Training in progress, step 700
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +11 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29034840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:086f56d8253ad2de065083ad9ed3e401f206ca6169266148720dc9056e97e11d
|
3 |
size 29034840
|
trainer_log.jsonl
CHANGED
@@ -141,3 +141,14 @@
|
|
141 |
{"current_steps": 645, "total_steps": 3882, "loss": 0.7867, "lr": 9.636929372778963e-05, "epoch": 0.3322173577131084, "percentage": 16.62, "elapsed_time": "3:19:43", "remaining_time": "16:42:18", "throughput": 629.56, "total_tokens": 7544040}
|
142 |
{"current_steps": 650, "total_steps": 3882, "loss": 0.8367, "lr": 9.628918171903485e-05, "epoch": 0.3347926860674736, "percentage": 16.74, "elapsed_time": "3:21:11", "remaining_time": "16:40:22", "throughput": 629.8, "total_tokens": 7602512}
|
143 |
{"current_steps": 650, "total_steps": 3882, "eval_loss": 0.7940558791160583, "epoch": 0.3347926860674736, "percentage": 16.74, "elapsed_time": "3:21:31", "remaining_time": "16:42:00", "throughput": 628.77, "total_tokens": 7602512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
{"current_steps": 645, "total_steps": 3882, "loss": 0.7867, "lr": 9.636929372778963e-05, "epoch": 0.3322173577131084, "percentage": 16.62, "elapsed_time": "3:19:43", "remaining_time": "16:42:18", "throughput": 629.56, "total_tokens": 7544040}
|
142 |
{"current_steps": 650, "total_steps": 3882, "loss": 0.8367, "lr": 9.628918171903485e-05, "epoch": 0.3347926860674736, "percentage": 16.74, "elapsed_time": "3:21:11", "remaining_time": "16:40:22", "throughput": 629.8, "total_tokens": 7602512}
|
143 |
{"current_steps": 650, "total_steps": 3882, "eval_loss": 0.7940558791160583, "epoch": 0.3347926860674736, "percentage": 16.74, "elapsed_time": "3:21:31", "remaining_time": "16:42:00", "throughput": 628.77, "total_tokens": 7602512}
|
144 |
+
{"current_steps": 655, "total_steps": 3882, "loss": 0.8131, "lr": 9.620822953030652e-05, "epoch": 0.3373680144218388, "percentage": 16.87, "elapsed_time": "3:23:05", "remaining_time": "16:40:34", "throughput": 628.7, "total_tokens": 7660968}
|
145 |
+
{"current_steps": 660, "total_steps": 3882, "loss": 0.8348, "lr": 9.612643863094163e-05, "epoch": 0.33994334277620397, "percentage": 17.0, "elapsed_time": "3:24:34", "remaining_time": "16:38:40", "throughput": 628.92, "total_tokens": 7719448}
|
146 |
+
{"current_steps": 665, "total_steps": 3882, "loss": 0.8289, "lr": 9.604381050550038e-05, "epoch": 0.34251867113056916, "percentage": 17.13, "elapsed_time": "3:26:03", "remaining_time": "16:36:50", "throughput": 629.1, "total_tokens": 7777928}
|
147 |
+
{"current_steps": 670, "total_steps": 3882, "loss": 0.7758, "lr": 9.596034665373916e-05, "epoch": 0.34509399948493436, "percentage": 17.26, "elapsed_time": "3:27:31", "remaining_time": "16:34:53", "throughput": 629.35, "total_tokens": 7836424}
|
148 |
+
{"current_steps": 675, "total_steps": 3882, "loss": 0.8189, "lr": 9.587604859058334e-05, "epoch": 0.3476693278392995, "percentage": 17.39, "elapsed_time": "3:29:01", "remaining_time": "16:33:07", "throughput": 629.49, "total_tokens": 7894904}
|
149 |
+
{"current_steps": 680, "total_steps": 3882, "loss": 0.8221, "lr": 9.579091784609984e-05, "epoch": 0.3502446561936647, "percentage": 17.52, "elapsed_time": "3:30:29", "remaining_time": "16:31:10", "throughput": 629.75, "total_tokens": 7953432}
|
150 |
+
{"current_steps": 685, "total_steps": 3882, "loss": 0.8378, "lr": 9.570495596546926e-05, "epoch": 0.3528199845480299, "percentage": 17.65, "elapsed_time": "3:31:59", "remaining_time": "16:29:21", "throughput": 629.91, "total_tokens": 8011888}
|
151 |
+
{"current_steps": 690, "total_steps": 3882, "loss": 0.7529, "lr": 9.561816450895793e-05, "epoch": 0.35539531290239507, "percentage": 17.77, "elapsed_time": "3:33:26", "remaining_time": "16:27:25", "throughput": 630.16, "total_tokens": 8070344}
|
152 |
+
{"current_steps": 695, "total_steps": 3882, "loss": 0.7311, "lr": 9.55305450518895e-05, "epoch": 0.35797064125676026, "percentage": 17.9, "elapsed_time": "3:34:56", "remaining_time": "16:25:39", "throughput": 630.3, "total_tokens": 8128816}
|
153 |
+
{"current_steps": 700, "total_steps": 3882, "loss": 0.774, "lr": 9.544209918461642e-05, "epoch": 0.3605459696111254, "percentage": 18.03, "elapsed_time": "3:36:24", "remaining_time": "16:23:44", "throughput": 630.54, "total_tokens": 8187320}
|
154 |
+
{"current_steps": 700, "total_steps": 3882, "eval_loss": 0.7318872809410095, "epoch": 0.3605459696111254, "percentage": 18.03, "elapsed_time": "3:36:44", "remaining_time": "16:25:14", "throughput": 629.58, "total_tokens": 8187320}
|