Hugging Face's logo

Weni
/
ZeroShot-2.2.1-Llama2-13b-Multilanguage-3.0.3

Zero-Shot Classification
PEFT
PyTorch
TensorBoard
Safetensors
Portuguese
llama
Model card Files Metrics Community
beamaia commited on
Commit
6c71f1f
•
1 Parent(s): a380242

Training in progress, epoch 0

Browse files
Files changed (20) hide show
  1. adapter_config.json +21 -0
  2. adapter_model.safetensors +3 -0
  3. checkpoint-3386/README.md +20 -0
  4. checkpoint-3386/adapter_config.json +21 -0
  5. checkpoint-3386/adapter_model.safetensors +3 -0
  6. checkpoint-3386/optimizer.pt +3 -0
  7. checkpoint-3386/rng_state.pth +3 -0
  8. checkpoint-3386/scheduler.pt +3 -0
  9. checkpoint-3386/special_tokens_map.json +24 -0
  10. checkpoint-3386/tokenizer.json +0 -0
  11. checkpoint-3386/tokenizer_config.json +32 -0
  12. checkpoint-3386/trainer_state.json +60 -0
  13. checkpoint-3386/training_args.bin +3 -0
  14. runs/Dec01_01-27-35_baa8ebef2c59/events.out.tfevents.1701394062.baa8ebef2c59.89158.0 +3 -0
  15. runs/Dec01_03-21-39_baa8ebef2c59/events.out.tfevents.1701400905.baa8ebef2c59.118280.0 +3 -0
  16. runs/Dec01_03-27-22_baa8ebef2c59/events.out.tfevents.1701401247.baa8ebef2c59.118280.1 +3 -0
  17. special_tokens_map.json +24 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +32 -0
  20. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Nous-Hermes-Llama2-13b",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2389992202714c8f032524ac354afc87b80592005303c1f7738ac6f66e115cbf
3
+ size 26235704
checkpoint-3386/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
checkpoint-3386/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Nous-Hermes-Llama2-13b",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-3386/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2389992202714c8f032524ac354afc87b80592005303c1f7738ac6f66e115cbf
3
+ size 26235704
checkpoint-3386/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df7a9fe6c29ae9d1cee81285d00b4924326df278e5f8aae24bada4a41e25811e
3
+ size 52562821
checkpoint-3386/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d860f3a3f4ef9b2be8ea7451ab83979994afe39792fa04bc8ad834c25b912d
3
+ size 14575
checkpoint-3386/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58bc423ff87cce40ba61734fb4339c634f5b95e00c36ab9616cfe70632580085
3
+ size 627
checkpoint-3386/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-3386/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3386/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-3386/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8459745645523071,
3
+ "best_model_checkpoint": "./Zeroshot/01-12-23-NousResearch-Nous-Hermes-Llama2-13b_multilang-dataset-3.0.3-portuguese-2_epochs-10_batch_2/checkpoints/checkpoint-3386",
4
+ "epoch": 0.9998523549387273,
5
+ "global_step": 3386,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.15,
12
+ "learning_rate": 5.8948611931482576e-05,
13
+ "loss": 1.3183,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.3,
18
+ "learning_rate": 0.00011801535735380982,
19
+ "loss": 0.9343,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.44,
24
+ "learning_rate": 0.00017708210277613703,
25
+ "loss": 0.9005,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.59,
30
+ "learning_rate": 0.00023614884819846425,
31
+ "loss": 0.8859,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.74,
36
+ "learning_rate": 0.0002952155936207915,
37
+ "loss": 0.8707,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.89,
42
+ "learning_rate": 0.00035416420555227406,
43
+ "loss": 0.8523,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_loss": 0.8459745645523071,
49
+ "eval_runtime": 133.0397,
50
+ "eval_samples_per_second": 11.32,
51
+ "eval_steps_per_second": 1.421,
52
+ "step": 3386
53
+ }
54
+ ],
55
+ "max_steps": 33860,
56
+ "num_train_epochs": 10,
57
+ "total_flos": 1.510076088815616e+17,
58
+ "trial_name": null,
59
+ "trial_params": null
60
+ }
checkpoint-3386/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb2200feb70e8262514df4fd89c2cc8501a63e46178c2943084ed504f58b222
3
+ size 4283
runs/Dec01_01-27-35_baa8ebef2c59/events.out.tfevents.1701394062.baa8ebef2c59.89158.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b742be39132b8d565ab762d4e63f34c29949d8dda6e30506a929f4a91578259c
3
+ size 5709
runs/Dec01_03-21-39_baa8ebef2c59/events.out.tfevents.1701400905.baa8ebef2c59.118280.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3003be0d4cc6b50c51d253202f208400acba4b917ca349620c5b744c669c0a71
3
+ size 4767
runs/Dec01_03-27-22_baa8ebef2c59/events.out.tfevents.1701401247.baa8ebef2c59.118280.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce80556854368fd93ae14cd69992bd30b4f027b3852dda2fbf298cbf22ba5731
3
+ size 5977
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
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_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb2200feb70e8262514df4fd89c2cc8501a63e46178c2943084ed504f58b222
3
+ size 4283