prapti19 commited on
Commit
11f11b7
·
verified ·
1 Parent(s): d986934

Upload folder using huggingface_hub

Browse files
Files changed (38) hide show
  1. 6c98b7f8d38de93169e65c460dc20275/data-00000-of-00026.arrow +3 -0
  2. 6c98b7f8d38de93169e65c460dc20275/data-00001-of-00026.arrow +3 -0
  3. 6c98b7f8d38de93169e65c460dc20275/data-00002-of-00026.arrow +3 -0
  4. 6c98b7f8d38de93169e65c460dc20275/data-00003-of-00026.arrow +3 -0
  5. 6c98b7f8d38de93169e65c460dc20275/data-00004-of-00026.arrow +3 -0
  6. 6c98b7f8d38de93169e65c460dc20275/data-00005-of-00026.arrow +3 -0
  7. 6c98b7f8d38de93169e65c460dc20275/data-00006-of-00026.arrow +3 -0
  8. 6c98b7f8d38de93169e65c460dc20275/data-00007-of-00026.arrow +3 -0
  9. 6c98b7f8d38de93169e65c460dc20275/data-00008-of-00026.arrow +3 -0
  10. 6c98b7f8d38de93169e65c460dc20275/data-00009-of-00026.arrow +3 -0
  11. 6c98b7f8d38de93169e65c460dc20275/data-00010-of-00026.arrow +3 -0
  12. 6c98b7f8d38de93169e65c460dc20275/data-00011-of-00026.arrow +3 -0
  13. 6c98b7f8d38de93169e65c460dc20275/data-00012-of-00026.arrow +3 -0
  14. 6c98b7f8d38de93169e65c460dc20275/data-00013-of-00026.arrow +3 -0
  15. 6c98b7f8d38de93169e65c460dc20275/data-00014-of-00026.arrow +3 -0
  16. 6c98b7f8d38de93169e65c460dc20275/data-00015-of-00026.arrow +3 -0
  17. 6c98b7f8d38de93169e65c460dc20275/data-00016-of-00026.arrow +3 -0
  18. 6c98b7f8d38de93169e65c460dc20275/data-00017-of-00026.arrow +3 -0
  19. 6c98b7f8d38de93169e65c460dc20275/data-00018-of-00026.arrow +3 -0
  20. 6c98b7f8d38de93169e65c460dc20275/data-00019-of-00026.arrow +3 -0
  21. 6c98b7f8d38de93169e65c460dc20275/data-00020-of-00026.arrow +3 -0
  22. 6c98b7f8d38de93169e65c460dc20275/data-00021-of-00026.arrow +3 -0
  23. 6c98b7f8d38de93169e65c460dc20275/data-00022-of-00026.arrow +3 -0
  24. 6c98b7f8d38de93169e65c460dc20275/data-00023-of-00026.arrow +3 -0
  25. 6c98b7f8d38de93169e65c460dc20275/data-00024-of-00026.arrow +3 -0
  26. 6c98b7f8d38de93169e65c460dc20275/data-00025-of-00026.arrow +3 -0
  27. 6c98b7f8d38de93169e65c460dc20275/dataset_info.json +29 -0
  28. 6c98b7f8d38de93169e65c460dc20275/state.json +88 -0
  29. README.md +174 -0
  30. adapter_config.json +39 -0
  31. adapter_model.safetensors +3 -0
  32. added_tokens.json +13 -0
  33. config.json +154 -0
  34. special_tokens_map.json +30 -0
  35. tokenizer.json +0 -0
  36. tokenizer.model +3 -0
  37. tokenizer_config.json +131 -0
  38. training_args.bin +3 -0
6c98b7f8d38de93169e65c460dc20275/data-00000-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31418120b790695c63e06a0902bc08e9cb85889420889ed0c4a65efa1082d43f
3
+ size 834355640
6c98b7f8d38de93169e65c460dc20275/data-00001-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1d30f5265cefea0a8ed41b8d390a24a07dc16142edc8c02d4aad6abab567ce
3
+ size 833660664
6c98b7f8d38de93169e65c460dc20275/data-00002-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b7c6b6b69657e68de21550734ad83582476a48bd969c45465af499b22b541b
3
+ size 834412336
6c98b7f8d38de93169e65c460dc20275/data-00003-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19d276c576d7b68220f70aa2769a5a96b9198ff9d5b3f620c150b2877faae4b
3
+ size 832741496
6c98b7f8d38de93169e65c460dc20275/data-00004-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e62cd60a2f9b9e5acdfb7d031268b099d4c5bffab66994f9773678b886f9a4a
3
+ size 836691784
6c98b7f8d38de93169e65c460dc20275/data-00005-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64a304d8a1ac8ddf212a86c06c37b72569904c41c13d5c36908f79af0f7fa2e
3
+ size 851254488
6c98b7f8d38de93169e65c460dc20275/data-00006-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab199ef1dc0e07d81e08360b894c498e9536144d08b90c0cf5b278be3f21120
3
+ size 498155648
6c98b7f8d38de93169e65c460dc20275/data-00007-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509fcd17d929d453b02dd1b0c3eb1144c42d603365451f002d29c4f876dc14ef
3
+ size 384505496
6c98b7f8d38de93169e65c460dc20275/data-00008-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5aa7a9689c536d9e8b7a9dfba28ddd7f4da8f8800c34cd90a1b6bc894535343
3
+ size 380280912
6c98b7f8d38de93169e65c460dc20275/data-00009-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3f33d7a336950a8774a06abacc26507362e664bd3a72f474a5f0110d3f914f
3
+ size 379072936
6c98b7f8d38de93169e65c460dc20275/data-00010-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d6252ece6a70c8560b248a00f98f5a2dcff4e4372f38375cefbf53d8b70ab0
3
+ size 380542872
6c98b7f8d38de93169e65c460dc20275/data-00011-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274b24f29fc04dfa496b98594c90d30908c1288d3ee713352cebb4eafd8dedde
3
+ size 382115048
6c98b7f8d38de93169e65c460dc20275/data-00012-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a424e1d7412897519803b5fd6b060f113c92efad7acfb2fdff924f48395eafae
3
+ size 377660936
6c98b7f8d38de93169e65c460dc20275/data-00013-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b1e8c626e49d1711353ac021a128a61061f793f8a2f331972a41f68f7d73d6
3
+ size 379692960
6c98b7f8d38de93169e65c460dc20275/data-00014-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bd85ada965ed00d6e62d6109208b27d778a92cb1ddf362fbae8ac5aa8737f5
3
+ size 380644288
6c98b7f8d38de93169e65c460dc20275/data-00015-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da58a438044437723d6099b2830b4aea7ae951cf20fa9b825a1d0325df093fc4
3
+ size 380550200
6c98b7f8d38de93169e65c460dc20275/data-00016-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f636bf2ebf0bc29f44e3f5eb8cb29f9ed12ba80de13ef2d6e629188c50a6b9d4
3
+ size 377024976
6c98b7f8d38de93169e65c460dc20275/data-00017-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f784480c502dc5cf6181a947e78f5313c981bceeeb042f5a99b80c18afb75e06
3
+ size 380151064
6c98b7f8d38de93169e65c460dc20275/data-00018-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc48c95a66ad607639e77a600dfaebd3aba963d56b3155d9849f3f1d2f726b6
3
+ size 377341792
6c98b7f8d38de93169e65c460dc20275/data-00019-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45053b4e37d720ccdf09adfbd6ebf70aa1b511f62c6a61122655b3806234d1a0
3
+ size 382241520
6c98b7f8d38de93169e65c460dc20275/data-00020-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0578f584ec3c6e942d1994ffe8c4b20939257caff06c12dc07e73f5a68952a7
3
+ size 379549576
6c98b7f8d38de93169e65c460dc20275/data-00021-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3efc5f6b1b60e221e500a4337ba68b72c5d75ed7142d7e591932f9a7410acec
3
+ size 381747904
6c98b7f8d38de93169e65c460dc20275/data-00022-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0763652aa7708c7a24b863bcc559fc1501eb76d958984b0a021a40c69a31533
3
+ size 379586888
6c98b7f8d38de93169e65c460dc20275/data-00023-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3a1848f767d9555d0a2d10b3173f4aac74a22ebd119e2020c3a855021decd6
3
+ size 378754384
6c98b7f8d38de93169e65c460dc20275/data-00024-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f7ece7a0d696c62b697ac05cc80b569d5f9911505e1335619fbe8b8e0c2b87
3
+ size 381905648
6c98b7f8d38de93169e65c460dc20275/data-00025-of-00026.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d419b5378c8ad4086815952469896deb80c9e137323c1d80ef2f7da2b35ad2d
3
+ size 514298856
6c98b7f8d38de93169e65c460dc20275/dataset_info.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "input_ids": {
6
+ "feature": {
7
+ "dtype": "int32",
8
+ "_type": "Value"
9
+ },
10
+ "_type": "Sequence"
11
+ },
12
+ "attention_mask": {
13
+ "feature": {
14
+ "dtype": "int8",
15
+ "_type": "Value"
16
+ },
17
+ "_type": "Sequence"
18
+ },
19
+ "labels": {
20
+ "feature": {
21
+ "dtype": "int64",
22
+ "_type": "Value"
23
+ },
24
+ "_type": "Sequence"
25
+ }
26
+ },
27
+ "homepage": "",
28
+ "license": ""
29
+ }
6c98b7f8d38de93169e65c460dc20275/state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00026.arrow"
5
+ },
6
+ {
7
+ "filename": "data-00001-of-00026.arrow"
8
+ },
9
+ {
10
+ "filename": "data-00002-of-00026.arrow"
11
+ },
12
+ {
13
+ "filename": "data-00003-of-00026.arrow"
14
+ },
15
+ {
16
+ "filename": "data-00004-of-00026.arrow"
17
+ },
18
+ {
19
+ "filename": "data-00005-of-00026.arrow"
20
+ },
21
+ {
22
+ "filename": "data-00006-of-00026.arrow"
23
+ },
24
+ {
25
+ "filename": "data-00007-of-00026.arrow"
26
+ },
27
+ {
28
+ "filename": "data-00008-of-00026.arrow"
29
+ },
30
+ {
31
+ "filename": "data-00009-of-00026.arrow"
32
+ },
33
+ {
34
+ "filename": "data-00010-of-00026.arrow"
35
+ },
36
+ {
37
+ "filename": "data-00011-of-00026.arrow"
38
+ },
39
+ {
40
+ "filename": "data-00012-of-00026.arrow"
41
+ },
42
+ {
43
+ "filename": "data-00013-of-00026.arrow"
44
+ },
45
+ {
46
+ "filename": "data-00014-of-00026.arrow"
47
+ },
48
+ {
49
+ "filename": "data-00015-of-00026.arrow"
50
+ },
51
+ {
52
+ "filename": "data-00016-of-00026.arrow"
53
+ },
54
+ {
55
+ "filename": "data-00017-of-00026.arrow"
56
+ },
57
+ {
58
+ "filename": "data-00018-of-00026.arrow"
59
+ },
60
+ {
61
+ "filename": "data-00019-of-00026.arrow"
62
+ },
63
+ {
64
+ "filename": "data-00020-of-00026.arrow"
65
+ },
66
+ {
67
+ "filename": "data-00021-of-00026.arrow"
68
+ },
69
+ {
70
+ "filename": "data-00022-of-00026.arrow"
71
+ },
72
+ {
73
+ "filename": "data-00023-of-00026.arrow"
74
+ },
75
+ {
76
+ "filename": "data-00024-of-00026.arrow"
77
+ },
78
+ {
79
+ "filename": "data-00025-of-00026.arrow"
80
+ }
81
+ ],
82
+ "_fingerprint": "027a8e8eb60ef9e1_00000_of_00064",
83
+ "_format_columns": null,
84
+ "_format_kwargs": {},
85
+ "_format_type": null,
86
+ "_output_all_columns": false,
87
+ "_split": null
88
+ }
README.md ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: microsoft/Phi-3.5-mini-instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: curator_math_phase1_sn_ensemble7_90325
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.5.0`
20
+ ```yaml
21
+ strict: false
22
+ base_model: microsoft/Phi-3.5-mini-instruct
23
+ tokenizer_config: microsoft/Phi-3.5-mini-instruct
24
+ model_type: AutoModelForCausalLM
25
+ tokenizer_type: AutoTokenizer
26
+
27
+ # Output configuration
28
+ hub_model_id: collinear-ai/curator_math_phase1_sn_ensemble7_90325
29
+ dataset_prepared_path: /workspace/prapti/curator_math_phase1_sn_ensemble7_90325
30
+ output_dir: /workspace/prapti/curator_math_phase1_sn_ensemble7_90325
31
+
32
+ # Format the dataset into the right instruction format.
33
+ chat_template: phi_3
34
+ datasets:
35
+ - path: collinear-ai/curator_math_phase1_sn_ensemble7_50325_sft
36
+ split: train
37
+ type: chat_template
38
+ chat_template: phi_3
39
+ field_messages: train_conv
40
+ message_field_role: role
41
+ message_field_content: content
42
+ train_on_inputs: false #FALSE
43
+
44
+ val_set_size: 0.05
45
+ # Data packing
46
+ sequence_len: 4096 #meghana can you please confirm this
47
+ eval_sample_packing: false
48
+ sample_packing: false
49
+ pad_to_sequence_len: true
50
+ group_by_length: false
51
+
52
+ # Lora config
53
+ adapter: qlora
54
+ lora_model_dir:
55
+ load_in_8bit: false
56
+ load_in_4bit: true
57
+ lora_r: 128
58
+ lora_alpha: 64
59
+ lora_dropout: 0.2
60
+ lora_target_linear: true
61
+ lora_fan_in_fan_out:
62
+ lora_target_modules:
63
+ - gate_proj
64
+ - down_proj
65
+ - up_proj
66
+ - q_proj
67
+ - v_proj
68
+ - k_proj
69
+ - o_proj
70
+ lora_modules_to_save:
71
+ - embed_tokens
72
+ - lm_head
73
+
74
+
75
+ # Logging config
76
+ wandb_project: sn-curators-downstream
77
+ wandb_entity: nazneen
78
+ wandb_name: curator_math_phase1_sn_ensemble7_90325
79
+
80
+ # Trainer config
81
+ gradient_accumulation_steps: 2
82
+ micro_batch_size: 8
83
+ num_epochs: 1
84
+ optimizer: paged_adamw_8bit
85
+ lr_scheduler: cosine
86
+ learning_rate: 0.000005
87
+
88
+ bfloat16: true
89
+ bf16: true
90
+ fp16:
91
+ tf32: false
92
+
93
+ gradient_checkpointing: true
94
+ early_stopping_patience:
95
+ resume_from_checkpoint:
96
+ local_rank:
97
+ logging_steps: 10
98
+ xformers_attention:
99
+ flash_attention: true
100
+ save_safetensors: true
101
+
102
+
103
+
104
+ warmup_steps: 50
105
+ evals_per_epoch: 3
106
+ eval_table_size: 3
107
+ eval_max_new_tokens: 2048
108
+ saves_per_epoch: 20
109
+ debug:
110
+ deepspeed:
111
+ weight_decay: 0.02
112
+ fsdp_config:
113
+ special_tokens:
114
+ bos_token: "<s>"
115
+ eos_token: "<|endoftext|>"
116
+ unk_token: "<unk>"
117
+ pad_token: "<|endoftext|>"
118
+ ```
119
+
120
+ </details><br>
121
+
122
+ # curator_math_phase1_sn_ensemble7_90325
123
+
124
+ This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
125
+ It achieves the following results on the evaluation set:
126
+ - Loss: 0.3203
127
+
128
+ ## Model description
129
+
130
+ More information needed
131
+
132
+ ## Intended uses & limitations
133
+
134
+ More information needed
135
+
136
+ ## Training and evaluation data
137
+
138
+ More information needed
139
+
140
+ ## Training procedure
141
+
142
+ ### Training hyperparameters
143
+
144
+ The following hyperparameters were used during training:
145
+ - learning_rate: 5e-06
146
+ - train_batch_size: 8
147
+ - eval_batch_size: 8
148
+ - seed: 42
149
+ - distributed_type: multi-GPU
150
+ - num_devices: 8
151
+ - gradient_accumulation_steps: 2
152
+ - total_train_batch_size: 128
153
+ - total_eval_batch_size: 64
154
+ - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
155
+ - lr_scheduler_type: cosine
156
+ - lr_scheduler_warmup_steps: 50
157
+ - num_epochs: 1
158
+
159
+ ### Training results
160
+
161
+ | Training Loss | Epoch | Step | Validation Loss |
162
+ |:-------------:|:------:|:----:|:---------------:|
163
+ | No log | 0.0003 | 1 | 0.6714 |
164
+ | 0.337 | 0.3335 | 1243 | 0.3361 |
165
+ | 0.3248 | 0.6669 | 2486 | 0.3203 |
166
+
167
+
168
+ ### Framework versions
169
+
170
+ - PEFT 0.13.2
171
+ - Transformers 4.46.1
172
+ - Pytorch 2.3.1+cu121
173
+ - Datasets 3.0.1
174
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.2,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "embed_tokens",
19
+ "lm_head"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "up_proj",
27
+ "k_proj",
28
+ "qkv_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "down_proj",
32
+ "gate_up_proj",
33
+ "gate_proj",
34
+ "q_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7633ed420cca664c6cb1309f5d52f9225bee4660e2620068dce0a81ea10487cd
3
+ size 1199344216
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "microsoft/Phi-3.5-mini-instruct",
4
+ "architectures": [
5
+ "Phi3ForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config",
11
+ "AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM"
12
+ },
13
+ "bos_token_id": 1,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 32000,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 3072,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 8192,
20
+ "max_position_embeddings": 131072,
21
+ "model_type": "phi3",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 32,
25
+ "original_max_position_embeddings": 4096,
26
+ "pad_token_id": 32000,
27
+ "quantization_config": {
28
+ "_load_in_4bit": true,
29
+ "_load_in_8bit": false,
30
+ "bnb_4bit_compute_dtype": "bfloat16",
31
+ "bnb_4bit_quant_storage": "bfloat16",
32
+ "bnb_4bit_quant_type": "nf4",
33
+ "bnb_4bit_use_double_quant": true,
34
+ "llm_int8_enable_fp32_cpu_offload": false,
35
+ "llm_int8_has_fp16_weight": false,
36
+ "llm_int8_skip_modules": null,
37
+ "llm_int8_threshold": 6.0,
38
+ "load_in_4bit": true,
39
+ "load_in_8bit": false,
40
+ "quant_method": "bitsandbytes"
41
+ },
42
+ "resid_pdrop": 0.0,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_scaling": {
45
+ "long_factor": [
46
+ 1.0800000429153442,
47
+ 1.1100000143051147,
48
+ 1.1399999856948853,
49
+ 1.340000033378601,
50
+ 1.5899999141693115,
51
+ 1.600000023841858,
52
+ 1.6200000047683716,
53
+ 2.620000123977661,
54
+ 3.2300000190734863,
55
+ 3.2300000190734863,
56
+ 4.789999961853027,
57
+ 7.400000095367432,
58
+ 7.700000286102295,
59
+ 9.09000015258789,
60
+ 12.199999809265137,
61
+ 17.670000076293945,
62
+ 24.46000099182129,
63
+ 28.57000160217285,
64
+ 30.420001983642578,
65
+ 30.840002059936523,
66
+ 32.590003967285156,
67
+ 32.93000411987305,
68
+ 42.320003509521484,
69
+ 44.96000289916992,
70
+ 50.340003967285156,
71
+ 50.45000457763672,
72
+ 57.55000305175781,
73
+ 57.93000411987305,
74
+ 58.21000289916992,
75
+ 60.1400032043457,
76
+ 62.61000442504883,
77
+ 62.62000274658203,
78
+ 62.71000289916992,
79
+ 63.1400032043457,
80
+ 63.1400032043457,
81
+ 63.77000427246094,
82
+ 63.93000411987305,
83
+ 63.96000289916992,
84
+ 63.970001220703125,
85
+ 64.02999877929688,
86
+ 64.06999969482422,
87
+ 64.08000183105469,
88
+ 64.12000274658203,
89
+ 64.41000366210938,
90
+ 64.4800033569336,
91
+ 64.51000213623047,
92
+ 64.52999877929688,
93
+ 64.83999633789062
94
+ ],
95
+ "short_factor": [
96
+ 1.0,
97
+ 1.0199999809265137,
98
+ 1.0299999713897705,
99
+ 1.0299999713897705,
100
+ 1.0499999523162842,
101
+ 1.0499999523162842,
102
+ 1.0499999523162842,
103
+ 1.0499999523162842,
104
+ 1.0499999523162842,
105
+ 1.0699999332427979,
106
+ 1.0999999046325684,
107
+ 1.1099998950958252,
108
+ 1.1599998474121094,
109
+ 1.1599998474121094,
110
+ 1.1699998378753662,
111
+ 1.2899998426437378,
112
+ 1.339999794960022,
113
+ 1.679999828338623,
114
+ 1.7899998426437378,
115
+ 1.8199998140335083,
116
+ 1.8499997854232788,
117
+ 1.8799997568130493,
118
+ 1.9099997282028198,
119
+ 1.9399996995925903,
120
+ 1.9899996519088745,
121
+ 2.0199997425079346,
122
+ 2.0199997425079346,
123
+ 2.0199997425079346,
124
+ 2.0199997425079346,
125
+ 2.0199997425079346,
126
+ 2.0199997425079346,
127
+ 2.0299997329711914,
128
+ 2.0299997329711914,
129
+ 2.0299997329711914,
130
+ 2.0299997329711914,
131
+ 2.0299997329711914,
132
+ 2.0299997329711914,
133
+ 2.0299997329711914,
134
+ 2.0299997329711914,
135
+ 2.0299997329711914,
136
+ 2.0799996852874756,
137
+ 2.0899996757507324,
138
+ 2.189999580383301,
139
+ 2.2199995517730713,
140
+ 2.5899994373321533,
141
+ 2.729999542236328,
142
+ 2.749999523162842,
143
+ 2.8399994373321533
144
+ ],
145
+ "type": "longrope"
146
+ },
147
+ "rope_theta": 10000.0,
148
+ "sliding_window": 262144,
149
+ "tie_word_embeddings": false,
150
+ "torch_dtype": "bfloat16",
151
+ "transformers_version": "4.46.1",
152
+ "use_cache": false,
153
+ "vocab_size": 32064
154
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b690ba6b3893fba2229aa3fec410091a13d1c32b0b8bbd0f11d2508365221819
3
+ size 6776