Training in progress, step 1130
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +7 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8388736
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64ea0c4afcde4373d87244857a664a1fc8b9db7d7c74b29228bd6e2e2af70d40
|
| 3 |
size 8388736
|
trainer_log.jsonl
CHANGED
|
@@ -237,3 +237,10 @@
|
|
| 237 |
{"current_steps": 1090, "total_steps": 1130, "loss": 0.0001, "lr": 2.0024189799641435e-07, "epoch": 9.646017699115044, "percentage": 96.46, "elapsed_time": "0:02:25", "remaining_time": "0:00:05", "throughput": 2041.97, "total_tokens": 297904}
|
| 238 |
{"current_steps": 1095, "total_steps": 1130, "loss": 0.0001, "lr": 1.5442771053230665e-07, "epoch": 9.690265486725664, "percentage": 96.9, "elapsed_time": "0:02:26", "remaining_time": "0:00:04", "throughput": 2046.48, "total_tokens": 299536}
|
| 239 |
{"current_steps": 1100, "total_steps": 1130, "loss": 0.0003, "lr": 1.1454056799370672e-07, "epoch": 9.734513274336283, "percentage": 97.35, "elapsed_time": "0:02:26", "remaining_time": "0:00:04", "throughput": 2049.02, "total_tokens": 300800}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
{"current_steps": 1090, "total_steps": 1130, "loss": 0.0001, "lr": 2.0024189799641435e-07, "epoch": 9.646017699115044, "percentage": 96.46, "elapsed_time": "0:02:25", "remaining_time": "0:00:05", "throughput": 2041.97, "total_tokens": 297904}
|
| 238 |
{"current_steps": 1095, "total_steps": 1130, "loss": 0.0001, "lr": 1.5442771053230665e-07, "epoch": 9.690265486725664, "percentage": 96.9, "elapsed_time": "0:02:26", "remaining_time": "0:00:04", "throughput": 2046.48, "total_tokens": 299536}
|
| 239 |
{"current_steps": 1100, "total_steps": 1130, "loss": 0.0003, "lr": 1.1454056799370672e-07, "epoch": 9.734513274336283, "percentage": 97.35, "elapsed_time": "0:02:26", "remaining_time": "0:00:04", "throughput": 2049.02, "total_tokens": 300800}
|
| 240 |
+
{"current_steps": 1105, "total_steps": 1130, "loss": 0.0003, "lr": 8.058998567304633e-08, "epoch": 9.778761061946902, "percentage": 97.79, "elapsed_time": "0:02:27", "remaining_time": "0:00:03", "throughput": 2052.68, "total_tokens": 302288}
|
| 241 |
+
{"current_steps": 1110, "total_steps": 1130, "loss": 0.0002, "lr": 5.2584062664368105e-08, "epoch": 9.823008849557523, "percentage": 98.23, "elapsed_time": "0:02:27", "remaining_time": "0:00:02", "throughput": 2056.22, "total_tokens": 303760}
|
| 242 |
+
{"current_steps": 1115, "total_steps": 1130, "loss": 0.0001, "lr": 3.0529479931265535e-08, "epoch": 9.867256637168142, "percentage": 98.67, "elapsed_time": "0:02:28", "remaining_time": "0:00:01", "throughput": 2059.77, "total_tokens": 305296}
|
| 243 |
+
{"current_steps": 1120, "total_steps": 1130, "loss": 0.0001, "lr": 1.443149871309113e-08, "epoch": 9.91150442477876, "percentage": 99.12, "elapsed_time": "0:02:28", "remaining_time": "0:00:01", "throughput": 2063.2, "total_tokens": 306704}
|
| 244 |
+
{"current_steps": 1125, "total_steps": 1130, "loss": 0.0003, "lr": 4.293959269863201e-09, "epoch": 9.955752212389381, "percentage": 99.56, "elapsed_time": "0:02:29", "remaining_time": "0:00:00", "throughput": 2067.24, "total_tokens": 308256}
|
| 245 |
+
{"current_steps": 1130, "total_steps": 1130, "loss": 0.0001, "lr": 1.192799661514643e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:29", "remaining_time": "0:00:00", "throughput": 2068.92, "total_tokens": 309584}
|
| 246 |
+
{"current_steps": 1130, "total_steps": 1130, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:31", "remaining_time": "0:00:00", "throughput": 2048.09, "total_tokens": 309584}
|