Pushing fine-tuned model to Hugging Face Hub
Browse files- README.md +48 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +8 -0
- emissions.csv +2 -0
- evaluation_results.csv +4 -0
- run_experiment.log +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +139 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
language:
|
4 |
+
- pt
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- aes
|
8 |
+
datasets:
|
9 |
+
- kamel-usp/aes_enem_dataset
|
10 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
11 |
+
metrics:
|
12 |
+
- accuracy
|
13 |
+
- qwk
|
14 |
+
library_name: peft
|
15 |
+
model-index:
|
16 |
+
- name: Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
|
17 |
+
results:
|
18 |
+
- task:
|
19 |
+
type: text-classification
|
20 |
+
name: Automated Essay Score
|
21 |
+
dataset:
|
22 |
+
name: Automated Essay Score ENEM Dataset
|
23 |
+
type: kamel-usp/aes_enem_dataset
|
24 |
+
config: JBCS2025
|
25 |
+
split: test
|
26 |
+
metrics:
|
27 |
+
- name: Macro F1
|
28 |
+
type: f1
|
29 |
+
value: 0.2562502976332206
|
30 |
+
- name: QWK
|
31 |
+
type: qwk
|
32 |
+
value: 0.4689490445859872
|
33 |
+
- name: Weighted Macro F1
|
34 |
+
type: f1
|
35 |
+
value: 0.6261409273457467
|
36 |
+
---
|
37 |
+
# Model ID: Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
|
38 |
+
## Results
|
39 |
+
| | test_data |
|
40 |
+
|:-----------------|------------:|
|
41 |
+
| eval_accuracy | 0.65942 |
|
42 |
+
| eval_RMSE | 25.9319 |
|
43 |
+
| eval_QWK | 0.468949 |
|
44 |
+
| eval_Macro_F1 | 0.25625 |
|
45 |
+
| eval_Weighted_F1 | 0.626141 |
|
46 |
+
| eval_Micro_F1 | 0.65942 |
|
47 |
+
| eval_HDIV | 0.00724638 |
|
48 |
+
|
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 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": [
|
22 |
+
"classifier",
|
23 |
+
"score"
|
24 |
+
],
|
25 |
+
"peft_type": "LORA",
|
26 |
+
"r": 8,
|
27 |
+
"rank_pattern": {},
|
28 |
+
"revision": null,
|
29 |
+
"target_modules": [
|
30 |
+
"down_proj",
|
31 |
+
"o_proj",
|
32 |
+
"gate_up_proj",
|
33 |
+
"qkv_proj"
|
34 |
+
],
|
35 |
+
"task_type": "SEQ_CLS",
|
36 |
+
"trainable_token_indices": null,
|
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 sha256:4f9ec4ed34d81aea506952a8b762baf6a82ecfcd680c693d52778e0939e3b488
|
3 |
+
size 50402728
|
chat_template.jinja
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>
|
2 |
+
' + message['content'] + '<|end|>
|
3 |
+
'}}{% elif message['role'] == 'user' %}{{'<|user|>
|
4 |
+
' + message['content'] + '<|end|>
|
5 |
+
'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
|
6 |
+
' + message['content'] + '<|end|>
|
7 |
+
'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
|
8 |
+
' }}{% else %}{{ eos_token }}{% endif %}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2025-06-30T17:50:00,jbcs2025,ef487043-7175-4a9f-a273-67f307de2f49,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context,3546.7051958506927,0.3317009238161962,9.352368057098591e-05,66.0,563.991415138017,70.0,0.06409057806339112,0.5514809300732963,0.06779559271416317,0.6833671008508508,Japan,JPN,,,,Linux-5.15.0-130-generic-x86_64-with-glibc2.35,3.12.11,3.0.2,192,INTEL(R) XEON(R) PLATINUM 8558,1,1 x NVIDIA H200,139.69,35.69,2015.3516235351562,machine,N,1.0
|
evaluation_results.csv
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss,eval_model_preparation_time,eval_accuracy,eval_RMSE,eval_QWK,eval_HDIV,eval_Macro_F1,eval_Micro_F1,eval_Weighted_F1,eval_TP_0,eval_TN_0,eval_FP_0,eval_FN_0,eval_TP_1,eval_TN_1,eval_FP_1,eval_FN_1,eval_TP_2,eval_TN_2,eval_FP_2,eval_FN_2,eval_TP_3,eval_TN_3,eval_FP_3,eval_FN_3,eval_TP_4,eval_TN_4,eval_FP_4,eval_FN_4,eval_TP_5,eval_TN_5,eval_FP_5,eval_FN_5,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,reference,timestamp,id
|
2 |
+
2.9400153160095215,0.008,0.3787878787878788,36.34848169060327,0.02069153280696978,0.007575757575757569,0.12446524064171123,0.3787878787878788,0.23699562469615945,0,131,0,1,0,132,0,0,0,128,0,4,3,67,1,61,47,3,81,1,0,117,0,15,17.6118,7.495,0.511,-1,validation_before_training,2025-06-30 16:51:06,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
|
3 |
+
2.4537546634674072,0.008,0.5909090909090909,29.336088024923512,0.37900874635568516,0.007575757575757569,0.25610021786492376,0.5909090909090909,0.5442001716511521,0,131,0,1,0,132,0,0,0,128,0,4,35,59,9,29,43,39,45,5,0,117,0,15,17.4331,7.572,0.516,17.0,validation_after_training,2025-06-30 16:51:06,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
|
4 |
+
1.6321039199829102,0.008,0.6594202898550725,25.931906372573962,0.4689490445859872,0.007246376811594235,0.25625029763322066,0.6594202898550725,0.6261409273457467,0,137,0,1,0,137,0,1,1,128,1,8,62,34,28,14,28,74,18,18,0,133,0,5,18.3107,7.537,0.492,17.0,test_results,2025-06-30 16:51:06,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
|
run_experiment.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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": "<|dummy_id_0|>",
|
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_config.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32011": {
|
119 |
+
"content": "<|dummy_id_0|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
}
|
126 |
+
},
|
127 |
+
"bos_token": "<s>",
|
128 |
+
"clean_up_tokenization_spaces": false,
|
129 |
+
"eos_token": "<|endoftext|>",
|
130 |
+
"extra_special_tokens": {},
|
131 |
+
"legacy": false,
|
132 |
+
"model_max_length": 131072,
|
133 |
+
"pad_token": "<|dummy_id_0|>",
|
134 |
+
"padding_side": "left",
|
135 |
+
"sp_model_kwargs": {},
|
136 |
+
"tokenizer_class": "LlamaTokenizer",
|
137 |
+
"unk_token": "<unk>",
|
138 |
+
"use_default_system_prompt": false
|
139 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eebbc603c5d06d6b8af97795b16a62447994aead4c732a21eb49296eaa0e63b
|
3 |
+
size 5777
|