16:20:12,855 - absl - INFO - Using default tokenizer.
1055
+ 2025-11-30 16:20:15,229 - absl - INFO - Using default tokenizer.
1056
+ 2025-11-30 16:20:17,704 - absl - INFO - Using default tokenizer.
1057
+ 2025-11-30 16:20:20,190 - absl - INFO - Using default tokenizer.
1058
+ 2025-11-30 16:20:22,166 - absl - INFO - Using default tokenizer.
1059
+ 2025-11-30 16:20:24,692 - absl - INFO - Using default tokenizer.
1060
+ 2025-11-30 16:20:27,160 - absl - INFO - Using default tokenizer.
1061
+ 2025-11-30 16:20:29,634 - absl - INFO - Using default tokenizer.
1062
+ 2025-11-30 16:20:31,697 - root - INFO - Epoch 20/20 eval rougeL: 0.24898792831535368
experiments/tuandao_qwen1.5-1.8b_to_gpt2-120m/20251130_132733/tuandao_qwen1.5-1.8b_to_gpt2-120m_metrics.jsonl CHANGED
The diff for this file is too large to render. See raw diff