Training in progress, step 84
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 sha256:4cd187cb7d92de53f2d816dfe4a2f0fd1c512817fb97df80991bff1fa217ad86
|
| 3 |
size 409728
|
trainer_log.jsonl
CHANGED
|
@@ -24,3 +24,8 @@
|
|
| 24 |
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.5987562537193298, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:00:21", "remaining_time": "0:00:16", "throughput": 1305.71, "total_tokens": 28064}
|
| 25 |
{"current_steps": 75, "total_steps": 125, "loss": 0.5519, "lr": 0.012903144906967513, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:00:23", "remaining_time": "0:00:15", "throughput": 1293.03, "total_tokens": 29824}
|
| 26 |
{"current_steps": 77, "total_steps": 125, "eval_loss": 0.447248637676239, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:00:23", "remaining_time": "0:00:14", "throughput": 1282.51, "total_tokens": 30720}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.5987562537193298, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:00:21", "remaining_time": "0:00:16", "throughput": 1305.71, "total_tokens": 28064}
|
| 25 |
{"current_steps": 75, "total_steps": 125, "loss": 0.5519, "lr": 0.012903144906967513, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:00:23", "remaining_time": "0:00:15", "throughput": 1293.03, "total_tokens": 29824}
|
| 26 |
{"current_steps": 77, "total_steps": 125, "eval_loss": 0.447248637676239, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:00:23", "remaining_time": "0:00:14", "throughput": 1282.51, "total_tokens": 30720}
|
| 27 |
+
{"current_steps": 80, "total_steps": 125, "loss": 0.471, "lr": 0.01084746732862726, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:00:25", "remaining_time": "0:00:14", "throughput": 1266.24, "total_tokens": 31904}
|
| 28 |
+
{"current_steps": 84, "total_steps": 125, "eval_loss": 0.42409372329711914, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:00:26", "remaining_time": "0:00:12", "throughput": 1276.88, "total_tokens": 33504}
|
| 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}
|