Training in progress, epoch 3
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f731ca782b6dbade195e1404a644a857523c3712efbc5155bda0fab320167353
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78275d0c4fb8c347882bfa5a0cba1ea5cd9a1d38dcecf67972864891e14a1937
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:178b282610de3e0386f2bf28ac0f7be9e257c9b5065b7b5e5feade0ad46c55ec
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac6434dc335625b6fac58fe1f5ffd681aeaf112fea777a5cc3de6edc4720274b
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -144,3 +144,77 @@
|
|
| 144 |
{"current_steps": 144, "total_steps": 219, "loss": 0.2838, "lr": 3.169760928381127e-06, "epoch": 1.9726027397260273, "percentage": 65.75, "elapsed_time": "0:04:17", "remaining_time": "0:02:14"}
|
| 145 |
{"current_steps": 145, "total_steps": 219, "loss": 0.2582, "lr": 3.0957949241371845e-06, "epoch": 1.9863013698630136, "percentage": 66.21, "elapsed_time": "0:04:18", "remaining_time": "0:02:12"}
|
| 146 |
{"current_steps": 146, "total_steps": 219, "loss": 0.2092, "lr": 3.0223131723220756e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:20", "remaining_time": "0:02:10"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
{"current_steps": 144, "total_steps": 219, "loss": 0.2838, "lr": 3.169760928381127e-06, "epoch": 1.9726027397260273, "percentage": 65.75, "elapsed_time": "0:04:17", "remaining_time": "0:02:14"}
|
| 145 |
{"current_steps": 145, "total_steps": 219, "loss": 0.2582, "lr": 3.0957949241371845e-06, "epoch": 1.9863013698630136, "percentage": 66.21, "elapsed_time": "0:04:18", "remaining_time": "0:02:12"}
|
| 146 |
{"current_steps": 146, "total_steps": 219, "loss": 0.2092, "lr": 3.0223131723220756e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:20", "remaining_time": "0:02:10"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 219, "loss": 0.2165, "lr": 2.949334359849957e-06, "epoch": 2.0136986301369864, "percentage": 67.12, "elapsed_time": "0:05:19", "remaining_time": "0:02:36"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 219, "loss": 0.2247, "lr": 2.876877045734058e-06, "epoch": 2.0273972602739727, "percentage": 67.58, "elapsed_time": "0:05:20", "remaining_time": "0:02:33"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 219, "loss": 0.1997, "lr": 2.8049596563669936e-06, "epoch": 2.041095890410959, "percentage": 68.04, "elapsed_time": "0:05:22", "remaining_time": "0:02:31"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 219, "loss": 0.2302, "lr": 2.7336004808348094e-06, "epoch": 2.0547945205479454, "percentage": 68.49, "elapsed_time": "0:05:23", "remaining_time": "0:02:28"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 219, "loss": 0.2337, "lr": 2.662817666265932e-06, "epoch": 2.0684931506849313, "percentage": 68.95, "elapsed_time": "0:05:24", "remaining_time": "0:02:26"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 219, "loss": 0.2303, "lr": 2.5926292132162432e-06, "epoch": 2.0821917808219177, "percentage": 69.41, "elapsed_time": "0:05:26", "remaining_time": "0:02:23"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 219, "loss": 0.2373, "lr": 2.5230529710914074e-06, "epoch": 2.095890410958904, "percentage": 69.86, "elapsed_time": "0:05:27", "remaining_time": "0:02:21"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 219, "loss": 0.1983, "lr": 2.4541066336076434e-06, "epoch": 2.1095890410958904, "percentage": 70.32, "elapsed_time": "0:05:28", "remaining_time": "0:02:18"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 219, "loss": 0.3069, "lr": 2.385807734292097e-06, "epoch": 2.1232876712328768, "percentage": 70.78, "elapsed_time": "0:05:30", "remaining_time": "0:02:16"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 219, "loss": 0.2487, "lr": 2.318173642023939e-06, "epoch": 2.136986301369863, "percentage": 71.23, "elapsed_time": "0:05:31", "remaining_time": "0:02:13"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 219, "loss": 0.2513, "lr": 2.251221556617344e-06, "epoch": 2.1506849315068495, "percentage": 71.69, "elapsed_time": "0:05:33", "remaining_time": "0:02:11"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 219, "loss": 0.2337, "lr": 2.184968504447453e-06, "epoch": 2.1643835616438354, "percentage": 72.15, "elapsed_time": "0:05:34", "remaining_time": "0:02:09"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 219, "loss": 0.1819, "lr": 2.11943133412046e-06, "epoch": 2.1780821917808217, "percentage": 72.6, "elapsed_time": "0:05:36", "remaining_time": "0:02:06"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 219, "loss": 0.2157, "lr": 2.0546267121888863e-06, "epoch": 2.191780821917808, "percentage": 73.06, "elapsed_time": "0:05:38", "remaining_time": "0:02:04"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 219, "loss": 0.2337, "lr": 1.990571118913166e-06, "epoch": 2.2054794520547945, "percentage": 73.52, "elapsed_time": "0:05:40", "remaining_time": "0:02:02"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 219, "loss": 0.2319, "lr": 1.9272808440706024e-06, "epoch": 2.219178082191781, "percentage": 73.97, "elapsed_time": "0:05:41", "remaining_time": "0:02:00"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 219, "loss": 0.2067, "lr": 1.864771982812763e-06, "epoch": 2.232876712328767, "percentage": 74.43, "elapsed_time": "0:05:42", "remaining_time": "0:01:57"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 219, "loss": 0.1983, "lr": 1.8030604315723765e-06, "epoch": 2.2465753424657535, "percentage": 74.89, "elapsed_time": "0:05:44", "remaining_time": "0:01:55"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 219, "loss": 0.2062, "lr": 1.7421618840207576e-06, "epoch": 2.26027397260274, "percentage": 75.34, "elapsed_time": "0:05:45", "remaining_time": "0:01:53"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 219, "loss": 0.2391, "lr": 1.682091827076796e-06, "epoch": 2.2739726027397262, "percentage": 75.8, "elapsed_time": "0:05:46", "remaining_time": "0:01:50"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 219, "loss": 0.2615, "lr": 1.6228655369685342e-06, "epoch": 2.287671232876712, "percentage": 76.26, "elapsed_time": "0:05:48", "remaining_time": "0:01:48"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 219, "loss": 0.2346, "lr": 1.5644980753483109e-06, "epoch": 2.3013698630136985, "percentage": 76.71, "elapsed_time": "0:05:49", "remaining_time": "0:01:46"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 219, "loss": 0.2281, "lr": 1.5070042854624833e-06, "epoch": 2.315068493150685, "percentage": 77.17, "elapsed_time": "0:05:50", "remaining_time": "0:01:43"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 219, "loss": 0.2411, "lr": 1.4503987883766857e-06, "epoch": 2.328767123287671, "percentage": 77.63, "elapsed_time": "0:05:52", "remaining_time": "0:01:41"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 219, "loss": 0.214, "lr": 1.3946959792575915e-06, "epoch": 2.3424657534246576, "percentage": 78.08, "elapsed_time": "0:05:53", "remaining_time": "0:01:39"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 219, "loss": 0.1733, "lr": 1.3399100237121266e-06, "epoch": 2.356164383561644, "percentage": 78.54, "elapsed_time": "0:05:54", "remaining_time": "0:01:36"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 219, "loss": 0.191, "lr": 1.2860548541850542e-06, "epoch": 2.3698630136986303, "percentage": 79.0, "elapsed_time": "0:05:56", "remaining_time": "0:01:34"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 219, "loss": 0.2372, "lr": 1.233144166415861e-06, "epoch": 2.383561643835616, "percentage": 79.45, "elapsed_time": "0:05:57", "remaining_time": "0:01:32"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 219, "loss": 0.187, "lr": 1.1811914159558374e-06, "epoch": 2.3972602739726026, "percentage": 79.91, "elapsed_time": "0:05:58", "remaining_time": "0:01:30"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 219, "loss": 0.2357, "lr": 1.1302098147462348e-06, "epoch": 2.410958904109589, "percentage": 80.37, "elapsed_time": "0:06:00", "remaining_time": "0:01:27"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 219, "loss": 0.2322, "lr": 1.080212327758382e-06, "epoch": 2.4246575342465753, "percentage": 80.82, "elapsed_time": "0:06:01", "remaining_time": "0:01:25"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 219, "loss": 0.1893, "lr": 1.0312116696966012e-06, "epoch": 2.4383561643835616, "percentage": 81.28, "elapsed_time": "0:06:02", "remaining_time": "0:01:23"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 219, "loss": 0.2097, "lr": 9.832203017647746e-07, "epoch": 2.452054794520548, "percentage": 81.74, "elapsed_time": "0:06:04", "remaining_time": "0:01:21"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 219, "loss": 0.187, "lr": 9.362504284973683e-07, "epoch": 2.4657534246575343, "percentage": 82.19, "elapsed_time": "0:06:05", "remaining_time": "0:01:19"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 219, "loss": 0.2157, "lr": 8.903139946557437e-07, "epoch": 2.4794520547945207, "percentage": 82.65, "elapsed_time": "0:06:06", "remaining_time": "0:01:16"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 219, "loss": 0.2315, "lr": 8.454226821905171e-07, "epoch": 2.493150684931507, "percentage": 83.11, "elapsed_time": "0:06:07", "remaining_time": "0:01:14"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 219, "loss": 0.2128, "lr": 8.015879072707611e-07, "epoch": 2.506849315068493, "percentage": 83.56, "elapsed_time": "0:06:09", "remaining_time": "0:01:12"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 219, "loss": 0.21, "lr": 7.588208173807943e-07, "epoch": 2.5205479452054793, "percentage": 84.02, "elapsed_time": "0:06:10", "remaining_time": "0:01:10"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 219, "loss": 0.227, "lr": 7.171322884852988e-07, "epoch": 2.5342465753424657, "percentage": 84.47, "elapsed_time": "0:06:11", "remaining_time": "0:01:08"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 219, "loss": 0.2004, "lr": 6.765329222634892e-07, "epoch": 2.547945205479452, "percentage": 84.93, "elapsed_time": "0:06:13", "remaining_time": "0:01:06"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 219, "loss": 0.2319, "lr": 6.370330434130317e-07, "epoch": 2.5616438356164384, "percentage": 85.39, "elapsed_time": "0:06:14", "remaining_time": "0:01:04"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 219, "loss": 0.242, "lr": 5.986426970244009e-07, "epoch": 2.5753424657534247, "percentage": 85.84, "elapsed_time": "0:06:15", "remaining_time": "0:01:01"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 219, "loss": 0.1823, "lr": 5.613716460263485e-07, "epoch": 2.589041095890411, "percentage": 86.3, "elapsed_time": "0:06:17", "remaining_time": "0:00:59"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 219, "loss": 0.2112, "lr": 5.252293687031196e-07, "epoch": 2.602739726027397, "percentage": 86.76, "elapsed_time": "0:06:18", "remaining_time": "0:00:57"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 219, "loss": 0.2016, "lr": 4.902250562840622e-07, "epoch": 2.616438356164384, "percentage": 87.21, "elapsed_time": "0:06:20", "remaining_time": "0:00:55"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 219, "loss": 0.2507, "lr": 4.5636761060623314e-07, "epoch": 2.6301369863013697, "percentage": 87.67, "elapsed_time": "0:06:21", "remaining_time": "0:00:53"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 219, "loss": 0.2042, "lr": 4.2366564185060134e-07, "epoch": 2.643835616438356, "percentage": 88.13, "elapsed_time": "0:06:22", "remaining_time": "0:00:51"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 219, "loss": 0.2087, "lr": 3.921274663524183e-07, "epoch": 2.6575342465753424, "percentage": 88.58, "elapsed_time": "0:06:24", "remaining_time": "0:00:49"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 219, "loss": 0.2578, "lr": 3.61761104486314e-07, "epoch": 2.671232876712329, "percentage": 89.04, "elapsed_time": "0:06:25", "remaining_time": "0:00:47"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 219, "loss": 0.2471, "lr": 3.3257427862666894e-07, "epoch": 2.684931506849315, "percentage": 89.5, "elapsed_time": "0:06:26", "remaining_time": "0:00:45"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 219, "loss": 0.2304, "lr": 3.045744111837529e-07, "epoch": 2.6986301369863015, "percentage": 89.95, "elapsed_time": "0:06:28", "remaining_time": "0:00:43"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 219, "loss": 0.1633, "lr": 2.777686227161591e-07, "epoch": 2.712328767123288, "percentage": 90.41, "elapsed_time": "0:06:29", "remaining_time": "0:00:41"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 219, "loss": 0.2266, "lr": 2.5216373011999697e-07, "epoch": 2.7260273972602738, "percentage": 90.87, "elapsed_time": "0:06:30", "remaining_time": "0:00:39"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 219, "loss": 0.234, "lr": 2.2776624489530664e-07, "epoch": 2.73972602739726, "percentage": 91.32, "elapsed_time": "0:06:31", "remaining_time": "0:00:37"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 219, "loss": 0.2286, "lr": 2.0458237149014347e-07, "epoch": 2.7534246575342465, "percentage": 91.78, "elapsed_time": "0:06:33", "remaining_time": "0:00:35"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 219, "loss": 0.2296, "lr": 1.8261800572274001e-07, "epoch": 2.767123287671233, "percentage": 92.24, "elapsed_time": "0:06:34", "remaining_time": "0:00:33"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 219, "loss": 0.2116, "lr": 1.6187873328216142e-07, "epoch": 2.780821917808219, "percentage": 92.69, "elapsed_time": "0:06:35", "remaining_time": "0:00:31"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 219, "loss": 0.2032, "lr": 1.4236982830782676e-07, "epoch": 2.7945205479452055, "percentage": 93.15, "elapsed_time": "0:06:37", "remaining_time": "0:00:29"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 219, "loss": 0.2345, "lr": 1.2409625204825802e-07, "epoch": 2.808219178082192, "percentage": 93.61, "elapsed_time": "0:06:38", "remaining_time": "0:00:27"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 219, "loss": 0.19, "lr": 1.0706265159939944e-07, "epoch": 2.821917808219178, "percentage": 94.06, "elapsed_time": "0:06:39", "remaining_time": "0:00:25"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 219, "loss": 0.1803, "lr": 9.12733587228326e-08, "epoch": 2.8356164383561646, "percentage": 94.52, "elapsed_time": "0:06:41", "remaining_time": "0:00:23"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 219, "loss": 0.1956, "lr": 7.673238874417676e-08, "epoch": 2.8493150684931505, "percentage": 94.98, "elapsed_time": "0:06:42", "remaining_time": "0:00:21"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 219, "loss": 0.2221, "lr": 6.344343953196386e-08, "epoch": 2.863013698630137, "percentage": 95.43, "elapsed_time": "0:06:43", "remaining_time": "0:00:19"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 219, "loss": 0.2437, "lr": 5.1409890557246876e-08, "epoch": 2.8767123287671232, "percentage": 95.89, "elapsed_time": "0:06:45", "remaining_time": "0:00:17"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 219, "loss": 0.2314, "lr": 4.063480203417625e-08, "epoch": 2.8904109589041096, "percentage": 96.35, "elapsed_time": "0:06:46", "remaining_time": "0:00:15"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 219, "loss": 0.249, "lr": 3.1120914141766214e-08, "epoch": 2.904109589041096, "percentage": 96.8, "elapsed_time": "0:06:47", "remaining_time": "0:00:13"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 219, "loss": 0.2131, "lr": 2.287064632705005e-08, "epoch": 2.9178082191780823, "percentage": 97.26, "elapsed_time": "0:06:49", "remaining_time": "0:00:11"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 219, "loss": 0.2178, "lr": 1.588609668979446e-08, "epoch": 2.9315068493150687, "percentage": 97.72, "elapsed_time": "0:06:50", "remaining_time": "0:00:09"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 219, "loss": 0.2207, "lr": 1.016904144894304e-08, "epoch": 2.9452054794520546, "percentage": 98.17, "elapsed_time": "0:06:52", "remaining_time": "0:00:07"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 219, "loss": 0.2142, "lr": 5.720934490907604e-09, "epoch": 2.958904109589041, "percentage": 98.63, "elapsed_time": "0:06:53", "remaining_time": "0:00:05"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 219, "loss": 0.2298, "lr": 2.542906999836725e-09, "epoch": 2.9726027397260273, "percentage": 99.09, "elapsed_time": "0:06:54", "remaining_time": "0:00:03"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 219, "loss": 0.2056, "lr": 6.357671699486201e-10, "epoch": 2.9863013698630136, "percentage": 99.54, "elapsed_time": "0:06:56", "remaining_time": "0:00:01"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 219, "loss": 0.1987, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:57", "remaining_time": "0:00:00"}
|
| 220 |
+
{"current_steps": 219, "total_steps": 219, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:06", "remaining_time": "0:00:00"}
|