Hugging Face's logo

zuhashaik
/
MaSaC-ERC-Z

Text Classification
PEFT
Safetensors
Hindi
English
Trigger
7B
LoRA
llama2
PEFT
Model card Files Community
1
zuhashaik commited on
Commit
2046a3e
•
1 Parent(s): 5a65606

uploading the model

Browse files
Files changed (11) hide show
  1. adapter_config.json +28 -0
  2. adapter_model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +29 -0
  7. tokenizer.json +0 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +46 -0
  10. trainer_state.json +133 -0
  11. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
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": 64,
12
+ "lora_dropout": 0.2,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "q_proj",
21
+ "up_proj",
22
+ "v_proj",
23
+ "o_proj",
24
+ "gate_proj",
25
+ "down_proj"
26
+ ],
27
+ "task_type": "SEQ_CLS"
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d4b857f37240520cd3af4803cfe05dde4580d32763893944c8b81a802ac207
3
+ size 167963416
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a647520a63f295da106a6617e29013d49ba77cd03f2fc4b24b137e9c3169927a
3
+ size 336185429
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037739b5400fa71246bffeb6e9d53e90aeabcf501e539ab07eef825c4eb8d34c
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd082e22c8895e446802d276460a69f984d9dafd3d83492bb8b40e3ab0911b8
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "</s>",
37
+ "legacy": true,
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "<s>",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "truncation_side": "left",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1479,
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": 2e-05,
14
+ "loss": 3.6557,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.41,
19
+ "learning_rate": 2e-05,
20
+ "loss": 1.6581,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.61,
25
+ "learning_rate": 2e-05,
26
+ "loss": 1.5014,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.81,
31
+ "learning_rate": 2e-05,
32
+ "loss": 1.3948,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 1.1438196897506714,
38
+ "eval_macro_f1": 0.43287074814809323,
39
+ "eval_runtime": 191.8217,
40
+ "eval_samples_per_second": 7.059,
41
+ "eval_steps_per_second": 1.413,
42
+ "eval_w_f1": 0.5734991666701943,
43
+ "step": 493
44
+ },
45
+ {
46
+ "epoch": 1.01,
47
+ "learning_rate": 2e-05,
48
+ "loss": 1.2719,
49
+ "step": 500
50
+ },
51
+ {
52
+ "epoch": 1.22,
53
+ "learning_rate": 2e-05,
54
+ "loss": 1.1415,
55
+ "step": 600
56
+ },
57
+ {
58
+ "epoch": 1.42,
59
+ "learning_rate": 2e-05,
60
+ "loss": 1.0834,
61
+ "step": 700
62
+ },
63
+ {
64
+ "epoch": 1.62,
65
+ "learning_rate": 2e-05,
66
+ "loss": 1.1151,
67
+ "step": 800
68
+ },
69
+ {
70
+ "epoch": 1.83,
71
+ "learning_rate": 2e-05,
72
+ "loss": 1.1067,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_loss": 0.6219320297241211,
78
+ "eval_macro_f1": 0.698736427313761,
79
+ "eval_runtime": 192.5646,
80
+ "eval_samples_per_second": 7.031,
81
+ "eval_steps_per_second": 1.407,
82
+ "eval_w_f1": 0.7795811904122447,
83
+ "step": 986
84
+ },
85
+ {
86
+ "epoch": 2.03,
87
+ "learning_rate": 2e-05,
88
+ "loss": 1.0408,
89
+ "step": 1000
90
+ },
91
+ {
92
+ "epoch": 2.23,
93
+ "learning_rate": 2e-05,
94
+ "loss": 0.5776,
95
+ "step": 1100
96
+ },
97
+ {
98
+ "epoch": 2.43,
99
+ "learning_rate": 2e-05,
100
+ "loss": 0.6012,
101
+ "step": 1200
102
+ },
103
+ {
104
+ "epoch": 2.64,
105
+ "learning_rate": 2e-05,
106
+ "loss": 0.6464,
107
+ "step": 1300
108
+ },
109
+ {
110
+ "epoch": 2.84,
111
+ "learning_rate": 2e-05,
112
+ "loss": 0.6282,
113
+ "step": 1400
114
+ },
115
+ {
116
+ "epoch": 3.0,
117
+ "eval_loss": 0.21291832625865936,
118
+ "eval_macro_f1": 0.919558189524972,
119
+ "eval_runtime": 190.235,
120
+ "eval_samples_per_second": 7.118,
121
+ "eval_steps_per_second": 1.425,
122
+ "eval_w_f1": 0.946814493022281,
123
+ "step": 1479
124
+ }
125
+ ],
126
+ "logging_steps": 100,
127
+ "max_steps": 2465,
128
+ "num_train_epochs": 5,
129
+ "save_steps": 500,
130
+ "total_flos": 3.163537548829901e+17,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6406893b40d75969eda87f486a42603ff1f0fd00639a0ee645443a1970aad1
3
+ size 4600