Hugging Face's logo

HydraLM
/
Nous-Hermes-llama-2-7b_7b_cluster00_partitioned_v3_standardized_00

PEFT
Model card Files Community
1
prateeky2806 commited on
Commit
1c6c01a
•
1 Parent(s): 5bd12cd

Training in progress, step 200

Browse files
Files changed (19) hide show
  1. adapter_config.json +26 -0
  2. adapter_model.bin +3 -0
  3. added_tokens.json +3 -0
  4. checkpoint-200/README.md +20 -0
  5. checkpoint-200/adapter_config.json +26 -0
  6. checkpoint-200/adapter_model.bin +3 -0
  7. checkpoint-200/added_tokens.json +3 -0
  8. checkpoint-200/optimizer.pt +3 -0
  9. checkpoint-200/rng_state.pth +3 -0
  10. checkpoint-200/scheduler.pt +3 -0
  11. checkpoint-200/special_tokens_map.json +6 -0
  12. checkpoint-200/tokenizer.model +3 -0
  13. checkpoint-200/tokenizer_config.json +35 -0
  14. checkpoint-200/trainer_state.json +144 -0
  15. checkpoint-200/training_args.bin +3 -0
  16. special_tokens_map.json +6 -0
  17. tokenizer.model +3 -0
  18. tokenizer_config.json +35 -0
  19. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "gate_proj",
18
+ "o_proj",
19
+ "k_proj",
20
+ "up_proj",
21
+ "v_proj",
22
+ "q_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1db379d02c4e5990d9c1f0ba0e9c732d2d60a70f9543614384ca2f3014c593
3
+ size 319977229
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-200/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-200/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "gate_proj",
18
+ "o_proj",
19
+ "k_proj",
20
+ "up_proj",
21
+ "v_proj",
22
+ "q_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-200/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1db379d02c4e5990d9c1f0ba0e9c732d2d60a70f9543614384ca2f3014c593
3
+ size 319977229
checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33ddc596e17f2d590a9dc16d0583d1a02cd8d49cb790a35fc14ca4f04ebb0cf
3
+ size 1279539525
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944287a16547a649c0a00319f9b7d451b75cc3f9b6437a68e6766889fa2cda45
3
+ size 14511
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
3
+ size 627
checkpoint-200/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-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4498298466205597,
3
+ "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_partitioned_v3_standardized_00/checkpoint-200",
4
+ "epoch": 0.21208907741251326,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.0002,
13
+ "loss": 0.5637,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 0.0002,
19
+ "loss": 0.4775,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 0.0002,
25
+ "loss": 0.5079,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 0.0002,
31
+ "loss": 0.4849,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.05,
36
+ "learning_rate": 0.0002,
37
+ "loss": 0.4587,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.06,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.4867,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.07,
48
+ "learning_rate": 0.0002,
49
+ "loss": 0.4578,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.08,
54
+ "learning_rate": 0.0002,
55
+ "loss": 0.4665,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.1,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.5044,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.11,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.4979,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.12,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.4715,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.13,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.4717,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.14,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.4419,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.15,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.4671,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.16,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.4503,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.17,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.4878,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.18,
108
+ "learning_rate": 0.0002,
109
+ "loss": 0.4648,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.19,
114
+ "learning_rate": 0.0002,
115
+ "loss": 0.4625,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.2,
120
+ "learning_rate": 0.0002,
121
+ "loss": 0.4473,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.21,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.4585,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.21,
132
+ "eval_loss": 0.4498298466205597,
133
+ "eval_runtime": 253.5551,
134
+ "eval_samples_per_second": 3.944,
135
+ "eval_steps_per_second": 0.986,
136
+ "step": 200
137
+ }
138
+ ],
139
+ "max_steps": 5000,
140
+ "num_train_epochs": 6,
141
+ "total_flos": 5.47322957438976e+16,
142
+ "trial_name": null,
143
+ "trial_params": null
144
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d43bb46b7e18307cd325d889344b3c5a6b0f12a2594434f5acb40117cbab761
3
+ size 6011
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.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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d43bb46b7e18307cd325d889344b3c5a6b0f12a2594434f5acb40117cbab761
3
+ size 6011