saicharan8 commited on
Commit
62e16e5
1 Parent(s): 39383c4

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/umt5-small
4
+ tags:
5
+ - summarization
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: output
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # output
16
+
17
+ This model is a fine-tuned version of [google/umt5-small](https://huggingface.co/google/umt5-small) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 2
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.36.0
51
+ - Pytorch 2.0.0
52
+ - Datasets 2.1.0
53
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/umt5-small",
3
+ "architectures": [
4
+ "UMT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "max_new_tokens": 64,
20
+ "model_type": "umt5",
21
+ "num_decoder_layers": 8,
22
+ "num_heads": 6,
23
+ "num_layers": 8,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "scalable_attention": true,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "T5Tokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.36.0",
32
+ "use_cache": true,
33
+ "vocab_size": 256384
34
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "max_new_tokens": 64,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.36.0"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59009b05dd97fcb4b25e55e6fc8ff197fb28fd7346514af613f6e33e2710a9a3
3
+ size 1226432312
runs/Jan09_06-16-15_808bc8082383/events.out.tfevents.1704780987.808bc8082383.42.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d719f4730a9ef09b3b72bbe2df714cb75e4abd882a1ca136c2af166443be08
3
+ size 8041
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bcd4cc7e40a58da582b8d406253177ef7356ba8e971d3ade4fd2cce82123653
3
+ size 4411