Training in progress, step 100
Browse files- config.json +7 -7
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"model_type": "xlstm",
|
6 |
"pad_token_id": 151643,
|
7 |
"torch_dtype": "float32",
|
8 |
-
"transformers_version": "4.47.
|
9 |
"xlstm_cfg": {
|
10 |
"_block_map": "1,0,1,0,1,0",
|
11 |
"add_embedding_dropout": false,
|
@@ -13,19 +13,19 @@
|
|
13 |
"bias": false,
|
14 |
"context_length": 512,
|
15 |
"dropout": 0.0,
|
16 |
-
"embedding_dim":
|
17 |
"mlstm_block": {
|
18 |
"_block_idx": null,
|
19 |
"_num_blocks": 6,
|
20 |
"mlstm": {
|
21 |
-
"_inner_embedding_dim":
|
22 |
"_num_blocks": 6,
|
23 |
-
"_proj_up_dim":
|
24 |
"bias": false,
|
25 |
"context_length": 512,
|
26 |
"conv1d_kernel_size": 4,
|
27 |
"dropout": 0.0,
|
28 |
-
"embedding_dim":
|
29 |
"num_heads": 16,
|
30 |
"proj_factor": 2.0,
|
31 |
"qkv_proj_blocksize": 32,
|
@@ -70,14 +70,14 @@
|
|
70 |
"dtype_r": "bfloat16",
|
71 |
"dtype_s": "bfloat16",
|
72 |
"dtype_w": "bfloat16",
|
73 |
-
"embedding_dim":
|
74 |
"enable_automatic_mixed_precision": true,
|
75 |
"forward_clipval": null,
|
76 |
"function": "slstm",
|
77 |
"gradient_recurrent_clipval": null,
|
78 |
"gradient_recurrent_cut": false,
|
79 |
"group_norm_weight": true,
|
80 |
-
"hidden_size":
|
81 |
"initial_val": 0.0,
|
82 |
"input_shape": "BSGNH",
|
83 |
"internal_input_shape": "SBNGH",
|
|
|
5 |
"model_type": "xlstm",
|
6 |
"pad_token_id": 151643,
|
7 |
"torch_dtype": "float32",
|
8 |
+
"transformers_version": "4.47.1",
|
9 |
"xlstm_cfg": {
|
10 |
"_block_map": "1,0,1,0,1,0",
|
11 |
"add_embedding_dropout": false,
|
|
|
13 |
"bias": false,
|
14 |
"context_length": 512,
|
15 |
"dropout": 0.0,
|
16 |
+
"embedding_dim": 1536,
|
17 |
"mlstm_block": {
|
18 |
"_block_idx": null,
|
19 |
"_num_blocks": 6,
|
20 |
"mlstm": {
|
21 |
+
"_inner_embedding_dim": 3072,
|
22 |
"_num_blocks": 6,
|
23 |
+
"_proj_up_dim": 3072,
|
24 |
"bias": false,
|
25 |
"context_length": 512,
|
26 |
"conv1d_kernel_size": 4,
|
27 |
"dropout": 0.0,
|
28 |
+
"embedding_dim": 1536,
|
29 |
"num_heads": 16,
|
30 |
"proj_factor": 2.0,
|
31 |
"qkv_proj_blocksize": 32,
|
|
|
70 |
"dtype_r": "bfloat16",
|
71 |
"dtype_s": "bfloat16",
|
72 |
"dtype_w": "bfloat16",
|
73 |
+
"embedding_dim": 1536,
|
74 |
"enable_automatic_mixed_precision": true,
|
75 |
"forward_clipval": null,
|
76 |
"function": "slstm",
|
77 |
"gradient_recurrent_clipval": null,
|
78 |
"gradient_recurrent_cut": false,
|
79 |
"group_norm_weight": true,
|
80 |
+
"hidden_size": 1536,
|
81 |
"initial_val": 0.0,
|
82 |
"input_shape": "BSGNH",
|
83 |
"internal_input_shape": "SBNGH",
|
model.safetensors
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:eb464cae802ff426ddc9d8c1d7c65397362f6a3beb1a388450de538fa85ae06d
|
3 |
+
size 2203703856
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96653b90ef5c8a1a6f8678ce98752b85d28dbfd1477d9efa92ece25be0e3c0e8
|
3 |
size 5944
|