Training in progress, step 112
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +5 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2818586248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a681b1052017f2ad662311fe5d05caae05e1e79b9342798ab07266faec070cf
|
| 3 |
size 2818586248
|
trainer_log.jsonl
CHANGED
|
@@ -36,3 +36,8 @@
|
|
| 36 |
{"current_steps": 105, "total_steps": 125, "eval_loss": 0.43045976758003235, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:06:12", "remaining_time": "0:01:10", "throughput": 110.81, "total_tokens": 41280}
|
| 37 |
{"current_steps": 110, "total_steps": 125, "loss": 0.3951, "lr": 2.475778302439524e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:06:32", "remaining_time": "0:00:53", "throughput": 110.83, "total_tokens": 43552}
|
| 38 |
{"current_steps": 112, "total_steps": 125, "eval_loss": 0.4486384391784668, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:06:33", "remaining_time": "0:00:45", "throughput": 112.08, "total_tokens": 44160}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
{"current_steps": 105, "total_steps": 125, "eval_loss": 0.43045976758003235, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:06:12", "remaining_time": "0:01:10", "throughput": 110.81, "total_tokens": 41280}
|
| 37 |
{"current_steps": 110, "total_steps": 125, "loss": 0.3951, "lr": 2.475778302439524e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:06:32", "remaining_time": "0:00:53", "throughput": 110.83, "total_tokens": 43552}
|
| 38 |
{"current_steps": 112, "total_steps": 125, "eval_loss": 0.4486384391784668, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:06:33", "remaining_time": "0:00:45", "throughput": 112.08, "total_tokens": 44160}
|
| 39 |
+
{"current_steps": 115, "total_steps": 125, "loss": 0.3107, "lr": 1.180621931927592e-06, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:06:58", "remaining_time": "0:00:36", "throughput": 107.98, "total_tokens": 45216}
|
| 40 |
+
{"current_steps": 119, "total_steps": 125, "eval_loss": 0.44127246737480164, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "0:07:00", "remaining_time": "0:00:21", "throughput": 111.72, "total_tokens": 46944}
|
| 41 |
+
{"current_steps": 120, "total_steps": 125, "loss": 0.2809, "lr": 3.5322453704410286e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:07:26", "remaining_time": "0:00:18", "throughput": 106.0, "total_tokens": 47360}
|
| 42 |
+
{"current_steps": 125, "total_steps": 125, "loss": 0.4785, "lr": 9.834340423678368e-09, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:28", "remaining_time": "0:00:00", "throughput": 110.18, "total_tokens": 49376}
|
| 43 |
+
{"current_steps": 125, "total_steps": 125, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:50", "remaining_time": "0:00:00", "throughput": 105.0, "total_tokens": 49376}
|