Training in progress, step 39800
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +38 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 460928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ea25947da24be3c52b7aaaec67d0fd91cd0ac4b34596a2cd7adae5064860d94
|
3 |
size 460928
|
trainer_log.jsonl
CHANGED
@@ -8119,3 +8119,41 @@
|
|
8119 |
{"current_steps": 39605, "total_steps": 40000, "loss": 0.0884, "lr": 7.254314656586214e-05, "epoch": 1.9351379082891556, "percentage": 99.01, "elapsed_time": "1 day, 2:26:57", "remaining_time": "0:15:49", "throughput": 539.25, "total_tokens": 51346080}
|
8120 |
{"current_steps": 39610, "total_steps": 40000, "loss": 0.0526, "lr": 7.07229569929968e-05, "epoch": 1.93538220995285, "percentage": 99.02, "elapsed_time": "1 day, 2:26:58", "remaining_time": "0:15:37", "throughput": 539.31, "total_tokens": 51352640}
|
8121 |
{"current_steps": 39615, "total_steps": 40000, "loss": 0.084, "lr": 6.892588839879643e-05, "epoch": 1.935626511616544, "percentage": 99.04, "elapsed_time": "1 day, 2:27:00", "remaining_time": "0:15:25", "throughput": 539.37, "total_tokens": 51358912}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8119 |
{"current_steps": 39605, "total_steps": 40000, "loss": 0.0884, "lr": 7.254314656586214e-05, "epoch": 1.9351379082891556, "percentage": 99.01, "elapsed_time": "1 day, 2:26:57", "remaining_time": "0:15:49", "throughput": 539.25, "total_tokens": 51346080}
|
8120 |
{"current_steps": 39610, "total_steps": 40000, "loss": 0.0526, "lr": 7.07229569929968e-05, "epoch": 1.93538220995285, "percentage": 99.02, "elapsed_time": "1 day, 2:26:58", "remaining_time": "0:15:37", "throughput": 539.31, "total_tokens": 51352640}
|
8121 |
{"current_steps": 39615, "total_steps": 40000, "loss": 0.084, "lr": 6.892588839879643e-05, "epoch": 1.935626511616544, "percentage": 99.04, "elapsed_time": "1 day, 2:27:00", "remaining_time": "0:15:25", "throughput": 539.37, "total_tokens": 51358912}
|
8122 |
+
{"current_steps": 39620, "total_steps": 40000, "loss": 0.0673, "lr": 6.71519410603727e-05, "epoch": 1.9358708132802385, "percentage": 99.05, "elapsed_time": "1 day, 2:27:02", "remaining_time": "0:15:13", "throughput": 539.43, "total_tokens": 51365760}
|
8123 |
+
{"current_steps": 39625, "total_steps": 40000, "loss": 0.0899, "lr": 6.540111525129011e-05, "epoch": 1.9361151149439326, "percentage": 99.06, "elapsed_time": "1 day, 2:27:04", "remaining_time": "0:15:01", "throughput": 539.48, "total_tokens": 51372128}
|
8124 |
+
{"current_steps": 39630, "total_steps": 40000, "loss": 0.075, "lr": 6.367341124154934e-05, "epoch": 1.936359416607627, "percentage": 99.08, "elapsed_time": "1 day, 2:27:06", "remaining_time": "0:14:49", "throughput": 539.54, "total_tokens": 51378656}
|
8125 |
+
{"current_steps": 39635, "total_steps": 40000, "loss": 0.0618, "lr": 6.19688292975873e-05, "epoch": 1.9366037182713214, "percentage": 99.09, "elapsed_time": "1 day, 2:27:08", "remaining_time": "0:14:36", "throughput": 539.6, "total_tokens": 51385120}
|
8126 |
+
{"current_steps": 39640, "total_steps": 40000, "loss": 0.0842, "lr": 6.0287369682260336e-05, "epoch": 1.9368480199350158, "percentage": 99.1, "elapsed_time": "1 day, 2:27:10", "remaining_time": "0:14:24", "throughput": 539.65, "total_tokens": 51391328}
|
8127 |
+
{"current_steps": 39645, "total_steps": 40000, "loss": 0.0932, "lr": 5.8629032654894384e-05, "epoch": 1.9370923215987101, "percentage": 99.11, "elapsed_time": "1 day, 2:27:12", "remaining_time": "0:14:12", "throughput": 539.71, "total_tokens": 51397472}
|
8128 |
+
{"current_steps": 39650, "total_steps": 40000, "loss": 0.092, "lr": 5.699381847120155e-05, "epoch": 1.9373366232624045, "percentage": 99.12, "elapsed_time": "1 day, 2:27:14", "remaining_time": "0:14:00", "throughput": 539.76, "total_tokens": 51403296}
|
8129 |
+
{"current_steps": 39655, "total_steps": 40000, "loss": 0.0796, "lr": 5.5381727383380094e-05, "epoch": 1.937580924926099, "percentage": 99.14, "elapsed_time": "1 day, 2:27:16", "remaining_time": "0:13:48", "throughput": 539.81, "total_tokens": 51409408}
|
8130 |
+
{"current_steps": 39660, "total_steps": 40000, "loss": 0.09, "lr": 5.379275964001451e-05, "epoch": 1.937825226589793, "percentage": 99.15, "elapsed_time": "1 day, 2:27:18", "remaining_time": "0:13:36", "throughput": 539.87, "total_tokens": 51416480}
|
8131 |
+
{"current_steps": 39665, "total_steps": 40000, "loss": 0.0776, "lr": 5.222691548614211e-05, "epoch": 1.9380695282534874, "percentage": 99.16, "elapsed_time": "1 day, 2:27:20", "remaining_time": "0:13:24", "throughput": 539.93, "total_tokens": 51423296}
|
8132 |
+
{"current_steps": 39670, "total_steps": 40000, "loss": 0.0788, "lr": 5.068419516323641e-05, "epoch": 1.9383138299171816, "percentage": 99.17, "elapsed_time": "1 day, 2:27:21", "remaining_time": "0:13:12", "throughput": 539.99, "total_tokens": 51429760}
|
8133 |
+
{"current_steps": 39675, "total_steps": 40000, "loss": 0.0802, "lr": 4.91645989092071e-05, "epoch": 1.938558131580876, "percentage": 99.19, "elapsed_time": "1 day, 2:27:23", "remaining_time": "0:13:00", "throughput": 540.05, "total_tokens": 51436160}
|
8134 |
+
{"current_steps": 39680, "total_steps": 40000, "loss": 0.0674, "lr": 4.7668126958400056e-05, "epoch": 1.9388024332445704, "percentage": 99.2, "elapsed_time": "1 day, 2:27:25", "remaining_time": "0:12:48", "throughput": 540.11, "total_tokens": 51442848}
|
8135 |
+
{"current_steps": 39685, "total_steps": 40000, "loss": 0.078, "lr": 4.619477954159734e-05, "epoch": 1.9390467349082647, "percentage": 99.21, "elapsed_time": "1 day, 2:27:27", "remaining_time": "0:12:36", "throughput": 540.16, "total_tokens": 51448896}
|
8136 |
+
{"current_steps": 39690, "total_steps": 40000, "loss": 0.0595, "lr": 4.4744556885983884e-05, "epoch": 1.9392910365719591, "percentage": 99.22, "elapsed_time": "1 day, 2:27:29", "remaining_time": "0:12:23", "throughput": 540.22, "total_tokens": 51455648}
|
8137 |
+
{"current_steps": 39695, "total_steps": 40000, "loss": 0.0724, "lr": 4.331745921523078e-05, "epoch": 1.9395353382356535, "percentage": 99.24, "elapsed_time": "1 day, 2:27:31", "remaining_time": "0:12:11", "throughput": 540.28, "total_tokens": 51462528}
|
8138 |
+
{"current_steps": 39700, "total_steps": 40000, "loss": 0.0511, "lr": 4.191348674937867e-05, "epoch": 1.9397796398993479, "percentage": 99.25, "elapsed_time": "1 day, 2:27:33", "remaining_time": "0:11:59", "throughput": 540.34, "total_tokens": 51469248}
|
8139 |
+
{"current_steps": 39705, "total_steps": 40000, "loss": 0.0597, "lr": 4.0532639704971006e-05, "epoch": 1.940023941563042, "percentage": 99.26, "elapsed_time": "1 day, 2:27:35", "remaining_time": "0:11:47", "throughput": 540.4, "total_tokens": 51476384}
|
8140 |
+
{"current_steps": 39710, "total_steps": 40000, "loss": 0.0777, "lr": 3.917491829493747e-05, "epoch": 1.9402682432267364, "percentage": 99.28, "elapsed_time": "1 day, 2:27:37", "remaining_time": "0:11:35", "throughput": 540.46, "total_tokens": 51482624}
|
8141 |
+
{"current_steps": 39715, "total_steps": 40000, "loss": 0.0992, "lr": 3.78403227286439e-05, "epoch": 1.9405125448904306, "percentage": 99.29, "elapsed_time": "1 day, 2:27:39", "remaining_time": "0:11:23", "throughput": 540.51, "total_tokens": 51488928}
|
8142 |
+
{"current_steps": 39720, "total_steps": 40000, "loss": 0.0844, "lr": 3.652885321192567e-05, "epoch": 1.940756846554125, "percentage": 99.3, "elapsed_time": "1 day, 2:27:41", "remaining_time": "0:11:11", "throughput": 540.57, "total_tokens": 51494944}
|
8143 |
+
{"current_steps": 39725, "total_steps": 40000, "loss": 0.0837, "lr": 3.524050994702099e-05, "epoch": 1.9410011482178193, "percentage": 99.31, "elapsed_time": "1 day, 2:27:43", "remaining_time": "0:10:59", "throughput": 540.62, "total_tokens": 51501408}
|
8144 |
+
{"current_steps": 39730, "total_steps": 40000, "loss": 0.0703, "lr": 3.3975293132604276e-05, "epoch": 1.9412454498815137, "percentage": 99.33, "elapsed_time": "1 day, 2:27:44", "remaining_time": "0:10:47", "throughput": 540.68, "total_tokens": 51507616}
|
8145 |
+
{"current_steps": 39735, "total_steps": 40000, "loss": 0.0808, "lr": 3.2733202963786125e-05, "epoch": 1.941489751545208, "percentage": 99.34, "elapsed_time": "1 day, 2:27:46", "remaining_time": "0:10:35", "throughput": 540.73, "total_tokens": 51514144}
|
8146 |
+
{"current_steps": 39740, "total_steps": 40000, "loss": 0.0715, "lr": 3.15142396321133e-05, "epoch": 1.9417340532089025, "percentage": 99.35, "elapsed_time": "1 day, 2:27:48", "remaining_time": "0:10:23", "throughput": 540.79, "total_tokens": 51520128}
|
8147 |
+
{"current_steps": 39745, "total_steps": 40000, "loss": 0.0932, "lr": 3.0318403325552132e-05, "epoch": 1.9419783548725968, "percentage": 99.36, "elapsed_time": "1 day, 2:27:50", "remaining_time": "0:10:11", "throughput": 540.84, "total_tokens": 51526656}
|
8148 |
+
{"current_steps": 39750, "total_steps": 40000, "loss": 0.0693, "lr": 2.914569422855506e-05, "epoch": 1.942222656536291, "percentage": 99.38, "elapsed_time": "1 day, 2:27:52", "remaining_time": "0:09:59", "throughput": 540.9, "total_tokens": 51532992}
|
8149 |
+
{"current_steps": 39755, "total_steps": 40000, "loss": 0.0789, "lr": 2.7996112521927462e-05, "epoch": 1.9424669581999854, "percentage": 99.39, "elapsed_time": "1 day, 2:27:54", "remaining_time": "0:09:47", "throughput": 540.96, "total_tokens": 51539456}
|
8150 |
+
{"current_steps": 39760, "total_steps": 40000, "loss": 0.1056, "lr": 2.68696583829775e-05, "epoch": 1.9427112598636795, "percentage": 99.4, "elapsed_time": "1 day, 2:27:56", "remaining_time": "0:09:35", "throughput": 541.01, "total_tokens": 51545600}
|
8151 |
+
{"current_steps": 39765, "total_steps": 40000, "loss": 0.0891, "lr": 2.576633198539957e-05, "epoch": 1.942955561527374, "percentage": 99.41, "elapsed_time": "1 day, 2:27:58", "remaining_time": "0:09:23", "throughput": 541.06, "total_tokens": 51551808}
|
8152 |
+
{"current_steps": 39770, "total_steps": 40000, "loss": 0.0754, "lr": 2.46861334993409e-05, "epoch": 1.9431998631910683, "percentage": 99.42, "elapsed_time": "1 day, 2:28:00", "remaining_time": "0:09:11", "throughput": 541.12, "total_tokens": 51558208}
|
8153 |
+
{"current_steps": 39775, "total_steps": 40000, "loss": 0.074, "lr": 2.3629063091384903e-05, "epoch": 1.9434441648547627, "percentage": 99.44, "elapsed_time": "1 day, 2:28:02", "remaining_time": "0:08:58", "throughput": 541.18, "total_tokens": 51564832}
|
8154 |
+
{"current_steps": 39780, "total_steps": 40000, "loss": 0.0804, "lr": 2.2595120924567834e-05, "epoch": 1.943688466518457, "percentage": 99.45, "elapsed_time": "1 day, 2:28:04", "remaining_time": "0:08:46", "throughput": 541.23, "total_tokens": 51570944}
|
8155 |
+
{"current_steps": 39785, "total_steps": 40000, "loss": 0.0822, "lr": 2.158430715829551e-05, "epoch": 1.9439327681821514, "percentage": 99.46, "elapsed_time": "1 day, 2:28:06", "remaining_time": "0:08:34", "throughput": 541.29, "total_tokens": 51577248}
|
8156 |
+
{"current_steps": 39790, "total_steps": 40000, "loss": 0.0582, "lr": 2.059662194849321e-05, "epoch": 1.9441770698458456, "percentage": 99.48, "elapsed_time": "1 day, 2:28:07", "remaining_time": "0:08:22", "throughput": 541.35, "total_tokens": 51584000}
|
8157 |
+
{"current_steps": 39795, "total_steps": 40000, "loss": 0.072, "lr": 1.9632065447422463e-05, "epoch": 1.94442137150954, "percentage": 99.49, "elapsed_time": "1 day, 2:28:09", "remaining_time": "0:08:10", "throughput": 541.41, "total_tokens": 51590464}
|
8158 |
+
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0663, "lr": 1.8690637803880916e-05, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 2:28:11", "remaining_time": "0:07:58", "throughput": 541.46, "total_tokens": 51597120}
|
8159 |
+
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08352842926979065, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 2:34:54", "remaining_time": "0:08:00", "throughput": 539.19, "total_tokens": 51597120}
|