Training in progress, step 1130
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +8 -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:ecb6289960de1c9722bd535c5ee27f17d2e3c8c41e3e957a06137f3e0e8d9188
|
| 3 |
size 8388736
|
trainer_log.jsonl
CHANGED
|
@@ -236,3 +236,11 @@
|
|
| 236 |
{"current_steps": 1085, "total_steps": 1130, "loss": 0.0007, "lr": 2.5197220116515987e-07, "epoch": 9.601769911504425, "percentage": 96.02, "elapsed_time": "0:02:29", "remaining_time": "0:00:06", "throughput": 2041.52, "total_tokens": 304296}
|
| 237 |
{"current_steps": 1090, "total_steps": 1130, "loss": 0.0007, "lr": 2.0024189799641435e-07, "epoch": 9.646017699115044, "percentage": 96.46, "elapsed_time": "0:02:29", "remaining_time": "0:00:05", "throughput": 2044.9, "total_tokens": 305784}
|
| 238 |
{"current_steps": 1095, "total_steps": 1130, "loss": 0.0003, "lr": 1.5442771053230665e-07, "epoch": 9.690265486725664, "percentage": 96.9, "elapsed_time": "0:02:30", "remaining_time": "0:00:04", "throughput": 2049.94, "total_tokens": 307592}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 236 |
{"current_steps": 1085, "total_steps": 1130, "loss": 0.0007, "lr": 2.5197220116515987e-07, "epoch": 9.601769911504425, "percentage": 96.02, "elapsed_time": "0:02:29", "remaining_time": "0:00:06", "throughput": 2041.52, "total_tokens": 304296}
|
| 237 |
{"current_steps": 1090, "total_steps": 1130, "loss": 0.0007, "lr": 2.0024189799641435e-07, "epoch": 9.646017699115044, "percentage": 96.46, "elapsed_time": "0:02:29", "remaining_time": "0:00:05", "throughput": 2044.9, "total_tokens": 305784}
|
| 238 |
{"current_steps": 1095, "total_steps": 1130, "loss": 0.0003, "lr": 1.5442771053230665e-07, "epoch": 9.690265486725664, "percentage": 96.9, "elapsed_time": "0:02:30", "remaining_time": "0:00:04", "throughput": 2049.94, "total_tokens": 307592}
|
| 239 |
+
{"current_steps": 1100, "total_steps": 1130, "loss": 0.0025, "lr": 1.1454056799370672e-07, "epoch": 9.734513274336283, "percentage": 97.35, "elapsed_time": "0:02:30", "remaining_time": "0:00:04", "throughput": 2051.81, "total_tokens": 308760}
|
| 240 |
+
{"current_steps": 1105, "total_steps": 1130, "loss": 0.0004, "lr": 8.058998567304633e-08, "epoch": 9.778761061946902, "percentage": 97.79, "elapsed_time": "0:02:30", "remaining_time": "0:00:03", "throughput": 2054.24, "total_tokens": 310040}
|
| 241 |
+
{"current_steps": 1110, "total_steps": 1130, "loss": 0.0004, "lr": 5.2584062664368105e-08, "epoch": 9.823008849557523, "percentage": 98.23, "elapsed_time": "0:02:31", "remaining_time": "0:00:02", "throughput": 2058.97, "total_tokens": 311752}
|
| 242 |
+
{"current_steps": 1115, "total_steps": 1130, "loss": 0.0003, "lr": 3.0529479931265535e-08, "epoch": 9.867256637168142, "percentage": 98.67, "elapsed_time": "0:02:31", "remaining_time": "0:00:02", "throughput": 2061.78, "total_tokens": 313128}
|
| 243 |
+
{"current_steps": 1120, "total_steps": 1130, "loss": 0.0008, "lr": 1.443149871309113e-08, "epoch": 9.91150442477876, "percentage": 99.12, "elapsed_time": "0:02:32", "remaining_time": "0:00:01", "throughput": 2065.29, "total_tokens": 314568}
|
| 244 |
+
{"current_steps": 1125, "total_steps": 1130, "loss": 0.0002, "lr": 4.293959269863201e-09, "epoch": 9.955752212389381, "percentage": 99.56, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 2067.65, "total_tokens": 315800}
|
| 245 |
+
{"current_steps": 1130, "total_steps": 1130, "loss": 0.0826, "lr": 1.192799661514643e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:33", "remaining_time": "0:00:00", "throughput": 2067.41, "total_tokens": 316840}
|
| 246 |
+
{"current_steps": 1130, "total_steps": 1130, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:34", "remaining_time": "0:00:00", "throughput": 2047.3, "total_tokens": 316840}
|