end of finetuning
Browse files- README.md +58 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +13 -0
- config.json +138 -0
- generation_config.json +11 -0
- runs/Oct27_09-26-57_6753c6390e38/events.out.tfevents.1730021233.6753c6390e38.20796.2 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +131 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: mit
|
4 |
+
base_model: microsoft/Phi-3-mini-128k-instruct
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: phi-3-mini-sft-indicqa-hindi-v0.1
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# phi-3-mini-sft-indicqa-hindi-v0.1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 4
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_ratio: 0.03
|
45 |
+
- num_epochs: 1
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- PEFT 0.13.2
|
55 |
+
- Transformers 4.44.2
|
56 |
+
- Pytorch 2.5.0+cu121
|
57 |
+
- Datasets 3.0.2
|
58 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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": 32,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj",
|
26 |
+
"down_proj",
|
27 |
+
"o_proj",
|
28 |
+
"up_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5893e02d13cbcd98a0e21fa79cc54f53c5ff8d2f1a2e3089fc524bf534d0780
|
3 |
+
size 35668592
|
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 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"embd_pdrop": 0.0,
|
14 |
+
"eos_token_id": 32000,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 3072,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"model_type": "phi3",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"original_max_position_embeddings": 4096,
|
25 |
+
"pad_token_id": 32000,
|
26 |
+
"resid_pdrop": 0.0,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"long_factor": [
|
30 |
+
1.0700000524520874,
|
31 |
+
1.1200000047683716,
|
32 |
+
1.149999976158142,
|
33 |
+
1.4199999570846558,
|
34 |
+
1.5699999332427979,
|
35 |
+
1.7999999523162842,
|
36 |
+
2.129999876022339,
|
37 |
+
2.129999876022339,
|
38 |
+
3.009999990463257,
|
39 |
+
5.910000324249268,
|
40 |
+
6.950000286102295,
|
41 |
+
9.070000648498535,
|
42 |
+
9.930000305175781,
|
43 |
+
10.710000038146973,
|
44 |
+
11.130000114440918,
|
45 |
+
14.609999656677246,
|
46 |
+
15.409998893737793,
|
47 |
+
19.809999465942383,
|
48 |
+
37.279998779296875,
|
49 |
+
38.279998779296875,
|
50 |
+
38.599998474121094,
|
51 |
+
40.12000274658203,
|
52 |
+
46.20000457763672,
|
53 |
+
50.940006256103516,
|
54 |
+
53.66000747680664,
|
55 |
+
54.9373893737793,
|
56 |
+
56.89738845825195,
|
57 |
+
57.28738784790039,
|
58 |
+
59.98738479614258,
|
59 |
+
60.86738586425781,
|
60 |
+
60.887386322021484,
|
61 |
+
61.71739196777344,
|
62 |
+
62.91739273071289,
|
63 |
+
62.957393646240234,
|
64 |
+
63.41739273071289,
|
65 |
+
63.8173942565918,
|
66 |
+
63.83739471435547,
|
67 |
+
63.897396087646484,
|
68 |
+
63.93739700317383,
|
69 |
+
64.06739807128906,
|
70 |
+
64.11434936523438,
|
71 |
+
64.12435150146484,
|
72 |
+
64.15435028076172,
|
73 |
+
64.19435119628906,
|
74 |
+
64.24435424804688,
|
75 |
+
64.57435607910156,
|
76 |
+
64.69000244140625,
|
77 |
+
64.76000213623047
|
78 |
+
],
|
79 |
+
"short_factor": [
|
80 |
+
1.1,
|
81 |
+
1.1,
|
82 |
+
1.1,
|
83 |
+
1.3000000000000003,
|
84 |
+
1.3500000000000003,
|
85 |
+
1.3500000000000003,
|
86 |
+
1.4000000000000004,
|
87 |
+
1.5500000000000005,
|
88 |
+
2.000000000000001,
|
89 |
+
2.000000000000001,
|
90 |
+
2.000000000000001,
|
91 |
+
2.000000000000001,
|
92 |
+
2.000000000000001,
|
93 |
+
2.000000000000001,
|
94 |
+
2.000000000000001,
|
95 |
+
2.000000000000001,
|
96 |
+
2.000000000000001,
|
97 |
+
2.000000000000001,
|
98 |
+
2.000000000000001,
|
99 |
+
2.000000000000001,
|
100 |
+
2.000000000000001,
|
101 |
+
2.000000000000001,
|
102 |
+
2.000000000000001,
|
103 |
+
2.000000000000001,
|
104 |
+
2.000000000000001,
|
105 |
+
2.0500000000000007,
|
106 |
+
2.0500000000000007,
|
107 |
+
2.0500000000000007,
|
108 |
+
2.0500000000000007,
|
109 |
+
2.0500000000000007,
|
110 |
+
2.0500000000000007,
|
111 |
+
2.1000000000000005,
|
112 |
+
2.1000000000000005,
|
113 |
+
2.1500000000000004,
|
114 |
+
2.25,
|
115 |
+
2.25,
|
116 |
+
2.25,
|
117 |
+
2.25,
|
118 |
+
2.25,
|
119 |
+
2.3999999999999995,
|
120 |
+
2.4499999999999993,
|
121 |
+
2.499999999999999,
|
122 |
+
2.6999999999999984,
|
123 |
+
2.6999999999999984,
|
124 |
+
2.7499999999999982,
|
125 |
+
2.799999999999998,
|
126 |
+
2.8999999999999977,
|
127 |
+
3.049999999999997
|
128 |
+
],
|
129 |
+
"type": "longrope"
|
130 |
+
},
|
131 |
+
"rope_theta": 10000.0,
|
132 |
+
"sliding_window": 262144,
|
133 |
+
"tie_word_embeddings": false,
|
134 |
+
"torch_dtype": "float16",
|
135 |
+
"transformers_version": "4.44.2",
|
136 |
+
"use_cache": true,
|
137 |
+
"vocab_size": 32064
|
138 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": [
|
5 |
+
32000,
|
6 |
+
32001,
|
7 |
+
32007
|
8 |
+
],
|
9 |
+
"pad_token_id": 32000,
|
10 |
+
"transformers_version": "4.44.2"
|
11 |
+
}
|
runs/Oct27_09-26-57_6753c6390e38/events.out.tfevents.1730021233.6753c6390e38.20796.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f7d22ef3c5688305177eeeb3152b571ff7997796bb68c762a7295b535604ca2
|
3 |
+
size 9276
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
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": "right",
|
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:c8ec6f12fdc6c2b70d0938aa316f79a88bb23e6b8d82282217957a2a925a6c6c
|
3 |
+
size 5496
|