Training in progress, step 20
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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1be390aea6f69300090a60bd8589c260d81fe27418b0ebb94be1a6ef68531d4b
|
| 3 |
size 83945296
|
trainer_log.jsonl
CHANGED
|
@@ -9,3 +9,14 @@
|
|
| 9 |
{"current_steps": 9, "total_steps": 125, "loss": 0.8352, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:03:50", "remaining_time": "0:49:33"}
|
| 10 |
{"current_steps": 10, "total_steps": 125, "loss": 0.5193, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:13", "remaining_time": "0:48:39"}
|
| 11 |
{"current_steps": 10, "total_steps": 125, "eval_loss": 0.4231546223163605, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:35", "remaining_time": "0:52:45"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
{"current_steps": 9, "total_steps": 125, "loss": 0.8352, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:03:50", "remaining_time": "0:49:33"}
|
| 10 |
{"current_steps": 10, "total_steps": 125, "loss": 0.5193, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:13", "remaining_time": "0:48:39"}
|
| 11 |
{"current_steps": 10, "total_steps": 125, "eval_loss": 0.4231546223163605, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:35", "remaining_time": "0:52:45"}
|
| 12 |
+
{"current_steps": 11, "total_steps": 125, "loss": 0.5075, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:05:03", "remaining_time": "0:52:22"}
|
| 13 |
+
{"current_steps": 12, "total_steps": 125, "loss": 0.5233, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:05:26", "remaining_time": "0:51:14"}
|
| 14 |
+
{"current_steps": 13, "total_steps": 125, "loss": 0.3608, "lr": 0.0001, "epoch": 0.5135802469135803, "percentage": 10.4, "elapsed_time": "0:05:48", "remaining_time": "0:50:02"}
|
| 15 |
+
{"current_steps": 14, "total_steps": 125, "loss": 0.4391, "lr": 9.998033131915266e-05, "epoch": 0.5530864197530864, "percentage": 11.2, "elapsed_time": "0:06:16", "remaining_time": "0:49:47"}
|
| 16 |
+
{"current_steps": 15, "total_steps": 125, "loss": 0.3174, "lr": 9.992134075089084e-05, "epoch": 0.5925925925925926, "percentage": 12.0, "elapsed_time": "0:06:43", "remaining_time": "0:49:19"}
|
| 17 |
+
{"current_steps": 16, "total_steps": 125, "loss": 0.3084, "lr": 9.982307470588098e-05, "epoch": 0.6320987654320988, "percentage": 12.8, "elapsed_time": "0:07:05", "remaining_time": "0:48:21"}
|
| 18 |
+
{"current_steps": 17, "total_steps": 125, "loss": 0.2395, "lr": 9.968561049466214e-05, "epoch": 0.671604938271605, "percentage": 13.6, "elapsed_time": "0:07:31", "remaining_time": "0:47:49"}
|
| 19 |
+
{"current_steps": 18, "total_steps": 125, "loss": 0.2883, "lr": 9.950905626682228e-05, "epoch": 0.7111111111111111, "percentage": 14.4, "elapsed_time": "0:07:55", "remaining_time": "0:47:03"}
|
| 20 |
+
{"current_steps": 19, "total_steps": 125, "loss": 0.3086, "lr": 9.92935509259118e-05, "epoch": 0.7506172839506173, "percentage": 15.2, "elapsed_time": "0:08:18", "remaining_time": "0:46:23"}
|
| 21 |
+
{"current_steps": 20, "total_steps": 125, "loss": 0.2655, "lr": 9.903926402016153e-05, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:08:43", "remaining_time": "0:45:47"}
|
| 22 |
+
{"current_steps": 20, "total_steps": 125, "eval_loss": 0.24311862885951996, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:09:04", "remaining_time": "0:47:38"}
|