Training in progress, step 1000
Browse files- config.json +2 -2
- merges.txt +1 -0
- model.safetensors +3 -0
- runs/Jan02_15-33-35_hyperion-255/events.out.tfevents.1735828554.hyperion-255 +3 -0
- special_tokens_map.json +10 -4
- tokenizer.json +1 -0
- tokenizer_config.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 6,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
-
"dropout": 0.
|
23 |
"encoder_attention_heads": 8,
|
24 |
"encoder_ffn_dim": 2048,
|
25 |
"encoder_layerdrop": 0.0,
|
@@ -44,7 +44,7 @@
|
|
44 |
"pad_token_id": 50257,
|
45 |
"scale_embedding": false,
|
46 |
"torch_dtype": "float32",
|
47 |
-
"transformers_version": "4.
|
48 |
"use_cache": false,
|
49 |
"use_weighted_layer_sum": false,
|
50 |
"vocab_size": 51865
|
|
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 6,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.1,
|
23 |
"encoder_attention_heads": 8,
|
24 |
"encoder_ffn_dim": 2048,
|
25 |
"encoder_layerdrop": 0.0,
|
|
|
44 |
"pad_token_id": 50257,
|
45 |
"scale_embedding": false,
|
46 |
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.37.2",
|
48 |
"use_cache": false,
|
49 |
"use_weighted_layer_sum": false,
|
50 |
"vocab_size": 51865
|
merges.txt
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
#version: 0.2
|
|
|
2 |
Ġ a
|
3 |
Ġt h
|
4 |
i n
|
|
|
1 |
#version: 0.2
|
2 |
+
Ġ t
|
3 |
Ġ a
|
4 |
Ġt h
|
5 |
i n
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfbc913b6c134ef9f0d8af8b4a7244de3647a9a550453c6931aba4a17508dd45
|
3 |
+
size 290403936
|
runs/Jan02_15-33-35_hyperion-255/events.out.tfevents.1735828554.hyperion-255
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afbd5b1994f51e8d18f377aefe8fbbebe27479c5eb56b718d5b31e13dc93f265
|
3 |
+
size 11334
|
special_tokens_map.json
CHANGED
@@ -111,22 +111,28 @@
|
|
111 |
"bos_token": {
|
112 |
"content": "<|endoftext|>",
|
113 |
"lstrip": false,
|
114 |
-
"normalized":
|
115 |
"rstrip": false,
|
116 |
"single_word": false
|
117 |
},
|
118 |
"eos_token": {
|
119 |
"content": "<|endoftext|>",
|
120 |
"lstrip": false,
|
121 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
"rstrip": false,
|
123 |
"single_word": false
|
124 |
},
|
125 |
-
"pad_token": "<|endoftext|>",
|
126 |
"unk_token": {
|
127 |
"content": "<|endoftext|>",
|
128 |
"lstrip": false,
|
129 |
-
"normalized":
|
130 |
"rstrip": false,
|
131 |
"single_word": false
|
132 |
}
|
|
|
111 |
"bos_token": {
|
112 |
"content": "<|endoftext|>",
|
113 |
"lstrip": false,
|
114 |
+
"normalized": false,
|
115 |
"rstrip": false,
|
116 |
"single_word": false
|
117 |
},
|
118 |
"eos_token": {
|
119 |
"content": "<|endoftext|>",
|
120 |
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false
|
124 |
+
},
|
125 |
+
"pad_token": {
|
126 |
+
"content": "<|endoftext|>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
"rstrip": false,
|
130 |
"single_word": false
|
131 |
},
|
|
|
132 |
"unk_token": {
|
133 |
"content": "<|endoftext|>",
|
134 |
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
"rstrip": false,
|
137 |
"single_word": false
|
138 |
}
|
tokenizer.json
CHANGED
@@ -64890,6 +64890,7 @@
|
|
64890 |
"<|endoftext|>": 50257
|
64891 |
},
|
64892 |
"merges": [
|
|
|
64893 |
"Ġ a",
|
64894 |
"Ġt h",
|
64895 |
"i n",
|
|
|
64890 |
"<|endoftext|>": 50257
|
64891 |
},
|
64892 |
"merges": [
|
64893 |
+
"Ġ t",
|
64894 |
"Ġ a",
|
64895 |
"Ġt h",
|
64896 |
"i n",
|
tokenizer_config.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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:913b6a37bd83f134eb0cc4752da1a9318664f54c6a5bf91c328e767d527ae4e6
|
3 |
+
size 4792
|