am-nandeesh commited on
Commit
62e7ec0
1 Parent(s): 895c04b

Upload folder using huggingface_hub

Browse files
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
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
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80484d7543d0031a830cf2ef16c33f972a9b4e3795820ab5b28a0f893e67062b
3
+ size 33600461
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-25/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 0.5.0
33
+
34
+ - PEFT 0.5.0
checkpoint-25/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
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-25/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80484d7543d0031a830cf2ef16c33f972a9b4e3795820ab5b28a0f893e67062b
3
+ size 33600461
checkpoint-25/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-25/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6609ac9935e095b8fc25cb631bd46f71c7f8c463ad0b018132b5af3a6c501563
3
+ size 67216581
checkpoint-25/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
3
+ size 443
checkpoint-25/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f78b2b6bc2e190c408751ffc153ca07e496bfaba09930e1086e756faf090dc9
3
+ size 14575
checkpoint-25/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf2952b233ef35de02f5ceb6fae08c1f798cceee9407d480c1e2df9abdbc490
3
+ size 627
checkpoint-25/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": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-25/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-25/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-25/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": false,
40
+ "model_max_length": 1024,
41
+ "pad_token": "<unk>",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
checkpoint-25/trainer_state.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 0.3065,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 2.0,
19
+ "learning_rate": 0.00013333333333333334,
20
+ "loss": 0.3065,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 3.0,
25
+ "learning_rate": 0.0002,
26
+ "loss": 0.3028,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 4.0,
31
+ "learning_rate": 0.00019090909090909092,
32
+ "loss": 0.2954,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 5.0,
37
+ "learning_rate": 0.00018181818181818183,
38
+ "loss": 0.2837,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 6.0,
43
+ "learning_rate": 0.00017272727272727275,
44
+ "loss": 0.2706,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 7.0,
49
+ "learning_rate": 0.00016363636363636366,
50
+ "loss": 0.2563,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 8.0,
55
+ "learning_rate": 0.00015454545454545454,
56
+ "loss": 0.2414,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 9.0,
61
+ "learning_rate": 0.00014545454545454546,
62
+ "loss": 0.2256,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 10.0,
67
+ "learning_rate": 0.00013636363636363637,
68
+ "loss": 0.2083,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 11.0,
73
+ "learning_rate": 0.00012727272727272728,
74
+ "loss": 0.1919,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 12.0,
79
+ "learning_rate": 0.0001181818181818182,
80
+ "loss": 0.1825,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 13.0,
85
+ "learning_rate": 0.00010909090909090909,
86
+ "loss": 0.1766,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 14.0,
91
+ "learning_rate": 0.0001,
92
+ "loss": 0.1706,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 15.0,
97
+ "learning_rate": 9.090909090909092e-05,
98
+ "loss": 0.1648,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 16.0,
103
+ "learning_rate": 8.181818181818183e-05,
104
+ "loss": 0.1591,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 17.0,
109
+ "learning_rate": 7.272727272727273e-05,
110
+ "loss": 0.1541,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 18.0,
115
+ "learning_rate": 6.363636363636364e-05,
116
+ "loss": 0.1492,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 19.0,
121
+ "learning_rate": 5.4545454545454546e-05,
122
+ "loss": 0.1448,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 20.0,
127
+ "learning_rate": 4.545454545454546e-05,
128
+ "loss": 0.1407,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 21.0,
133
+ "learning_rate": 3.6363636363636364e-05,
134
+ "loss": 0.1373,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 22.0,
139
+ "learning_rate": 2.7272727272727273e-05,
140
+ "loss": 0.1343,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 23.0,
145
+ "learning_rate": 1.8181818181818182e-05,
146
+ "loss": 0.1319,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 24.0,
151
+ "learning_rate": 9.090909090909091e-06,
152
+ "loss": 0.13,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 25.0,
157
+ "learning_rate": 0.0,
158
+ "loss": 0.1287,
159
+ "step": 25
160
+ }
161
+ ],
162
+ "logging_steps": 1,
163
+ "max_steps": 25,
164
+ "num_train_epochs": 25,
165
+ "save_steps": 500,
166
+ "total_flos": 4064708395008000.0,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
checkpoint-25/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4318085b1f41232f17235447d953bcd8f2add2dddfd8f6b59191b77dd5481fe5
3
+ size 4027
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": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": false,
40
+ "model_max_length": 1024,
41
+ "pad_token": "<unk>",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4318085b1f41232f17235447d953bcd8f2add2dddfd8f6b59191b77dd5481fe5
3
+ size 4027