Training in progress, epoch 2
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:afa70aa5b7e2f5ea45206192e257ac56bb0bfd65456f50f953bcc1e07f1f1cef
|
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 sha256:6543f99426f1999569fe2c032a57e52ec0839b7daa1197ae0ed7c768a527105c
|
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:e2d58b3e61841476fc742def32b6c0ca7c60dca008ff37bff866232a3e5e73ea
|
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:bc54b7596760a70c75100bcc15c9e996c8b1fda04c65608f0ca49b5eb3b0ec30
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -4,3 +4,7 @@
|
|
4 |
{"current_steps": 30, "total_steps": 69, "loss": 1.159, "lr": 5e-06, "epoch": 1.2765957446808511, "percentage": 43.48, "elapsed_time": "0:17:39", "remaining_time": "0:22:56"}
|
5 |
{"current_steps": 40, "total_steps": 69, "loss": 1.0659, "lr": 5e-06, "epoch": 1.702127659574468, "percentage": 57.97, "elapsed_time": "0:22:59", "remaining_time": "0:16:40"}
|
6 |
{"current_steps": 47, "total_steps": 69, "eval_loss": 1.0796161890029907, "epoch": 2.0, "percentage": 68.12, "elapsed_time": "0:26:56", "remaining_time": "0:12:36"}
|
|
|
|
|
|
|
|
|
|
4 |
{"current_steps": 30, "total_steps": 69, "loss": 1.159, "lr": 5e-06, "epoch": 1.2765957446808511, "percentage": 43.48, "elapsed_time": "0:17:39", "remaining_time": "0:22:56"}
|
5 |
{"current_steps": 40, "total_steps": 69, "loss": 1.0659, "lr": 5e-06, "epoch": 1.702127659574468, "percentage": 57.97, "elapsed_time": "0:22:59", "remaining_time": "0:16:40"}
|
6 |
{"current_steps": 47, "total_steps": 69, "eval_loss": 1.0796161890029907, "epoch": 2.0, "percentage": 68.12, "elapsed_time": "0:26:56", "remaining_time": "0:12:36"}
|
7 |
+
{"current_steps": 50, "total_steps": 69, "loss": 1.0857, "lr": 5e-06, "epoch": 2.127659574468085, "percentage": 72.46, "elapsed_time": "0:29:48", "remaining_time": "0:11:19"}
|
8 |
+
{"current_steps": 60, "total_steps": 69, "loss": 0.9919, "lr": 5e-06, "epoch": 2.5531914893617023, "percentage": 86.96, "elapsed_time": "0:35:07", "remaining_time": "0:05:16"}
|
9 |
+
{"current_steps": 69, "total_steps": 69, "eval_loss": 1.063197374343872, "epoch": 2.9361702127659575, "percentage": 100.0, "elapsed_time": "0:41:29", "remaining_time": "0:00:00"}
|
10 |
+
{"current_steps": 69, "total_steps": 69, "epoch": 2.9361702127659575, "percentage": 100.0, "elapsed_time": "0:42:44", "remaining_time": "0:00:00"}
|