Hugging Face's logo

distily
/
distily_tinyBenchmarks

TensorBoard
Safetensors
llama
Model card Files Metrics Community
lapp0 commited on
Commit
165fac3
·
verified ·
1 Parent(s): 73ff168

Training in progress, step 125

Browse files
Files changed (8) hide show
  1. benchmarks.shelve.bak +1 -0
  2. benchmarks.shelve.dat +0 -0
  3. benchmarks.shelve.dir +1 -0
  4. logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0002, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727031551.1c1a426a2fee +3 -0
  5. logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1/events.out.tfevents.1727030701.1c1a426a2fee +3 -0
  6. logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1/events.out.tfevents.1727031505.1c1a426a2fee +0 -0
  7. model.safetensors +1 -1
  8. training_args.bin +1 -1
benchmarks.shelve.bak CHANGED
@@ -3,3 +3,4 @@
3
  'logis/teacher', (27648, 448)
4
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1', (41472, 448)
5
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8', (41984, 448)
 
 
3
  'logis/teacher', (27648, 448)
4
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1', (41472, 448)
5
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8', (41984, 448)
6
+ 'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1', (42496, 448)
benchmarks.shelve.dat CHANGED
Binary files a/benchmarks.shelve.dat and b/benchmarks.shelve.dat differ
 
benchmarks.shelve.dir CHANGED
@@ -3,3 +3,4 @@
3
  'logis/teacher', (27648, 448)
4
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1', (41472, 448)
5
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8', (41984, 448)
 
 
3
  'logis/teacher', (27648, 448)
4
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1', (41472, 448)
5
  'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8', (41984, 448)
6
+ 'distily_tinyBenchmarks/logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1', (42496, 448)
logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0002, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727031551.1c1a426a2fee ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccd71769b6e6102a91280a58e6e6384eedc48264c69bede61be3164c40c47b4
3
+ size 9163
logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1/events.out.tfevents.1727030701.1c1a426a2fee ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a16c4fd7c03b53a6b4bb180962b3f69bb5df43707871225658bfed5a757b22d
3
+ size 511
logs/harness_benchmarks=tinyBenchmarks, learning_rate=5e-05, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1/events.out.tfevents.1727031505.1c1a426a2fee ADDED
File without changes
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e9379066c5236a9d6477308c4c8ca9cc48dc3640c733f2e901bf36e68f7c1fd
3
  size 325669528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0821dcb57daf05e993031b49fe6d3e60174e2d1c973646b20cb1ff2ee80eb0e0
3
  size 325669528
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f9a7d7c7e39d129a416423817cfc9409690ca97d53ac1896d8427ca9dae53c7
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c722fb67ecdfc262812a68d1df2922d62b5356f43a8bc2c4a829b3e4dc9f31
3
  size 5688