Training in progress, step 70
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +11 -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 sha256:6d0caf7d49bd00a93fe035a0db720213e39888b49b84e8608e35b3d1dae37802
|
| 3 |
size 2819582528
|
trainer_log.jsonl
CHANGED
|
@@ -19,3 +19,14 @@
|
|
| 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}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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}
|
| 22 |
+
{"current_steps": 65, "total_steps": 125, "loss": 0.4013, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:02:12", "remaining_time": "0:02:01", "throughput": 197.7, "total_tokens": 26112}
|
| 23 |
+
{"current_steps": 70, "total_steps": 125, "loss": 0.3242, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:02:12", "remaining_time": "0:01:44", "throughput": 211.13, "total_tokens": 28064}
|
| 24 |
+
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.37164703011512756, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:02:13", "remaining_time": "0:01:45", "throughput": 209.84, "total_tokens": 28064}
|
| 25 |
+
{"current_steps": 75, "total_steps": 125, "loss": 0.3963, "lr": 2.1505241511612522e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:02:32", "remaining_time": "0:01:41", "throughput": 195.25, "total_tokens": 29824}
|
| 26 |
+
{"current_steps": 77, "total_steps": 125, "eval_loss": 0.3748786747455597, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:02:33", "remaining_time": "0:01:35", "throughput": 199.61, "total_tokens": 30720}
|
| 27 |
+
{"current_steps": 80, "total_steps": 125, "loss": 0.3946, "lr": 1.8079112214378768e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:02:44", "remaining_time": "0:01:32", "throughput": 193.61, "total_tokens": 31904}
|
| 28 |
+
{"current_steps": 84, "total_steps": 125, "eval_loss": 0.3603578209877014, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:02:46", "remaining_time": "0:01:21", "throughput": 201.5, "total_tokens": 33504}
|
| 29 |
+
{"current_steps": 85, "total_steps": 125, "loss": 0.3496, "lr": 1.4788893576600099e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:02:54", "remaining_time": "0:01:22", "throughput": 194.65, "total_tokens": 33984}
|
| 30 |
+
{"current_steps": 90, "total_steps": 125, "loss": 0.337, "lr": 1.1699198087116589e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:02:55", "remaining_time": "0:01:08", "throughput": 203.97, "total_tokens": 35776}
|
| 31 |
+
{"current_steps": 91, "total_steps": 125, "eval_loss": 0.35710158944129944, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:02:56", "remaining_time": "0:01:05", "throughput": 204.78, "total_tokens": 36128}
|
| 32 |
+
{"current_steps": 95, "total_steps": 125, "loss": 0.4315, "lr": 8.870700411447816e-06, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:03:05", "remaining_time": "0:00:58", "throughput": 201.87, "total_tokens": 37472}
|