Training in progress, step 1500
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 25200088
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e709276458b29bdda62ffb80109a1dce8fdf6ca3b91d0e8ec9643c4094709875
|
| 3 |
size 25200088
|
trainer_log.jsonl
CHANGED
|
@@ -172,3 +172,10 @@
|
|
| 172 |
{"current_steps": 1440, "total_steps": 1500, "loss": 0.2086, "accuracy": 0.9750000238418579, "learning_rate": 1.9713246713805588e-08, "epoch": 1.095890410958904, "percentage": 96.0, "elapsed_time": "3:19:26", "remaining_time": "0:08:18", "throughput": "0.00", "total_tokens": 0}
|
| 173 |
{"current_steps": 1450, "total_steps": 1500, "loss": 0.2, "accuracy": 0.925000011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.1035007610350076, "percentage": 96.67, "elapsed_time": "3:20:39", "remaining_time": "0:06:55", "throughput": "0.00", "total_tokens": 0}
|
| 174 |
{"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.1981535106897354, "epoch": 1.1035007610350076, "percentage": 96.67, "elapsed_time": "3:21:10", "remaining_time": "0:06:56", "throughput": "0.00", "total_tokens": 0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 172 |
{"current_steps": 1440, "total_steps": 1500, "loss": 0.2086, "accuracy": 0.9750000238418579, "learning_rate": 1.9713246713805588e-08, "epoch": 1.095890410958904, "percentage": 96.0, "elapsed_time": "3:19:26", "remaining_time": "0:08:18", "throughput": "0.00", "total_tokens": 0}
|
| 173 |
{"current_steps": 1450, "total_steps": 1500, "loss": 0.2, "accuracy": 0.925000011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.1035007610350076, "percentage": 96.67, "elapsed_time": "3:20:39", "remaining_time": "0:06:55", "throughput": "0.00", "total_tokens": 0}
|
| 174 |
{"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.1981535106897354, "epoch": 1.1035007610350076, "percentage": 96.67, "elapsed_time": "3:21:10", "remaining_time": "0:06:56", "throughput": "0.00", "total_tokens": 0}
|
| 175 |
+
{"current_steps": 1460, "total_steps": 1500, "loss": 0.1766, "accuracy": 0.9375, "learning_rate": 8.767851876239075e-09, "epoch": 1.1111111111111112, "percentage": 97.33, "elapsed_time": "3:22:38", "remaining_time": "0:05:33", "throughput": "0.00", "total_tokens": 0}
|
| 176 |
+
{"current_steps": 1470, "total_steps": 1500, "loss": 0.1705, "accuracy": 0.9375, "learning_rate": 4.933178929321103e-09, "epoch": 1.1187214611872145, "percentage": 98.0, "elapsed_time": "3:23:55", "remaining_time": "0:04:09", "throughput": "0.00", "total_tokens": 0}
|
| 177 |
+
{"current_steps": 1480, "total_steps": 1500, "loss": 0.1807, "accuracy": 0.949999988079071, "learning_rate": 2.192924752854042e-09, "epoch": 1.126331811263318, "percentage": 98.67, "elapsed_time": "3:25:10", "remaining_time": "0:02:46", "throughput": "0.00", "total_tokens": 0}
|
| 178 |
+
{"current_steps": 1490, "total_steps": 1500, "loss": 0.1526, "accuracy": 0.9624999761581421, "learning_rate": 5.48291312886251e-10, "epoch": 1.1339421613394216, "percentage": 99.33, "elapsed_time": "3:26:21", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0}
|
| 179 |
+
{"current_steps": 1500, "total_steps": 1500, "loss": 0.1493, "accuracy": 0.9375, "learning_rate": 0.0, "epoch": 1.1415525114155252, "percentage": 100.0, "elapsed_time": "3:27:44", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
| 180 |
+
{"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.1974586695432663, "epoch": 1.1415525114155252, "percentage": 100.0, "elapsed_time": "3:28:15", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
| 181 |
+
{"current_steps": 1500, "total_steps": 1500, "epoch": 1.1415525114155252, "percentage": 100.0, "elapsed_time": "3:28:29", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|