kpriyanshu256
commited on
Commit
•
a4f34e7
1
Parent(s):
68e5b36
End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- runs/Nov24_18-20-11_18a182a10601/events.out.tfevents.1669333034.18a182a10601.1202.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +313 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.3690952822914751,
|
4 |
+
"eval_loss": 3.151942014694214,
|
5 |
+
"eval_runtime": 326.5177,
|
6 |
+
"eval_samples": 10066,
|
7 |
+
"eval_samples_per_second": 30.828,
|
8 |
+
"eval_steps_per_second": 3.856,
|
9 |
+
"perplexity": 23.381427594826878,
|
10 |
+
"train_loss": 3.103326614534778,
|
11 |
+
"train_runtime": 18434.3928,
|
12 |
+
"train_samples": 38613,
|
13 |
+
"train_samples_per_second": 10.473,
|
14 |
+
"train_steps_per_second": 1.309
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.3690952822914751,
|
4 |
+
"eval_loss": 3.151942014694214,
|
5 |
+
"eval_runtime": 326.5177,
|
6 |
+
"eval_samples": 10066,
|
7 |
+
"eval_samples_per_second": 30.828,
|
8 |
+
"eval_steps_per_second": 3.856,
|
9 |
+
"perplexity": 23.381427594826878
|
10 |
+
}
|
runs/Nov24_18-20-11_18a182a10601/events.out.tfevents.1669333034.18a182a10601.1202.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2823bdde1a2b81aee2d2b3d597b7a46b0d83c573f169f3f1c0b12299a976aca2
|
3 |
+
size 369
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 3.103326614534778,
|
4 |
+
"train_runtime": 18434.3928,
|
5 |
+
"train_samples": 38613,
|
6 |
+
"train_samples_per_second": 10.473,
|
7 |
+
"train_steps_per_second": 1.309
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 24135,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 4.8968303293971416e-05,
|
13 |
+
"loss": 3.4484,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.21,
|
18 |
+
"learning_rate": 4.7932463227677646e-05,
|
19 |
+
"loss": 3.355,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.31,
|
24 |
+
"learning_rate": 4.6896623161383883e-05,
|
25 |
+
"loss": 3.3179,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.41,
|
30 |
+
"learning_rate": 4.586078309509012e-05,
|
31 |
+
"loss": 3.2949,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.52,
|
36 |
+
"learning_rate": 4.482494302879636e-05,
|
37 |
+
"loss": 3.2563,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.62,
|
42 |
+
"learning_rate": 4.3789102962502596e-05,
|
43 |
+
"loss": 3.2521,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.73,
|
48 |
+
"learning_rate": 4.2753262896208826e-05,
|
49 |
+
"loss": 3.2356,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.83,
|
54 |
+
"learning_rate": 4.1717422829915064e-05,
|
55 |
+
"loss": 3.2286,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.93,
|
60 |
+
"learning_rate": 4.06815827636213e-05,
|
61 |
+
"loss": 3.2046,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.04,
|
66 |
+
"learning_rate": 3.964574269732754e-05,
|
67 |
+
"loss": 3.1894,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.14,
|
72 |
+
"learning_rate": 3.860990263103377e-05,
|
73 |
+
"loss": 3.1449,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.24,
|
78 |
+
"learning_rate": 3.7574062564740006e-05,
|
79 |
+
"loss": 3.1414,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.35,
|
84 |
+
"learning_rate": 3.653822249844624e-05,
|
85 |
+
"loss": 3.1392,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.45,
|
90 |
+
"learning_rate": 3.5502382432152474e-05,
|
91 |
+
"loss": 3.1346,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.55,
|
96 |
+
"learning_rate": 3.446654236585871e-05,
|
97 |
+
"loss": 3.1401,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.66,
|
102 |
+
"learning_rate": 3.343070229956495e-05,
|
103 |
+
"loss": 3.1233,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.76,
|
108 |
+
"learning_rate": 3.239693391340377e-05,
|
109 |
+
"loss": 3.1274,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.86,
|
114 |
+
"learning_rate": 3.136109384711001e-05,
|
115 |
+
"loss": 3.1225,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.97,
|
120 |
+
"learning_rate": 3.0325253780816242e-05,
|
121 |
+
"loss": 3.1163,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 2.07,
|
126 |
+
"learning_rate": 2.928941371452248e-05,
|
127 |
+
"loss": 3.0867,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.18,
|
132 |
+
"learning_rate": 2.82556453283613e-05,
|
133 |
+
"loss": 3.073,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.28,
|
138 |
+
"learning_rate": 2.721980526206754e-05,
|
139 |
+
"loss": 3.0646,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.38,
|
144 |
+
"learning_rate": 2.6183965195773773e-05,
|
145 |
+
"loss": 3.0672,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.49,
|
150 |
+
"learning_rate": 2.514812512948001e-05,
|
151 |
+
"loss": 3.0713,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.59,
|
156 |
+
"learning_rate": 2.411642842345142e-05,
|
157 |
+
"loss": 3.0715,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.69,
|
162 |
+
"learning_rate": 2.3080588357157657e-05,
|
163 |
+
"loss": 3.064,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.8,
|
168 |
+
"learning_rate": 2.204474829086389e-05,
|
169 |
+
"loss": 3.0619,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.9,
|
174 |
+
"learning_rate": 2.100890822457013e-05,
|
175 |
+
"loss": 3.0659,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 3.0,
|
180 |
+
"learning_rate": 1.9973068158276362e-05,
|
181 |
+
"loss": 3.0686,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 3.11,
|
186 |
+
"learning_rate": 1.8937228091982596e-05,
|
187 |
+
"loss": 3.024,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 3.21,
|
192 |
+
"learning_rate": 1.7901388025688834e-05,
|
193 |
+
"loss": 3.0245,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.31,
|
198 |
+
"learning_rate": 1.6867619639527656e-05,
|
199 |
+
"loss": 3.0451,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 3.42,
|
204 |
+
"learning_rate": 1.5831779573233893e-05,
|
205 |
+
"loss": 3.0224,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 3.52,
|
210 |
+
"learning_rate": 1.4795939506940129e-05,
|
211 |
+
"loss": 3.0343,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3.63,
|
216 |
+
"learning_rate": 1.3760099440646364e-05,
|
217 |
+
"loss": 3.0188,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 3.73,
|
222 |
+
"learning_rate": 1.2726331054485188e-05,
|
223 |
+
"loss": 3.0242,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 3.83,
|
228 |
+
"learning_rate": 1.1690490988191424e-05,
|
229 |
+
"loss": 3.0264,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 3.94,
|
234 |
+
"learning_rate": 1.065465092189766e-05,
|
235 |
+
"loss": 3.0394,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 4.04,
|
240 |
+
"learning_rate": 9.618810855603895e-06,
|
241 |
+
"loss": 3.025,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 4.14,
|
246 |
+
"learning_rate": 8.585042469442718e-06,
|
247 |
+
"loss": 2.9995,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 4.25,
|
252 |
+
"learning_rate": 7.549202403148954e-06,
|
253 |
+
"loss": 3.0081,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 4.35,
|
258 |
+
"learning_rate": 6.51336233685519e-06,
|
259 |
+
"loss": 2.9937,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 4.45,
|
264 |
+
"learning_rate": 5.4775222705614255e-06,
|
265 |
+
"loss": 3.0028,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 4.56,
|
270 |
+
"learning_rate": 4.441682204267662e-06,
|
271 |
+
"loss": 3.0022,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 4.66,
|
276 |
+
"learning_rate": 3.4079138181064847e-06,
|
277 |
+
"loss": 3.0221,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 4.76,
|
282 |
+
"learning_rate": 2.37207375181272e-06,
|
283 |
+
"loss": 2.9937,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 4.87,
|
288 |
+
"learning_rate": 1.336233685518956e-06,
|
289 |
+
"loss": 3.0063,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 4.97,
|
294 |
+
"learning_rate": 3.0039361922519165e-07,
|
295 |
+
"loss": 3.0098,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 5.0,
|
300 |
+
"step": 24135,
|
301 |
+
"total_flos": 5.044634615808e+16,
|
302 |
+
"train_loss": 3.103326614534778,
|
303 |
+
"train_runtime": 18434.3928,
|
304 |
+
"train_samples_per_second": 10.473,
|
305 |
+
"train_steps_per_second": 1.309
|
306 |
+
}
|
307 |
+
],
|
308 |
+
"max_steps": 24135,
|
309 |
+
"num_train_epochs": 5,
|
310 |
+
"total_flos": 5.044634615808e+16,
|
311 |
+
"trial_name": null,
|
312 |
+
"trial_params": null
|
313 |
+
}
|