Training in progress, epoch 2
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:b6c6cca3c8adf68a6476ebc768cb0ff7e4f0a770f3208c0c4774f76f6c8fdba1
|
| 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:baec0a8f82e160391eba9db6f3240ccb7ed5ce508ce22f815c650455b86e1957
|
| 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 sha256:7e86724d2af336bbdb65d91eb26f5012ceb801790ec223117eedd8e754425270
|
| 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 sha256:646661f9d8d00f27b1f0c445b394a1bf77725d7d377c08c3408c8282f19a7065
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -142,3 +142,67 @@
|
|
| 142 |
{"current_steps": 142, "total_steps": 207, "loss": 0.7364, "lr": 2.72252606654683e-06, "epoch": 2.0382775119617227, "percentage": 68.6, "elapsed_time": "1:15:08", "remaining_time": "0:34:23"}
|
| 143 |
{"current_steps": 143, "total_steps": 207, "loss": 0.6684, "lr": 2.6476725969862227e-06, "epoch": 2.0526315789473686, "percentage": 69.08, "elapsed_time": "1:15:43", "remaining_time": "0:33:53"}
|
| 144 |
{"current_steps": 144, "total_steps": 207, "loss": 0.5368, "lr": 2.573490187344596e-06, "epoch": 2.0669856459330145, "percentage": 69.57, "elapsed_time": "1:16:17", "remaining_time": "0:33:22"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142 |
{"current_steps": 142, "total_steps": 207, "loss": 0.7364, "lr": 2.72252606654683e-06, "epoch": 2.0382775119617227, "percentage": 68.6, "elapsed_time": "1:15:08", "remaining_time": "0:34:23"}
|
| 143 |
{"current_steps": 143, "total_steps": 207, "loss": 0.6684, "lr": 2.6476725969862227e-06, "epoch": 2.0526315789473686, "percentage": 69.08, "elapsed_time": "1:15:43", "remaining_time": "0:33:53"}
|
| 144 |
{"current_steps": 144, "total_steps": 207, "loss": 0.5368, "lr": 2.573490187344596e-06, "epoch": 2.0669856459330145, "percentage": 69.57, "elapsed_time": "1:16:17", "remaining_time": "0:33:22"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 207, "loss": 0.7555, "lr": 2.5000000000000015e-06, "epoch": 2.0813397129186604, "percentage": 70.05, "elapsed_time": "1:16:52", "remaining_time": "0:32:52"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 207, "loss": 0.6411, "lr": 2.4272229998568576e-06, "epoch": 2.0956937799043063, "percentage": 70.53, "elapsed_time": "1:17:20", "remaining_time": "0:32:18"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 207, "loss": 0.6331, "lr": 2.3551799483651894e-06, "epoch": 2.110047846889952, "percentage": 71.01, "elapsed_time": "1:17:50", "remaining_time": "0:31:46"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 207, "loss": 0.605, "lr": 2.283891397597908e-06, "epoch": 2.124401913875598, "percentage": 71.5, "elapsed_time": "1:18:22", "remaining_time": "0:31:14"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 207, "loss": 0.742, "lr": 2.2133776843878185e-06, "epoch": 2.138755980861244, "percentage": 71.98, "elapsed_time": "1:18:52", "remaining_time": "0:30:42"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 207, "loss": 0.6863, "lr": 2.1436589245260375e-06, "epoch": 2.15311004784689, "percentage": 72.46, "elapsed_time": "1:19:27", "remaining_time": "0:30:11"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 207, "loss": 0.612, "lr": 2.074755007023461e-06, "epoch": 2.1674641148325358, "percentage": 72.95, "elapsed_time": "1:20:01", "remaining_time": "0:29:40"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 207, "loss": 0.6694, "lr": 2.0066855884369246e-06, "epoch": 2.1818181818181817, "percentage": 73.43, "elapsed_time": "1:20:32", "remaining_time": "0:29:08"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 207, "loss": 0.6622, "lr": 1.9394700872616856e-06, "epoch": 2.1961722488038276, "percentage": 73.91, "elapsed_time": "1:20:58", "remaining_time": "0:28:34"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 207, "loss": 0.6711, "lr": 1.8731276783918162e-06, "epoch": 2.2105263157894735, "percentage": 74.4, "elapsed_time": "1:21:33", "remaining_time": "0:28:04"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 207, "loss": 0.6175, "lr": 1.8076772876500831e-06, "epoch": 2.22488038277512, "percentage": 74.88, "elapsed_time": "1:21:58", "remaining_time": "0:27:30"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 207, "loss": 0.6674, "lr": 1.74313758638889e-06, "epoch": 2.2392344497607657, "percentage": 75.36, "elapsed_time": "1:22:34", "remaining_time": "0:26:59"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 207, "loss": 0.6965, "lr": 1.6795269861638041e-06, "epoch": 2.2535885167464116, "percentage": 75.85, "elapsed_time": "1:23:00", "remaining_time": "0:26:26"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 207, "loss": 0.7523, "lr": 1.6168636334812126e-06, "epoch": 2.2679425837320575, "percentage": 76.33, "elapsed_time": "1:23:33", "remaining_time": "0:25:54"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 207, "loss": 0.5923, "lr": 1.555165404621567e-06, "epoch": 2.2822966507177034, "percentage": 76.81, "elapsed_time": "1:24:02", "remaining_time": "0:25:22"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 207, "loss": 0.6462, "lr": 1.4944499005397372e-06, "epoch": 2.2966507177033493, "percentage": 77.29, "elapsed_time": "1:24:31", "remaining_time": "0:24:49"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 207, "loss": 0.688, "lr": 1.434734441843899e-06, "epoch": 2.311004784688995, "percentage": 77.78, "elapsed_time": "1:24:58", "remaining_time": "0:24:16"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 207, "loss": 0.663, "lr": 1.3760360638544012e-06, "epoch": 2.325358851674641, "percentage": 78.26, "elapsed_time": "1:25:27", "remaining_time": "0:23:44"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 207, "loss": 0.7095, "lr": 1.3183715117440143e-06, "epoch": 2.339712918660287, "percentage": 78.74, "elapsed_time": "1:26:01", "remaining_time": "0:23:13"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 207, "loss": 0.6137, "lr": 1.2617572357609565e-06, "epoch": 2.354066985645933, "percentage": 79.23, "elapsed_time": "1:26:29", "remaining_time": "0:22:40"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 207, "loss": 0.7442, "lr": 1.2062093865360458e-06, "epoch": 2.3684210526315788, "percentage": 79.71, "elapsed_time": "1:27:02", "remaining_time": "0:22:09"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 207, "loss": 0.6041, "lr": 1.1517438104753386e-06, "epoch": 2.382775119617225, "percentage": 80.19, "elapsed_time": "1:27:34", "remaining_time": "0:21:37"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 207, "loss": 0.651, "lr": 1.0983760452395415e-06, "epoch": 2.397129186602871, "percentage": 80.68, "elapsed_time": "1:28:03", "remaining_time": "0:21:05"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 207, "loss": 0.6922, "lr": 1.046121315311508e-06, "epoch": 2.411483253588517, "percentage": 81.16, "elapsed_time": "1:28:28", "remaining_time": "0:20:32"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 207, "loss": 0.6473, "lr": 9.949945276530782e-07, "epoch": 2.425837320574163, "percentage": 81.64, "elapsed_time": "1:28:58", "remaining_time": "0:20:00"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 207, "loss": 0.6628, "lr": 9.450102674524952e-07, "epoch": 2.4401913875598087, "percentage": 82.13, "elapsed_time": "1:29:29", "remaining_time": "0:19:28"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 207, "loss": 0.6354, "lr": 8.961827939636198e-07, "epoch": 2.4545454545454546, "percentage": 82.61, "elapsed_time": "1:29:54", "remaining_time": "0:18:55"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 207, "loss": 0.6546, "lr": 8.485260364381187e-07, "epoch": 2.4688995215311005, "percentage": 83.09, "elapsed_time": "1:30:22", "remaining_time": "0:18:23"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 207, "loss": 0.6334, "lr": 8.02053590151805e-07, "epoch": 2.4832535885167464, "percentage": 83.57, "elapsed_time": "1:30:53", "remaining_time": "0:17:51"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 207, "loss": 0.6522, "lr": 7.567787125262449e-07, "epoch": 2.4976076555023923, "percentage": 84.06, "elapsed_time": "1:31:26", "remaining_time": "0:17:20"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 207, "loss": 0.6983, "lr": 7.127143193467445e-07, "epoch": 2.511961722488038, "percentage": 84.54, "elapsed_time": "1:32:01", "remaining_time": "0:16:49"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 207, "loss": 0.6803, "lr": 6.698729810778065e-07, "epoch": 2.526315789473684, "percentage": 85.02, "elapsed_time": "1:32:32", "remaining_time": "0:16:17"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 207, "loss": 0.6338, "lr": 6.282669192770896e-07, "epoch": 2.5406698564593304, "percentage": 85.51, "elapsed_time": "1:32:58", "remaining_time": "0:15:45"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 207, "loss": 0.6442, "lr": 5.879080031089047e-07, "epoch": 2.555023923444976, "percentage": 85.99, "elapsed_time": "1:33:31", "remaining_time": "0:15:14"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 207, "loss": 0.6702, "lr": 5.488077459582425e-07, "epoch": 2.569377990430622, "percentage": 86.47, "elapsed_time": "1:34:01", "remaining_time": "0:14:42"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 207, "loss": 0.6578, "lr": 5.109773021462921e-07, "epoch": 2.583732057416268, "percentage": 86.96, "elapsed_time": "1:34:26", "remaining_time": "0:14:09"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 207, "loss": 0.6506, "lr": 4.7442746374839363e-07, "epoch": 2.598086124401914, "percentage": 87.44, "elapsed_time": "1:34:57", "remaining_time": "0:13:38"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 207, "loss": 0.7005, "lr": 4.3916865751533313e-07, "epoch": 2.61244019138756, "percentage": 87.92, "elapsed_time": "1:35:29", "remaining_time": "0:13:07"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 207, "loss": 0.5862, "lr": 4.05210941898847e-07, "epoch": 2.626794258373206, "percentage": 88.41, "elapsed_time": "1:35:56", "remaining_time": "0:12:35"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 207, "loss": 0.6294, "lr": 3.725640041822026e-07, "epoch": 2.6411483253588517, "percentage": 88.89, "elapsed_time": "1:36:24", "remaining_time": "0:12:03"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 207, "loss": 0.6718, "lr": 3.4123715771665786e-07, "epoch": 2.6555023923444976, "percentage": 89.37, "elapsed_time": "1:36:59", "remaining_time": "0:11:31"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 207, "loss": 0.6035, "lr": 3.112393392645985e-07, "epoch": 2.6698564593301435, "percentage": 89.86, "elapsed_time": "1:37:27", "remaining_time": "0:11:00"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 207, "loss": 0.6878, "lr": 2.8257910645009935e-07, "epoch": 2.6842105263157894, "percentage": 90.34, "elapsed_time": "1:38:01", "remaining_time": "0:10:29"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 207, "loss": 0.7033, "lr": 2.5526463531765467e-07, "epoch": 2.6985645933014353, "percentage": 90.82, "elapsed_time": "1:38:30", "remaining_time": "0:09:57"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 207, "loss": 0.6613, "lr": 2.2930371799975593e-07, "epoch": 2.712918660287081, "percentage": 91.3, "elapsed_time": "1:39:01", "remaining_time": "0:09:25"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 207, "loss": 0.7166, "lr": 2.0470376049398944e-07, "epoch": 2.7272727272727275, "percentage": 91.79, "elapsed_time": "1:39:32", "remaining_time": "0:08:54"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 207, "loss": 0.6435, "lr": 1.814717805502958e-07, "epoch": 2.741626794258373, "percentage": 92.27, "elapsed_time": "1:40:07", "remaining_time": "0:08:23"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 207, "loss": 0.6877, "lr": 1.5961440566897913e-07, "epoch": 2.7559808612440193, "percentage": 92.75, "elapsed_time": "1:40:40", "remaining_time": "0:07:51"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 207, "loss": 0.6212, "lr": 1.3913787121004717e-07, "epoch": 2.770334928229665, "percentage": 93.24, "elapsed_time": "1:41:08", "remaining_time": "0:07:20"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 207, "loss": 0.6511, "lr": 1.2004801861442373e-07, "epoch": 2.784688995215311, "percentage": 93.72, "elapsed_time": "1:41:40", "remaining_time": "0:06:48"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 207, "loss": 0.5578, "lr": 1.0235029373752758e-07, "epoch": 2.799043062200957, "percentage": 94.2, "elapsed_time": "1:42:11", "remaining_time": "0:06:17"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 207, "loss": 0.7044, "lr": 8.604974529571042e-08, "epoch": 2.813397129186603, "percentage": 94.69, "elapsed_time": "1:42:44", "remaining_time": "0:05:45"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 207, "loss": 0.6089, "lr": 7.115102342598101e-08, "epoch": 2.827751196172249, "percentage": 95.17, "elapsed_time": "1:43:11", "remaining_time": "0:05:14"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 207, "loss": 0.6637, "lr": 5.7658378359443104e-08, "epoch": 2.8421052631578947, "percentage": 95.65, "elapsed_time": "1:43:39", "remaining_time": "0:04:42"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 207, "loss": 0.6709, "lr": 4.55756592088058e-08, "epoch": 2.8564593301435406, "percentage": 96.14, "elapsed_time": "1:44:15", "remaining_time": "0:04:11"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 207, "loss": 0.6988, "lr": 3.4906312870331973e-08, "epoch": 2.8708133971291865, "percentage": 96.62, "elapsed_time": "1:44:42", "remaining_time": "0:03:39"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 207, "loss": 0.7137, "lr": 2.5653383040524228e-08, "epoch": 2.8851674641148324, "percentage": 97.1, "elapsed_time": "1:45:19", "remaining_time": "0:03:08"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 207, "loss": 0.6376, "lr": 1.781950934783505e-08, "epoch": 2.8995215311004783, "percentage": 97.58, "elapsed_time": "1:45:47", "remaining_time": "0:02:37"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 207, "loss": 0.7062, "lr": 1.1406926599646373e-08, "epoch": 2.9138755980861246, "percentage": 98.07, "elapsed_time": "1:46:13", "remaining_time": "0:02:05"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 207, "loss": 0.705, "lr": 6.417464144736208e-09, "epoch": 2.92822966507177, "percentage": 98.55, "elapsed_time": "1:46:41", "remaining_time": "0:01:34"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 207, "loss": 0.5968, "lr": 2.8525453514099966e-09, "epoch": 2.9425837320574164, "percentage": 99.03, "elapsed_time": "1:47:16", "remaining_time": "0:01:02"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 207, "loss": 0.7064, "lr": 7.131872014509711e-10, "epoch": 2.9569377990430623, "percentage": 99.52, "elapsed_time": "1:47:49", "remaining_time": "0:00:31"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 207, "loss": 0.6739, "lr": 0.0, "epoch": 2.971291866028708, "percentage": 100.0, "elapsed_time": "1:48:20", "remaining_time": "0:00:00"}
|
| 208 |
+
{"current_steps": 207, "total_steps": 207, "epoch": 2.971291866028708, "percentage": 100.0, "elapsed_time": "1:49:48", "remaining_time": "0:00:00"}
|