Commit from Andrija
Browse files- config.json +23 -0
- log_history.json +282 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RobertaForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "roberta",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"total_flos": 86931019038720000,
|
21 |
+
"type_vocab_size": 1,
|
22 |
+
"vocab_size": 100000
|
23 |
+
}
|
log_history.json
ADDED
@@ -0,0 +1,282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"loss": 8.7351650390625,
|
4 |
+
"learning_rate": 4.875491807360925e-05,
|
5 |
+
"epoch": 0.02490163852781513,
|
6 |
+
"total_flos": 2173275475968000,
|
7 |
+
"step": 500
|
8 |
+
},
|
9 |
+
{
|
10 |
+
"loss": 8.1599990234375,
|
11 |
+
"learning_rate": 4.750983614721849e-05,
|
12 |
+
"epoch": 0.04980327705563026,
|
13 |
+
"total_flos": 4346550951936000,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"loss": 7.94335546875,
|
18 |
+
"learning_rate": 4.6264754220827736e-05,
|
19 |
+
"epoch": 0.07470491558344539,
|
20 |
+
"total_flos": 6519826427904000,
|
21 |
+
"step": 1500
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"loss": 7.817630859375,
|
25 |
+
"learning_rate": 4.5019672294436976e-05,
|
26 |
+
"epoch": 0.09960655411126051,
|
27 |
+
"total_flos": 8693101903872000,
|
28 |
+
"step": 2000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"loss": 7.721162109375,
|
32 |
+
"learning_rate": 4.377459036804622e-05,
|
33 |
+
"epoch": 0.12450819263907566,
|
34 |
+
"total_flos": 10866377379840000,
|
35 |
+
"step": 2500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"loss": 7.63598046875,
|
39 |
+
"learning_rate": 4.252950844165546e-05,
|
40 |
+
"epoch": 0.14940983116689077,
|
41 |
+
"total_flos": 13039652855808000,
|
42 |
+
"step": 3000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"loss": 7.557828125,
|
46 |
+
"learning_rate": 4.128442651526471e-05,
|
47 |
+
"epoch": 0.1743114696947059,
|
48 |
+
"total_flos": 15212928331776000,
|
49 |
+
"step": 3500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"loss": 7.47056640625,
|
53 |
+
"learning_rate": 4.003934458887395e-05,
|
54 |
+
"epoch": 0.19921310822252103,
|
55 |
+
"total_flos": 17386203807744000,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"loss": 7.40528125,
|
60 |
+
"learning_rate": 3.8794262662483196e-05,
|
61 |
+
"epoch": 0.22411474675033619,
|
62 |
+
"total_flos": 19559479283712000,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"loss": 7.32109375,
|
67 |
+
"learning_rate": 3.7549180736092436e-05,
|
68 |
+
"epoch": 0.24901638527815131,
|
69 |
+
"total_flos": 21732754759680000,
|
70 |
+
"step": 5000
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"loss": 7.1830703125,
|
74 |
+
"learning_rate": 3.630409880970168e-05,
|
75 |
+
"epoch": 0.2739180238059664,
|
76 |
+
"total_flos": 23906030235648000,
|
77 |
+
"step": 5500
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"loss": 7.075640625,
|
81 |
+
"learning_rate": 3.505901688331092e-05,
|
82 |
+
"epoch": 0.29881966233378154,
|
83 |
+
"total_flos": 26079305711616000,
|
84 |
+
"step": 6000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"loss": 6.9607734375,
|
88 |
+
"learning_rate": 3.381393495692017e-05,
|
89 |
+
"epoch": 0.3237213008615967,
|
90 |
+
"total_flos": 28252581187584000,
|
91 |
+
"step": 6500
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"loss": 6.8397734375,
|
95 |
+
"learning_rate": 3.256885303052941e-05,
|
96 |
+
"epoch": 0.3486229393894118,
|
97 |
+
"total_flos": 30425856663552000,
|
98 |
+
"step": 7000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"loss": 6.7368984375,
|
102 |
+
"learning_rate": 3.1323771104138656e-05,
|
103 |
+
"epoch": 0.37352457791722693,
|
104 |
+
"total_flos": 32599132139520000,
|
105 |
+
"step": 7500
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"loss": 6.6454296875,
|
109 |
+
"learning_rate": 3.00786891777479e-05,
|
110 |
+
"epoch": 0.39842621644504206,
|
111 |
+
"total_flos": 34772407615488000,
|
112 |
+
"step": 8000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"loss": 6.573265625,
|
116 |
+
"learning_rate": 2.8833607251357143e-05,
|
117 |
+
"epoch": 0.4233278549728572,
|
118 |
+
"total_flos": 36945683091456000,
|
119 |
+
"step": 8500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"loss": 6.4836328125,
|
123 |
+
"learning_rate": 2.7588525324966386e-05,
|
124 |
+
"epoch": 0.44822949350067237,
|
125 |
+
"total_flos": 39118958567424000,
|
126 |
+
"step": 9000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"loss": 6.418890625,
|
130 |
+
"learning_rate": 2.634344339857563e-05,
|
131 |
+
"epoch": 0.4731311320284875,
|
132 |
+
"total_flos": 41292234043392000,
|
133 |
+
"step": 9500
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"loss": 6.3506875,
|
137 |
+
"learning_rate": 2.5098361472184873e-05,
|
138 |
+
"epoch": 0.49803277055630263,
|
139 |
+
"total_flos": 43465509519360000,
|
140 |
+
"step": 10000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"loss": 6.298296875,
|
144 |
+
"learning_rate": 2.3853279545794113e-05,
|
145 |
+
"epoch": 0.5229344090841177,
|
146 |
+
"total_flos": 45638784995328000,
|
147 |
+
"step": 10500
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"loss": 6.242953125,
|
151 |
+
"learning_rate": 2.2608197619403356e-05,
|
152 |
+
"epoch": 0.5478360476119328,
|
153 |
+
"total_flos": 47812060471296000,
|
154 |
+
"step": 11000
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"loss": 6.193828125,
|
158 |
+
"learning_rate": 2.13631156930126e-05,
|
159 |
+
"epoch": 0.572737686139748,
|
160 |
+
"total_flos": 49985335947264000,
|
161 |
+
"step": 11500
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"loss": 6.149265625,
|
165 |
+
"learning_rate": 2.0118033766621843e-05,
|
166 |
+
"epoch": 0.5976393246675631,
|
167 |
+
"total_flos": 52158611423232000,
|
168 |
+
"step": 12000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"loss": 6.112984375,
|
172 |
+
"learning_rate": 1.8872951840231086e-05,
|
173 |
+
"epoch": 0.6225409631953782,
|
174 |
+
"total_flos": 54331886899200000,
|
175 |
+
"step": 12500
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"loss": 6.054078125,
|
179 |
+
"learning_rate": 1.762786991384033e-05,
|
180 |
+
"epoch": 0.6474426017231933,
|
181 |
+
"total_flos": 56505162375168000,
|
182 |
+
"step": 13000
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"loss": 6.0306875,
|
186 |
+
"learning_rate": 1.6382787987449573e-05,
|
187 |
+
"epoch": 0.6723442402510085,
|
188 |
+
"total_flos": 58678437851136000,
|
189 |
+
"step": 13500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"loss": 5.998078125,
|
193 |
+
"learning_rate": 1.5137706061058818e-05,
|
194 |
+
"epoch": 0.6972458787788236,
|
195 |
+
"total_flos": 60851713327104000,
|
196 |
+
"step": 14000
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"loss": 5.964859375,
|
200 |
+
"learning_rate": 1.3892624134668061e-05,
|
201 |
+
"epoch": 0.7221475173066387,
|
202 |
+
"total_flos": 63024988803072000,
|
203 |
+
"step": 14500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"loss": 5.938515625,
|
207 |
+
"learning_rate": 1.2647542208277304e-05,
|
208 |
+
"epoch": 0.7470491558344539,
|
209 |
+
"total_flos": 65198264279040000,
|
210 |
+
"step": 15000
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"loss": 5.9313125,
|
214 |
+
"learning_rate": 1.1402460281886548e-05,
|
215 |
+
"epoch": 0.771950794362269,
|
216 |
+
"total_flos": 67371539755008000,
|
217 |
+
"step": 15500
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"loss": 5.897203125,
|
221 |
+
"learning_rate": 1.0157378355495791e-05,
|
222 |
+
"epoch": 0.7968524328900841,
|
223 |
+
"total_flos": 69544815230976000,
|
224 |
+
"step": 16000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"loss": 5.880890625,
|
228 |
+
"learning_rate": 8.912296429105036e-06,
|
229 |
+
"epoch": 0.8217540714178992,
|
230 |
+
"total_flos": 71718090706944000,
|
231 |
+
"step": 16500
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"loss": 5.86578125,
|
235 |
+
"learning_rate": 7.66721450271428e-06,
|
236 |
+
"epoch": 0.8466557099457144,
|
237 |
+
"total_flos": 73891366182912000,
|
238 |
+
"step": 17000
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"loss": 5.839921875,
|
242 |
+
"learning_rate": 6.422132576323522e-06,
|
243 |
+
"epoch": 0.8715573484735295,
|
244 |
+
"total_flos": 76064641658880000,
|
245 |
+
"step": 17500
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"loss": 5.851390625,
|
249 |
+
"learning_rate": 5.177050649932766e-06,
|
250 |
+
"epoch": 0.8964589870013447,
|
251 |
+
"total_flos": 78237917134848000,
|
252 |
+
"step": 18000
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"loss": 5.8313125,
|
256 |
+
"learning_rate": 3.9319687235420096e-06,
|
257 |
+
"epoch": 0.9213606255291599,
|
258 |
+
"total_flos": 80411192610816000,
|
259 |
+
"step": 18500
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"loss": 5.813203125,
|
263 |
+
"learning_rate": 2.6868867971512525e-06,
|
264 |
+
"epoch": 0.946262264056975,
|
265 |
+
"total_flos": 82584468086784000,
|
266 |
+
"step": 19000
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"loss": 5.82146875,
|
270 |
+
"learning_rate": 1.441804870760496e-06,
|
271 |
+
"epoch": 0.9711639025847901,
|
272 |
+
"total_flos": 84757743562752000,
|
273 |
+
"step": 19500
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"loss": 5.809875,
|
277 |
+
"learning_rate": 1.9672294436973953e-07,
|
278 |
+
"epoch": 0.9960655411126053,
|
279 |
+
"total_flos": 86931019038720000,
|
280 |
+
"step": 20000
|
281 |
+
}
|
282 |
+
]
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e49cdca272f55169d00329bcf0954449b134b1e4fcc5d98b96068f1363a3b840
|
3 |
+
size 481714453
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71367e5afabecf4d5bd74a4656cae6608c712860509d15976441da4b74f41a85
|
3 |
+
size 1775
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|