Training in progress, step 40000
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +42 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1638528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7e7b9fa31921e78ff19f8ab526234672ff6d628392eb2af29b202bf38121f28
|
| 3 |
size 1638528
|
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.3145, "lr": 1.9632065447422463e-05, "epoch": 6.4918835141528675, "percentage": 99.49, "elapsed_time": "14:18:26", "remaining_time": "0:04:25", "throughput": 1613.72, "total_tokens": 83117280}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.3382, "lr": 1.8690637803880916e-05, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "14:18:29", "remaining_time": "0:04:18", "throughput": 1613.85, "total_tokens": 83128704}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.31521594524383545, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "14:21:05", "remaining_time": "0:04:19", "throughput": 1608.98, "total_tokens": 83128704}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.3145, "lr": 1.9632065447422463e-05, "epoch": 6.4918835141528675, "percentage": 99.49, "elapsed_time": "14:18:26", "remaining_time": "0:04:25", "throughput": 1613.72, "total_tokens": 83117280}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.3382, "lr": 1.8690637803880916e-05, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "14:18:29", "remaining_time": "0:04:18", "throughput": 1613.85, "total_tokens": 83128704}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.31521594524383545, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "14:21:05", "remaining_time": "0:04:19", "throughput": 1608.98, "total_tokens": 83128704}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.3129, "lr": 1.7772339163019123e-05, "epoch": 6.493514968594502, "percentage": 99.51, "elapsed_time": "14:21:09", "remaining_time": "0:04:13", "throughput": 1609.07, "total_tokens": 83139264}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.3981, "lr": 1.6877169666457138e-05, "epoch": 6.49433069581532, "percentage": 99.52, "elapsed_time": "14:21:11", "remaining_time": "0:04:06", "throughput": 1609.19, "total_tokens": 83149616}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.3205, "lr": 1.6005129452234532e-05, "epoch": 6.495146423036137, "percentage": 99.54, "elapsed_time": "14:21:14", "remaining_time": "0:04:00", "throughput": 1609.32, "total_tokens": 83160880}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.3856, "lr": 1.5156218654843733e-05, "epoch": 6.495962150256954, "percentage": 99.55, "elapsed_time": "14:21:17", "remaining_time": "0:03:53", "throughput": 1609.45, "total_tokens": 83171664}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.3042, "lr": 1.4330437405196683e-05, "epoch": 6.496777877477771, "percentage": 99.56, "elapsed_time": "14:21:19", "remaining_time": "0:03:47", "throughput": 1609.57, "total_tokens": 83182000}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.3844, "lr": 1.352778583062486e-05, "epoch": 6.497593604698589, "percentage": 99.58, "elapsed_time": "14:21:21", "remaining_time": "0:03:40", "throughput": 1609.67, "total_tokens": 83190688}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.2926, "lr": 1.2748264054929237e-05, "epoch": 6.498409331919406, "percentage": 99.59, "elapsed_time": "14:21:24", "remaining_time": "0:03:34", "throughput": 1609.76, "total_tokens": 83199120}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.397, "lr": 1.1991872198297004e-05, "epoch": 6.499225059140223, "percentage": 99.6, "elapsed_time": "14:21:26", "remaining_time": "0:03:27", "throughput": 1609.9, "total_tokens": 83210832}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.296, "lr": 1.1258610377384847e-05, "epoch": 6.5000407863610405, "percentage": 99.61, "elapsed_time": "14:21:29", "remaining_time": "0:03:21", "throughput": 1610.05, "total_tokens": 83222880}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.3033, "lr": 1.0548478705268982e-05, "epoch": 6.500856513581859, "percentage": 99.62, "elapsed_time": "14:21:32", "remaining_time": "0:03:14", "throughput": 1610.17, "total_tokens": 83233184}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.3344, "lr": 9.86147729147846e-06, "epoch": 6.501672240802676, "percentage": 99.64, "elapsed_time": "14:21:34", "remaining_time": "0:03:08", "throughput": 1610.29, "total_tokens": 83243648}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.2919, "lr": 9.197606241928557e-06, "epoch": 6.502487968023493, "percentage": 99.65, "elapsed_time": "14:21:37", "remaining_time": "0:03:01", "throughput": 1610.41, "total_tokens": 83254464}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.295, "lr": 8.556865659004042e-06, "epoch": 6.50330369524431, "percentage": 99.66, "elapsed_time": "14:21:40", "remaining_time": "0:02:55", "throughput": 1610.53, "total_tokens": 83264800}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.3775, "lr": 7.939255641525867e-06, "epoch": 6.504119422465128, "percentage": 99.67, "elapsed_time": "14:21:42", "remaining_time": "0:02:48", "throughput": 1610.66, "total_tokens": 83275616}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.3501, "lr": 7.344776284751164e-06, "epoch": 6.504935149685945, "percentage": 99.69, "elapsed_time": "14:21:45", "remaining_time": "0:02:42", "throughput": 1610.78, "total_tokens": 83285712}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.3387, "lr": 6.773427680323296e-06, "epoch": 6.505750876906762, "percentage": 99.7, "elapsed_time": "14:21:48", "remaining_time": "0:02:35", "throughput": 1610.91, "total_tokens": 83297248}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.3645, "lr": 6.225209916355112e-06, "epoch": 6.506566604127579, "percentage": 99.71, "elapsed_time": "14:21:50", "remaining_time": "0:02:29", "throughput": 1611.05, "total_tokens": 83308752}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.3132, "lr": 5.7001230774123e-06, "epoch": 6.507382331348397, "percentage": 99.72, "elapsed_time": "14:21:53", "remaining_time": "0:02:22", "throughput": 1611.15, "total_tokens": 83317312}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.3491, "lr": 5.198167244446772e-06, "epoch": 6.5081980585692145, "percentage": 99.74, "elapsed_time": "14:21:55", "remaining_time": "0:02:16", "throughput": 1611.27, "total_tokens": 83327600}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.2696, "lr": 4.71934249487993e-06, "epoch": 6.509013785790032, "percentage": 99.75, "elapsed_time": "14:21:58", "remaining_time": "0:02:09", "throughput": 1611.39, "total_tokens": 83338448}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.2819, "lr": 4.2636489025527075e-06, "epoch": 6.50982951301085, "percentage": 99.76, "elapsed_time": "14:22:00", "remaining_time": "0:02:03", "throughput": 1611.52, "total_tokens": 83348896}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.2953, "lr": 3.831086537742223e-06, "epoch": 6.510645240231667, "percentage": 99.78, "elapsed_time": "14:22:03", "remaining_time": "0:01:56", "throughput": 1611.63, "total_tokens": 83359104}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.3382, "lr": 3.4216554671451236e-06, "epoch": 6.511460967452484, "percentage": 99.79, "elapsed_time": "14:22:05", "remaining_time": "0:01:50", "throughput": 1611.74, "total_tokens": 83368384}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.2941, "lr": 3.035355753894242e-06, "epoch": 6.512276694673301, "percentage": 99.8, "elapsed_time": "14:22:08", "remaining_time": "0:01:43", "throughput": 1611.85, "total_tokens": 83378352}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.2854, "lr": 2.6721874575752477e-06, "epoch": 6.513092421894118, "percentage": 99.81, "elapsed_time": "14:22:10", "remaining_time": "0:01:37", "throughput": 1611.97, "total_tokens": 83388128}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.3535, "lr": 2.3321506341933418e-06, "epoch": 6.513908149114936, "percentage": 99.83, "elapsed_time": "14:22:13", "remaining_time": "0:01:30", "throughput": 1612.09, "total_tokens": 83398288}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.3134, "lr": 2.0152453361732546e-06, "epoch": 6.514723876335753, "percentage": 99.84, "elapsed_time": "14:22:15", "remaining_time": "0:01:24", "throughput": 1612.2, "total_tokens": 83408256}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.3362, "lr": 1.7214716123925554e-06, "epoch": 6.5155396035565705, "percentage": 99.85, "elapsed_time": "14:22:18", "remaining_time": "0:01:17", "throughput": 1612.32, "total_tokens": 83418560}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.3013, "lr": 1.4508295081649968e-06, "epoch": 6.5163553307773885, "percentage": 99.86, "elapsed_time": "14:22:20", "remaining_time": "0:01:11", "throughput": 1612.45, "total_tokens": 83429440}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.2943, "lr": 1.2033190652238623e-06, "epoch": 6.517171057998206, "percentage": 99.88, "elapsed_time": "14:22:23", "remaining_time": "0:01:04", "throughput": 1612.56, "total_tokens": 83439312}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.2957, "lr": 9.78940321721966e-07, "epoch": 6.517986785219023, "percentage": 99.89, "elapsed_time": "14:22:25", "remaining_time": "0:00:58", "throughput": 1612.68, "total_tokens": 83449776}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.3523, "lr": 7.776933122816132e-07, "epoch": 6.51880251243984, "percentage": 99.9, "elapsed_time": "14:22:28", "remaining_time": "0:00:51", "throughput": 1612.81, "total_tokens": 83460704}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.3477, "lr": 5.99578067927986e-07, "epoch": 6.519618239660657, "percentage": 99.91, "elapsed_time": "14:22:31", "remaining_time": "0:00:45", "throughput": 1612.93, "total_tokens": 83470784}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.2752, "lr": 4.445946161224512e-07, "epoch": 6.520433966881475, "percentage": 99.92, "elapsed_time": "14:22:33", "remaining_time": "0:00:38", "throughput": 1613.06, "total_tokens": 83481760}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.2927, "lr": 3.127429807792126e-07, "epoch": 6.521249694102292, "percentage": 99.94, "elapsed_time": "14:22:35", "remaining_time": "0:00:32", "throughput": 1613.15, "total_tokens": 83490128}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.2386, "lr": 2.040231822320049e-07, "epoch": 6.522065421323109, "percentage": 99.95, "elapsed_time": "14:22:38", "remaining_time": "0:00:25", "throughput": 1613.27, "total_tokens": 83499984}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.2995, "lr": 1.1843523723409354e-07, "epoch": 6.522881148543927, "percentage": 99.96, "elapsed_time": "14:22:40", "remaining_time": "0:00:19", "throughput": 1613.4, "total_tokens": 83511088}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.3238, "lr": 5.597915897492811e-08, "epoch": 6.523696875764744, "percentage": 99.98, "elapsed_time": "14:22:43", "remaining_time": "0:00:12", "throughput": 1613.53, "total_tokens": 83522192}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.3434, "lr": 1.6654957113448885e-08, "epoch": 6.524512602985562, "percentage": 99.99, "elapsed_time": "14:22:46", "remaining_time": "0:00:06", "throughput": 1613.65, "total_tokens": 83532624}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.3072, "lr": 4.626377114735902e-10, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "14:22:48", "remaining_time": "0:00:00", "throughput": 1613.77, "total_tokens": 83543088}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.315355122089386, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "14:25:24", "remaining_time": "0:00:00", "throughput": 1608.93, "total_tokens": 83543088}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "14:25:25", "remaining_time": "0:00:00", "throughput": 1608.91, "total_tokens": 83543088}
|