Training in progress, step 900
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +19 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 58745928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed967b35896f6d514f9288cb7f87b470f527edbccffbe6d51385cd2a5bea7325
|
| 3 |
size 58745928
|
trainer_log.jsonl
CHANGED
|
@@ -177,3 +177,22 @@
|
|
| 177 |
{"current_steps": 840, "total_steps": 1800, "loss": 0.0, "lr": 3.2216511948570374e-05, "epoch": 9.333333333333334, "percentage": 46.67, "elapsed_time": "0:03:12", "remaining_time": "0:03:40", "throughput": 1369.13, "total_tokens": 263616}
|
| 178 |
{"current_steps": 845, "total_steps": 1800, "loss": 0.0, "lr": 3.198408839647911e-05, "epoch": 9.38888888888889, "percentage": 46.94, "elapsed_time": "0:03:13", "remaining_time": "0:03:38", "throughput": 1370.03, "total_tokens": 265152}
|
| 179 |
{"current_steps": 850, "total_steps": 1800, "loss": 0.0, "lr": 3.1751008221450025e-05, "epoch": 9.444444444444445, "percentage": 47.22, "elapsed_time": "0:03:14", "remaining_time": "0:03:37", "throughput": 1370.92, "total_tokens": 266688}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
{"current_steps": 840, "total_steps": 1800, "loss": 0.0, "lr": 3.2216511948570374e-05, "epoch": 9.333333333333334, "percentage": 46.67, "elapsed_time": "0:03:12", "remaining_time": "0:03:40", "throughput": 1369.13, "total_tokens": 263616}
|
| 178 |
{"current_steps": 845, "total_steps": 1800, "loss": 0.0, "lr": 3.198408839647911e-05, "epoch": 9.38888888888889, "percentage": 46.94, "elapsed_time": "0:03:13", "remaining_time": "0:03:38", "throughput": 1370.03, "total_tokens": 265152}
|
| 179 |
{"current_steps": 850, "total_steps": 1800, "loss": 0.0, "lr": 3.1751008221450025e-05, "epoch": 9.444444444444445, "percentage": 47.22, "elapsed_time": "0:03:14", "remaining_time": "0:03:37", "throughput": 1370.92, "total_tokens": 266688}
|
| 180 |
+
{"current_steps": 855, "total_steps": 1800, "loss": 0.0, "lr": 3.151729333697854e-05, "epoch": 9.5, "percentage": 47.5, "elapsed_time": "0:03:15", "remaining_time": "0:03:36", "throughput": 1371.93, "total_tokens": 268256}
|
| 181 |
+
{"current_steps": 860, "total_steps": 1800, "loss": 0.0, "lr": 3.1282965716233594e-05, "epoch": 9.555555555555555, "percentage": 47.78, "elapsed_time": "0:03:16", "remaining_time": "0:03:34", "throughput": 1373.0, "total_tokens": 269824}
|
| 182 |
+
{"current_steps": 865, "total_steps": 1800, "loss": 0.0, "lr": 3.104804738999169e-05, "epoch": 9.61111111111111, "percentage": 48.06, "elapsed_time": "0:03:17", "remaining_time": "0:03:33", "throughput": 1374.24, "total_tokens": 271424}
|
| 183 |
+
{"current_steps": 870, "total_steps": 1800, "loss": 0.0, "lr": 3.0812560444565745e-05, "epoch": 9.666666666666666, "percentage": 48.33, "elapsed_time": "0:03:18", "remaining_time": "0:03:32", "throughput": 1375.11, "total_tokens": 272960}
|
| 184 |
+
{"current_steps": 875, "total_steps": 1800, "loss": 0.0, "lr": 3.057652701972848e-05, "epoch": 9.722222222222221, "percentage": 48.61, "elapsed_time": "0:03:19", "remaining_time": "0:03:30", "throughput": 1376.11, "total_tokens": 274528}
|
| 185 |
+
{"current_steps": 880, "total_steps": 1800, "loss": 0.0, "lr": 3.0339969306631005e-05, "epoch": 9.777777777777779, "percentage": 48.89, "elapsed_time": "0:03:20", "remaining_time": "0:03:29", "throughput": 1377.28, "total_tokens": 276128}
|
| 186 |
+
{"current_steps": 885, "total_steps": 1800, "loss": 0.0, "lr": 3.0102909545716396e-05, "epoch": 9.833333333333334, "percentage": 49.17, "elapsed_time": "0:03:21", "remaining_time": "0:03:28", "throughput": 1378.18, "total_tokens": 277664}
|
| 187 |
+
{"current_steps": 890, "total_steps": 1800, "loss": 0.0, "lr": 2.9865370024628775e-05, "epoch": 9.88888888888889, "percentage": 49.44, "elapsed_time": "0:03:22", "remaining_time": "0:03:27", "throughput": 1379.2, "total_tokens": 279232}
|
| 188 |
+
{"current_steps": 895, "total_steps": 1800, "loss": 0.0, "lr": 2.9627373076117863e-05, "epoch": 9.944444444444445, "percentage": 49.72, "elapsed_time": "0:03:23", "remaining_time": "0:03:25", "throughput": 1380.07, "total_tokens": 280768}
|
| 189 |
+
{"current_steps": 900, "total_steps": 1800, "loss": 0.0, "lr": 2.9388941075939334e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:03:24", "remaining_time": "0:03:24", "throughput": 1380.98, "total_tokens": 282368}
|
| 190 |
+
{"current_steps": 900, "total_steps": 1800, "eval_loss": 0.09752228856086731, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:03:25", "remaining_time": "0:03:25", "throughput": 1376.9, "total_tokens": 282368}
|
| 191 |
+
{"current_steps": 905, "total_steps": 1800, "loss": 0.0, "lr": 2.9150096440751107e-05, "epoch": 10.055555555555555, "percentage": 50.28, "elapsed_time": "0:03:27", "remaining_time": "0:03:25", "throughput": 1368.7, "total_tokens": 283936}
|
| 192 |
+
{"current_steps": 910, "total_steps": 1800, "loss": 0.0, "lr": 2.8910861626005776e-05, "epoch": 10.11111111111111, "percentage": 50.56, "elapsed_time": "0:03:28", "remaining_time": "0:03:23", "throughput": 1369.63, "total_tokens": 285504}
|
| 193 |
+
{"current_steps": 915, "total_steps": 1800, "loss": 0.0, "lr": 2.8671259123839472e-05, "epoch": 10.166666666666666, "percentage": 50.83, "elapsed_time": "0:03:29", "remaining_time": "0:03:22", "throughput": 1370.56, "total_tokens": 287072}
|
| 194 |
+
{"current_steps": 920, "total_steps": 1800, "loss": 0.0, "lr": 2.843131146095719e-05, "epoch": 10.222222222222221, "percentage": 51.11, "elapsed_time": "0:03:30", "remaining_time": "0:03:21", "throughput": 1368.75, "total_tokens": 288576}
|
| 195 |
+
{"current_steps": 925, "total_steps": 1800, "loss": 0.0, "lr": 2.8191041196514873e-05, "epoch": 10.277777777777779, "percentage": 51.39, "elapsed_time": "0:03:31", "remaining_time": "0:03:20", "throughput": 1369.72, "total_tokens": 290144}
|
| 196 |
+
{"current_steps": 930, "total_steps": 1800, "loss": 0.0, "lr": 2.795047091999849e-05, "epoch": 10.333333333333334, "percentage": 51.67, "elapsed_time": "0:03:32", "remaining_time": "0:03:19", "throughput": 1370.78, "total_tokens": 291744}
|
| 197 |
+
{"current_steps": 935, "total_steps": 1800, "loss": 0.0, "lr": 2.770962324910027e-05, "epoch": 10.38888888888889, "percentage": 51.94, "elapsed_time": "0:03:33", "remaining_time": "0:03:17", "throughput": 1371.91, "total_tokens": 293344}
|
| 198 |
+
{"current_steps": 940, "total_steps": 1800, "loss": 0.0, "lr": 2.7468520827592197e-05, "epoch": 10.444444444444445, "percentage": 52.22, "elapsed_time": "0:03:34", "remaining_time": "0:03:16", "throughput": 1372.92, "total_tokens": 294912}
|