Training in progress, step 98
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 409728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:381ac486feb832b85b5ae58370baf8911395fc6fd8877adb7d2c163c189028ff
|
| 3 |
size 409728
|
trainer_log.jsonl
CHANGED
|
@@ -29,3 +29,8 @@
|
|
| 29 |
{"current_steps": 85, "total_steps": 125, "loss": 0.44, "lr": 0.008873336145960059, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:00:27", "remaining_time": "0:00:12", "throughput": 1233.02, "total_tokens": 33984}
|
| 30 |
{"current_steps": 90, "total_steps": 125, "loss": 0.407, "lr": 0.007019518852269953, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:00:28", "remaining_time": "0:00:10", "throughput": 1275.28, "total_tokens": 35776}
|
| 31 |
{"current_steps": 91, "total_steps": 125, "eval_loss": 0.4211791157722473, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:00:28", "remaining_time": "0:00:10", "throughput": 1252.36, "total_tokens": 36128}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
{"current_steps": 85, "total_steps": 125, "loss": 0.44, "lr": 0.008873336145960059, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:00:27", "remaining_time": "0:00:12", "throughput": 1233.02, "total_tokens": 33984}
|
| 30 |
{"current_steps": 90, "total_steps": 125, "loss": 0.407, "lr": 0.007019518852269953, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:00:28", "remaining_time": "0:00:10", "throughput": 1275.28, "total_tokens": 35776}
|
| 31 |
{"current_steps": 91, "total_steps": 125, "eval_loss": 0.4211791157722473, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:00:28", "remaining_time": "0:00:10", "throughput": 1252.36, "total_tokens": 36128}
|
| 32 |
+
{"current_steps": 95, "total_steps": 125, "loss": 0.4525, "lr": 0.005322420246868689, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:00:30", "remaining_time": "0:00:09", "throughput": 1247.46, "total_tokens": 37472}
|
| 33 |
+
{"current_steps": 98, "total_steps": 125, "eval_loss": 0.4424297511577606, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "0:00:31", "remaining_time": "0:00:08", "throughput": 1244.27, "total_tokens": 38592}
|
| 34 |
+
{"current_steps": 100, "total_steps": 125, "loss": 0.419, "lr": 0.003815367526752516, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:00:32", "remaining_time": "0:00:08", "throughput": 1221.95, "total_tokens": 39328}
|
| 35 |
+
{"current_steps": 105, "total_steps": 125, "loss": 0.3686, "lr": 0.0025279558154618197, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:00:32", "remaining_time": "0:00:06", "throughput": 1263.56, "total_tokens": 41280}
|
| 36 |
+
{"current_steps": 105, "total_steps": 125, "eval_loss": 0.4465864300727844, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:00:33", "remaining_time": "0:00:06", "throughput": 1236.42, "total_tokens": 41280}
|