Training in progress, step 1000, checkpoint
Browse files- last-checkpoint/config.json +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +2 -2
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +0 -0
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"dtype": "float32",
|
| 9 |
"embedding_size": 128,
|
| 10 |
"expert_intermediate_size": 2624,
|
| 11 |
-
"group_depth":
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
"hidden_size": 768,
|
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"num_attention_heads": 12,
|
| 24 |
"num_expert_modules": 2,
|
| 25 |
"num_experts": 4,
|
| 26 |
-
"num_hidden_layers":
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 1,
|
|
|
|
| 8 |
"dtype": "float32",
|
| 9 |
"embedding_size": 128,
|
| 10 |
"expert_intermediate_size": 2624,
|
| 11 |
+
"group_depth": 2,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
"hidden_size": 768,
|
|
|
|
| 23 |
"num_attention_heads": 12,
|
| 24 |
"num_expert_modules": 2,
|
| 25 |
"num_experts": 4,
|
| 26 |
+
"num_hidden_layers": 14,
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 1,
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3f7005f211bb6c9849974e2b5fd072ba75e545a244650a8d366490e2dca4f4c
|
| 3 |
+
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62842584bcf2dda53258e996def0ee2a7e1915ba26342af13ff9382f86683cf4
|
| 3 |
+
size 402029570
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9136fabc21a4ae7cb3c9c094e7570cd9311d1c25699a3be05328f65f23a6e2df
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a02eaa2a071888384d807396f6b5ab793443d26e21787174d5a296f8a0154d2e
|
| 3 |
size 14960
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c5d8fce1137089135ccf256a2ef5f7b480b4418e703c799af426b8e1ac0d1f8
|
| 3 |
size 14960
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:666ea91556f4528e8d7dae5d6622cac3019281f4b32b653616d733931ba3ae8b
|
| 3 |
size 14960
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4825a838b5caa94f340bb27a46cde36b6e29133f464b4f6087b90702a9a9346b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dccca07d27100677936cb8a7294295fefbf7e8d8b5b07969e20edc9f40ec97a
|
| 3 |
size 5432
|