Training in progress, step 28
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 2818586248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca6cdcb092133bd2a1bcc28eb7a243a07d1d99b253ad46a0ca6f4bf40cc937d6
|
| 3 |
size 2818586248
|
trainer_log.jsonl
CHANGED
|
@@ -7,3 +7,10 @@
|
|
| 7 |
{"current_steps": 21, "total_steps": 125, "eval_loss": 0.35109928250312805, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:01:14", "remaining_time": "0:06:09", "throughput": 112.93, "total_tokens": 8416}
|
| 8 |
{"current_steps": 25, "total_steps": 125, "loss": 0.7142, "lr": 4.881937806807241e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:01:35", "remaining_time": "0:06:22", "throughput": 105.64, "total_tokens": 10112}
|
| 9 |
{"current_steps": 28, "total_steps": 125, "eval_loss": 0.38589543104171753, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:01:36", "remaining_time": "0:05:35", "throughput": 116.17, "total_tokens": 11264}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
{"current_steps": 21, "total_steps": 125, "eval_loss": 0.35109928250312805, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:01:14", "remaining_time": "0:06:09", "throughput": 112.93, "total_tokens": 8416}
|
| 8 |
{"current_steps": 25, "total_steps": 125, "loss": 0.7142, "lr": 4.881937806807241e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:01:35", "remaining_time": "0:06:22", "throughput": 105.64, "total_tokens": 10112}
|
| 9 |
{"current_steps": 28, "total_steps": 125, "eval_loss": 0.38589543104171753, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:01:36", "remaining_time": "0:05:35", "throughput": 116.17, "total_tokens": 11264}
|
| 10 |
+
{"current_steps": 30, "total_steps": 125, "loss": 0.385, "lr": 4.752422169756048e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:02:05", "remaining_time": "0:06:38", "throughput": 95.58, "total_tokens": 12032}
|
| 11 |
+
{"current_steps": 35, "total_steps": 125, "loss": 0.5983, "lr": 4.5786740307563636e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:02:06", "remaining_time": "0:05:26", "throughput": 108.97, "total_tokens": 13824}
|
| 12 |
+
{"current_steps": 35, "total_steps": 125, "eval_loss": 0.658510684967041, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:02:07", "remaining_time": "0:05:27", "throughput": 108.4, "total_tokens": 13824}
|
| 13 |
+
{"current_steps": 40, "total_steps": 125, "loss": 0.394, "lr": 4.364105412207914e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:02:25", "remaining_time": "0:05:08", "throughput": 109.17, "total_tokens": 15840}
|
| 14 |
+
{"current_steps": 42, "total_steps": 125, "eval_loss": 0.41257768869400024, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:02:26", "remaining_time": "0:04:48", "throughput": 114.07, "total_tokens": 16672}
|
| 15 |
+
{"current_steps": 45, "total_steps": 125, "loss": 0.4533, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:02:51", "remaining_time": "0:05:04", "throughput": 104.78, "total_tokens": 17920}
|
| 16 |
+
{"current_steps": 49, "total_steps": 125, "eval_loss": 1.1762187480926514, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:02:52", "remaining_time": "0:04:27", "throughput": 111.92, "total_tokens": 19296}
|