Sriram-Gov sriram-g commited on
Commit
2b60d74
1 Parent(s): f9e3e02

added output adapter files from fine tuning (#1)

Browse files

- added output adapter files from fine tuning (94837a2fad166fe9d9b3313bf3b4d4d39d501b56)


Co-authored-by: sriram_g <[email protected]>

checkpoint-672/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-672/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
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": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-672/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96108b9b122965ce48ef33916a24aee0f5ad6f5e7148489fdc758b1952870d5
3
+ size 33600461
checkpoint-672/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30215ee1b9c2d172d7a5732b94eab2adeec75a9f471ddb287eba6e47bba2f15
3
+ size 67216581
checkpoint-672/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ba545e04e51e43cba6e578fb17332802d38a7cc94b401982295e96d50ff730
3
+ size 14511
checkpoint-672/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a35f013979a507c07573a899158aa07173000d9fe1743b865c9c20c330a96e
3
+ size 627
checkpoint-672/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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-672/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-672/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-672/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
+ "model_max_length": 340,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "use_default_system_prompt": true
32
+ }
checkpoint-672/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.319391634980988,
5
+ "eval_steps": 500,
6
+ "global_step": 672,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 4.928909952606635e-05,
14
+ "loss": 1.7844,
15
+ "step": 52
16
+ },
17
+ {
18
+ "epoch": 1.08,
19
+ "learning_rate": 9.85781990521327e-05,
20
+ "loss": 1.0308,
21
+ "step": 104
22
+ },
23
+ {
24
+ "epoch": 1.27,
25
+ "learning_rate": 0.00014786729857819904,
26
+ "loss": 0.832,
27
+ "step": 156
28
+ },
29
+ {
30
+ "epoch": 2.15,
31
+ "learning_rate": 0.0001971563981042654,
32
+ "loss": 0.7868,
33
+ "step": 208
34
+ },
35
+ {
36
+ "epoch": 3.03,
37
+ "learning_rate": 0.0001948230322239831,
38
+ "loss": 0.7672,
39
+ "step": 260
40
+ },
41
+ {
42
+ "epoch": 3.23,
43
+ "learning_rate": 0.00018932910723718966,
44
+ "loss": 0.7315,
45
+ "step": 312
46
+ },
47
+ {
48
+ "epoch": 4.11,
49
+ "learning_rate": 0.0001838351822503962,
50
+ "loss": 0.6889,
51
+ "step": 364
52
+ },
53
+ {
54
+ "epoch": 4.3,
55
+ "learning_rate": 0.00017834125726360275,
56
+ "loss": 0.6646,
57
+ "step": 416
58
+ },
59
+ {
60
+ "epoch": 5.18,
61
+ "learning_rate": 0.00017284733227680932,
62
+ "loss": 0.6056,
63
+ "step": 468
64
+ },
65
+ {
66
+ "epoch": 6.06,
67
+ "learning_rate": 0.00016735340729001586,
68
+ "loss": 0.5724,
69
+ "step": 520
70
+ },
71
+ {
72
+ "epoch": 6.26,
73
+ "learning_rate": 0.0001618594823032224,
74
+ "loss": 0.5251,
75
+ "step": 572
76
+ },
77
+ {
78
+ "epoch": 7.14,
79
+ "learning_rate": 0.00015636555731642895,
80
+ "loss": 0.4665,
81
+ "step": 624
82
+ }
83
+ ],
84
+ "logging_steps": 52,
85
+ "max_steps": 2104,
86
+ "num_train_epochs": 8,
87
+ "save_steps": 500,
88
+ "total_flos": 3.682319674638336e+16,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
checkpoint-672/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd040e94deeb93fb5664fab182f4eecb9002a7a1647a63d23aadfd2405bfd72
3
+ size 4091