karthikrathod commited on
Commit
96ae8b4
1 Parent(s): 46c642f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ license: other
8
+ ---
9
+
10
+ # Model Trained Using AutoTrain
11
+
12
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
13
+
14
+ # Usage
15
+
16
+ ```python
17
+
18
+ from transformers import AutoModelForCausalLM, AutoTokenizer
19
+
20
+ model_path = "PATH_TO_THIS_REPO"
21
+
22
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
23
+ model = AutoModelForCausalLM.from_pretrained(
24
+ model_path,
25
+ device_map="auto",
26
+ torch_dtype='auto'
27
+ ).eval()
28
+
29
+ # Prompt content: "hi"
30
+ messages = [
31
+ {"role": "user", "content": "hi"}
32
+ ]
33
+
34
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
35
+ output_ids = model.generate(input_ids.to('cuda'))
36
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
37
+
38
+ # Model response: "Hello! How can I assist you today?"
39
+ print(response)
40
+ ```
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
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
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "o_proj",
24
+ "k_proj",
25
+ "gate_proj",
26
+ "q_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa85fe3e5d0eaa29d9441b4002b983c902ad694c8fc4bb50c832d0d22559f75e
3
+ size 92317600
checkpoint-100/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.7.1
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
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
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "o_proj",
24
+ "k_proj",
25
+ "gate_proj",
26
+ "q_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa85fe3e5d0eaa29d9441b4002b983c902ad694c8fc4bb50c832d0d22559f75e
3
+ size 92317600
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f0235db080282cc942d13e66453e0df264e4a4c7ab1e689234c7914cd48552
3
+ size 184818874
checkpoint-100/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273be72067560ba36b3fa3df1ac4e9d765648d872d3613df97e851a3650e6034
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1024,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,621 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 2e-05,
14
+ "loss": 2.3971,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.461,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 1.5,
25
+ "learning_rate": 6e-05,
26
+ "loss": 2.5204,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "learning_rate": 8e-05,
32
+ "loss": 2.1248,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 2.5,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.9833,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00012,
44
+ "loss": 2.1376,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 3.5,
49
+ "learning_rate": 0.00014,
50
+ "loss": 1.8588,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "learning_rate": 0.00016,
56
+ "loss": 1.7741,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 4.5,
61
+ "learning_rate": 0.00018,
62
+ "loss": 1.6101,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "learning_rate": 0.0002,
68
+ "loss": 1.602,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 5.5,
73
+ "learning_rate": 0.00019777777777777778,
74
+ "loss": 1.3506,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 6.0,
79
+ "learning_rate": 0.00019555555555555556,
80
+ "loss": 1.3243,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 6.5,
85
+ "learning_rate": 0.00019333333333333333,
86
+ "loss": 1.1528,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 7.0,
91
+ "learning_rate": 0.00019111111111111114,
92
+ "loss": 1.0344,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 7.5,
97
+ "learning_rate": 0.00018888888888888888,
98
+ "loss": 0.9344,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 8.0,
103
+ "learning_rate": 0.0001866666666666667,
104
+ "loss": 0.866,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 8.5,
109
+ "learning_rate": 0.00018444444444444446,
110
+ "loss": 0.6751,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 9.0,
115
+ "learning_rate": 0.00018222222222222224,
116
+ "loss": 0.66,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 9.5,
121
+ "learning_rate": 0.00018,
122
+ "loss": 0.5083,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 10.0,
127
+ "learning_rate": 0.00017777777777777779,
128
+ "loss": 0.4227,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 10.5,
133
+ "learning_rate": 0.00017555555555555556,
134
+ "loss": 0.3149,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 11.0,
139
+ "learning_rate": 0.00017333333333333334,
140
+ "loss": 0.2655,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 11.5,
145
+ "learning_rate": 0.0001711111111111111,
146
+ "loss": 0.1734,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 12.0,
151
+ "learning_rate": 0.00016888888888888889,
152
+ "loss": 0.1669,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 12.5,
157
+ "learning_rate": 0.0001666666666666667,
158
+ "loss": 0.1155,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 13.0,
163
+ "learning_rate": 0.00016444444444444444,
164
+ "loss": 0.0967,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 13.5,
169
+ "learning_rate": 0.00016222222222222224,
170
+ "loss": 0.0663,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 14.0,
175
+ "learning_rate": 0.00016,
176
+ "loss": 0.0794,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 14.5,
181
+ "learning_rate": 0.0001577777777777778,
182
+ "loss": 0.0642,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 15.0,
187
+ "learning_rate": 0.00015555555555555556,
188
+ "loss": 0.0495,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 15.5,
193
+ "learning_rate": 0.00015333333333333334,
194
+ "loss": 0.0395,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 16.0,
199
+ "learning_rate": 0.0001511111111111111,
200
+ "loss": 0.0731,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 16.5,
205
+ "learning_rate": 0.0001488888888888889,
206
+ "loss": 0.0458,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 17.0,
211
+ "learning_rate": 0.00014666666666666666,
212
+ "loss": 0.0499,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 17.5,
217
+ "learning_rate": 0.00014444444444444444,
218
+ "loss": 0.0345,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 18.0,
223
+ "learning_rate": 0.00014222222222222224,
224
+ "loss": 0.0463,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 18.5,
229
+ "learning_rate": 0.00014,
230
+ "loss": 0.0333,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 19.0,
235
+ "learning_rate": 0.0001377777777777778,
236
+ "loss": 0.0361,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 19.5,
241
+ "learning_rate": 0.00013555555555555556,
242
+ "loss": 0.0315,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 20.0,
247
+ "learning_rate": 0.00013333333333333334,
248
+ "loss": 0.0322,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 20.5,
253
+ "learning_rate": 0.00013111111111111111,
254
+ "loss": 0.0281,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 21.0,
259
+ "learning_rate": 0.00012888888888888892,
260
+ "loss": 0.0243,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 21.5,
265
+ "learning_rate": 0.00012666666666666666,
266
+ "loss": 0.0181,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 22.0,
271
+ "learning_rate": 0.00012444444444444444,
272
+ "loss": 0.0277,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 22.5,
277
+ "learning_rate": 0.00012222222222222224,
278
+ "loss": 0.0196,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 23.0,
283
+ "learning_rate": 0.00012,
284
+ "loss": 0.0257,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 23.5,
289
+ "learning_rate": 0.00011777777777777779,
290
+ "loss": 0.0153,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 24.0,
295
+ "learning_rate": 0.00011555555555555555,
296
+ "loss": 0.0252,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 24.5,
301
+ "learning_rate": 0.00011333333333333334,
302
+ "loss": 0.0134,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 25.0,
307
+ "learning_rate": 0.00011111111111111112,
308
+ "loss": 0.0256,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 25.5,
313
+ "learning_rate": 0.00010888888888888889,
314
+ "loss": 0.025,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 26.0,
319
+ "learning_rate": 0.00010666666666666667,
320
+ "loss": 0.0137,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 26.5,
325
+ "learning_rate": 0.00010444444444444445,
326
+ "loss": 0.0195,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 27.0,
331
+ "learning_rate": 0.00010222222222222222,
332
+ "loss": 0.0179,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 27.5,
337
+ "learning_rate": 0.0001,
338
+ "loss": 0.0178,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 28.0,
343
+ "learning_rate": 9.777777777777778e-05,
344
+ "loss": 0.0181,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 28.5,
349
+ "learning_rate": 9.555555555555557e-05,
350
+ "loss": 0.013,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 29.0,
355
+ "learning_rate": 9.333333333333334e-05,
356
+ "loss": 0.0226,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 29.5,
361
+ "learning_rate": 9.111111111111112e-05,
362
+ "loss": 0.0223,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 30.0,
367
+ "learning_rate": 8.888888888888889e-05,
368
+ "loss": 0.0126,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 30.5,
373
+ "learning_rate": 8.666666666666667e-05,
374
+ "loss": 0.0173,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 31.0,
379
+ "learning_rate": 8.444444444444444e-05,
380
+ "loss": 0.0168,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 31.5,
385
+ "learning_rate": 8.222222222222222e-05,
386
+ "loss": 0.0158,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 32.0,
391
+ "learning_rate": 8e-05,
392
+ "loss": 0.0176,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 32.5,
397
+ "learning_rate": 7.777777777777778e-05,
398
+ "loss": 0.0214,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 33.0,
403
+ "learning_rate": 7.555555555555556e-05,
404
+ "loss": 0.0117,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 33.5,
409
+ "learning_rate": 7.333333333333333e-05,
410
+ "loss": 0.0215,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 34.0,
415
+ "learning_rate": 7.111111111111112e-05,
416
+ "loss": 0.0108,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 34.5,
421
+ "learning_rate": 6.88888888888889e-05,
422
+ "loss": 0.0109,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 35.0,
427
+ "learning_rate": 6.666666666666667e-05,
428
+ "loss": 0.0206,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 35.5,
433
+ "learning_rate": 6.444444444444446e-05,
434
+ "loss": 0.0158,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 36.0,
439
+ "learning_rate": 6.222222222222222e-05,
440
+ "loss": 0.0152,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 36.5,
445
+ "learning_rate": 6e-05,
446
+ "loss": 0.0089,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 37.0,
451
+ "learning_rate": 5.7777777777777776e-05,
452
+ "loss": 0.0215,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 37.5,
457
+ "learning_rate": 5.555555555555556e-05,
458
+ "loss": 0.0147,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 38.0,
463
+ "learning_rate": 5.333333333333333e-05,
464
+ "loss": 0.0148,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 38.5,
469
+ "learning_rate": 5.111111111111111e-05,
470
+ "loss": 0.0144,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 39.0,
475
+ "learning_rate": 4.888888888888889e-05,
476
+ "loss": 0.0145,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 39.5,
481
+ "learning_rate": 4.666666666666667e-05,
482
+ "loss": 0.0142,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 40.0,
487
+ "learning_rate": 4.4444444444444447e-05,
488
+ "loss": 0.0142,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 40.5,
493
+ "learning_rate": 4.222222222222222e-05,
494
+ "loss": 0.0137,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 41.0,
499
+ "learning_rate": 4e-05,
500
+ "loss": 0.0138,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 41.5,
505
+ "learning_rate": 3.777777777777778e-05,
506
+ "loss": 0.0146,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 42.0,
511
+ "learning_rate": 3.555555555555556e-05,
512
+ "loss": 0.0129,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 42.5,
517
+ "learning_rate": 3.3333333333333335e-05,
518
+ "loss": 0.0078,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 43.0,
523
+ "learning_rate": 3.111111111111111e-05,
524
+ "loss": 0.0186,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 43.5,
529
+ "learning_rate": 2.8888888888888888e-05,
530
+ "loss": 0.0075,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 44.0,
535
+ "learning_rate": 2.6666666666666667e-05,
536
+ "loss": 0.0186,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 44.5,
541
+ "learning_rate": 2.4444444444444445e-05,
542
+ "loss": 0.0129,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 45.0,
547
+ "learning_rate": 2.2222222222222223e-05,
548
+ "loss": 0.0128,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 45.5,
553
+ "learning_rate": 2e-05,
554
+ "loss": 0.0187,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 46.0,
559
+ "learning_rate": 1.777777777777778e-05,
560
+ "loss": 0.0065,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 46.5,
565
+ "learning_rate": 1.5555555555555555e-05,
566
+ "loss": 0.0128,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 47.0,
571
+ "learning_rate": 1.3333333333333333e-05,
572
+ "loss": 0.0126,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 47.5,
577
+ "learning_rate": 1.1111111111111112e-05,
578
+ "loss": 0.0123,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 48.0,
583
+ "learning_rate": 8.88888888888889e-06,
584
+ "loss": 0.0128,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 48.5,
589
+ "learning_rate": 6.666666666666667e-06,
590
+ "loss": 0.0124,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 49.0,
595
+ "learning_rate": 4.444444444444445e-06,
596
+ "loss": 0.0124,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 49.5,
601
+ "learning_rate": 2.2222222222222225e-06,
602
+ "loss": 0.0124,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 50.0,
607
+ "learning_rate": 0.0,
608
+ "loss": 0.0123,
609
+ "step": 100
610
+ }
611
+ ],
612
+ "logging_steps": 1,
613
+ "max_steps": 100,
614
+ "num_input_tokens_seen": 0,
615
+ "num_train_epochs": 50,
616
+ "save_steps": 500,
617
+ "total_flos": 1.75318518202368e+16,
618
+ "train_batch_size": 1,
619
+ "trial_name": null,
620
+ "trial_params": null
621
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083fbf13af3ea247886ec79dad9f260ba26c206249619be7661ee7e3740dcb62
3
+ size 4728
handler.py ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from typing import Dict, List, Any
2
+ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
3
+ import torch
4
+ from peft import PeftModel
5
+ import json
6
+ import os
7
+
8
+
9
+ class EndpointHandler():
10
+ def __init__(self, path=""):
11
+ base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
12
+ model = AutoModelForCausalLM.from_pretrained(
13
+ base_model_path,
14
+ torch_dtype=torch.float16,
15
+ low_cpu_mem_usage=True,
16
+ trust_remote_code=True,
17
+ device_map="auto",
18
+ )
19
+ tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True)
20
+ model = PeftModel.from_pretrained(model, path)
21
+ model = model.merge_and_unload()
22
+ self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
23
+
24
+ def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
25
+ inputs = data.pop("inputs", data)
26
+ parameters = data.pop("parameters", None)
27
+ if parameters is not None:
28
+ prediction = self.pipeline(inputs, **parameters)
29
+ else:
30
+ prediction = self.pipeline(inputs)
31
+ return prediction
requirements.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ peft==0.7.1
2
+ transformers==4.36.1
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1024,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083fbf13af3ea247886ec79dad9f260ba26c206249619be7661ee7e3740dcb62
3
+ size 4728
training_params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "mistralai/Mistral-7B-Instruct-v0.2",
3
+ "project_name": "my_autotrain_llm_3",
4
+ "data_path": "data/",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": false,
8
+ "block_size": 1024,
9
+ "model_max_length": 1024,
10
+ "padding": null,
11
+ "trainer": "default",
12
+ "use_flash_attention_2": false,
13
+ "log": "wandb",
14
+ "disable_gradient_checkpointing": false,
15
+ "logging_steps": -1,
16
+ "evaluation_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "save_strategy": "epoch",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "fp16",
21
+ "lr": 0.0002,
22
+ "epochs": 50,
23
+ "batch_size": 1,
24
+ "warmup_ratio": 0.1,
25
+ "gradient_accumulation": 4,
26
+ "optimizer": "adamw_torch",
27
+ "scheduler": "linear",
28
+ "weight_decay": 0.01,
29
+ "max_grad_norm": 1.0,
30
+ "seed": 42,
31
+ "apply_chat_template": false,
32
+ "quantization": "int4",
33
+ "target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj",
34
+ "merge_adapter": false,
35
+ "peft": true,
36
+ "lora_r": 16,
37
+ "lora_alpha": 32,
38
+ "lora_dropout": 0.05,
39
+ "model_ref": null,
40
+ "dpo_beta": 0.1,
41
+ "prompt_text_column": "prompt",
42
+ "text_column": "text",
43
+ "rejected_text_column": "rejected",
44
+ "push_to_hub": true,
45
+ "repo_id": "karthikrathod/llm_repo_v8_10e",
46
+ "username": null
47
+ }