Training in progress, epoch 1
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:977cd42e06fc797939a267e993d61536d5eb58b7a17169fff40a7fb119b6193f
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fb17cee7a37f4c0619f71bddf877cd602e2fa57517e99ddea2660f5dfcc2e2a
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:131f9275790877c9ba201a570816e3da8f1134fd50bc45841ee775e3e96ede87
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09119ef47fa7c54780de67531eacc2e80c39bc316add47afc3ed17a304535370
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -2,3 +2,8 @@
|
|
| 2 |
{"current_steps": 20, "total_steps": 102, "loss": 0.8217, "lr": 5e-06, "epoch": 0.5818181818181818, "percentage": 19.61, "elapsed_time": "0:10:46", "remaining_time": "0:44:12"}
|
| 3 |
{"current_steps": 30, "total_steps": 102, "loss": 0.784, "lr": 5e-06, "epoch": 0.8727272727272727, "percentage": 29.41, "elapsed_time": "0:16:06", "remaining_time": "0:38:39"}
|
| 4 |
{"current_steps": 34, "total_steps": 102, "eval_loss": 0.7713841795921326, "epoch": 0.9890909090909091, "percentage": 33.33, "elapsed_time": "0:18:42", "remaining_time": "0:37:24"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
{"current_steps": 20, "total_steps": 102, "loss": 0.8217, "lr": 5e-06, "epoch": 0.5818181818181818, "percentage": 19.61, "elapsed_time": "0:10:46", "remaining_time": "0:44:12"}
|
| 3 |
{"current_steps": 30, "total_steps": 102, "loss": 0.784, "lr": 5e-06, "epoch": 0.8727272727272727, "percentage": 29.41, "elapsed_time": "0:16:06", "remaining_time": "0:38:39"}
|
| 4 |
{"current_steps": 34, "total_steps": 102, "eval_loss": 0.7713841795921326, "epoch": 0.9890909090909091, "percentage": 33.33, "elapsed_time": "0:18:42", "remaining_time": "0:37:24"}
|
| 5 |
+
{"current_steps": 40, "total_steps": 102, "loss": 0.8212, "lr": 5e-06, "epoch": 1.170909090909091, "percentage": 39.22, "elapsed_time": "0:23:01", "remaining_time": "0:35:40"}
|
| 6 |
+
{"current_steps": 50, "total_steps": 102, "loss": 0.7242, "lr": 5e-06, "epoch": 1.461818181818182, "percentage": 49.02, "elapsed_time": "0:28:20", "remaining_time": "0:29:28"}
|
| 7 |
+
{"current_steps": 60, "total_steps": 102, "loss": 0.7099, "lr": 5e-06, "epoch": 1.7527272727272727, "percentage": 58.82, "elapsed_time": "0:33:39", "remaining_time": "0:23:33"}
|
| 8 |
+
{"current_steps": 68, "total_steps": 102, "eval_loss": 0.7391919493675232, "epoch": 1.9854545454545454, "percentage": 66.67, "elapsed_time": "0:38:25", "remaining_time": "0:19:12"}
|
| 9 |
+
{"current_steps": 70, "total_steps": 102, "loss": 0.7641, "lr": 5e-06, "epoch": 2.050909090909091, "percentage": 68.63, "elapsed_time": "0:40:38", "remaining_time": "0:18:34"}
|