Hugging Face's logo

Yova
/
baseline

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Yova commited on
Commit
f862dd6
•
1 Parent(s): d3d2ce4

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +9 -9
  2. model.safetensors +2 -2
  3. runs/Nov22_11-46-38_5e1282a16015/events.out.tfevents.1700653599.5e1282a16015.153.12 +3 -0
  4. runs/Nov22_11-51-23_5e1282a16015/events.out.tfevents.1700653884.5e1282a16015.153.13 +3 -0
  5. runs/Nov22_11-51-46_5e1282a16015/events.out.tfevents.1700653907.5e1282a16015.153.14 +3 -0
  6. runs/Nov22_11-56-57_5e1282a16015/events.out.tfevents.1700654218.5e1282a16015.153.15 +3 -0
  7. training_args.bin +1 -1
config.json CHANGED
@@ -3,12 +3,12 @@
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
- "d_ff": 512,
7
- "d_kv": 16,
8
- "d_model": 128,
9
  "decoder_start_token_id": 259,
10
  "dense_act_fn": "relu",
11
- "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
  "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
@@ -16,12 +16,12 @@
16
  "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
- "num_decoder_layers": 2,
20
- "num_heads": 2,
21
- "num_layers": 2,
22
  "pad_token_id": 0,
23
- "relative_attention_max_distance": 64,
24
- "relative_attention_num_buckets": 16,
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.35.2",
27
  "use_cache": true,
 
3
  "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 256,
9
  "decoder_start_token_id": 259,
10
  "dense_act_fn": "relu",
11
+ "dropout_rate": 0.3,
12
  "eos_token_id": 1,
13
  "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
 
16
  "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
+ "num_decoder_layers": 4,
20
+ "num_heads": 4,
21
+ "num_layers": 4,
22
  "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.35.2",
27
  "use_cache": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd89516243a31537d2ae1963e01df839e9aee338734648f5ee1b1f38f19304fb
3
- size 2699200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c36eb0f55e272ea12e9ba2d364d45747882b33b3a67b6ca519f423d3fe684c
3
+ size 29788248
runs/Nov22_11-46-38_5e1282a16015/events.out.tfevents.1700653599.5e1282a16015.153.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c4bf0a47c000d321b996dc6b9db253f1cfea0c405ab75db2ecd3964de78f5d
3
+ size 4452
runs/Nov22_11-51-23_5e1282a16015/events.out.tfevents.1700653884.5e1282a16015.153.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed00818fe398fdb34145c2495e73a073e28b3b12cb0e10867d99c7b28ae3cfa7
3
+ size 4295
runs/Nov22_11-51-46_5e1282a16015/events.out.tfevents.1700653907.5e1282a16015.153.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6b4ba70673e254032731e69f62b80677bef6da2bc9600c447a31c3339df700
3
+ size 4450
runs/Nov22_11-56-57_5e1282a16015/events.out.tfevents.1700654218.5e1282a16015.153.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:393da333e434f3dd661edbf9a3cc54c010dabcdc8df6f485853911c831859a5f
3
+ size 4780
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e277cfb6a3be61a72578af129789c87ef4a9a87ddae5024e83e8ee7bb50a12f9
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1d63bdb118f17954e86c95660a8b57a79abcf6104b5ba870ecf028363303c0
3
  size 4728