Training in progress, step 1000
Browse files- config.json +5 -5
- pytorch_model.bin +2 -2
- runs/Sep26_17-14-52_nid006626/events.out.tfevents.1758899709.nid006626.72753.0 +3 -0
- runs/Sep26_17-20-17_nid007230/events.out.tfevents.1758900025.nid007230.107958.0 +3 -0
- runs/Sep26_17-26-04_nid007218/events.out.tfevents.1758900371.nid007218.216098.0 +3 -0
- runs/Sep26_17-32-35_nid007218/events.out.tfevents.1758900763.nid007218.220467.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -7,13 +7,13 @@
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
"dtype": "float32",
|
| 9 |
"embedding_size": 128,
|
| 10 |
-
"expert_intermediate_size":
|
| 11 |
"group_depth": 4,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
-
"hidden_size":
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size":
|
| 17 |
"layer_norm_eps": 1e-06,
|
| 18 |
"load_balancing_loss_coef": 0.2,
|
| 19 |
"lora_alpha": 32,
|
|
@@ -21,9 +21,9 @@
|
|
| 21 |
"max_position_embeddings": 8192,
|
| 22 |
"model_type": "ModernALBERT",
|
| 23 |
"num_attention_heads": 16,
|
| 24 |
-
"num_expert_modules":
|
| 25 |
"num_experts": 8,
|
| 26 |
-
"num_hidden_layers":
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 2,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
"dtype": "float32",
|
| 9 |
"embedding_size": 128,
|
| 10 |
+
"expert_intermediate_size": 2624,
|
| 11 |
"group_depth": 4,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 1152,
|
| 17 |
"layer_norm_eps": 1e-06,
|
| 18 |
"load_balancing_loss_coef": 0.2,
|
| 19 |
"lora_alpha": 32,
|
|
|
|
| 21 |
"max_position_embeddings": 8192,
|
| 22 |
"model_type": "ModernALBERT",
|
| 23 |
"num_attention_heads": 16,
|
| 24 |
+
"num_expert_modules": 2,
|
| 25 |
"num_experts": 8,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 2,
|
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:dffd333913e4ed94e5ed1309111e2f93752cf719ce33e2ad74841fef8a730e2d
|
| 3 |
+
size 363608098
|
runs/Sep26_17-14-52_nid006626/events.out.tfevents.1758899709.nid006626.72753.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f521b451fc364fb4c415f6c88c2aab749cea172be2c4e7885b5d92a450c9a9cb
|
| 3 |
+
size 5332
|
runs/Sep26_17-20-17_nid007230/events.out.tfevents.1758900025.nid007230.107958.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f898b7dcb3b8347afaa4aacccb30ef5e1d78b2206d6eb9390dff8640edc8b37
|
| 3 |
+
size 5332
|
runs/Sep26_17-26-04_nid007218/events.out.tfevents.1758900371.nid007218.216098.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aaadc27e365b1db6c691a4ebb7dfe124afd36757e152a8e815e62d45c9164ba
|
| 3 |
+
size 5332
|
runs/Sep26_17-32-35_nid007218/events.out.tfevents.1758900763.nid007218.220467.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c2bdf4085bc65e0f220ef795319b0fd62e903de43fd0304b7f404e9e52f3b21
|
| 3 |
+
size 15858
|
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 sha256:1f7ab0ffa64a712076054007d1389d5f4c75c80b03fcc26405d9947d274385f9
|
| 3 |
size 5432
|