Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +32 -0
- pytorch_model.bin +3 -0
- runs/Jan27_02-12-12_munich/1706296354.2827573/events.out.tfevents.1706296354.munich.1635096.1 +3 -0
- runs/Jan27_02-12-12_munich/events.out.tfevents.1706296354.munich.1635096.0 +3 -0
- runs/Jan27_02-14-13_munich/1706296462.2140734/events.out.tfevents.1706296462.munich.1635789.1 +3 -0
- runs/Jan27_02-14-13_munich/events.out.tfevents.1706296462.munich.1635789.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-base",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "mt5",
|
19 |
+
"num_decoder_layers": 12,
|
20 |
+
"num_heads": 12,
|
21 |
+
"num_layers": 12,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"tokenizer_class": "T5Tokenizer",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.26.1",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250112
|
32 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83558da77a02b3b78973d342340af51c6eaee908fae6dc14c447c9530ef4def3
|
3 |
+
size 2329702453
|
runs/Jan27_02-12-12_munich/1706296354.2827573/events.out.tfevents.1706296354.munich.1635096.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11d1dfa596c51059f98acacbfa837d49c13070b5e8033114f3c30495fe6c823a
|
3 |
+
size 6062
|
runs/Jan27_02-12-12_munich/events.out.tfevents.1706296354.munich.1635096.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de5a96bcb9c613aa85c983ceff191262bd1b57e3c87c1c10b7ca5542f9c43e38
|
3 |
+
size 4225
|
runs/Jan27_02-14-13_munich/1706296462.2140734/events.out.tfevents.1706296462.munich.1635789.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdd97a338dd6c9007f5e62bfd2f2974b835c4441f97f89f518ea590bdbd5c4af
|
3 |
+
size 6062
|
runs/Jan27_02-14-13_munich/events.out.tfevents.1706296462.munich.1635789.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e33b3bc2a87d969fccad8542d4ec38c1c4f24d95223e9999cd53d5d7f40e7e0
|
3 |
+
size 5929
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c96aef2de87571f47342f30c06ebd19019a7a49d017bcee708f855d7dbd3566
|
3 |
+
size 3707
|