Hugging Face's logo

richtsai1103
/
finetuning-summarization-model

Transformers
PyTorch
TensorBoard
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
richtsai1103 commited on
Commit
765f6fe
·
1 Parent(s): ce98e00

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +7 -6
  2. pytorch_model.bin +2 -2
  3. runs/Apr28_05-46-27_c554c67d50d4/1682661108.0909321/events.out.tfevents.1682661108.c554c67d50d4.747.1 +3 -0
  4. runs/Apr28_05-46-27_c554c67d50d4/events.out.tfevents.1682661108.c554c67d50d4.747.0 +3 -0
  5. runs/Apr28_05-59-37_c554c67d50d4/1682661587.3778865/events.out.tfevents.1682661587.c554c67d50d4.747.3 +3 -0
  6. runs/Apr28_05-59-37_c554c67d50d4/events.out.tfevents.1682661587.c554c67d50d4.747.2 +3 -0
  7. runs/Apr28_06-06-02_c554c67d50d4/1682661984.4594398/events.out.tfevents.1682661984.c554c67d50d4.6292.1 +3 -0
  8. runs/Apr28_06-06-02_c554c67d50d4/events.out.tfevents.1682661984.c554c67d50d4.6292.0 +3 -0
  9. training_args.bin +1 -1
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "google/mt5-small",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
6
- "d_ff": 1024,
7
  "d_kv": 64,
8
- "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
@@ -16,9 +16,10 @@
16
  "is_gated_act": true,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "mt5",
19
- "num_decoder_layers": 8,
20
- "num_heads": 6,
21
- "num_layers": 8,
 
22
  "pad_token_id": 0,
23
  "relative_attention_max_distance": 128,
24
  "relative_attention_num_buckets": 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,
 
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,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eb8f24f86726533580fdd43fa1f1e62c5e82f68647d329dafefc76702aec740
3
- size 1200772485
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74380a9c52178128fe98864ce60de46e9fd3e472a07939f722f8e584704e07c2
3
+ size 2329702453
runs/Apr28_05-46-27_c554c67d50d4/1682661108.0909321/events.out.tfevents.1682661108.c554c67d50d4.747.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:341f8f047894cedf826825eb8668510bf19ad36f2dab28c32676d17cd35dd9ba
3
+ size 6196
runs/Apr28_05-46-27_c554c67d50d4/events.out.tfevents.1682661108.c554c67d50d4.747.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa13bc9f9314af6289719d232d83e30978fd3193f745503fa26e7af0518478b0
3
+ size 4313
runs/Apr28_05-59-37_c554c67d50d4/1682661587.3778865/events.out.tfevents.1682661587.c554c67d50d4.747.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a253e2dbbc02767b7660fbb7d1095767e3dce572b1789165b696a49987b39af1
3
+ size 6196
runs/Apr28_05-59-37_c554c67d50d4/events.out.tfevents.1682661587.c554c67d50d4.747.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2b6f4568f3e0c5af87b6babeea993b8a28270c982c7c2f53b892fff2cebcf9
3
+ size 4184
runs/Apr28_06-06-02_c554c67d50d4/1682661984.4594398/events.out.tfevents.1682661984.c554c67d50d4.6292.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ecf1656600d8bc9ac1d667057cbffe7899613984ab252a3a782eacffb97ed8
3
+ size 6196
runs/Apr28_06-06-02_c554c67d50d4/events.out.tfevents.1682661984.c554c67d50d4.6292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9c5bdc8188e8ecb1a672dbe7b25f67af892809f00bec3ee7139c1809a6f674
3
+ size 4942
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30f6f84c8185319e2b67d850520fda86a75191bccae76a826de448f86b86e0d6
3
  size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c43e25ca688e54c8a4306cdf41d239b88712a21d6ceaca9ab4a05fab0ebade
3
  size 3771