Training in progress, epoch 1
Browse files- config.json +7 -7
- model.safetensors +2 -2
- tokenizer.json +0 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -6,14 +6,14 @@
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
-
"hidden_size":
|
10 |
"initializer_range": 0.02,
|
11 |
-
"intermediate_size":
|
12 |
-
"max_position_embeddings":
|
13 |
"model_type": "llama",
|
14 |
-
"num_attention_heads":
|
15 |
-
"num_hidden_layers":
|
16 |
-
"num_key_value_heads":
|
17 |
"pad_token_id": 2,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
@@ -23,5 +23,5 @@
|
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.35.0",
|
25 |
"use_cache": true,
|
26 |
-
"vocab_size":
|
27 |
}
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
+
"hidden_size": 64,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 256,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
"model_type": "llama",
|
14 |
+
"num_attention_heads": 4,
|
15 |
+
"num_hidden_layers": 6,
|
16 |
+
"num_key_value_heads": 4,
|
17 |
"pad_token_id": 2,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
|
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.35.0",
|
25 |
"use_cache": true,
|
26 |
+
"vocab_size": 5000
|
27 |
}
|
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 sha256:8f89c4cc9afcde3cc76cc0a9def7f91a97910d6251eee2c2ee45c370fc97174f
|
3 |
+
size 4142176
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:035c8d78a9ef44969e4c434c05c56975218fac6772ffa3df4d3365f29a251773
|
3 |
size 4600
|