Training in progress, step 70
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +8 -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 sha256:0d47de590364b93be506e2032c6a5c7508356cce4a0795a8eb93c1b3589b516f
|
| 3 |
size 2818586248
|
trainer_log.jsonl
CHANGED
|
@@ -20,3 +20,11 @@
|
|
| 20 |
{"current_steps": 60, "total_steps": 125, "loss": 0.7948, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:03:41", "remaining_time": "0:03:59", "throughput": 109.23, "total_tokens": 24160}
|
| 21 |
{"current_steps": 63, "total_steps": 125, "eval_loss": 1.0268325805664062, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:03:42", "remaining_time": "0:03:38", "throughput": 114.67, "total_tokens": 25504}
|
| 22 |
{"current_steps": 65, "total_steps": 125, "loss": 0.6941, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:04:04", "remaining_time": "0:03:45", "throughput": 106.72, "total_tokens": 26112}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
{"current_steps": 60, "total_steps": 125, "loss": 0.7948, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:03:41", "remaining_time": "0:03:59", "throughput": 109.23, "total_tokens": 24160}
|
| 21 |
{"current_steps": 63, "total_steps": 125, "eval_loss": 1.0268325805664062, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:03:42", "remaining_time": "0:03:38", "throughput": 114.67, "total_tokens": 25504}
|
| 22 |
{"current_steps": 65, "total_steps": 125, "loss": 0.6941, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:04:04", "remaining_time": "0:03:45", "throughput": 106.72, "total_tokens": 26112}
|
| 23 |
+
{"current_steps": 70, "total_steps": 125, "loss": 0.3463, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:04:05", "remaining_time": "0:03:13", "throughput": 114.24, "total_tokens": 28064}
|
| 24 |
+
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.35280704498291016, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:04:06", "remaining_time": "0:03:13", "throughput": 113.93, "total_tokens": 28064}
|
| 25 |
+
{"current_steps": 75, "total_steps": 125, "loss": 0.3652, "lr": 2.1505241511612522e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:04:37", "remaining_time": "0:03:04", "throughput": 107.65, "total_tokens": 29824}
|
| 26 |
+
{"current_steps": 77, "total_steps": 125, "eval_loss": 0.3505268096923828, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:04:38", "remaining_time": "0:02:53", "throughput": 110.46, "total_tokens": 30720}
|
| 27 |
+
{"current_steps": 80, "total_steps": 125, "loss": 0.3476, "lr": 1.8079112214378768e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:04:55", "remaining_time": "0:02:46", "throughput": 107.81, "total_tokens": 31904}
|
| 28 |
+
{"current_steps": 84, "total_steps": 125, "eval_loss": 0.34708982706069946, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:04:57", "remaining_time": "0:02:25", "throughput": 112.69, "total_tokens": 33504}
|
| 29 |
+
{"current_steps": 85, "total_steps": 125, "loss": 0.3491, "lr": 1.4788893576600099e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:05:18", "remaining_time": "0:02:29", "throughput": 106.64, "total_tokens": 33984}
|
| 30 |
+
{"current_steps": 90, "total_steps": 125, "loss": 0.3395, "lr": 1.1699198087116589e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:05:19", "remaining_time": "0:02:04", "throughput": 111.91, "total_tokens": 35776}
|