Hugging Face's logo

distily
/
distily_tinyBenchmarks

TensorBoard
Safetensors
llama
Model card Files Metrics Community
lapp0 commited on
Commit
a58e975
·
verified ·
1 Parent(s): ec71a92

Training in progress, step 125

Browse files
Files changed (13) 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=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8, warmup_ratio=0.1/events.out.tfevents.1727028505.1c1a426a2fee +3 -0
  5. 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/events.out.tfevents.1727026979.1c1a426a2fee +3 -0
  6. 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/events.out.tfevents.1727035379.1c1a426a2fee +3 -0
  7. 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, warmup_ratio=0.1/events.out.tfevents.1727033706.1c1a426a2fee +3 -0
  8. 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, warmup_ratio=0.1/events.out.tfevents.1727034512.1c1a426a2fee +3 -0
  9. 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.1727033023.1c1a426a2fee +3 -0
  10. 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 +3 -0
  11. 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/events.out.tfevents.1727030024.1c1a426a2fee +3 -0
  12. model.safetensors +1 -1
  13. training_args.bin +1 -1
benchmarks.shelve.bak CHANGED
@@ -5,3 +5,4 @@
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)
7
  'distily_tinyBenchmarks/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', (43008, 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)
7
  'distily_tinyBenchmarks/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', (43008, 448)
8
+ 'distily_tinyBenchmarks/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, warmup_ratio=0.1', (43520, 448)
benchmarks.shelve.dat CHANGED
Binary files a/benchmarks.shelve.dat and b/benchmarks.shelve.dat differ
 
benchmarks.shelve.dir CHANGED
@@ -5,3 +5,4 @@
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)
7
  'distily_tinyBenchmarks/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', (43008, 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)
7
  'distily_tinyBenchmarks/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', (43008, 448)
8
+ 'distily_tinyBenchmarks/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, warmup_ratio=0.1', (43520, 448)
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/events.out.tfevents.1727028505.1c1a426a2fee CHANGED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a141e4dfdc59176a463ab2f98d94b7c2304bf869c2f2f352e5cffbb96cf787ba
3
+ size 40
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/events.out.tfevents.1727026979.1c1a426a2fee CHANGED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ba6bd4e32cf0fb58181640c588204d35c9d4b0a20e2ea094098c77eb6af13e
3
+ size 40
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/events.out.tfevents.1727035379.1c1a426a2fee ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019d9b7415c1f24610986854b0a804389cd991cce5a56b3b2d48bf48a06f2781
3
+ size 9163
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, warmup_ratio=0.1/events.out.tfevents.1727033706.1c1a426a2fee ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0821831ec451ef640b0f0d3526ba5bf75db28a6bcbf5ce6a67251cfffb4c959f
3
+ size 511
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, warmup_ratio=0.1/events.out.tfevents.1727034512.1c1a426a2fee ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ebc63098e0325763e65339a2e1aa252feecd9cbf0c8a0314e5903f9eb713a3e
3
+ size 40
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.1727033023.1c1a426a2fee CHANGED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77dc9faa19dbc517a693adc1ff909a82bdfe947ab4604c18084cb1d1cea091b
3
+ size 40
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 CHANGED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252d0b68b8e0ff3d8e9c389c151aea00d4c8af8772d391b2b10af54ca56b51b1
3
+ size 40
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/events.out.tfevents.1727030024.1c1a426a2fee CHANGED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbbc0f2bdfc36a3ca50d374cb7e02ce520b3a3f8d70542489121ae847a28a46c
3
+ size 40
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5279d230bff7ff61362eba83b6678d63af2b8c14cbd8174ac612e692cb1114c
3
  size 325669528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ddcb1620a387c545dc8268e86e82dfe6d8caea9fff84e0951b876b17c284dd
3
  size 325669528
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57d7f4d77b590122aeb7258966683c980344216fc987512ce1fb60b4c8c00e8d
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33770307270dda4ff4ae179bd8dcf984c23818fe946bac64c4f3bb769b90e44d
3
  size 5688