Training in progress, epoch 1
Browse files- ipu_config.json +3 -3
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
ipu_config.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"execute_encoder_on_cpu_for_generation": false,
|
8 |
"gradient_accumulation_steps": 32,
|
9 |
"inference_device_iterations": 4,
|
10 |
-
"inference_replication_factor":
|
11 |
"ipus_per_replica": 4,
|
12 |
"layers_per_ipu": [
|
13 |
3,
|
@@ -22,8 +22,8 @@
|
|
22 |
"optimum_version": "1.5.0",
|
23 |
"output_mode": "final",
|
24 |
"recompute_checkpoint_every_layer": true,
|
25 |
-
"replicated_tensor_sharding":
|
26 |
-
"replication_factor":
|
27 |
"seed": 42,
|
28 |
"sharded_execution_for_inference": false,
|
29 |
"transformers_version": "4.20.1"
|
|
|
7 |
"execute_encoder_on_cpu_for_generation": false,
|
8 |
"gradient_accumulation_steps": 32,
|
9 |
"inference_device_iterations": 4,
|
10 |
+
"inference_replication_factor": 4,
|
11 |
"ipus_per_replica": 4,
|
12 |
"layers_per_ipu": [
|
13 |
3,
|
|
|
22 |
"optimum_version": "1.5.0",
|
23 |
"output_mode": "final",
|
24 |
"recompute_checkpoint_every_layer": true,
|
25 |
+
"replicated_tensor_sharding": true,
|
26 |
+
"replication_factor": 4,
|
27 |
"seed": 42,
|
28 |
"sharded_execution_for_inference": false,
|
29 |
"transformers_version": "4.20.1"
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 171676081
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c35dca4357e44911e359dfb3578e96efa4a3534d31ffdc2801d65fb02e0f946
|
3 |
size 171676081
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2799
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bada2581011cea3e15f6beb1758c1db42be1cb14b328fae070dc7c921c6081bf
|
3 |
size 2799
|