Hugging Face's logo

monsoon-nlp
/
tinyllama-mixpretrain-quinoa-sciphi

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
monsoon-nlp commited on
Commit
224cbe6
•
1 Parent(s): 6a20ecc

End of training

Browse files
Files changed (16) hide show
  1. README.md +49 -0
  2. config.json +28 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. runs/Apr21_22-22-53_5778b0f30e47/events.out.tfevents.1713738178.5778b0f30e47.1017.0 +3 -0
  6. runs/Apr21_22-24-38_5778b0f30e47/events.out.tfevents.1713738279.5778b0f30e47.2744.0 +3 -0
  7. runs/Apr21_22-27-32_5778b0f30e47/events.out.tfevents.1713738454.5778b0f30e47.3646.0 +3 -0
  8. runs/Apr21_22-31-23_5778b0f30e47/events.out.tfevents.1713738684.5778b0f30e47.4786.0 +3 -0
  9. runs/Apr21_22-34-28_5778b0f30e47/events.out.tfevents.1713738872.5778b0f30e47.4786.1 +3 -0
  10. runs/Apr21_22-36-26_5778b0f30e47/events.out.tfevents.1713738988.5778b0f30e47.4786.2 +3 -0
  11. runs/Apr21_22-39-10_5778b0f30e47/events.out.tfevents.1713739151.5778b0f30e47.6539.0 +3 -0
  12. special_tokens_map.json +24 -0
  13. tokenizer.json +0 -0
  14. tokenizer.model +3 -0
  15. tokenizer_config.json +43 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: tinyllama-mixpretrain-quinoa-sciphi
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
+ # tinyllama-mixpretrain-quinoa-sciphi
15
+
16
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None 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: 5e-05
36
+ - train_batch_size: 1
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
+ - training_steps: 15000
42
+ - mixed_precision_training: Native AMP
43
+
44
+ ### Framework versions
45
+
46
+ - Transformers 4.38.2
47
+ - Pytorch 2.2.1+cu121
48
+ - Datasets 2.19.0
49
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.38.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43077882e23408e76ddb24f1e2f07f5b98eca8b3b411fcf18fd5436aafc0ad5b
3
+ size 4400216536
runs/Apr21_22-22-53_5778b0f30e47/events.out.tfevents.1713738178.5778b0f30e47.1017.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:418925cb062a4a8665ecf98427d016cbb837163789cc9cc09a12bd1cffde93d9
3
+ size 4184
runs/Apr21_22-24-38_5778b0f30e47/events.out.tfevents.1713738279.5778b0f30e47.2744.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473e4a35749d0557eb5de213072549926e338ea23c3fb0e2983fa94f6dc1c0e
3
+ size 4719
runs/Apr21_22-27-32_5778b0f30e47/events.out.tfevents.1713738454.5778b0f30e47.3646.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7e7775679a23bd1fdf99b7a4e7ceea68b773c4cac20efe4add91f7bf91c629
3
+ size 4719
runs/Apr21_22-31-23_5778b0f30e47/events.out.tfevents.1713738684.5778b0f30e47.4786.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335fa37b6ea4243e686685ae3d949e5021ddb13f86a52d1ffdb285e70c9b3c46
3
+ size 4719
runs/Apr21_22-34-28_5778b0f30e47/events.out.tfevents.1713738872.5778b0f30e47.4786.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d7db1bdcc52bfa1b840990ee110c6784725ac276aa8fc63078ee057cbe8253
3
+ size 4723
runs/Apr21_22-36-26_5778b0f30e47/events.out.tfevents.1713738988.5778b0f30e47.4786.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1119205579b65f443d90a34871dabe894c25fbb9f6693d723ee9c8878b3ba60
3
+ size 4723
runs/Apr21_22-39-10_5778b0f30e47/events.out.tfevents.1713739151.5778b0f30e47.6539.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b924d1b5499c03616d3510f30868471c05d717934d3f4360ee2c34ef023c48ce
3
+ size 11053
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "max_length": 400,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "truncation": true,
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012b4e197281bc536a7807247021b0d6a8234b8cef14bf147b7a55b2b199a1aa
3
+ size 4920