Training in progress, step 39800
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +41 -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 sha256:76537adfadb7579b4d1c4c95fe3ece1f3655cec5e3a76d13001ba1a00775d745
|
| 3 |
size 1638528
|
trainer_log.jsonl
CHANGED
|
@@ -8116,3 +8116,44 @@
|
|
| 8116 |
{"current_steps": 39595, "total_steps": 40000, "loss": 0.3291, "lr": 7.625288752117209e-05, "epoch": 6.459254425320173, "percentage": 98.99, "elapsed_time": "14:14:07", "remaining_time": "0:08:44", "throughput": 1613.79, "total_tokens": 82702032}
|
| 8117 |
{"current_steps": 39600, "total_steps": 40000, "loss": 0.2828, "lr": 7.4386456836667e-05, "epoch": 6.4600701525409905, "percentage": 99.0, "elapsed_time": "14:14:09", "remaining_time": "0:08:37", "throughput": 1613.92, "total_tokens": 82712800}
|
| 8118 |
{"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.3149668872356415, "epoch": 6.4600701525409905, "percentage": 99.0, "elapsed_time": "14:16:45", "remaining_time": "0:08:39", "throughput": 1609.01, "total_tokens": 82712800}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8116 |
{"current_steps": 39595, "total_steps": 40000, "loss": 0.3291, "lr": 7.625288752117209e-05, "epoch": 6.459254425320173, "percentage": 98.99, "elapsed_time": "14:14:07", "remaining_time": "0:08:44", "throughput": 1613.79, "total_tokens": 82702032}
|
| 8117 |
{"current_steps": 39600, "total_steps": 40000, "loss": 0.2828, "lr": 7.4386456836667e-05, "epoch": 6.4600701525409905, "percentage": 99.0, "elapsed_time": "14:14:09", "remaining_time": "0:08:37", "throughput": 1613.92, "total_tokens": 82712800}
|
| 8118 |
{"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.3149668872356415, "epoch": 6.4600701525409905, "percentage": 99.0, "elapsed_time": "14:16:45", "remaining_time": "0:08:39", "throughput": 1609.01, "total_tokens": 82712800}
|
| 8119 |
+
{"current_steps": 39605, "total_steps": 40000, "loss": 0.2152, "lr": 7.254314656586214e-05, "epoch": 6.460885879761808, "percentage": 99.01, "elapsed_time": "14:16:49", "remaining_time": "0:08:32", "throughput": 1609.12, "total_tokens": 82724720}
|
| 8120 |
+
{"current_steps": 39610, "total_steps": 40000, "loss": 0.3186, "lr": 7.07229569929968e-05, "epoch": 6.461701606982625, "percentage": 99.02, "elapsed_time": "14:16:52", "remaining_time": "0:08:26", "throughput": 1609.24, "total_tokens": 82734720}
|
| 8121 |
+
{"current_steps": 39615, "total_steps": 40000, "loss": 0.288, "lr": 6.892588839879643e-05, "epoch": 6.462517334203443, "percentage": 99.04, "elapsed_time": "14:16:55", "remaining_time": "0:08:19", "throughput": 1609.38, "total_tokens": 82746320}
|
| 8122 |
+
{"current_steps": 39620, "total_steps": 40000, "loss": 0.2884, "lr": 6.71519410603727e-05, "epoch": 6.46333306142426, "percentage": 99.05, "elapsed_time": "14:16:57", "remaining_time": "0:08:13", "throughput": 1609.5, "total_tokens": 82756992}
|
| 8123 |
+
{"current_steps": 39625, "total_steps": 40000, "loss": 0.2818, "lr": 6.540111525129011e-05, "epoch": 6.464148788645077, "percentage": 99.06, "elapsed_time": "14:17:00", "remaining_time": "0:08:06", "throughput": 1609.64, "total_tokens": 82768560}
|
| 8124 |
+
{"current_steps": 39630, "total_steps": 40000, "loss": 0.3299, "lr": 6.367341124154934e-05, "epoch": 6.464964515865894, "percentage": 99.08, "elapsed_time": "14:17:02", "remaining_time": "0:08:00", "throughput": 1609.74, "total_tokens": 82777632}
|
| 8125 |
+
{"current_steps": 39635, "total_steps": 40000, "loss": 0.319, "lr": 6.19688292975873e-05, "epoch": 6.465780243086712, "percentage": 99.09, "elapsed_time": "14:17:05", "remaining_time": "0:07:53", "throughput": 1609.86, "total_tokens": 82787616}
|
| 8126 |
+
{"current_steps": 39640, "total_steps": 40000, "loss": 0.3002, "lr": 6.0287369682260336e-05, "epoch": 6.466595970307529, "percentage": 99.1, "elapsed_time": "14:17:07", "remaining_time": "0:07:47", "throughput": 1609.97, "total_tokens": 82796992}
|
| 8127 |
+
{"current_steps": 39645, "total_steps": 40000, "loss": 0.3435, "lr": 5.8629032654894384e-05, "epoch": 6.467411697528346, "percentage": 99.11, "elapsed_time": "14:17:10", "remaining_time": "0:07:40", "throughput": 1610.09, "total_tokens": 82807456}
|
| 8128 |
+
{"current_steps": 39650, "total_steps": 40000, "loss": 0.3478, "lr": 5.699381847120155e-05, "epoch": 6.468227424749164, "percentage": 99.12, "elapsed_time": "14:17:12", "remaining_time": "0:07:34", "throughput": 1610.22, "total_tokens": 82818016}
|
| 8129 |
+
{"current_steps": 39655, "total_steps": 40000, "loss": 0.2973, "lr": 5.5381727383380094e-05, "epoch": 6.469043151969982, "percentage": 99.14, "elapsed_time": "14:17:15", "remaining_time": "0:07:27", "throughput": 1610.33, "total_tokens": 82827872}
|
| 8130 |
+
{"current_steps": 39660, "total_steps": 40000, "loss": 0.3107, "lr": 5.379275964001451e-05, "epoch": 6.469858879190799, "percentage": 99.15, "elapsed_time": "14:17:17", "remaining_time": "0:07:20", "throughput": 1610.45, "total_tokens": 82837984}
|
| 8131 |
+
{"current_steps": 39665, "total_steps": 40000, "loss": 0.2645, "lr": 5.222691548614211e-05, "epoch": 6.470674606411616, "percentage": 99.16, "elapsed_time": "14:17:20", "remaining_time": "0:07:14", "throughput": 1610.56, "total_tokens": 82847584}
|
| 8132 |
+
{"current_steps": 39670, "total_steps": 40000, "loss": 0.3007, "lr": 5.068419516323641e-05, "epoch": 6.471490333632433, "percentage": 99.17, "elapsed_time": "14:17:22", "remaining_time": "0:07:07", "throughput": 1610.67, "total_tokens": 82857392}
|
| 8133 |
+
{"current_steps": 39675, "total_steps": 40000, "loss": 0.3051, "lr": 4.91645989092071e-05, "epoch": 6.472306060853251, "percentage": 99.19, "elapsed_time": "14:17:25", "remaining_time": "0:07:01", "throughput": 1610.8, "total_tokens": 82868144}
|
| 8134 |
+
{"current_steps": 39680, "total_steps": 40000, "loss": 0.29, "lr": 4.7668126958400056e-05, "epoch": 6.473121788074068, "percentage": 99.2, "elapsed_time": "14:17:28", "remaining_time": "0:06:54", "throughput": 1610.93, "total_tokens": 82879424}
|
| 8135 |
+
{"current_steps": 39685, "total_steps": 40000, "loss": 0.3549, "lr": 4.619477954159734e-05, "epoch": 6.473937515294885, "percentage": 99.21, "elapsed_time": "14:17:30", "remaining_time": "0:06:48", "throughput": 1611.04, "total_tokens": 82888720}
|
| 8136 |
+
{"current_steps": 39690, "total_steps": 40000, "loss": 0.3152, "lr": 4.4744556885983884e-05, "epoch": 6.474753242515702, "percentage": 99.22, "elapsed_time": "14:17:33", "remaining_time": "0:06:41", "throughput": 1611.17, "total_tokens": 82899440}
|
| 8137 |
+
{"current_steps": 39695, "total_steps": 40000, "loss": 0.3224, "lr": 4.331745921523078e-05, "epoch": 6.47556896973652, "percentage": 99.24, "elapsed_time": "14:17:35", "remaining_time": "0:06:35", "throughput": 1611.28, "total_tokens": 82908896}
|
| 8138 |
+
{"current_steps": 39700, "total_steps": 40000, "loss": 0.3018, "lr": 4.191348674937867e-05, "epoch": 6.4763846969573375, "percentage": 99.25, "elapsed_time": "14:17:37", "remaining_time": "0:06:28", "throughput": 1611.4, "total_tokens": 82919536}
|
| 8139 |
+
{"current_steps": 39705, "total_steps": 40000, "loss": 0.2785, "lr": 4.0532639704971006e-05, "epoch": 6.477200424178155, "percentage": 99.26, "elapsed_time": "14:17:40", "remaining_time": "0:06:22", "throughput": 1611.53, "total_tokens": 82930080}
|
| 8140 |
+
{"current_steps": 39710, "total_steps": 40000, "loss": 0.2249, "lr": 3.917491829493747e-05, "epoch": 6.478016151398972, "percentage": 99.28, "elapsed_time": "14:17:43", "remaining_time": "0:06:15", "throughput": 1611.65, "total_tokens": 82940800}
|
| 8141 |
+
{"current_steps": 39715, "total_steps": 40000, "loss": 0.3264, "lr": 3.78403227286439e-05, "epoch": 6.47883187861979, "percentage": 99.29, "elapsed_time": "14:17:45", "remaining_time": "0:06:09", "throughput": 1611.76, "total_tokens": 82949920}
|
| 8142 |
+
{"current_steps": 39720, "total_steps": 40000, "loss": 0.2633, "lr": 3.652885321192567e-05, "epoch": 6.479647605840607, "percentage": 99.3, "elapsed_time": "14:17:48", "remaining_time": "0:06:02", "throughput": 1611.89, "total_tokens": 82961248}
|
| 8143 |
+
{"current_steps": 39725, "total_steps": 40000, "loss": 0.2681, "lr": 3.524050994702099e-05, "epoch": 6.480463333061424, "percentage": 99.31, "elapsed_time": "14:17:51", "remaining_time": "0:05:56", "throughput": 1612.03, "total_tokens": 82972816}
|
| 8144 |
+
{"current_steps": 39730, "total_steps": 40000, "loss": 0.2506, "lr": 3.3975293132604276e-05, "epoch": 6.481279060282241, "percentage": 99.33, "elapsed_time": "14:17:53", "remaining_time": "0:05:49", "throughput": 1612.16, "total_tokens": 82983440}
|
| 8145 |
+
{"current_steps": 39735, "total_steps": 40000, "loss": 0.2567, "lr": 3.2733202963786125e-05, "epoch": 6.482094787503059, "percentage": 99.34, "elapsed_time": "14:17:56", "remaining_time": "0:05:43", "throughput": 1612.29, "total_tokens": 82994512}
|
| 8146 |
+
{"current_steps": 39740, "total_steps": 40000, "loss": 0.3134, "lr": 3.15142396321133e-05, "epoch": 6.482910514723876, "percentage": 99.35, "elapsed_time": "14:17:58", "remaining_time": "0:05:36", "throughput": 1612.41, "total_tokens": 83005104}
|
| 8147 |
+
{"current_steps": 39745, "total_steps": 40000, "loss": 0.2738, "lr": 3.0318403325552132e-05, "epoch": 6.4837262419446935, "percentage": 99.36, "elapsed_time": "14:18:01", "remaining_time": "0:05:30", "throughput": 1612.56, "total_tokens": 83017120}
|
| 8148 |
+
{"current_steps": 39750, "total_steps": 40000, "loss": 0.2849, "lr": 2.914569422855506e-05, "epoch": 6.484541969165511, "percentage": 99.38, "elapsed_time": "14:18:04", "remaining_time": "0:05:23", "throughput": 1612.65, "total_tokens": 83025888}
|
| 8149 |
+
{"current_steps": 39755, "total_steps": 40000, "loss": 0.2651, "lr": 2.7996112521927462e-05, "epoch": 6.485357696386329, "percentage": 99.39, "elapsed_time": "14:18:06", "remaining_time": "0:05:17", "throughput": 1612.78, "total_tokens": 83036416}
|
| 8150 |
+
{"current_steps": 39760, "total_steps": 40000, "loss": 0.31, "lr": 2.68696583829775e-05, "epoch": 6.486173423607146, "percentage": 99.4, "elapsed_time": "14:18:09", "remaining_time": "0:05:10", "throughput": 1612.89, "total_tokens": 83046304}
|
| 8151 |
+
{"current_steps": 39765, "total_steps": 40000, "loss": 0.307, "lr": 2.576633198539957e-05, "epoch": 6.486989150827963, "percentage": 99.41, "elapsed_time": "14:18:11", "remaining_time": "0:05:04", "throughput": 1613.0, "total_tokens": 83055904}
|
| 8152 |
+
{"current_steps": 39770, "total_steps": 40000, "loss": 0.4111, "lr": 2.46861334993409e-05, "epoch": 6.487804878048781, "percentage": 99.42, "elapsed_time": "14:18:13", "remaining_time": "0:04:57", "throughput": 1613.11, "total_tokens": 83065600}
|
| 8153 |
+
{"current_steps": 39775, "total_steps": 40000, "loss": 0.3858, "lr": 2.3629063091384903e-05, "epoch": 6.488620605269598, "percentage": 99.44, "elapsed_time": "14:18:16", "remaining_time": "0:04:51", "throughput": 1613.25, "total_tokens": 83076960}
|
| 8154 |
+
{"current_steps": 39780, "total_steps": 40000, "loss": 0.3664, "lr": 2.2595120924567834e-05, "epoch": 6.489436332490415, "percentage": 99.45, "elapsed_time": "14:18:19", "remaining_time": "0:04:44", "throughput": 1613.38, "total_tokens": 83088112}
|
| 8155 |
+
{"current_steps": 39785, "total_steps": 40000, "loss": 0.2996, "lr": 2.158430715829551e-05, "epoch": 6.490252059711232, "percentage": 99.46, "elapsed_time": "14:18:21", "remaining_time": "0:04:38", "throughput": 1613.49, "total_tokens": 83097584}
|
| 8156 |
+
{"current_steps": 39790, "total_steps": 40000, "loss": 0.2838, "lr": 2.059662194849321e-05, "epoch": 6.49106778693205, "percentage": 99.48, "elapsed_time": "14:18:24", "remaining_time": "0:04:31", "throughput": 1613.6, "total_tokens": 83106912}
|
| 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}
|