Training in progress, step 125
Browse files- benchmarks.shelve.bak +1 -0
- benchmarks.shelve.dat +0 -0
- benchmarks.shelve.dir +1 -0
- 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.1727033070.1c1a426a2fee +3 -0
- 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.1727032190.1c1a426a2fee +3 -0
- 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 +0 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
benchmarks.shelve.bak
CHANGED
@@ -4,3 +4,4 @@
|
|
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)
|
|
|
|
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)
|
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)
|
benchmarks.shelve.dat
CHANGED
Binary files a/benchmarks.shelve.dat and b/benchmarks.shelve.dat differ
|
|
benchmarks.shelve.dir
CHANGED
@@ -4,3 +4,4 @@
|
|
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)
|
|
|
|
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)
|
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)
|
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.1727033070.1c1a426a2fee
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05634206d7ffceec8033664603cf65975a3cdc1660d67153e6b8d6b40805d169
|
3 |
+
size 9199
|
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.1727032190.1c1a426a2fee
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b338a7cc3f383a58c20e28a59d8029e6b9099ebf65aaf4eaae24fa462f99598
|
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/events.out.tfevents.1727033023.1c1a426a2fee
ADDED
File without changes
|
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:b5279d230bff7ff61362eba83b6678d63af2b8c14cbd8174ac612e692cb1114c
|
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 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57d7f4d77b590122aeb7258966683c980344216fc987512ce1fb60b4c8c00e8d
|
3 |
size 5688
|