Training in progress, step 42
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +9 -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 sha256:6e42b7b7e5330754c9b25b56095227cecc32de7cc14986b9e921285ae4001a12
|
| 3 |
size 2819582528
|
trainer_log.jsonl
CHANGED
|
@@ -10,3 +10,12 @@
|
|
| 10 |
{"current_steps": 30, "total_steps": 125, "loss": 0.4563, "lr": 4.752422169756048e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:01:02", "remaining_time": "0:03:16", "throughput": 193.76, "total_tokens": 12032}
|
| 11 |
{"current_steps": 35, "total_steps": 125, "loss": 0.4802, "lr": 4.5786740307563636e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:01:02", "remaining_time": "0:02:41", "throughput": 219.77, "total_tokens": 13824}
|
| 12 |
{"current_steps": 35, "total_steps": 125, "eval_loss": 0.36931881308555603, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:01:03", "remaining_time": "0:02:44", "throughput": 216.75, "total_tokens": 13824}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{"current_steps": 30, "total_steps": 125, "loss": 0.4563, "lr": 4.752422169756048e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:01:02", "remaining_time": "0:03:16", "throughput": 193.76, "total_tokens": 12032}
|
| 11 |
{"current_steps": 35, "total_steps": 125, "loss": 0.4802, "lr": 4.5786740307563636e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:01:02", "remaining_time": "0:02:41", "throughput": 219.77, "total_tokens": 13824}
|
| 12 |
{"current_steps": 35, "total_steps": 125, "eval_loss": 0.36931881308555603, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:01:03", "remaining_time": "0:02:44", "throughput": 216.75, "total_tokens": 13824}
|
| 13 |
+
{"current_steps": 40, "total_steps": 125, "loss": 0.3809, "lr": 4.364105412207914e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:01:14", "remaining_time": "0:02:38", "throughput": 212.26, "total_tokens": 15840}
|
| 14 |
+
{"current_steps": 42, "total_steps": 125, "eval_loss": 0.3872639238834381, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:01:15", "remaining_time": "0:02:29", "throughput": 220.32, "total_tokens": 16672}
|
| 15 |
+
{"current_steps": 45, "total_steps": 125, "loss": 0.3844, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:01:34", "remaining_time": "0:02:47", "throughput": 190.21, "total_tokens": 17920}
|
| 16 |
+
{"current_steps": 49, "total_steps": 125, "eval_loss": 0.3777945637702942, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:01:35", "remaining_time": "0:02:28", "throughput": 201.79, "total_tokens": 19296}
|
| 17 |
+
{"current_steps": 50, "total_steps": 125, "loss": 0.2817, "lr": 3.830080191288342e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:01:46", "remaining_time": "0:02:39", "throughput": 185.1, "total_tokens": 19712}
|
| 18 |
+
{"current_steps": 55, "total_steps": 125, "loss": 0.3831, "lr": 3.521110642339991e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:01:47", "remaining_time": "0:02:16", "throughput": 204.49, "total_tokens": 21952}
|
| 19 |
+
{"current_steps": 56, "total_steps": 125, "eval_loss": 0.4436803460121155, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:01:48", "remaining_time": "0:02:13", "throughput": 207.14, "total_tokens": 22432}
|
| 20 |
+
{"current_steps": 60, "total_steps": 125, "loss": 0.5576, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:01:59", "remaining_time": "0:02:09", "throughput": 201.61, "total_tokens": 24160}
|
| 21 |
+
{"current_steps": 63, "total_steps": 125, "eval_loss": 0.35032057762145996, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:02:01", "remaining_time": "0:01:59", "throughput": 210.33, "total_tokens": 25504}
|