Upload 4 files
Browse files- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +511 -0
- training_args.bin +3 -0
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0562d72f8f607c26ff25e8776825d1b831ce6932909f05f72b430fae0bc3ed1f
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d74203b12bf4e8534ae360cb2493b87397182e53d618ae4d9bbdf463188f5d1
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,511 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.34351145038168,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 35000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08,
|
13 |
+
"grad_norm": 7.7123026847839355,
|
14 |
+
"learning_rate": 1.23e-05,
|
15 |
+
"loss": 3.9019,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15,
|
20 |
+
"grad_norm": 5.605632781982422,
|
21 |
+
"learning_rate": 2.4775000000000003e-05,
|
22 |
+
"loss": 1.5616,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23,
|
27 |
+
"grad_norm": 3.154059886932373,
|
28 |
+
"learning_rate": 3.7275000000000005e-05,
|
29 |
+
"loss": 1.4864,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31,
|
34 |
+
"grad_norm": 2.2530698776245117,
|
35 |
+
"learning_rate": 4.9775000000000004e-05,
|
36 |
+
"loss": 1.4422,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.38,
|
41 |
+
"grad_norm": 2.2986319065093994,
|
42 |
+
"learning_rate": 4.9341823056300266e-05,
|
43 |
+
"loss": 1.4061,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46,
|
48 |
+
"grad_norm": 1.661163091659546,
|
49 |
+
"learning_rate": 4.8671581769436996e-05,
|
50 |
+
"loss": 1.4029,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.53,
|
55 |
+
"grad_norm": 4.1285400390625,
|
56 |
+
"learning_rate": 4.800134048257373e-05,
|
57 |
+
"loss": 1.3777,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.61,
|
62 |
+
"grad_norm": 1.6614463329315186,
|
63 |
+
"learning_rate": 4.733109919571046e-05,
|
64 |
+
"loss": 1.359,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.69,
|
69 |
+
"grad_norm": 1.6893428564071655,
|
70 |
+
"learning_rate": 4.666085790884719e-05,
|
71 |
+
"loss": 1.3417,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.76,
|
76 |
+
"grad_norm": 1.9169539213180542,
|
77 |
+
"learning_rate": 4.599061662198392e-05,
|
78 |
+
"loss": 1.3231,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.84,
|
83 |
+
"grad_norm": 1.7877219915390015,
|
84 |
+
"learning_rate": 4.532037533512065e-05,
|
85 |
+
"loss": 1.3365,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.92,
|
90 |
+
"grad_norm": 1.6105085611343384,
|
91 |
+
"learning_rate": 4.465013404825737e-05,
|
92 |
+
"loss": 1.3108,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.99,
|
97 |
+
"grad_norm": 3.9035630226135254,
|
98 |
+
"learning_rate": 4.39798927613941e-05,
|
99 |
+
"loss": 1.3242,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.07,
|
104 |
+
"grad_norm": 1.9192873239517212,
|
105 |
+
"learning_rate": 4.330965147453083e-05,
|
106 |
+
"loss": 1.2635,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.15,
|
111 |
+
"grad_norm": 2.6928493976593018,
|
112 |
+
"learning_rate": 4.263941018766756e-05,
|
113 |
+
"loss": 1.2415,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.22,
|
118 |
+
"grad_norm": 2.442293643951416,
|
119 |
+
"learning_rate": 4.196916890080429e-05,
|
120 |
+
"loss": 1.2646,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3,
|
125 |
+
"grad_norm": 1.960336446762085,
|
126 |
+
"learning_rate": 4.129892761394102e-05,
|
127 |
+
"loss": 1.2569,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.37,
|
132 |
+
"grad_norm": 1.510266661643982,
|
133 |
+
"learning_rate": 4.062868632707775e-05,
|
134 |
+
"loss": 1.249,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.45,
|
139 |
+
"grad_norm": 2.045361042022705,
|
140 |
+
"learning_rate": 3.9958445040214485e-05,
|
141 |
+
"loss": 1.2357,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.53,
|
146 |
+
"grad_norm": 1.5785582065582275,
|
147 |
+
"learning_rate": 3.928820375335121e-05,
|
148 |
+
"loss": 1.2464,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.6,
|
153 |
+
"grad_norm": 1.7004880905151367,
|
154 |
+
"learning_rate": 3.861796246648794e-05,
|
155 |
+
"loss": 1.2521,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.68,
|
160 |
+
"grad_norm": 6.9023847579956055,
|
161 |
+
"learning_rate": 3.7947721179624666e-05,
|
162 |
+
"loss": 1.2383,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.76,
|
167 |
+
"grad_norm": 1.391236424446106,
|
168 |
+
"learning_rate": 3.7277479892761396e-05,
|
169 |
+
"loss": 1.2449,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.83,
|
174 |
+
"grad_norm": 2.4769670963287354,
|
175 |
+
"learning_rate": 3.6607238605898125e-05,
|
176 |
+
"loss": 1.2397,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.91,
|
181 |
+
"grad_norm": 2.1677072048187256,
|
182 |
+
"learning_rate": 3.5936997319034855e-05,
|
183 |
+
"loss": 1.2375,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.98,
|
188 |
+
"grad_norm": 1.4357081651687622,
|
189 |
+
"learning_rate": 3.5266756032171584e-05,
|
190 |
+
"loss": 1.2176,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.06,
|
195 |
+
"grad_norm": 1.5423144102096558,
|
196 |
+
"learning_rate": 3.4596514745308314e-05,
|
197 |
+
"loss": 1.1792,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.14,
|
202 |
+
"grad_norm": 2.3282928466796875,
|
203 |
+
"learning_rate": 3.392627345844504e-05,
|
204 |
+
"loss": 1.1803,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.21,
|
209 |
+
"grad_norm": 1.8388934135437012,
|
210 |
+
"learning_rate": 3.325603217158177e-05,
|
211 |
+
"loss": 1.1808,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.29,
|
216 |
+
"grad_norm": 1.5079582929611206,
|
217 |
+
"learning_rate": 3.2585790884718495e-05,
|
218 |
+
"loss": 1.1779,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.37,
|
223 |
+
"grad_norm": 1.625044345855713,
|
224 |
+
"learning_rate": 3.1916890080428955e-05,
|
225 |
+
"loss": 1.1788,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.44,
|
230 |
+
"grad_norm": 1.4615004062652588,
|
231 |
+
"learning_rate": 3.1246648793565684e-05,
|
232 |
+
"loss": 1.185,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.52,
|
237 |
+
"grad_norm": 1.3896290063858032,
|
238 |
+
"learning_rate": 3.0576407506702414e-05,
|
239 |
+
"loss": 1.1716,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.6,
|
244 |
+
"grad_norm": 1.5188448429107666,
|
245 |
+
"learning_rate": 2.9906166219839143e-05,
|
246 |
+
"loss": 1.1811,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.67,
|
251 |
+
"grad_norm": 1.431693434715271,
|
252 |
+
"learning_rate": 2.9235924932975873e-05,
|
253 |
+
"loss": 1.1667,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.75,
|
258 |
+
"grad_norm": 1.6156121492385864,
|
259 |
+
"learning_rate": 2.8565683646112602e-05,
|
260 |
+
"loss": 1.1801,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.82,
|
265 |
+
"grad_norm": 1.875617265701294,
|
266 |
+
"learning_rate": 2.789678284182306e-05,
|
267 |
+
"loss": 1.1717,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.9,
|
272 |
+
"grad_norm": 1.362160325050354,
|
273 |
+
"learning_rate": 2.7226541554959788e-05,
|
274 |
+
"loss": 1.1721,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.98,
|
279 |
+
"grad_norm": 1.9847090244293213,
|
280 |
+
"learning_rate": 2.6556300268096518e-05,
|
281 |
+
"loss": 1.1659,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.05,
|
286 |
+
"grad_norm": 1.6233386993408203,
|
287 |
+
"learning_rate": 2.5886058981233247e-05,
|
288 |
+
"loss": 1.126,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 3.13,
|
293 |
+
"grad_norm": 1.5847933292388916,
|
294 |
+
"learning_rate": 2.5215817694369976e-05,
|
295 |
+
"loss": 1.1146,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.21,
|
300 |
+
"grad_norm": 1.467008352279663,
|
301 |
+
"learning_rate": 2.454691689008043e-05,
|
302 |
+
"loss": 1.1267,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.28,
|
307 |
+
"grad_norm": 1.5421602725982666,
|
308 |
+
"learning_rate": 2.387667560321716e-05,
|
309 |
+
"loss": 1.1332,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 3.36,
|
314 |
+
"grad_norm": 1.4515670537948608,
|
315 |
+
"learning_rate": 2.320643431635389e-05,
|
316 |
+
"loss": 1.1319,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.44,
|
321 |
+
"grad_norm": 1.4106440544128418,
|
322 |
+
"learning_rate": 2.2536193029490618e-05,
|
323 |
+
"loss": 1.1215,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.51,
|
328 |
+
"grad_norm": 1.476091980934143,
|
329 |
+
"learning_rate": 2.1867292225201075e-05,
|
330 |
+
"loss": 1.1221,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 3.59,
|
335 |
+
"grad_norm": 1.3340860605239868,
|
336 |
+
"learning_rate": 2.1197050938337804e-05,
|
337 |
+
"loss": 1.122,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.66,
|
342 |
+
"grad_norm": 2.5545642375946045,
|
343 |
+
"learning_rate": 2.0526809651474533e-05,
|
344 |
+
"loss": 1.1311,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.74,
|
349 |
+
"grad_norm": 1.5924307107925415,
|
350 |
+
"learning_rate": 1.985656836461126e-05,
|
351 |
+
"loss": 1.1339,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 3.82,
|
356 |
+
"grad_norm": 1.6188321113586426,
|
357 |
+
"learning_rate": 1.918632707774799e-05,
|
358 |
+
"loss": 1.1179,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 3.89,
|
363 |
+
"grad_norm": 1.5157597064971924,
|
364 |
+
"learning_rate": 1.8516085790884718e-05,
|
365 |
+
"loss": 1.1147,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 3.97,
|
370 |
+
"grad_norm": 1.6910189390182495,
|
371 |
+
"learning_rate": 1.7845844504021448e-05,
|
372 |
+
"loss": 1.1282,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 4.05,
|
377 |
+
"grad_norm": 1.870836853981018,
|
378 |
+
"learning_rate": 1.7176943699731904e-05,
|
379 |
+
"loss": 1.105,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.12,
|
384 |
+
"grad_norm": 1.5650787353515625,
|
385 |
+
"learning_rate": 1.6506702412868634e-05,
|
386 |
+
"loss": 1.0913,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 4.2,
|
391 |
+
"grad_norm": 1.369066596031189,
|
392 |
+
"learning_rate": 1.583646112600536e-05,
|
393 |
+
"loss": 1.0874,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 4.27,
|
398 |
+
"grad_norm": 1.8052254915237427,
|
399 |
+
"learning_rate": 1.5166219839142093e-05,
|
400 |
+
"loss": 1.101,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 4.35,
|
405 |
+
"grad_norm": 1.5547306537628174,
|
406 |
+
"learning_rate": 1.4495978552278822e-05,
|
407 |
+
"loss": 1.0728,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 4.43,
|
412 |
+
"grad_norm": 1.4759701490402222,
|
413 |
+
"learning_rate": 1.382573726541555e-05,
|
414 |
+
"loss": 1.0975,
|
415 |
+
"step": 29000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 4.5,
|
419 |
+
"grad_norm": 1.3856291770935059,
|
420 |
+
"learning_rate": 1.3155495978552279e-05,
|
421 |
+
"loss": 1.0851,
|
422 |
+
"step": 29500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.58,
|
426 |
+
"grad_norm": 1.5180363655090332,
|
427 |
+
"learning_rate": 1.2486595174262736e-05,
|
428 |
+
"loss": 1.0878,
|
429 |
+
"step": 30000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 4.66,
|
433 |
+
"grad_norm": 1.4963964223861694,
|
434 |
+
"learning_rate": 1.1816353887399465e-05,
|
435 |
+
"loss": 1.0904,
|
436 |
+
"step": 30500
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 4.73,
|
440 |
+
"grad_norm": 1.6953232288360596,
|
441 |
+
"learning_rate": 1.1146112600536193e-05,
|
442 |
+
"loss": 1.0908,
|
443 |
+
"step": 31000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 4.81,
|
447 |
+
"grad_norm": 1.5045945644378662,
|
448 |
+
"learning_rate": 1.0475871313672924e-05,
|
449 |
+
"loss": 1.0894,
|
450 |
+
"step": 31500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 4.89,
|
454 |
+
"grad_norm": 1.935835599899292,
|
455 |
+
"learning_rate": 9.805630026809652e-06,
|
456 |
+
"loss": 1.0839,
|
457 |
+
"step": 32000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 4.96,
|
461 |
+
"grad_norm": 1.7409507036209106,
|
462 |
+
"learning_rate": 9.136729222520107e-06,
|
463 |
+
"loss": 1.0923,
|
464 |
+
"step": 32500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 5.04,
|
468 |
+
"grad_norm": 1.4888629913330078,
|
469 |
+
"learning_rate": 8.466487935656838e-06,
|
470 |
+
"loss": 1.0795,
|
471 |
+
"step": 33000
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 5.11,
|
475 |
+
"grad_norm": 1.7588920593261719,
|
476 |
+
"learning_rate": 7.796246648793565e-06,
|
477 |
+
"loss": 1.0697,
|
478 |
+
"step": 33500
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 5.19,
|
482 |
+
"grad_norm": 1.4674702882766724,
|
483 |
+
"learning_rate": 7.126005361930295e-06,
|
484 |
+
"loss": 1.0567,
|
485 |
+
"step": 34000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 5.27,
|
489 |
+
"grad_norm": 1.5165821313858032,
|
490 |
+
"learning_rate": 6.455764075067025e-06,
|
491 |
+
"loss": 1.0583,
|
492 |
+
"step": 34500
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 5.34,
|
496 |
+
"grad_norm": 1.7669235467910767,
|
497 |
+
"learning_rate": 5.785522788203754e-06,
|
498 |
+
"loss": 1.0621,
|
499 |
+
"step": 35000
|
500 |
+
}
|
501 |
+
],
|
502 |
+
"logging_steps": 500,
|
503 |
+
"max_steps": 39300,
|
504 |
+
"num_input_tokens_seen": 0,
|
505 |
+
"num_train_epochs": 6,
|
506 |
+
"save_steps": 5000,
|
507 |
+
"total_flos": 1.705082093568e+17,
|
508 |
+
"train_batch_size": 8,
|
509 |
+
"trial_name": null,
|
510 |
+
"trial_params": null
|
511 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d31dcaac08146f742e4a2c68bcfce4d059fdaa1d8168a19cad599baaa6d891
|
3 |
+
size 4920
|