Model save
Browse files- README.md +101 -101
- emissions.csv +1 -1
- model.safetensors +1 -1
- runs/Mar06_13-33-03_hcdsgpu2/events.out.tfevents.1709731988.hcdsgpu2.1078775.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model was trained from scratch on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss:
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -44,106 +44,106 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
| No log | 1.0 | 4 | 4.
|
48 |
-
| No log | 2.0 | 8 |
|
49 |
-
| No log | 3.0 | 12 | 3.
|
50 |
-
| No log | 4.0 | 16 | 3.
|
51 |
-
| No log | 5.0 | 20 |
|
52 |
-
| No log | 6.0 | 24 |
|
53 |
-
| No log | 7.0 | 28 |
|
54 |
-
| No log | 8.0 | 32 |
|
55 |
-
| No log | 9.0 | 36 |
|
56 |
-
| No log | 10.0 | 40 |
|
57 |
-
| No log | 11.0 | 44 |
|
58 |
-
| No log | 12.0 | 48 |
|
59 |
-
| No log | 13.0 | 52 |
|
60 |
-
| No log | 14.0 | 56 |
|
61 |
-
| No log | 15.0 | 60 |
|
62 |
-
| No log | 16.0 | 64 |
|
63 |
-
| No log | 17.0 | 68 |
|
64 |
-
| No log | 18.0 | 72 |
|
65 |
-
| No log | 19.0 | 76 |
|
66 |
-
| No log | 20.0 | 80 |
|
67 |
-
| No log | 21.0 | 84 |
|
68 |
-
| No log | 22.0 | 88 |
|
69 |
-
| No log | 23.0 | 92 |
|
70 |
-
| No log | 24.0 | 96 |
|
71 |
-
| No log | 25.0 | 100 |
|
72 |
-
| No log | 26.0 | 104 |
|
73 |
-
| No log | 27.0 | 108 |
|
74 |
-
| No log | 28.0 | 112 |
|
75 |
-
| No log | 29.0 | 116 |
|
76 |
-
| No log | 30.0 | 120 |
|
77 |
-
| No log | 31.0 | 124 |
|
78 |
-
| No log | 32.0 | 128 |
|
79 |
-
| No log | 33.0 | 132 |
|
80 |
-
| No log | 34.0 | 136 |
|
81 |
-
| No log | 35.0 | 140 |
|
82 |
-
| No log | 36.0 | 144 |
|
83 |
-
| No log | 37.0 | 148 |
|
84 |
-
| No log | 38.0 | 152 |
|
85 |
-
| No log | 39.0 | 156 |
|
86 |
-
| No log | 40.0 | 160 |
|
87 |
-
| No log | 41.0 | 164 |
|
88 |
-
| No log | 42.0 | 168 |
|
89 |
-
| No log | 43.0 | 172 |
|
90 |
-
| No log | 44.0 | 176 |
|
91 |
-
| No log | 45.0 | 180 |
|
92 |
-
| No log | 46.0 | 184 |
|
93 |
-
| No log | 47.0 | 188 |
|
94 |
-
| No log | 48.0 | 192 |
|
95 |
-
| No log | 49.0 | 196 |
|
96 |
-
| No log | 50.0 | 200 |
|
97 |
-
| No log | 51.0 | 204 |
|
98 |
-
| No log | 52.0 | 208 |
|
99 |
-
| No log | 53.0 | 212 |
|
100 |
-
| No log | 54.0 | 216 |
|
101 |
-
| No log | 55.0 | 220 |
|
102 |
-
| No log | 56.0 | 224 |
|
103 |
-
| No log | 57.0 | 228 |
|
104 |
-
| No log | 58.0 | 232 |
|
105 |
-
| No log | 59.0 | 236 |
|
106 |
-
| No log | 60.0 | 240 |
|
107 |
-
| No log | 61.0 | 244 |
|
108 |
-
| No log | 62.0 | 248 |
|
109 |
-
| No log | 63.0 | 252 |
|
110 |
-
| No log | 64.0 | 256 |
|
111 |
-
| No log | 65.0 | 260 |
|
112 |
-
| No log | 66.0 | 264 |
|
113 |
-
| No log | 67.0 | 268 |
|
114 |
-
| No log | 68.0 | 272 |
|
115 |
-
| No log | 69.0 | 276 |
|
116 |
-
| No log | 70.0 | 280 |
|
117 |
-
| No log | 71.0 | 284 |
|
118 |
-
| No log | 72.0 | 288 |
|
119 |
-
| No log | 73.0 | 292 |
|
120 |
-
| No log | 74.0 | 296 |
|
121 |
-
| No log | 75.0 | 300 |
|
122 |
-
| No log | 76.0 | 304 |
|
123 |
-
| No log | 77.0 | 308 |
|
124 |
-
| No log | 78.0 | 312 |
|
125 |
-
| No log | 79.0 | 316 |
|
126 |
-
| No log | 80.0 | 320 |
|
127 |
-
| No log | 81.0 | 324 |
|
128 |
-
| No log | 82.0 | 328 |
|
129 |
-
| No log | 83.0 | 332 |
|
130 |
-
| No log | 84.0 | 336 |
|
131 |
-
| No log | 85.0 | 340 |
|
132 |
-
| No log | 86.0 | 344 |
|
133 |
-
| No log | 87.0 | 348 |
|
134 |
-
| No log | 88.0 | 352 |
|
135 |
-
| No log | 89.0 | 356 |
|
136 |
-
| No log | 90.0 | 360 |
|
137 |
-
| No log | 91.0 | 364 |
|
138 |
-
| No log | 92.0 | 368 |
|
139 |
-
| No log | 93.0 | 372 |
|
140 |
-
| No log | 94.0 | 376 |
|
141 |
-
| No log | 95.0 | 380 |
|
142 |
-
| No log | 96.0 | 384 |
|
143 |
-
| No log | 97.0 | 388 |
|
144 |
-
| No log | 98.0 | 392 |
|
145 |
-
| No log | 99.0 | 396 |
|
146 |
-
| No log | 100.0 | 400 |
|
147 |
|
148 |
|
149 |
### Framework versions
|
|
|
13 |
|
14 |
This model was trained from scratch on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 1.2100
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| No log | 1.0 | 4 | 4.8682 |
|
48 |
+
| No log | 2.0 | 8 | 4.2730 |
|
49 |
+
| No log | 3.0 | 12 | 3.6398 |
|
50 |
+
| No log | 4.0 | 16 | 3.1455 |
|
51 |
+
| No log | 5.0 | 20 | 2.7297 |
|
52 |
+
| No log | 6.0 | 24 | 2.3844 |
|
53 |
+
| No log | 7.0 | 28 | 2.0725 |
|
54 |
+
| No log | 8.0 | 32 | 1.8236 |
|
55 |
+
| No log | 9.0 | 36 | 1.6463 |
|
56 |
+
| No log | 10.0 | 40 | 1.4038 |
|
57 |
+
| No log | 11.0 | 44 | 1.3019 |
|
58 |
+
| No log | 12.0 | 48 | 1.2451 |
|
59 |
+
| No log | 13.0 | 52 | 1.1405 |
|
60 |
+
| No log | 14.0 | 56 | 1.0619 |
|
61 |
+
| No log | 15.0 | 60 | 1.0517 |
|
62 |
+
| No log | 16.0 | 64 | 1.0360 |
|
63 |
+
| No log | 17.0 | 68 | 1.0107 |
|
64 |
+
| No log | 18.0 | 72 | 0.9929 |
|
65 |
+
| No log | 19.0 | 76 | 1.0244 |
|
66 |
+
| No log | 20.0 | 80 | 1.0331 |
|
67 |
+
| No log | 21.0 | 84 | 1.0257 |
|
68 |
+
| No log | 22.0 | 88 | 1.0301 |
|
69 |
+
| No log | 23.0 | 92 | 1.0251 |
|
70 |
+
| No log | 24.0 | 96 | 1.0220 |
|
71 |
+
| No log | 25.0 | 100 | 1.0126 |
|
72 |
+
| No log | 26.0 | 104 | 1.0261 |
|
73 |
+
| No log | 27.0 | 108 | 1.0237 |
|
74 |
+
| No log | 28.0 | 112 | 1.0297 |
|
75 |
+
| No log | 29.0 | 116 | 1.0327 |
|
76 |
+
| No log | 30.0 | 120 | 1.0501 |
|
77 |
+
| No log | 31.0 | 124 | 1.0614 |
|
78 |
+
| No log | 32.0 | 128 | 1.0668 |
|
79 |
+
| No log | 33.0 | 132 | 1.0503 |
|
80 |
+
| No log | 34.0 | 136 | 1.0463 |
|
81 |
+
| No log | 35.0 | 140 | 1.0490 |
|
82 |
+
| No log | 36.0 | 144 | 1.0738 |
|
83 |
+
| No log | 37.0 | 148 | 1.0968 |
|
84 |
+
| No log | 38.0 | 152 | 1.1256 |
|
85 |
+
| No log | 39.0 | 156 | 1.1218 |
|
86 |
+
| No log | 40.0 | 160 | 1.1161 |
|
87 |
+
| No log | 41.0 | 164 | 1.1145 |
|
88 |
+
| No log | 42.0 | 168 | 1.1072 |
|
89 |
+
| No log | 43.0 | 172 | 1.0991 |
|
90 |
+
| No log | 44.0 | 176 | 1.1346 |
|
91 |
+
| No log | 45.0 | 180 | 1.1308 |
|
92 |
+
| No log | 46.0 | 184 | 1.1307 |
|
93 |
+
| No log | 47.0 | 188 | 1.1457 |
|
94 |
+
| No log | 48.0 | 192 | 1.1671 |
|
95 |
+
| No log | 49.0 | 196 | 1.1499 |
|
96 |
+
| No log | 50.0 | 200 | 1.1410 |
|
97 |
+
| No log | 51.0 | 204 | 1.1357 |
|
98 |
+
| No log | 52.0 | 208 | 1.1664 |
|
99 |
+
| No log | 53.0 | 212 | 1.1656 |
|
100 |
+
| No log | 54.0 | 216 | 1.1656 |
|
101 |
+
| No log | 55.0 | 220 | 1.1729 |
|
102 |
+
| No log | 56.0 | 224 | 1.1928 |
|
103 |
+
| No log | 57.0 | 228 | 1.1795 |
|
104 |
+
| No log | 58.0 | 232 | 1.1924 |
|
105 |
+
| No log | 59.0 | 236 | 1.1687 |
|
106 |
+
| No log | 60.0 | 240 | 1.1868 |
|
107 |
+
| No log | 61.0 | 244 | 1.1977 |
|
108 |
+
| No log | 62.0 | 248 | 1.1880 |
|
109 |
+
| No log | 63.0 | 252 | 1.1950 |
|
110 |
+
| No log | 64.0 | 256 | 1.2011 |
|
111 |
+
| No log | 65.0 | 260 | 1.1962 |
|
112 |
+
| No log | 66.0 | 264 | 1.1938 |
|
113 |
+
| No log | 67.0 | 268 | 1.2008 |
|
114 |
+
| No log | 68.0 | 272 | 1.2157 |
|
115 |
+
| No log | 69.0 | 276 | 1.2155 |
|
116 |
+
| No log | 70.0 | 280 | 1.2192 |
|
117 |
+
| No log | 71.0 | 284 | 1.2031 |
|
118 |
+
| No log | 72.0 | 288 | 1.2139 |
|
119 |
+
| No log | 73.0 | 292 | 1.2196 |
|
120 |
+
| No log | 74.0 | 296 | 1.2374 |
|
121 |
+
| No log | 75.0 | 300 | 1.2325 |
|
122 |
+
| No log | 76.0 | 304 | 1.2169 |
|
123 |
+
| No log | 77.0 | 308 | 1.2152 |
|
124 |
+
| No log | 78.0 | 312 | 1.2238 |
|
125 |
+
| No log | 79.0 | 316 | 1.2258 |
|
126 |
+
| No log | 80.0 | 320 | 1.2208 |
|
127 |
+
| No log | 81.0 | 324 | 1.2250 |
|
128 |
+
| No log | 82.0 | 328 | 1.2251 |
|
129 |
+
| No log | 83.0 | 332 | 1.2254 |
|
130 |
+
| No log | 84.0 | 336 | 1.2104 |
|
131 |
+
| No log | 85.0 | 340 | 1.2003 |
|
132 |
+
| No log | 86.0 | 344 | 1.2023 |
|
133 |
+
| No log | 87.0 | 348 | 1.2176 |
|
134 |
+
| No log | 88.0 | 352 | 1.2245 |
|
135 |
+
| No log | 89.0 | 356 | 1.2248 |
|
136 |
+
| No log | 90.0 | 360 | 1.2203 |
|
137 |
+
| No log | 91.0 | 364 | 1.2138 |
|
138 |
+
| No log | 92.0 | 368 | 1.2116 |
|
139 |
+
| No log | 93.0 | 372 | 1.2097 |
|
140 |
+
| No log | 94.0 | 376 | 1.2159 |
|
141 |
+
| No log | 95.0 | 380 | 1.2224 |
|
142 |
+
| No log | 96.0 | 384 | 1.2220 |
|
143 |
+
| No log | 97.0 | 388 | 1.2182 |
|
144 |
+
| No log | 98.0 | 392 | 1.2128 |
|
145 |
+
| No log | 99.0 | 396 | 1.2107 |
|
146 |
+
| No log | 100.0 | 400 | 1.2100 |
|
147 |
|
148 |
|
149 |
### Framework versions
|
emissions.csv
CHANGED
@@ -1,2 +1,2 @@
|
|
1 |
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
-
2024-03-
|
|
|
1 |
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2024-03-06T13:39:15,codecarbon,e7ce0efc-76fc-4437-ac5e-e6a73e29f25b,366.31281542778015,0.054828438666223354,0.00014967655063390206,112.5,1072.152,377.88994789123535,0.011447098836302757,0.10490885600820554,0.03838807004344049,0.1547440248879488,Germany,DEU,free and hanseatic city of hamburg,,,Linux-6.5.0-21-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7065277099609,machine,N,1.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 433992496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fc12ff35826a4f286663fc0f6f9522b0c98b518cdff57e00cfe969020845176
|
3 |
size 433992496
|
runs/Mar06_13-33-03_hcdsgpu2/events.out.tfevents.1709731988.hcdsgpu2.1078775.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad46f88e2e7bb3c926b83a3b21c65bd33054c050955c320a55aa30a0e4274001
|
3 |
+
size 31943
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bbd2cd65b5982e96be4b4096be78896cc37888fa1e837b1ef585853f5de81da
|
3 |
size 4920
|