Hugging Face's logo

bickett
/
meme-llama

Text Generation
Transformers
TensorBoard
English
llama
Trained with AutoTrain
llm
memes
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
bickett commited on
Commit
bc8dfff
•
1 Parent(s): 0ef63f0

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. README.md +9 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +3 -0
  5. checkpoint-3/README.md +34 -0
  6. checkpoint-3/adapter_config.json +23 -0
  7. checkpoint-3/adapter_model.bin +3 -0
  8. checkpoint-3/added_tokens.json +3 -0
  9. checkpoint-3/optimizer.pt +3 -0
  10. checkpoint-3/rng_state.pth +3 -0
  11. checkpoint-3/scheduler.pt +3 -0
  12. checkpoint-3/special_tokens_map.json +6 -0
  13. checkpoint-3/tokenizer.json +0 -0
  14. checkpoint-3/tokenizer.model +3 -0
  15. checkpoint-3/tokenizer_config.json +47 -0
  16. checkpoint-3/trainer_state.json +37 -0
  17. checkpoint-3/training_args.bin +3 -0
  18. runs/Sep27_00-43-49_46dc9884b460/events.out.tfevents.1695775430.46dc9884b460.6191.0 +3 -0
  19. runs/Sep27_00-51-11_46dc9884b460/events.out.tfevents.1695775872.46dc9884b460.8700.0 +3 -0
  20. runs/Sep27_00-58-55_46dc9884b460/events.out.tfevents.1695776335.46dc9884b460.10641.0 +3 -0
  21. runs/Sep27_01-04-34_46dc9884b460/events.out.tfevents.1695776674.46dc9884b460.12057.0 +3 -0
  22. special_tokens_map.json +6 -0
  23. tokenizer.json +0 -0
  24. tokenizer.model +3 -0
  25. tokenizer_config.json +47 -0
  26. training_args.bin +3 -0
  27. training_params.json +1 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac5032c2ac358b0b871702ff0f799926a3fdbfc1c0dd818a31d3ef168a6a7c3
3
+ size 33600461
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-3/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-3/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-3/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac5032c2ac358b0b871702ff0f799926a3fdbfc1c0dd818a31d3ef168a6a7c3
3
+ size 33600461
checkpoint-3/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b022f8473078f15c43dbb1f28fb1af4c9591e235388e5c62874348cde858063e
3
+ size 67216581
checkpoint-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcebc8344a60db30e256fd4fd5b3fff1f66cd1194e9d7d18b0e95dcaea5b9ce2
3
+ size 14575
checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7174dbc3bfab8c3745e931f08aeb049489d23b6c3255ff00a2b85a6a26479d92
3
+ size 627
checkpoint-3/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<unk>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-3/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<pad>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "legacy": false,
41
+ "model_max_length": 1024,
42
+ "pad_token": "<unk>",
43
+ "sp_model_kwargs": {},
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }
checkpoint-3/trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.3333333333333335,
5
+ "eval_steps": 500,
6
+ "global_step": 3,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.33,
13
+ "learning_rate": 0.0002,
14
+ "loss": 1.9691,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 1.33,
19
+ "learning_rate": 0.000175,
20
+ "loss": 1.9691,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 2.33,
25
+ "learning_rate": 0.00015000000000000001,
26
+ "loss": 1.6601,
27
+ "step": 3
28
+ }
29
+ ],
30
+ "logging_steps": 1,
31
+ "max_steps": 9,
32
+ "num_train_epochs": 3,
33
+ "save_steps": 500,
34
+ "total_flos": 121941251850240.0,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b45cf4b3cd0fc5c38d47646dc29598c141187f5d212184ce162a67347b1d36
3
+ size 4027
runs/Sep27_00-43-49_46dc9884b460/events.out.tfevents.1695775430.46dc9884b460.6191.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef547a31ea928105093f2eded1604ffd6c4551c2d880967294bb2ae1c8dd131
3
+ size 5347
runs/Sep27_00-51-11_46dc9884b460/events.out.tfevents.1695775872.46dc9884b460.8700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f635fce01c92a738b13e323b7de4682b847b725a37829bbf6950d9bcf53e2362
3
+ size 5347
runs/Sep27_00-58-55_46dc9884b460/events.out.tfevents.1695776335.46dc9884b460.10641.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a532019c1dfdee614428adb009466b8ccca9d0e17fc75998a93b011d725e9fe2
3
+ size 5347
runs/Sep27_01-04-34_46dc9884b460/events.out.tfevents.1695776674.46dc9884b460.12057.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53821131f313916c2afbe021d6a3a9ba677d898ef1e20e899bc63a7bf5badb8e
3
+ size 5347
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<unk>",
5
+ "unk_token": "<unk>"
6
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<pad>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "legacy": false,
41
+ "model_max_length": 1024,
42
+ "pad_token": "<unk>",
43
+ "sp_model_kwargs": {},
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b45cf4b3cd0fc5c38d47646dc29598c141187f5d212184ce162a67347b1d36
3
+ size 4027
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "abhishek/llama-2-7b-hf-small-shards", "data_path": ".", "project_name": "my-llm", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 3, "batch_size": 12, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "bickett/meme-llama", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}