Training in progress, epoch 1
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 sha256:2f3c971660901a1655ee18c29f3c53e3dc71935e9e4c7275a11efdccfc6b94dd
|
| 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:ea615d92e25de72d20fe37daf50e674ce5448f14772bbd012547d33e2638b481
|
| 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:dca65352e4675b8c82bb0a8db1b8c2c43f1e375990c7619700ce6d3c87cb7fea
|
| 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 sha256:24eb1b719b3e939488a63aa320db2f244c67c1215c41830be868bfc7fbfb2a7f
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -166,3 +166,169 @@
|
|
| 166 |
{"current_steps": 166, "total_steps": 498, "loss": 0.9096, "lr": 8.43498463017451e-06, "epoch": 0.996, "percentage": 33.33, "elapsed_time": "2:32:57", "remaining_time": "5:05:54"}
|
| 167 |
{"current_steps": 167, "total_steps": 498, "loss": 1.4196, "lr": 8.409421913817526e-06, "epoch": 1.004, "percentage": 33.53, "elapsed_time": "2:35:03", "remaining_time": "5:07:19"}
|
| 168 |
{"current_steps": 168, "total_steps": 498, "loss": 0.7903, "lr": 8.383691540076372e-06, "epoch": 1.01, "percentage": 33.73, "elapsed_time": "2:36:01", "remaining_time": "5:06:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
{"current_steps": 166, "total_steps": 498, "loss": 0.9096, "lr": 8.43498463017451e-06, "epoch": 0.996, "percentage": 33.33, "elapsed_time": "2:32:57", "remaining_time": "5:05:54"}
|
| 167 |
{"current_steps": 167, "total_steps": 498, "loss": 1.4196, "lr": 8.409421913817526e-06, "epoch": 1.004, "percentage": 33.53, "elapsed_time": "2:35:03", "remaining_time": "5:07:19"}
|
| 168 |
{"current_steps": 168, "total_steps": 498, "loss": 0.7903, "lr": 8.383691540076372e-06, "epoch": 1.01, "percentage": 33.73, "elapsed_time": "2:36:01", "remaining_time": "5:06:29"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 498, "loss": 0.8664, "lr": 8.357794774235094e-06, "epoch": 1.016, "percentage": 33.94, "elapsed_time": "2:36:56", "remaining_time": "5:05:30"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 498, "loss": 0.7368, "lr": 8.331732889760021e-06, "epoch": 1.022, "percentage": 34.14, "elapsed_time": "2:37:54", "remaining_time": "5:04:39"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 498, "loss": 0.9978, "lr": 8.305507168237152e-06, "epoch": 1.028, "percentage": 34.34, "elapsed_time": "2:39:01", "remaining_time": "5:04:05"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 498, "loss": 0.7603, "lr": 8.279118899309121e-06, "epoch": 1.034, "percentage": 34.54, "elapsed_time": "2:39:51", "remaining_time": "5:02:58"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 498, "loss": 0.8794, "lr": 8.252569380611793e-06, "epoch": 1.04, "percentage": 34.74, "elapsed_time": "2:40:52", "remaining_time": "5:02:12"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 498, "loss": 0.7344, "lr": 8.22585991771044e-06, "epoch": 1.046, "percentage": 34.94, "elapsed_time": "2:41:37", "remaining_time": "5:00:56"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 498, "loss": 0.7881, "lr": 8.198991824035546e-06, "epoch": 1.052, "percentage": 35.14, "elapsed_time": "2:42:24", "remaining_time": "4:59:46"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 498, "loss": 0.8771, "lr": 8.171966420818227e-06, "epoch": 1.058, "percentage": 35.34, "elapsed_time": "2:43:22", "remaining_time": "4:58:54"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 498, "loss": 0.9245, "lr": 8.144785037025246e-06, "epoch": 1.064, "percentage": 35.54, "elapsed_time": "2:44:23", "remaining_time": "4:58:07"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 498, "loss": 0.7209, "lr": 8.117449009293668e-06, "epoch": 1.07, "percentage": 35.74, "elapsed_time": "2:45:11", "remaining_time": "4:56:57"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 498, "loss": 0.9277, "lr": 8.089959681865134e-06, "epoch": 1.076, "percentage": 35.94, "elapsed_time": "2:46:08", "remaining_time": "4:56:04"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 498, "loss": 0.7997, "lr": 8.062318406519751e-06, "epoch": 1.082, "percentage": 36.14, "elapsed_time": "2:46:52", "remaining_time": "4:54:49"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 498, "loss": 0.792, "lr": 8.034526542509629e-06, "epoch": 1.088, "percentage": 36.35, "elapsed_time": "2:47:40", "remaining_time": "4:53:39"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 498, "loss": 0.9122, "lr": 8.00658545649203e-06, "epoch": 1.094, "percentage": 36.55, "elapsed_time": "2:48:38", "remaining_time": "4:52:48"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 498, "loss": 0.8256, "lr": 7.978496522462167e-06, "epoch": 1.1, "percentage": 36.75, "elapsed_time": "2:49:39", "remaining_time": "4:52:02"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 498, "loss": 0.8305, "lr": 7.950261121685642e-06, "epoch": 1.106, "percentage": 36.95, "elapsed_time": "2:50:38", "remaining_time": "4:51:13"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 498, "loss": 0.8153, "lr": 7.921880642630514e-06, "epoch": 1.112, "percentage": 37.15, "elapsed_time": "2:51:30", "remaining_time": "4:50:10"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 498, "loss": 0.803, "lr": 7.89335648089903e-06, "epoch": 1.1179999999999999, "percentage": 37.35, "elapsed_time": "2:52:12", "remaining_time": "4:48:52"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 498, "loss": 0.8451, "lr": 7.864690039158991e-06, "epoch": 1.124, "percentage": 37.55, "elapsed_time": "2:53:02", "remaining_time": "4:47:47"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 498, "loss": 0.8614, "lr": 7.835882727074779e-06, "epoch": 1.13, "percentage": 37.75, "elapsed_time": "2:53:52", "remaining_time": "4:46:43"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 498, "loss": 0.8056, "lr": 7.806935961238041e-06, "epoch": 1.1360000000000001, "percentage": 37.95, "elapsed_time": "2:54:53", "remaining_time": "4:45:55"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 498, "loss": 0.7189, "lr": 7.777851165098012e-06, "epoch": 1.142, "percentage": 38.15, "elapsed_time": "2:55:43", "remaining_time": "4:44:52"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 498, "loss": 0.9553, "lr": 7.748629768891542e-06, "epoch": 1.148, "percentage": 38.35, "elapsed_time": "2:56:47", "remaining_time": "4:44:09"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 498, "loss": 0.8351, "lr": 7.719273209572745e-06, "epoch": 1.154, "percentage": 38.55, "elapsed_time": "2:57:41", "remaining_time": "4:43:12"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 498, "loss": 0.7966, "lr": 7.689782930742345e-06, "epoch": 1.16, "percentage": 38.76, "elapsed_time": "2:58:33", "remaining_time": "4:42:10"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 498, "loss": 0.8904, "lr": 7.660160382576683e-06, "epoch": 1.166, "percentage": 38.96, "elapsed_time": "2:59:31", "remaining_time": "4:41:19"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 498, "loss": 0.7649, "lr": 7.630407021756419e-06, "epoch": 1.172, "percentage": 39.16, "elapsed_time": "3:00:30", "remaining_time": "4:40:28"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 498, "loss": 0.8274, "lr": 7.600524311394873e-06, "epoch": 1.178, "percentage": 39.36, "elapsed_time": "3:01:17", "remaining_time": "4:39:20"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 498, "loss": 0.7915, "lr": 7.570513720966108e-06, "epoch": 1.184, "percentage": 39.56, "elapsed_time": "3:02:07", "remaining_time": "4:38:15"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 498, "loss": 0.8471, "lr": 7.540376726232648e-06, "epoch": 1.19, "percentage": 39.76, "elapsed_time": "3:02:58", "remaining_time": "4:37:14"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 498, "loss": 0.8698, "lr": 7.51011480917291e-06, "epoch": 1.196, "percentage": 39.96, "elapsed_time": "3:03:49", "remaining_time": "4:36:12"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 498, "loss": 0.9333, "lr": 7.4797294579083405e-06, "epoch": 1.202, "percentage": 40.16, "elapsed_time": "3:04:50", "remaining_time": "4:35:25"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 498, "loss": 0.8904, "lr": 7.449222166630218e-06, "epoch": 1.208, "percentage": 40.36, "elapsed_time": "3:05:51", "remaining_time": "4:34:38"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 498, "loss": 0.7593, "lr": 7.4185944355261996e-06, "epoch": 1.214, "percentage": 40.56, "elapsed_time": "3:06:51", "remaining_time": "4:33:48"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 498, "loss": 0.7174, "lr": 7.3878477707065314e-06, "epoch": 1.22, "percentage": 40.76, "elapsed_time": "3:07:47", "remaining_time": "4:32:54"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 498, "loss": 0.9422, "lr": 7.3569836841299905e-06, "epoch": 1.226, "percentage": 40.96, "elapsed_time": "3:08:50", "remaining_time": "4:32:08"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 498, "loss": 0.7474, "lr": 7.326003693529538e-06, "epoch": 1.232, "percentage": 41.16, "elapsed_time": "3:09:40", "remaining_time": "4:31:05"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 498, "loss": 0.8327, "lr": 7.294909322337689e-06, "epoch": 1.238, "percentage": 41.37, "elapsed_time": "3:10:31", "remaining_time": "4:30:03"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 498, "loss": 0.8315, "lr": 7.263702099611586e-06, "epoch": 1.244, "percentage": 41.57, "elapsed_time": "3:11:29", "remaining_time": "4:29:12"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 498, "loss": 0.8018, "lr": 7.232383559957815e-06, "epoch": 1.25, "percentage": 41.77, "elapsed_time": "3:12:20", "remaining_time": "4:28:10"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 498, "loss": 0.8009, "lr": 7.200955243456946e-06, "epoch": 1.256, "percentage": 41.97, "elapsed_time": "3:13:11", "remaining_time": "4:27:08"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 498, "loss": 0.8355, "lr": 7.169418695587791e-06, "epoch": 1.262, "percentage": 42.17, "elapsed_time": "3:14:07", "remaining_time": "4:26:13"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 498, "loss": 0.8522, "lr": 7.137775467151411e-06, "epoch": 1.268, "percentage": 42.37, "elapsed_time": "3:15:05", "remaining_time": "4:25:21"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 498, "loss": 0.8511, "lr": 7.106027114194856e-06, "epoch": 1.274, "percentage": 42.57, "elapsed_time": "3:15:57", "remaining_time": "4:24:22"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 498, "loss": 0.8573, "lr": 7.0741751979346395e-06, "epoch": 1.28, "percentage": 42.77, "elapsed_time": "3:16:54", "remaining_time": "4:23:28"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 498, "loss": 0.8298, "lr": 7.042221284679982e-06, "epoch": 1.286, "percentage": 42.97, "elapsed_time": "3:17:56", "remaining_time": "4:22:40"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 498, "loss": 0.8252, "lr": 7.010166945755768e-06, "epoch": 1.292, "percentage": 43.17, "elapsed_time": "3:18:56", "remaining_time": "4:21:52"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 498, "loss": 0.8492, "lr": 6.978013757425295e-06, "epoch": 1.298, "percentage": 43.37, "elapsed_time": "3:19:50", "remaining_time": "4:20:54"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 498, "loss": 0.8621, "lr": 6.945763300812746e-06, "epoch": 1.304, "percentage": 43.57, "elapsed_time": "3:20:48", "remaining_time": "4:20:02"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 498, "loss": 0.7941, "lr": 6.913417161825449e-06, "epoch": 1.31, "percentage": 43.78, "elapsed_time": "3:21:46", "remaining_time": "4:19:09"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 498, "loss": 0.9207, "lr": 6.880976931075887e-06, "epoch": 1.316, "percentage": 43.98, "elapsed_time": "3:22:52", "remaining_time": "4:18:27"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 498, "loss": 0.7331, "lr": 6.848444203803476e-06, "epoch": 1.322, "percentage": 44.18, "elapsed_time": "3:23:38", "remaining_time": "4:17:19"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 498, "loss": 0.9655, "lr": 6.8158205797961265e-06, "epoch": 1.328, "percentage": 44.38, "elapsed_time": "3:24:33", "remaining_time": "4:16:24"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 498, "loss": 0.6941, "lr": 6.783107663311566e-06, "epoch": 1.334, "percentage": 44.58, "elapsed_time": "3:25:25", "remaining_time": "4:15:23"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 498, "loss": 0.8132, "lr": 6.750307062998462e-06, "epoch": 1.34, "percentage": 44.78, "elapsed_time": "3:26:16", "remaining_time": "4:14:23"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 498, "loss": 0.8235, "lr": 6.717420391817306e-06, "epoch": 1.346, "percentage": 44.98, "elapsed_time": "3:27:16", "remaining_time": "4:13:32"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 498, "loss": 0.816, "lr": 6.684449266961101e-06, "epoch": 1.3519999999999999, "percentage": 45.18, "elapsed_time": "3:28:07", "remaining_time": "4:12:31"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 498, "loss": 0.9069, "lr": 6.651395309775837e-06, "epoch": 1.358, "percentage": 45.38, "elapsed_time": "3:29:02", "remaining_time": "4:11:35"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 498, "loss": 0.7992, "lr": 6.618260145680758e-06, "epoch": 1.3639999999999999, "percentage": 45.58, "elapsed_time": "3:29:58", "remaining_time": "4:10:40"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 498, "loss": 0.7207, "lr": 6.585045404088442e-06, "epoch": 1.37, "percentage": 45.78, "elapsed_time": "3:30:42", "remaining_time": "4:09:30"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 498, "loss": 0.8031, "lr": 6.55175271832466e-06, "epoch": 1.376, "percentage": 45.98, "elapsed_time": "3:31:31", "remaining_time": "4:08:28"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 498, "loss": 0.8563, "lr": 6.518383725548074e-06, "epoch": 1.3820000000000001, "percentage": 46.18, "elapsed_time": "3:32:31", "remaining_time": "4:07:38"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 498, "loss": 0.8494, "lr": 6.484940066669718e-06, "epoch": 1.388, "percentage": 46.39, "elapsed_time": "3:33:28", "remaining_time": "4:06:44"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 498, "loss": 0.8715, "lr": 6.451423386272312e-06, "epoch": 1.3940000000000001, "percentage": 46.59, "elapsed_time": "3:34:27", "remaining_time": "4:05:53"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 498, "loss": 0.8714, "lr": 6.417835332529389e-06, "epoch": 1.4, "percentage": 46.79, "elapsed_time": "3:35:28", "remaining_time": "4:05:03"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 498, "loss": 0.9023, "lr": 6.384177557124247e-06, "epoch": 1.4060000000000001, "percentage": 46.99, "elapsed_time": "3:36:33", "remaining_time": "4:04:19"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 498, "loss": 0.7481, "lr": 6.350451715168728e-06, "epoch": 1.412, "percentage": 47.19, "elapsed_time": "3:37:25", "remaining_time": "4:03:19"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 498, "loss": 0.9063, "lr": 6.3166594651218235e-06, "epoch": 1.418, "percentage": 47.39, "elapsed_time": "3:38:27", "remaining_time": "4:02:31"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 498, "loss": 0.7979, "lr": 6.282802468708133e-06, "epoch": 1.424, "percentage": 47.59, "elapsed_time": "3:39:23", "remaining_time": "4:01:36"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 498, "loss": 0.9127, "lr": 6.248882390836135e-06, "epoch": 1.43, "percentage": 47.79, "elapsed_time": "3:40:22", "remaining_time": "4:00:44"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 498, "loss": 0.7837, "lr": 6.21490089951632e-06, "epoch": 1.436, "percentage": 47.99, "elapsed_time": "3:41:11", "remaining_time": "3:59:42"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 498, "loss": 0.8533, "lr": 6.180859665779173e-06, "epoch": 1.442, "percentage": 48.19, "elapsed_time": "3:42:05", "remaining_time": "3:58:44"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 498, "loss": 0.8272, "lr": 6.14676036359299e-06, "epoch": 1.448, "percentage": 48.39, "elapsed_time": "3:43:00", "remaining_time": "3:57:48"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 498, "loss": 0.8428, "lr": 6.112604669781572e-06, "epoch": 1.454, "percentage": 48.59, "elapsed_time": "3:44:08", "remaining_time": "3:57:06"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 498, "loss": 0.8013, "lr": 6.078394263941762e-06, "epoch": 1.46, "percentage": 48.8, "elapsed_time": "3:45:02", "remaining_time": "3:56:09"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 498, "loss": 0.8215, "lr": 6.04413082836085e-06, "epoch": 1.466, "percentage": 49.0, "elapsed_time": "3:45:59", "remaining_time": "3:55:15"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 498, "loss": 0.87, "lr": 6.009816047933849e-06, "epoch": 1.472, "percentage": 49.2, "elapsed_time": "3:46:58", "remaining_time": "3:54:22"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 498, "loss": 0.7694, "lr": 5.975451610080643e-06, "epoch": 1.478, "percentage": 49.4, "elapsed_time": "3:47:52", "remaining_time": "3:53:25"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 498, "loss": 0.9321, "lr": 5.941039204663001e-06, "epoch": 1.484, "percentage": 49.6, "elapsed_time": "3:48:50", "remaining_time": "3:52:32"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 498, "loss": 0.7809, "lr": 5.906580523901493e-06, "epoch": 1.49, "percentage": 49.8, "elapsed_time": "3:49:40", "remaining_time": "3:51:31"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 498, "loss": 0.8733, "lr": 5.872077262292255e-06, "epoch": 1.496, "percentage": 50.0, "elapsed_time": "3:50:34", "remaining_time": "3:50:34"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 498, "loss": 0.7802, "lr": 5.837531116523683e-06, "epoch": 1.502, "percentage": 50.2, "elapsed_time": "3:51:32", "remaining_time": "3:49:41"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 498, "loss": 0.8852, "lr": 5.802943785392986e-06, "epoch": 1.508, "percentage": 50.4, "elapsed_time": "3:52:30", "remaining_time": "3:48:47"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 498, "loss": 0.795, "lr": 5.768316969722651e-06, "epoch": 1.514, "percentage": 50.6, "elapsed_time": "3:53:18", "remaining_time": "3:47:45"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 498, "loss": 0.8377, "lr": 5.733652372276809e-06, "epoch": 1.52, "percentage": 50.8, "elapsed_time": "3:54:18", "remaining_time": "3:46:54"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 498, "loss": 0.8324, "lr": 5.698951697677498e-06, "epoch": 1.526, "percentage": 51.0, "elapsed_time": "3:55:15", "remaining_time": "3:45:59"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 498, "loss": 0.8394, "lr": 5.66421665232084e-06, "epoch": 1.532, "percentage": 51.2, "elapsed_time": "3:56:11", "remaining_time": "3:45:04"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 498, "loss": 0.8914, "lr": 5.629448944293128e-06, "epoch": 1.538, "percentage": 51.41, "elapsed_time": "3:57:05", "remaining_time": "3:44:07"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 498, "loss": 0.8513, "lr": 5.594650283286835e-06, "epoch": 1.544, "percentage": 51.61, "elapsed_time": "3:58:02", "remaining_time": "3:43:12"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 498, "loss": 0.8624, "lr": 5.559822380516539e-06, "epoch": 1.55, "percentage": 51.81, "elapsed_time": "3:59:05", "remaining_time": "3:42:24"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 498, "loss": 0.7434, "lr": 5.524966948634774e-06, "epoch": 1.556, "percentage": 52.01, "elapsed_time": "3:59:59", "remaining_time": "3:41:27"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 498, "loss": 0.8681, "lr": 5.490085701647805e-06, "epoch": 1.562, "percentage": 52.21, "elapsed_time": "4:00:50", "remaining_time": "3:40:27"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 498, "loss": 0.7842, "lr": 5.4551803548313505e-06, "epoch": 1.568, "percentage": 52.41, "elapsed_time": "4:01:49", "remaining_time": "3:39:35"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 498, "loss": 0.942, "lr": 5.420252624646238e-06, "epoch": 1.5739999999999998, "percentage": 52.61, "elapsed_time": "4:02:43", "remaining_time": "3:38:38"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 498, "loss": 0.8119, "lr": 5.385304228653983e-06, "epoch": 1.58, "percentage": 52.81, "elapsed_time": "4:03:33", "remaining_time": "3:37:37"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 498, "loss": 0.7853, "lr": 5.350336885432337e-06, "epoch": 1.5859999999999999, "percentage": 53.01, "elapsed_time": "4:04:22", "remaining_time": "3:36:36"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 498, "loss": 0.7943, "lr": 5.315352314490781e-06, "epoch": 1.592, "percentage": 53.21, "elapsed_time": "4:05:22", "remaining_time": "3:35:44"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 498, "loss": 0.8226, "lr": 5.2803522361859596e-06, "epoch": 1.5979999999999999, "percentage": 53.41, "elapsed_time": "4:06:14", "remaining_time": "3:34:46"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 498, "loss": 0.9019, "lr": 5.245338371637091e-06, "epoch": 1.604, "percentage": 53.61, "elapsed_time": "4:07:12", "remaining_time": "3:33:52"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 498, "loss": 0.8341, "lr": 5.210312442641327e-06, "epoch": 1.6099999999999999, "percentage": 53.82, "elapsed_time": "4:08:10", "remaining_time": "3:32:59"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 498, "loss": 0.8727, "lr": 5.175276171589082e-06, "epoch": 1.616, "percentage": 54.02, "elapsed_time": "4:09:05", "remaining_time": "3:32:03"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 498, "loss": 0.8318, "lr": 5.140231281379345e-06, "epoch": 1.6219999999999999, "percentage": 54.22, "elapsed_time": "4:10:08", "remaining_time": "3:31:13"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 498, "loss": 0.8061, "lr": 5.1051794953349445e-06, "epoch": 1.6280000000000001, "percentage": 54.42, "elapsed_time": "4:11:00", "remaining_time": "3:30:15"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 498, "loss": 0.8135, "lr": 5.070122537117812e-06, "epoch": 1.634, "percentage": 54.62, "elapsed_time": "4:12:06", "remaining_time": "3:29:27"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 498, "loss": 0.897, "lr": 5.0350621306442185e-06, "epoch": 1.6400000000000001, "percentage": 54.82, "elapsed_time": "4:12:57", "remaining_time": "3:28:28"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 498, "loss": 0.7674, "lr": 5e-06, "epoch": 1.646, "percentage": 55.02, "elapsed_time": "4:13:52", "remaining_time": "3:27:33"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 498, "loss": 0.9136, "lr": 4.964937869355782e-06, "epoch": 1.6520000000000001, "percentage": 55.22, "elapsed_time": "4:14:52", "remaining_time": "3:26:40"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 498, "loss": 0.7627, "lr": 4.92987746288219e-06, "epoch": 1.658, "percentage": 55.42, "elapsed_time": "4:15:38", "remaining_time": "3:25:37"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 498, "loss": 0.8228, "lr": 4.894820504665056e-06, "epoch": 1.6640000000000001, "percentage": 55.62, "elapsed_time": "4:16:34", "remaining_time": "3:24:42"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 498, "loss": 0.8384, "lr": 4.859768718620656e-06, "epoch": 1.67, "percentage": 55.82, "elapsed_time": "4:17:29", "remaining_time": "3:23:46"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 498, "loss": 0.8781, "lr": 4.82472382841092e-06, "epoch": 1.6760000000000002, "percentage": 56.02, "elapsed_time": "4:18:20", "remaining_time": "3:22:46"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 498, "loss": 0.8741, "lr": 4.789687557358676e-06, "epoch": 1.682, "percentage": 56.22, "elapsed_time": "4:19:20", "remaining_time": "3:21:54"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 498, "loss": 0.7455, "lr": 4.75466162836291e-06, "epoch": 1.688, "percentage": 56.43, "elapsed_time": "4:20:06", "remaining_time": "3:20:52"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 498, "loss": 0.8629, "lr": 4.719647763814041e-06, "epoch": 1.694, "percentage": 56.63, "elapsed_time": "4:21:08", "remaining_time": "3:20:01"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 498, "loss": 0.8333, "lr": 4.684647685509221e-06, "epoch": 1.7, "percentage": 56.83, "elapsed_time": "4:22:02", "remaining_time": "3:19:04"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 498, "loss": 0.7671, "lr": 4.649663114567663e-06, "epoch": 1.706, "percentage": 57.03, "elapsed_time": "4:22:44", "remaining_time": "3:17:59"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 498, "loss": 0.8266, "lr": 4.61469577134602e-06, "epoch": 1.712, "percentage": 57.23, "elapsed_time": "4:23:36", "remaining_time": "3:17:01"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 498, "loss": 0.9051, "lr": 4.579747375353763e-06, "epoch": 1.718, "percentage": 57.43, "elapsed_time": "4:24:37", "remaining_time": "3:16:08"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 498, "loss": 0.7786, "lr": 4.54481964516865e-06, "epoch": 1.724, "percentage": 57.63, "elapsed_time": "4:25:28", "remaining_time": "3:15:10"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 498, "loss": 0.7692, "lr": 4.509914298352197e-06, "epoch": 1.73, "percentage": 57.83, "elapsed_time": "4:26:21", "remaining_time": "3:14:12"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 498, "loss": 0.8352, "lr": 4.475033051365228e-06, "epoch": 1.736, "percentage": 58.03, "elapsed_time": "4:27:13", "remaining_time": "3:13:15"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 498, "loss": 0.8252, "lr": 4.4401776194834615e-06, "epoch": 1.742, "percentage": 58.23, "elapsed_time": "4:28:03", "remaining_time": "3:12:15"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 498, "loss": 0.8048, "lr": 4.405349716713165e-06, "epoch": 1.748, "percentage": 58.43, "elapsed_time": "4:28:56", "remaining_time": "3:11:18"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 498, "loss": 0.8922, "lr": 4.3705510557068746e-06, "epoch": 1.754, "percentage": 58.63, "elapsed_time": "4:30:00", "remaining_time": "3:10:29"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 498, "loss": 0.7183, "lr": 4.335783347679162e-06, "epoch": 1.76, "percentage": 58.84, "elapsed_time": "4:30:50", "remaining_time": "3:09:29"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 498, "loss": 0.8822, "lr": 4.3010483023225045e-06, "epoch": 1.766, "percentage": 59.04, "elapsed_time": "4:31:40", "remaining_time": "3:08:30"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 498, "loss": 0.7692, "lr": 4.266347627723192e-06, "epoch": 1.772, "percentage": 59.24, "elapsed_time": "4:32:30", "remaining_time": "3:07:31"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 498, "loss": 0.8841, "lr": 4.231683030277349e-06, "epoch": 1.778, "percentage": 59.44, "elapsed_time": "4:33:22", "remaining_time": "3:06:33"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 498, "loss": 0.7784, "lr": 4.197056214607016e-06, "epoch": 1.784, "percentage": 59.64, "elapsed_time": "4:34:19", "remaining_time": "3:05:39"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 498, "loss": 0.9245, "lr": 4.162468883476319e-06, "epoch": 1.79, "percentage": 59.84, "elapsed_time": "4:35:16", "remaining_time": "3:04:44"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 498, "loss": 0.799, "lr": 4.1279227377077465e-06, "epoch": 1.796, "percentage": 60.04, "elapsed_time": "4:36:09", "remaining_time": "3:03:47"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 498, "loss": 0.7813, "lr": 4.0934194760985095e-06, "epoch": 1.802, "percentage": 60.24, "elapsed_time": "4:36:58", "remaining_time": "3:02:48"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 498, "loss": 0.8129, "lr": 4.058960795337001e-06, "epoch": 1.808, "percentage": 60.44, "elapsed_time": "4:37:49", "remaining_time": "3:01:50"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 498, "loss": 0.7941, "lr": 4.02454838991936e-06, "epoch": 1.814, "percentage": 60.64, "elapsed_time": "4:38:38", "remaining_time": "3:00:50"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 498, "loss": 0.8791, "lr": 3.990183952066151e-06, "epoch": 1.8199999999999998, "percentage": 60.84, "elapsed_time": "4:39:36", "remaining_time": "2:59:56"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 498, "loss": 0.771, "lr": 3.955869171639151e-06, "epoch": 1.826, "percentage": 61.04, "elapsed_time": "4:40:27", "remaining_time": "2:58:58"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 498, "loss": 0.8339, "lr": 3.921605736058238e-06, "epoch": 1.8319999999999999, "percentage": 61.24, "elapsed_time": "4:41:16", "remaining_time": "2:57:59"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 498, "loss": 0.8521, "lr": 3.887395330218429e-06, "epoch": 1.838, "percentage": 61.45, "elapsed_time": "4:42:09", "remaining_time": "2:57:02"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 498, "loss": 0.8309, "lr": 3.853239636407012e-06, "epoch": 1.8439999999999999, "percentage": 61.65, "elapsed_time": "4:42:59", "remaining_time": "2:56:04"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 498, "loss": 0.7261, "lr": 3.81914033422083e-06, "epoch": 1.85, "percentage": 61.85, "elapsed_time": "4:43:57", "remaining_time": "2:55:09"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 498, "loss": 0.8609, "lr": 3.7850991004836813e-06, "epoch": 1.8559999999999999, "percentage": 62.05, "elapsed_time": "4:44:50", "remaining_time": "2:54:13"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 498, "loss": 0.8973, "lr": 3.751117609163865e-06, "epoch": 1.862, "percentage": 62.25, "elapsed_time": "4:45:47", "remaining_time": "2:53:18"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 498, "loss": 0.7725, "lr": 3.7171975312918674e-06, "epoch": 1.8679999999999999, "percentage": 62.45, "elapsed_time": "4:46:40", "remaining_time": "2:52:22"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 498, "loss": 0.7935, "lr": 3.683340534878176e-06, "epoch": 1.874, "percentage": 62.65, "elapsed_time": "4:47:36", "remaining_time": "2:51:27"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 498, "loss": 0.8476, "lr": 3.6495482848312745e-06, "epoch": 1.88, "percentage": 62.85, "elapsed_time": "4:48:38", "remaining_time": "2:50:36"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 498, "loss": 0.8902, "lr": 3.6158224428757538e-06, "epoch": 1.8860000000000001, "percentage": 63.05, "elapsed_time": "4:49:39", "remaining_time": "2:49:44"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 498, "loss": 0.851, "lr": 3.5821646674706124e-06, "epoch": 1.892, "percentage": 63.25, "elapsed_time": "4:50:33", "remaining_time": "2:48:47"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 498, "loss": 0.8573, "lr": 3.5485766137276894e-06, "epoch": 1.8980000000000001, "percentage": 63.45, "elapsed_time": "4:51:41", "remaining_time": "2:48:00"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 498, "loss": 0.7711, "lr": 3.5150599333302826e-06, "epoch": 1.904, "percentage": 63.65, "elapsed_time": "4:52:33", "remaining_time": "2:47:02"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 498, "loss": 0.7175, "lr": 3.4816162744519266e-06, "epoch": 1.9100000000000001, "percentage": 63.86, "elapsed_time": "4:53:20", "remaining_time": "2:46:02"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 498, "loss": 0.8976, "lr": 3.4482472816753404e-06, "epoch": 1.916, "percentage": 64.06, "elapsed_time": "4:54:24", "remaining_time": "2:45:11"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 498, "loss": 0.8046, "lr": 3.4149545959115604e-06, "epoch": 1.9220000000000002, "percentage": 64.26, "elapsed_time": "4:55:25", "remaining_time": "2:44:19"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 498, "loss": 0.872, "lr": 3.3817398543192426e-06, "epoch": 1.928, "percentage": 64.46, "elapsed_time": "4:56:25", "remaining_time": "2:43:26"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 498, "loss": 0.8611, "lr": 3.3486046902241663e-06, "epoch": 1.9340000000000002, "percentage": 64.66, "elapsed_time": "4:57:25", "remaining_time": "2:42:34"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 498, "loss": 0.7822, "lr": 3.3155507330389004e-06, "epoch": 1.94, "percentage": 64.86, "elapsed_time": "4:58:25", "remaining_time": "2:41:41"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 498, "loss": 0.8046, "lr": 3.2825796081826943e-06, "epoch": 1.946, "percentage": 65.06, "elapsed_time": "4:59:15", "remaining_time": "2:40:42"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 498, "loss": 0.8355, "lr": 3.2496929370015383e-06, "epoch": 1.952, "percentage": 65.26, "elapsed_time": "5:00:13", "remaining_time": "2:39:48"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 498, "loss": 0.8173, "lr": 3.216892336688435e-06, "epoch": 1.958, "percentage": 65.46, "elapsed_time": "5:01:01", "remaining_time": "2:38:49"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 498, "loss": 0.8948, "lr": 3.184179420203877e-06, "epoch": 1.964, "percentage": 65.66, "elapsed_time": "5:02:01", "remaining_time": "2:37:56"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 498, "loss": 0.779, "lr": 3.1515557961965254e-06, "epoch": 1.97, "percentage": 65.86, "elapsed_time": "5:02:59", "remaining_time": "2:37:02"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 498, "loss": 0.8453, "lr": 3.119023068924115e-06, "epoch": 1.976, "percentage": 66.06, "elapsed_time": "5:03:53", "remaining_time": "2:36:05"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 498, "loss": 0.8481, "lr": 3.0865828381745515e-06, "epoch": 1.982, "percentage": 66.27, "elapsed_time": "5:04:39", "remaining_time": "2:35:05"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 498, "loss": 0.7723, "lr": 3.0542366991872546e-06, "epoch": 1.988, "percentage": 66.47, "elapsed_time": "5:05:30", "remaining_time": "2:34:08"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 498, "loss": 0.9373, "lr": 3.021986242574707e-06, "epoch": 1.994, "percentage": 66.67, "elapsed_time": "5:06:37", "remaining_time": "2:33:18"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 498, "loss": 1.2604, "lr": 2.989833054244232e-06, "epoch": 2.002, "percentage": 66.87, "elapsed_time": "5:08:40", "remaining_time": "2:32:56"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 498, "loss": 0.7464, "lr": 2.95777871532002e-06, "epoch": 2.008, "percentage": 67.07, "elapsed_time": "5:09:41", "remaining_time": "2:32:03"}
|