Megareyka commited on
Commit
c68e872
1 Parent(s): e486ee2

End of training

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/blenderbot-90M
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: facebook-blenderbot-90M-open-instruct
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # facebook-blenderbot-90M-open-instruct
15
+
16
+ This model is a fine-tuned version of [facebook/blenderbot-90M](https://huggingface.co/facebook/blenderbot-90M) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.002
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 1
42
+ - mixed_precision_training: Native AMP
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.38.2
51
+ - Pytorch 2.2.1+cu118
52
+ - Datasets 2.18.0
53
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/blenderbot-90M",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BlenderbotSmallForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 1,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 512,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 2048,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 8,
19
+ "decoder_start_token_id": 1,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 2048,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 8,
25
+ "eos_token_id": 2,
26
+ "extra_pos_embeddings": 0,
27
+ "force_bos_token_to_be_generated": false,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "length_penalty": 0.65,
43
+ "max_length": 128,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 20,
46
+ "model_type": "blenderbot-small",
47
+ "no_repeat_ngram_size": 3,
48
+ "normalize_before": false,
49
+ "normalize_embedding": true,
50
+ "num_beams": 10,
51
+ "num_hidden_layers": 8,
52
+ "pad_token_id": 0,
53
+ "scale_embedding": true,
54
+ "static_position_embeddings": false,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.38.2",
57
+ "unk_token_id": 3,
58
+ "use_cache": true,
59
+ "vocab_size": 54944
60
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "length_penalty": 0.65,
8
+ "max_length": 128,
9
+ "min_length": 20,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 10,
12
+ "pad_token_id": 0,
13
+ "transformers_version": "4.38.2"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7538b2c1ff36f94ff70fd6c8afec05b6314932391172ada7e71f413f85dd9c
3
+ size 350295176
runs/Mar22_16-01-32_DESKTOP-PRQKU91/events.out.tfevents.1711108895.DESKTOP-PRQKU91.19004.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb80b2767803f6e6ad944658497c5c4ca20946c58795ea6518b27eda67e77f2
3
+ size 5545
runs/Mar22_16-02-44_DESKTOP-PRQKU91/events.out.tfevents.1711108967.DESKTOP-PRQKU91.26544.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6275937292f3da825cbf2e8e0cc4071d00dcc5a29b95f5e3dacc50279b4988e4
3
+ size 6110
runs/Mar22_16-12-52_DESKTOP-PRQKU91/events.out.tfevents.1711109574.DESKTOP-PRQKU91.24296.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af232fa3ac31dbcf21a276b2d1d4fd64e7bb2622c1244007f3e4c9b90f70570
3
+ size 6531
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "__start__",
3
+ "eos_token": "__end__",
4
+ "pad_token": "__null__",
5
+ "unk_token": "__unk__"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "__null__",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "__start__",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "__end__",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "__unk__",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "__start__",
37
+ "clean_up_tokenization_spaces": true,
38
+ "eos_token": "__end__",
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "__null__",
41
+ "tokenizer_class": "BlenderbotSmallTokenizer",
42
+ "unk_token": "__unk__"
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93a884247ddf485ebddcecd178820a2269c42a9b4f1a1d16c24695f2f85e465
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff