Upload 4 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +448 -0
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca7521e28f2004422d216cf8624d4979b133771bb8589f919c0c0f56e4a9503
|
3 |
+
size 54633978
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf4cd47df197813052578d843702d3b1f9cbedf509f73cca54b01749f04edb5
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:576054ea70dd0b6405818d7dda312122ebda5ad8278b10c1cec3a1569fbfd905
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1548,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"grad_norm": 3.802351951599121,
|
14 |
+
"learning_rate": 3.2258064516129034e-05,
|
15 |
+
"loss": 3.7331,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06,
|
20 |
+
"grad_norm": 3.442800760269165,
|
21 |
+
"learning_rate": 6.451612903225807e-05,
|
22 |
+
"loss": 2.9581,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1,
|
27 |
+
"grad_norm": 3.616957902908325,
|
28 |
+
"learning_rate": 9.677419354838711e-05,
|
29 |
+
"loss": 2.4309,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.13,
|
34 |
+
"grad_norm": 2.3956120014190674,
|
35 |
+
"learning_rate": 0.00012903225806451613,
|
36 |
+
"loss": 2.2667,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.16,
|
41 |
+
"grad_norm": 2.698212146759033,
|
42 |
+
"learning_rate": 0.00016129032258064516,
|
43 |
+
"loss": 2.0782,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19,
|
48 |
+
"grad_norm": 2.7342419624328613,
|
49 |
+
"learning_rate": 0.00019354838709677422,
|
50 |
+
"loss": 2.0691,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.23,
|
55 |
+
"grad_norm": 2.039422035217285,
|
56 |
+
"learning_rate": 0.00019712849964106247,
|
57 |
+
"loss": 2.0865,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.26,
|
62 |
+
"grad_norm": 2.0298664569854736,
|
63 |
+
"learning_rate": 0.00019353912419239053,
|
64 |
+
"loss": 1.9552,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.29,
|
69 |
+
"grad_norm": 1.8978090286254883,
|
70 |
+
"learning_rate": 0.0001899497487437186,
|
71 |
+
"loss": 2.0111,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.32,
|
76 |
+
"grad_norm": 1.9588110446929932,
|
77 |
+
"learning_rate": 0.00018636037329504667,
|
78 |
+
"loss": 1.961,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.36,
|
83 |
+
"grad_norm": 2.160839796066284,
|
84 |
+
"learning_rate": 0.00018277099784637474,
|
85 |
+
"loss": 2.0133,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.39,
|
90 |
+
"grad_norm": 2.0899839401245117,
|
91 |
+
"learning_rate": 0.00017918162239770278,
|
92 |
+
"loss": 1.958,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.42,
|
97 |
+
"grad_norm": 2.029879570007324,
|
98 |
+
"learning_rate": 0.00017559224694903088,
|
99 |
+
"loss": 1.9116,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.45,
|
104 |
+
"grad_norm": 1.7021583318710327,
|
105 |
+
"learning_rate": 0.00017200287150035895,
|
106 |
+
"loss": 1.8842,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.48,
|
111 |
+
"grad_norm": 1.5238200426101685,
|
112 |
+
"learning_rate": 0.00016841349605168702,
|
113 |
+
"loss": 1.8229,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.52,
|
118 |
+
"grad_norm": 1.9168670177459717,
|
119 |
+
"learning_rate": 0.0001648241206030151,
|
120 |
+
"loss": 1.9235,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.55,
|
125 |
+
"grad_norm": 1.8892511129379272,
|
126 |
+
"learning_rate": 0.00016123474515434316,
|
127 |
+
"loss": 1.8859,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.58,
|
132 |
+
"grad_norm": 1.7955598831176758,
|
133 |
+
"learning_rate": 0.00015764536970567123,
|
134 |
+
"loss": 1.8619,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.61,
|
139 |
+
"grad_norm": 1.7658586502075195,
|
140 |
+
"learning_rate": 0.00015405599425699927,
|
141 |
+
"loss": 1.8235,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.65,
|
146 |
+
"grad_norm": 1.598111629486084,
|
147 |
+
"learning_rate": 0.00015046661880832737,
|
148 |
+
"loss": 1.8554,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.68,
|
153 |
+
"grad_norm": 1.9352959394454956,
|
154 |
+
"learning_rate": 0.00014687724335965544,
|
155 |
+
"loss": 1.801,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.71,
|
160 |
+
"grad_norm": 1.9746991395950317,
|
161 |
+
"learning_rate": 0.0001432878679109835,
|
162 |
+
"loss": 1.895,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.74,
|
167 |
+
"grad_norm": 1.476921796798706,
|
168 |
+
"learning_rate": 0.00013969849246231157,
|
169 |
+
"loss": 1.7978,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.78,
|
174 |
+
"grad_norm": 1.667672872543335,
|
175 |
+
"learning_rate": 0.00013610911701363964,
|
176 |
+
"loss": 1.76,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.81,
|
181 |
+
"grad_norm": 1.5855716466903687,
|
182 |
+
"learning_rate": 0.00013251974156496769,
|
183 |
+
"loss": 1.8171,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.84,
|
188 |
+
"grad_norm": 1.9429579973220825,
|
189 |
+
"learning_rate": 0.00012893036611629576,
|
190 |
+
"loss": 1.811,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.87,
|
195 |
+
"grad_norm": 1.684810996055603,
|
196 |
+
"learning_rate": 0.00012534099066762382,
|
197 |
+
"loss": 1.8148,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.9,
|
202 |
+
"grad_norm": 1.6180702447891235,
|
203 |
+
"learning_rate": 0.00012175161521895191,
|
204 |
+
"loss": 1.7356,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.94,
|
209 |
+
"grad_norm": 1.7795788049697876,
|
210 |
+
"learning_rate": 0.00011816223977027998,
|
211 |
+
"loss": 1.7969,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.97,
|
216 |
+
"grad_norm": 1.7645013332366943,
|
217 |
+
"learning_rate": 0.00011457286432160806,
|
218 |
+
"loss": 1.8198,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.0,
|
223 |
+
"grad_norm": 1.713512897491455,
|
224 |
+
"learning_rate": 0.00011098348887293613,
|
225 |
+
"loss": 1.7514,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.03,
|
230 |
+
"grad_norm": 1.3435418605804443,
|
231 |
+
"learning_rate": 0.00010739411342426417,
|
232 |
+
"loss": 1.6679,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.07,
|
237 |
+
"grad_norm": 1.5819846391677856,
|
238 |
+
"learning_rate": 0.00010380473797559225,
|
239 |
+
"loss": 1.7182,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.1,
|
244 |
+
"grad_norm": 1.3324297666549683,
|
245 |
+
"learning_rate": 0.00010021536252692032,
|
246 |
+
"loss": 1.7301,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.13,
|
251 |
+
"grad_norm": 1.4800920486450195,
|
252 |
+
"learning_rate": 9.662598707824839e-05,
|
253 |
+
"loss": 1.7123,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.16,
|
258 |
+
"grad_norm": 1.5812880992889404,
|
259 |
+
"learning_rate": 9.303661162957645e-05,
|
260 |
+
"loss": 1.7816,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.2,
|
265 |
+
"grad_norm": 1.5376070737838745,
|
266 |
+
"learning_rate": 8.944723618090453e-05,
|
267 |
+
"loss": 1.7446,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.23,
|
272 |
+
"grad_norm": 1.5884149074554443,
|
273 |
+
"learning_rate": 8.58578607322326e-05,
|
274 |
+
"loss": 1.6483,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.26,
|
279 |
+
"grad_norm": 2.03753662109375,
|
280 |
+
"learning_rate": 8.226848528356066e-05,
|
281 |
+
"loss": 1.6695,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.29,
|
286 |
+
"grad_norm": 1.7924336194992065,
|
287 |
+
"learning_rate": 7.867910983488873e-05,
|
288 |
+
"loss": 1.7109,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.32,
|
293 |
+
"grad_norm": 1.80973219871521,
|
294 |
+
"learning_rate": 7.508973438621681e-05,
|
295 |
+
"loss": 1.7017,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.36,
|
300 |
+
"grad_norm": 1.7763901948928833,
|
301 |
+
"learning_rate": 7.150035893754488e-05,
|
302 |
+
"loss": 1.6669,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.39,
|
307 |
+
"grad_norm": 3.0561070442199707,
|
308 |
+
"learning_rate": 6.791098348887293e-05,
|
309 |
+
"loss": 1.6681,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.42,
|
314 |
+
"grad_norm": 1.7292817831039429,
|
315 |
+
"learning_rate": 6.4321608040201e-05,
|
316 |
+
"loss": 1.6787,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.45,
|
321 |
+
"grad_norm": 1.6157281398773193,
|
322 |
+
"learning_rate": 6.073223259152908e-05,
|
323 |
+
"loss": 1.6716,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.49,
|
328 |
+
"grad_norm": 1.5873336791992188,
|
329 |
+
"learning_rate": 5.714285714285714e-05,
|
330 |
+
"loss": 1.6724,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.52,
|
335 |
+
"grad_norm": 1.7574703693389893,
|
336 |
+
"learning_rate": 5.355348169418522e-05,
|
337 |
+
"loss": 1.6608,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.55,
|
342 |
+
"grad_norm": 1.7600945234298706,
|
343 |
+
"learning_rate": 4.996410624551328e-05,
|
344 |
+
"loss": 1.7204,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.58,
|
349 |
+
"grad_norm": 1.4515677690505981,
|
350 |
+
"learning_rate": 4.6374730796841356e-05,
|
351 |
+
"loss": 1.6755,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.61,
|
356 |
+
"grad_norm": 1.9057530164718628,
|
357 |
+
"learning_rate": 4.278535534816942e-05,
|
358 |
+
"loss": 1.6953,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.65,
|
363 |
+
"grad_norm": 1.7482775449752808,
|
364 |
+
"learning_rate": 3.919597989949749e-05,
|
365 |
+
"loss": 1.686,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.68,
|
370 |
+
"grad_norm": 1.8991056680679321,
|
371 |
+
"learning_rate": 3.560660445082556e-05,
|
372 |
+
"loss": 1.6611,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.71,
|
377 |
+
"grad_norm": 1.7882860898971558,
|
378 |
+
"learning_rate": 3.201722900215363e-05,
|
379 |
+
"loss": 1.7103,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.74,
|
384 |
+
"grad_norm": 1.6628391742706299,
|
385 |
+
"learning_rate": 2.84278535534817e-05,
|
386 |
+
"loss": 1.6925,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.78,
|
391 |
+
"grad_norm": 1.5516228675842285,
|
392 |
+
"learning_rate": 2.4838478104809766e-05,
|
393 |
+
"loss": 1.652,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.81,
|
398 |
+
"grad_norm": 1.5719884634017944,
|
399 |
+
"learning_rate": 2.1249102656137835e-05,
|
400 |
+
"loss": 1.6383,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.84,
|
405 |
+
"grad_norm": 1.8628472089767456,
|
406 |
+
"learning_rate": 1.76597272074659e-05,
|
407 |
+
"loss": 1.6922,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.87,
|
412 |
+
"grad_norm": 1.7590694427490234,
|
413 |
+
"learning_rate": 1.407035175879397e-05,
|
414 |
+
"loss": 1.687,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.91,
|
419 |
+
"grad_norm": 1.6741101741790771,
|
420 |
+
"learning_rate": 1.048097631012204e-05,
|
421 |
+
"loss": 1.6599,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.94,
|
426 |
+
"grad_norm": 1.7378610372543335,
|
427 |
+
"learning_rate": 6.891600861450108e-06,
|
428 |
+
"loss": 1.6765,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.97,
|
433 |
+
"grad_norm": 1.5435367822647095,
|
434 |
+
"learning_rate": 3.3022254127781766e-06,
|
435 |
+
"loss": 1.607,
|
436 |
+
"step": 1525
|
437 |
+
}
|
438 |
+
],
|
439 |
+
"logging_steps": 25,
|
440 |
+
"max_steps": 1548,
|
441 |
+
"num_input_tokens_seen": 0,
|
442 |
+
"num_train_epochs": 2,
|
443 |
+
"save_steps": 500,
|
444 |
+
"total_flos": 1.0151913205845197e+17,
|
445 |
+
"train_batch_size": 6,
|
446 |
+
"trial_name": null,
|
447 |
+
"trial_params": null
|
448 |
+
}
|