Training in progress, step 61875
Browse files- logs/attn_layer_mapper=last, attn_loss_fn=mse, attn_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163181.f383272e719b +3 -0
- logs/attn_layer_mapper=layer-2, attn_loss_fn=mse, attn_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163346.f383272e719b +3 -0
- logs/dataset_subset=default, dataset_uri=distily_c4_multilingual_1M, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724164276.f383272e719b +3 -0
- logs/hs_layer_mapper=last, hs_loss_fn=mse, hs_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163702.f383272e719b +3 -0
- logs/hs_layer_mapper=layer-2, hs_loss_fn=mse, hs_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163871.f383272e719b +3 -0
- logs/lr_scheduler_type=cosine, warmup_ratio=0.5/completed.flag +0 -0
- logs/lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724162963.f383272e719b +2 -2
- model.safetensors +1 -1
- training_args.bin +2 -2
logs/attn_layer_mapper=last, attn_loss_fn=mse, attn_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163181.f383272e719b
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8ac07e3958dfd46f330a5fce66c6ec181a35e1763bbdcc543beff0531dc7deb
|
| 3 |
+
size 5607
|
logs/attn_layer_mapper=layer-2, attn_loss_fn=mse, attn_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163346.f383272e719b
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dd662346caa7fccfa50758aa9c709f26f7c95860e3754ad6e2e24a21b481518
|
| 3 |
+
size 5610
|
logs/dataset_subset=default, dataset_uri=distily_c4_multilingual_1M, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724164276.f383272e719b
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c88fcaa4196b4d659818553bdf9e144d858399afcd4c4dc1f1f2c6e56f9efec
|
| 3 |
+
size 29652761
|
logs/hs_layer_mapper=last, hs_loss_fn=mse, hs_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163702.f383272e719b
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:343b7ed10c7f9c27e799745a0a21e36f8580cd4bea34700721a285d8bcad01c0
|
| 3 |
+
size 5601
|
logs/hs_layer_mapper=layer-2, hs_loss_fn=mse, hs_weight=1.0, lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724163871.f383272e719b
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67d2279d01e850ae39acb34efd9a597f207aae0dfd31b968ebdc6b82e50f2d8c
|
| 3 |
+
size 5604
|
logs/lr_scheduler_type=cosine, warmup_ratio=0.5/completed.flag
ADDED
|
File without changes
|
logs/lr_scheduler_type=cosine, warmup_ratio=0.5/events.out.tfevents.1724162963.f383272e719b
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6d9a1a4b9b3e6fdb0eea03691de6750698302cd305a43caf0608d5eff12401e
|
| 3 |
+
size 588
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 163832792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f10db7db2ee6942a704df8ea77a2f82e9b80d3a17f589745facf61f3e1a5016d
|
| 3 |
size 163832792
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff7218cbeefc782c3afaf2c6ad962c90ac2440fec49b7e08a526f25e4ffbfc83
|
| 3 |
+
size 1017899144
|