Hugging Face's logo

mixtralyanis
/
t5-small-finetuned

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
mixtralyanis commited on
Commit
b1dd139
•
1 Parent(s): 7b34d9e

End of training

Browse files
Files changed (9) hide show
  1. README.md +2 -3
  2. config.json +6 -6
  3. model.safetensors +2 -2
  4. runs/Feb27_14-44-23_16b108c97436/events.out.tfevents.1709045355.16b108c97436.10799.1 +3 -0
  5. runs/Feb27_14-50-42_16b108c97436/events.out.tfevents.1709045454.16b108c97436.10799.2 +3 -0
  6. runs/Feb27_14-57-55_16b108c97436/events.out.tfevents.1709045876.16b108c97436.14413.0 +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +1 -3
  9. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/flan-t5-small
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # t5-small-finetuned
15
 
16
- This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
17
 
18
  ## Model description
19
 
@@ -39,7 +39,6 @@ The following hyperparameters were used during training:
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
  - num_epochs: 4
42
- - mixed_precision_training: Native AMP
43
 
44
  ### Training results
45
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/flan-t5-base
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # t5-small-finetuned
15
 
16
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
17
 
18
  ## Model description
19
 
 
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
  - num_epochs: 4
 
42
 
43
  ### Training results
44
 
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "google/flan-t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
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,
@@ -18,9 +18,9 @@
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 8,
22
- "num_heads": 6,
23
- "num_layers": 8,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
 
1
  {
2
+ "_name_or_path": "google/flan-t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
  "d_kv": 64,
9
+ "d_model": 768,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "gelu_new",
12
  "dropout_rate": 0.1,
 
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
3
- size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ba132863338483ff92c4c758388edbe6842c4d8b61e13b0326934c16c01cd9
3
+ size 990345064
runs/Feb27_14-44-23_16b108c97436/events.out.tfevents.1709045355.16b108c97436.10799.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245922ceffb155654cce38c771d8490becbc2e46f8120baf365eff007506bcbe
3
+ size 8355
runs/Feb27_14-50-42_16b108c97436/events.out.tfevents.1709045454.16b108c97436.10799.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5abde8a1d97cb68712747a10d796bd4ba69f03a733ecb11061353d83d0406c2
3
+ size 48527
runs/Feb27_14-57-55_16b108c97436/events.out.tfevents.1709045876.16b108c97436.14413.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5b6f0d740d63bc17e5d7a1767d0a24194eb1c29dfb16a8d9f6b52930c2ef39
3
+ size 45153
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<pad>",
@@ -931,8 +930,7 @@
931
  "clean_up_tokenization_spaces": true,
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
- "legacy": true,
935
- "model_max_length": 1000000000000000019884624838656,
936
  "pad_token": "<pad>",
937
  "sp_model_kwargs": {},
938
  "tokenizer_class": "T5Tokenizer",
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<pad>",
 
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
+ "model_max_length": 512,
 
934
  "pad_token": "<pad>",
935
  "sp_model_kwargs": {},
936
  "tokenizer_class": "T5Tokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:898e6c2a2af1863dfcf4b433dbe5fe9e25f8857522543bc262ff8234c5a074b1
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66529d7351039076c62cbec0f1faf33b00e4ffd5a4c04e8dec20c38481360b37
3
  size 5048