Training in progress, epoch 1
Browse files- config.json +4 -4
- pytorch_model.bin +2 -2
- runs/Jan09_06-40-33_019427d741e3/1673246508.5932755/events.out.tfevents.1673246508.019427d741e3.613.7 +3 -0
- runs/Jan09_06-40-33_019427d741e3/events.out.tfevents.1673246508.019427d741e3.613.6 +3 -0
- tokenizer.json +1 -1
- tokenizer_config.json +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "google/t5-efficient-tiny-
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
@@ -17,9 +17,9 @@
|
|
17 |
"layer_norm_epsilon": 1e-06,
|
18 |
"model_type": "t5",
|
19 |
"n_positions": 512,
|
20 |
-
"num_decoder_layers":
|
21 |
-
"num_heads":
|
22 |
-
"num_layers":
|
23 |
"pad_token_id": 0,
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/t5-efficient-tiny-nl32",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
17 |
"layer_norm_epsilon": 1e-06,
|
18 |
"model_type": "t5",
|
19 |
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 32,
|
21 |
+
"num_heads": 4,
|
22 |
+
"num_layers": 32,
|
23 |
"pad_token_id": 0,
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
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 sha256:579ec27c701cae0cce026f61eedf775a10851da320d1eb1fb6f1fa5c1c96394a
|
3 |
+
size 268181345
|
runs/Jan09_06-40-33_019427d741e3/1673246508.5932755/events.out.tfevents.1673246508.019427d741e3.613.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44a5ae2256c21a80251ec7f46bda2b564935c372789b15f862129d805d954303
|
3 |
+
size 5738
|
runs/Jan09_06-40-33_019427d741e3/events.out.tfevents.1673246508.019427d741e3.613.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:617ff1a6e34209125f35dd60ebc1f5903dcaa91ded32960d25498bec17f20b1e
|
3 |
+
size 4987
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 64,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
tokenizer_config.json
CHANGED
@@ -104,10 +104,10 @@
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 1000000000000000019884624838656,
|
107 |
-
"name_or_path": "google/t5-efficient-tiny-
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
110 |
-
"special_tokens_map_file": "t5-efficient-tiny-
|
111 |
"tokenizer_class": "T5Tokenizer",
|
112 |
"unk_token": "<unk>"
|
113 |
}
|
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 1000000000000000019884624838656,
|
107 |
+
"name_or_path": "google/t5-efficient-tiny-nl32",
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
110 |
+
"special_tokens_map_file": "t5-efficient-tiny-nl32/special_tokens_map.json",
|
111 |
"tokenizer_class": "T5Tokenizer",
|
112 |
"unk_token": "<unk>"
|
113 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3515
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adf93e55d60a8633998bf4fddf89e4b57ceb86189fba3adbc31923f3e4c78811
|
3 |
size 3515
|