nestoralvaro
commited on
Commit
•
a69412e
1
Parent(s):
b2312ad
Training in progress, step 500
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- runs/Jun05_17-41-30_a3686dfcd2e0/1654450917.1225603/events.out.tfevents.1654450917.a3686dfcd2e0.98.1 +3 -0
- runs/Jun05_17-41-30_a3686dfcd2e0/events.out.tfevents.1654450917.a3686dfcd2e0.98.0 +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"length_penalty": 0.6,
|
17 |
+
"max_length": 84,
|
18 |
+
"model_type": "mt5",
|
19 |
+
"no_repeat_ngram_size": 2,
|
20 |
+
"num_beams": 4,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"tokenizer_class": "T5Tokenizer",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.19.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 250112
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c0e1b438598cc5cd8dc273d2f6ec3a26386dace06c6c9794c2c4b88c27105f3
|
3 |
+
size 2329700301
|
runs/Jun05_17-41-30_a3686dfcd2e0/1654450917.1225603/events.out.tfevents.1654450917.a3686dfcd2e0.98.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05e227fa3305c9cf32066432f411628f6541fb4cff53604ec2e071ebf2465f9c
|
3 |
+
size 5517
|
runs/Jun05_17-41-30_a3686dfcd2e0/events.out.tfevents.1654450917.a3686dfcd2e0.98.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82622989632a52078125cd5d0a86c995451c5bd55212d27cc2d79aa87210bd95
|
3 |
+
size 4095
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af95700bf514fc57a9f58055fec955839f0a378f707ddbc3df840291cbb709db
|
3 |
+
size 16330466
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "csebuetnlp/mT5_multilingual_XLSum", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb5986b0f5fa8a07c57f62e9e2158bcebc83d09245622972332fe0d73a0cecfe
|
3 |
+
size 3439
|