e22vvb commited on
Commit
0197dbd
1 Parent(s): fa18876

Training in progress, epoch 1

Browse files
.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:e46fd7bb024a23db1026010f42f98855a87d3a0ada6fb0206cdbe376f101390a
3
+ size 2329702453
runs/Jan24_16-41-30_munich/1706089305.3057623/events.out.tfevents.1706089305.munich.912490.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695d2c8f4fe8c5740510cdfe7a3dcbd94f2307a5045527fb5f0746b050b95ae4
3
+ size 6056
runs/Jan24_16-41-30_munich/events.out.tfevents.1706089304.munich.912490.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb893d00bfa16c7c276f2d10875ef8b05fa892f0ba1561d759f8e65640e93fbc
3
+ size 4219
runs/Jan24_16-42-56_munich/1706089384.1391356/events.out.tfevents.1706089384.munich.913068.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3bf607b490c96ee205990945e2b1d7df83e6f8eead8f938153513686e1ad15
3
+ size 6056
runs/Jan24_16-42-56_munich/events.out.tfevents.1706089384.munich.913068.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6542d0128d622cea05f33a9453459b8b049200ad50ffb797941511df88541b3c
3
+ size 4666
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37451aec93ba24034c0e68e2dfa73323be71ca19c3b123241bd1e08d6478e03
3
+ size 3707