Training in progress, step 63
Browse files- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- notebook.ipynb +112 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +220 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vwxyzjn/EleutherAI_pythia-1b-deduped__sft__tldr",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32.0,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": [
|
17 |
+
"lm_head"
|
18 |
+
],
|
19 |
+
"peft_type": "LORA",
|
20 |
+
"r": 8,
|
21 |
+
"rank_pattern": {},
|
22 |
+
"revision": null,
|
23 |
+
"target_modules": [
|
24 |
+
"query_key_value",
|
25 |
+
"dense_4h_to_h",
|
26 |
+
"dense_h_to_4h",
|
27 |
+
"dense",
|
28 |
+
"embed_out"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3618245d3159020330f7446e5ee96837360d7dc7c52c1b021715769c6568bafe
|
3 |
+
size 9244136
|
notebook.ipynb
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": null,
|
6 |
+
"id": "c8b7c85d",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [],
|
9 |
+
"source": [
|
10 |
+
"\n",
|
11 |
+
"from haven import haven_jupyter as hj\n",
|
12 |
+
"from haven import haven_results as hr\n",
|
13 |
+
"from haven import haven_utils as hu\n",
|
14 |
+
"\n",
|
15 |
+
"# path to where the experiments got saved\n",
|
16 |
+
"savedir_base = '/home/toolkit/trl/results'\n",
|
17 |
+
"exp_list = None\n",
|
18 |
+
"\n",
|
19 |
+
"# get experiments from the exp config\n",
|
20 |
+
"exp_config_fname = None\n",
|
21 |
+
"if exp_config_fname:\n",
|
22 |
+
" config = hu.load_py(exp_config_fname)\n",
|
23 |
+
" exp_list = []\n",
|
24 |
+
" for exp_group in [\n",
|
25 |
+
" \"example\"\n",
|
26 |
+
" ]:\n",
|
27 |
+
" exp_list += config.EXP_GROUPS[exp_group]\n",
|
28 |
+
"\n",
|
29 |
+
"# filter exps\n",
|
30 |
+
"\n",
|
31 |
+
"filterby_list = None\n",
|
32 |
+
"# filterby_list =[{'dataset':'mnist'}]\n",
|
33 |
+
"\n",
|
34 |
+
"# get experiments\n",
|
35 |
+
"rm = hr.ResultManager(exp_list=exp_list,\n",
|
36 |
+
" savedir_base=savedir_base,\n",
|
37 |
+
" filterby_list=filterby_list,\n",
|
38 |
+
" verbose=0,\n",
|
39 |
+
" exp_groups=None,\n",
|
40 |
+
" job_scheduler='slurm'\n",
|
41 |
+
" )\n",
|
42 |
+
"\n",
|
43 |
+
"# specify display parameters\n",
|
44 |
+
"\n",
|
45 |
+
"# groupby_list = ['dataset']\n",
|
46 |
+
"# title_list = ['dataset']\n",
|
47 |
+
"# legend_list = ['model']\n",
|
48 |
+
"y_metrics = ['train_loss']\n",
|
49 |
+
"x_metric = 'epoch'\n",
|
50 |
+
"\n",
|
51 |
+
"# launch dashboard\n",
|
52 |
+
"hj.get_dashboard(rm, vars(), wide_display=False, enable_datatables=False)\n",
|
53 |
+
" "
|
54 |
+
]
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"cell_type": "code",
|
58 |
+
"execution_count": null,
|
59 |
+
"id": "87acb700",
|
60 |
+
"metadata": {},
|
61 |
+
"outputs": [],
|
62 |
+
"source": [
|
63 |
+
"\n",
|
64 |
+
"# get table \n",
|
65 |
+
"rm.get_score_df().head()\n",
|
66 |
+
"\n",
|
67 |
+
"# get latex \n",
|
68 |
+
"# print(rm.get_latex_table(legend=['dataset'], metrics=['train_loss'], decimals=1, caption=\"Results\", label='tab:results'))\n",
|
69 |
+
"\n",
|
70 |
+
"# get custom plots\n",
|
71 |
+
"fig = rm.get_plot_all(\n",
|
72 |
+
" # order='metrics_by_groups',\n",
|
73 |
+
" # avg_across='runs',\n",
|
74 |
+
" y_metric_list=y_metrics, \n",
|
75 |
+
" x_metric=x_metric,\n",
|
76 |
+
" # legend_fontsize=18,\n",
|
77 |
+
" # x_fontsize=20,\n",
|
78 |
+
" # y_fontsize=20,\n",
|
79 |
+
" # xtick_fontsize=20,\n",
|
80 |
+
" # ytick_fontsize=20,\n",
|
81 |
+
" # title_fontsize=24,\n",
|
82 |
+
" # legend_list=['model], \n",
|
83 |
+
" # title_list = ['dataset'], \n",
|
84 |
+
" # title_format='Dataset:{}',\n",
|
85 |
+
" # log_metric_list = ['train_loss'], \n",
|
86 |
+
" # groupby_list = ['dataset'],\n",
|
87 |
+
" # map_ylabel_list=[{'train_loss':'Train loss'}],\n",
|
88 |
+
" # map_xlabel_list=[{'epoch':'Epoch'}],\n",
|
89 |
+
" # figsize=(15,5),\n",
|
90 |
+
" # plot_confidence=False,\n",
|
91 |
+
" # savedir_plots='%s' % (name)\n",
|
92 |
+
")\n",
|
93 |
+
" "
|
94 |
+
]
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"cell_type": "code",
|
98 |
+
"execution_count": null,
|
99 |
+
"id": "1820c04c",
|
100 |
+
"metadata": {},
|
101 |
+
"outputs": [],
|
102 |
+
"source": [
|
103 |
+
"\n",
|
104 |
+
" !pip install --upgrade git+https://github.com/haven-ai/haven-ai\n",
|
105 |
+
" "
|
106 |
+
]
|
107 |
+
}
|
108 |
+
],
|
109 |
+
"metadata": {},
|
110 |
+
"nbformat": 4,
|
111 |
+
"nbformat_minor": 5
|
112 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
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": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
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_config.json
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|padding|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50254": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50255": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50256": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50257": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50258": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50259": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50260": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50261": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50262": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50263": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50264": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50265": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50266": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50267": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50268": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50269": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50270": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50271": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50272": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50273": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50274": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50275": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50276": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"50277": {
|
205 |
+
"content": "[PAD]",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
}
|
212 |
+
},
|
213 |
+
"bos_token": "<|endoftext|>",
|
214 |
+
"clean_up_tokenization_spaces": true,
|
215 |
+
"eos_token": "<|endoftext|>",
|
216 |
+
"model_max_length": 1000000000000000019884624838656,
|
217 |
+
"pad_token": "[PAD]",
|
218 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
219 |
+
"unk_token": "<|endoftext|>"
|
220 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ba78dd9361aeb9c8ca7a329b090dfea65275fe361315288c858840f4970d186
|
3 |
+
size 5048
|