Training in progress, step 112
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 2819582528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfbad3b3bbe0780e94ac83258a352ada4e15b8231133708e191bf48a16ed199f
|
| 3 |
size 2819582528
|
trainer_log.jsonl
CHANGED
|
@@ -34,3 +34,10 @@
|
|
| 34 |
{"current_steps": 100, "total_steps": 125, "loss": 0.38, "lr": 6.358945877920861e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:02:46", "remaining_time": "0:00:41", "throughput": 235.57, "total_tokens": 39328}
|
| 35 |
{"current_steps": 105, "total_steps": 125, "loss": 0.371, "lr": 4.213259692436367e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:47", "remaining_time": "0:00:31", "throughput": 246.21, "total_tokens": 41280}
|
| 36 |
{"current_steps": 105, "total_steps": 125, "eval_loss": 0.34758228063583374, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:48", "remaining_time": "0:00:32", "throughput": 245.11, "total_tokens": 41280}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
{"current_steps": 100, "total_steps": 125, "loss": 0.38, "lr": 6.358945877920861e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:02:46", "remaining_time": "0:00:41", "throughput": 235.57, "total_tokens": 39328}
|
| 35 |
{"current_steps": 105, "total_steps": 125, "loss": 0.371, "lr": 4.213259692436367e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:47", "remaining_time": "0:00:31", "throughput": 246.21, "total_tokens": 41280}
|
| 36 |
{"current_steps": 105, "total_steps": 125, "eval_loss": 0.34758228063583374, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:02:48", "remaining_time": "0:00:32", "throughput": 245.11, "total_tokens": 41280}
|
| 37 |
+
{"current_steps": 110, "total_steps": 125, "loss": 0.364, "lr": 2.475778302439524e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:02:57", "remaining_time": "0:00:24", "throughput": 244.9, "total_tokens": 43552}
|
| 38 |
+
{"current_steps": 112, "total_steps": 125, "eval_loss": 0.34589245915412903, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:02:58", "remaining_time": "0:00:20", "throughput": 246.85, "total_tokens": 44160}
|
| 39 |
+
{"current_steps": 115, "total_steps": 125, "loss": 0.3554, "lr": 1.180621931927592e-06, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:03:15", "remaining_time": "0:00:17", "throughput": 231.09, "total_tokens": 45216}
|
| 40 |
+
{"current_steps": 119, "total_steps": 125, "eval_loss": 0.3492301404476166, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "0:03:17", "remaining_time": "0:00:09", "throughput": 238.18, "total_tokens": 46944}
|
| 41 |
+
{"current_steps": 120, "total_steps": 125, "loss": 0.3494, "lr": 3.5322453704410286e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:03:25", "remaining_time": "0:00:08", "throughput": 230.1, "total_tokens": 47360}
|
| 42 |
+
{"current_steps": 125, "total_steps": 125, "loss": 0.3588, "lr": 9.834340423678368e-09, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:26", "remaining_time": "0:00:00", "throughput": 238.53, "total_tokens": 49376}
|
| 43 |
+
{"current_steps": 125, "total_steps": 125, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:37", "remaining_time": "0:00:00", "throughput": 226.8, "total_tokens": 49376}
|