Hugging Face's logo

amdnsr
/
llama7b-finetuned-0

Model card Files Community
amdnsr commited on
Commit
87b500d
•
2 Parent(s): 1f7e930 b934ba4

update .gitattributes

Browse files
Files changed (16) hide show
  1. adapter_model/adapter_config.json +22 -0
  2. adapter_model/adapter_model.bin +3 -0
  3. added_tokens.json +3 -0
  4. all_results.json +11 -0
  5. eval_results.json +7 -0
  6. metrics.json +1 -0
  7. optimizer.pt +3 -0
  8. rng_state.pth +3 -0
  9. scheduler.pt +3 -0
  10. special_tokens_map.json +6 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +34 -0
  14. train_results.json +7 -0
  15. trainer_state.json +55 -0
  16. training_args.bin +3 -0
adapter_model/adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "/home/kokil/ahmad/llms/ml-models/huggyllama/llama-7b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 16,
8
+ "lora_dropout": 0.0,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 64,
12
+ "target_modules": [
13
+ "gate_proj",
14
+ "up_proj",
15
+ "q_proj",
16
+ "k_proj",
17
+ "down_proj",
18
+ "v_proj",
19
+ "o_proj"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11df700bf60f64acc1c8cb6164d1be9b7565f24b39d737f63b61e522b3111aa8
3
+ size 639792909
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.02,
3
+ "eval_loss": 1.4698705673217773,
4
+ "eval_runtime": 294.5013,
5
+ "eval_samples_per_second": 3.396,
6
+ "eval_steps_per_second": 0.849,
7
+ "train_loss": 1.198510036468506,
8
+ "train_runtime": 688.023,
9
+ "train_samples_per_second": 1.163,
10
+ "train_steps_per_second": 0.073
11
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.02,
3
+ "eval_loss": 1.4698705673217773,
4
+ "eval_runtime": 294.5013,
5
+ "eval_samples_per_second": 3.396,
6
+ "eval_steps_per_second": 0.849
7
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"run_name": "./output3", "train_runtime": 688.023, "train_samples_per_second": 1.163, "train_steps_per_second": 0.073, "train_loss": 1.198510036468506, "epoch": 0.02, "eval_loss": 1.4698705673217773, "eval_runtime": 294.5013, "eval_samples_per_second": 3.396, "eval_steps_per_second": 0.849}
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5158c10fef1ab638e9af09653b8576dd85db707377b47615b0ebb6c1eb17e55
3
+ size 3376758277
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d217edb059555be97837810de03dc22d79976c8832aac609d084f6016b5003c4
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.02,
3
+ "train_loss": 1.198510036468506,
4
+ "train_runtime": 688.023,
5
+ "train_samples_per_second": 1.163,
6
+ "train_steps_per_second": 0.073
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.01569242840329541,
5
+ "global_step": 50,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.4673,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.2893,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.1835,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.0317,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.0207,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "step": 50,
43
+ "total_flos": 2292376788271104.0,
44
+ "train_loss": 1.198510036468506,
45
+ "train_runtime": 688.023,
46
+ "train_samples_per_second": 1.163,
47
+ "train_steps_per_second": 0.073
48
+ }
49
+ ],
50
+ "max_steps": 50,
51
+ "num_train_epochs": 1,
52
+ "total_flos": 2292376788271104.0,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7210638a3776eeb80498f9016fbee1e34134d62066d4a675fe5b52ae32ca75
3
+ size 5627