Training in progress, step 5000
Browse files- benchmarks.shelve.bak +2 -0
- benchmarks.shelve.dat +0 -0
- benchmarks.shelve.dir +2 -0
- logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia, per_device_train_batch_size=8/events.out.tfevents.1727132112.1c1a426a2fee +3 -0
- logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia, per_device_train_batch_size=8/events.out.tfevents.1727133001.1c1a426a2fee +3 -0
- logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=None, dataset_uri=distily_filtered_redpajama_en, per_device_train_batch_size=8/events.out.tfevents.1727133954.1c1a426a2fee +3 -0
- logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=None, dataset_uri=distily_filtered_redpajama_en, per_device_train_batch_size=8/events.out.tfevents.1727135569.1c1a426a2fee +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
benchmarks.shelve.bak
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
'logs/teacher', (0, 448)
|
2 |
+
'distily_smollm_dataset_sweep/logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia, per_device_train_batch_size=8', (512, 448)
|
benchmarks.shelve.dat
ADDED
Binary file (960 Bytes). View file
|
|
benchmarks.shelve.dir
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
'logs/teacher', (0, 448)
|
2 |
+
'distily_smollm_dataset_sweep/logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia, per_device_train_batch_size=8', (512, 448)
|
logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia, per_device_train_batch_size=8/events.out.tfevents.1727132112.1c1a426a2fee
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c016d721ad9971dfd846ff08477a205807e5706fd91b0410dbf0f1bef1ff4e7
|
3 |
+
size 529
|
logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=20231101.en, dataset_uri=wikimedia_wikipedia, per_device_train_batch_size=8/events.out.tfevents.1727133001.1c1a426a2fee
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7927ed675b1922923e4c4ed3516210ccc7967229c8136b5d2e64cce996da643e
|
3 |
+
size 40
|
logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=None, dataset_uri=distily_filtered_redpajama_en, per_device_train_batch_size=8/events.out.tfevents.1727133954.1c1a426a2fee
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4bc5974855c64297bc755124fc24553480bcbc823abbb02e00fa0e3e482e0db
|
3 |
+
size 129908
|
logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=None, dataset_uri=distily_filtered_redpajama_en, per_device_train_batch_size=8/events.out.tfevents.1727135569.1c1a426a2fee
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d17e88a6a9339d565dbaccb785ff0870cd0e0e596186c486f4a07b4bc679706
|
3 |
+
size 140461
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 325669528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfd44edcc5be780442bd9d52a4fafdc3be09aa211e4adbda9e3bffdf90be691b
|
3 |
size 325669528
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfeddbd76502aa135ac992ce99d71293bf7e7da197f140c69f6898bf597d0719
|
3 |
size 5624
|