Training in progress, step 2000
Browse files
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "models/smolm-autoreg-bpe-seed_666
|
3 |
"_remove_final_layer_norm": false,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
@@ -24,7 +24,7 @@
|
|
24 |
"pad_token_id": 0,
|
25 |
"prefix": "<s>",
|
26 |
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 8192,
|
30 |
"word_embed_proj_dim": 256
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "models/smolm-autoreg-bpe-seed_666",
|
3 |
"_remove_final_layer_norm": false,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
|
|
24 |
"pad_token_id": 0,
|
25 |
"prefix": "<s>",
|
26 |
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.38.2",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 8192,
|
30 |
"word_embed_proj_dim": 256
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:738eb348c24816c0fa69f65bab4641d235c0171c1396894a45d1199ed91ea9b5
|
3 |
+
size 33810896
|
runs/Mar25_21-06-31_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1711418810.phyl-ling-p01.la.utexas.edu.1054509.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7875d782b17babdbd76ad2603ec1a2e934ba370babf95b8205230fad55a06ed6
|
3 |
+
size 5615
|
tokenizer_config.json
CHANGED
@@ -1,17 +1,48 @@
|
|
1 |
{
|
2 |
"add_prefix_space": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token": "<|endoftext|>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
"eos_token": "<|endoftext|>",
|
6 |
-
"max_length":
|
7 |
"model_max_length": 1000000000000000019884624838656,
|
8 |
"pad_to_multiple_of": null,
|
9 |
"pad_token": "<pad>",
|
10 |
"pad_token_type_id": 0,
|
11 |
"padding_side": "right",
|
12 |
-
"stride": 0,
|
13 |
"tokenizer_class": "GPT2Tokenizer",
|
14 |
-
"truncation_side": "right",
|
15 |
-
"truncation_strategy": "longest_first",
|
16 |
"unk_token": "<|endoftext|>"
|
17 |
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"8192": {
|
29 |
+
"content": "<|endoftext|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
}
|
36 |
+
},
|
37 |
"bos_token": "<|endoftext|>",
|
38 |
"clean_up_tokenization_spaces": true,
|
39 |
"eos_token": "<|endoftext|>",
|
40 |
+
"max_length": null,
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
42 |
"pad_to_multiple_of": null,
|
43 |
"pad_token": "<pad>",
|
44 |
"pad_token_type_id": 0,
|
45 |
"padding_side": "right",
|
|
|
46 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
47 |
"unk_token": "<|endoftext|>"
|
48 |
}
|
training_args.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 sha256:93953bb55cf9edd51721bfc0846edae5859bd8d4e82e80632da7a817cc3d673b
|
3 |
+
size 4984
|