hibana2077 commited on
Commit
b39d2e0
1 Parent(s): 11d88e4

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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
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
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fadbc43ab7686fc20e11f6116343cf1030a1f97afbfeaf556cfbc0ce1f86b236
3
+ size 27280152
checkpoint-306/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.1
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-306/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
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
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-306/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fadbc43ab7686fc20e11f6116343cf1030a1f97afbfeaf556cfbc0ce1f86b236
3
+ size 27280152
checkpoint-306/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed352fc4bfd788f1ca291f17a5e4a8c85190b33195788f4cdebd20dc839a897
3
+ size 54633978
checkpoint-306/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
checkpoint-306/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8311fff5fdf6f326f37ac053e588c167c6fc19c93586e1f68bb5f134a1fc18bd
3
+ size 1064
checkpoint-306/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-306/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-306/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-306/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": 2048,
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-306/trainer_state.json ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 306,
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": 1.4516129032258065e-05,
14
+ "logits/chosen": -2.4829204082489014,
15
+ "logits/rejected": -2.623030185699463,
16
+ "logps/chosen": -55.93037033081055,
17
+ "logps/rejected": -33.53595733642578,
18
+ "loss": 0.5107,
19
+ "rewards/accuracies": 0.6499999761581421,
20
+ "rewards/chosen": 0.15422411262989044,
21
+ "rewards/margins": 0.5176956057548523,
22
+ "rewards/rejected": -0.36347147822380066,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.39,
27
+ "learning_rate": 2.9563636363636365e-05,
28
+ "logits/chosen": -2.385016918182373,
29
+ "logits/rejected": -2.5468831062316895,
30
+ "logps/chosen": -34.7657585144043,
31
+ "logps/rejected": -52.43476104736328,
32
+ "loss": 0.0274,
33
+ "rewards/accuracies": 1.0,
34
+ "rewards/chosen": 2.29936146736145,
35
+ "rewards/margins": 4.539745807647705,
36
+ "rewards/rejected": -2.240384578704834,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.59,
41
+ "learning_rate": 2.7381818181818182e-05,
42
+ "logits/chosen": -2.2574870586395264,
43
+ "logits/rejected": -2.420015811920166,
44
+ "logps/chosen": -13.00920295715332,
45
+ "logps/rejected": -70.32115936279297,
46
+ "loss": 0.0003,
47
+ "rewards/accuracies": 1.0,
48
+ "rewards/chosen": 4.496087074279785,
49
+ "rewards/margins": 8.517866134643555,
50
+ "rewards/rejected": -4.021780490875244,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.78,
55
+ "learning_rate": 2.52e-05,
56
+ "logits/chosen": -2.2138588428497314,
57
+ "logits/rejected": -2.3903181552886963,
58
+ "logps/chosen": -8.080777168273926,
59
+ "logps/rejected": -77.32413482666016,
60
+ "loss": 0.0001,
61
+ "rewards/accuracies": 1.0,
62
+ "rewards/chosen": 5.011228084564209,
63
+ "rewards/margins": 9.755220413208008,
64
+ "rewards/rejected": -4.743992805480957,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.98,
69
+ "learning_rate": 2.3018181818181816e-05,
70
+ "logits/chosen": -2.1865017414093018,
71
+ "logits/rejected": -2.3809409141540527,
72
+ "logps/chosen": -7.149311065673828,
73
+ "logps/rejected": -79.04914093017578,
74
+ "loss": 0.0,
75
+ "rewards/accuracies": 1.0,
76
+ "rewards/chosen": 5.135758399963379,
77
+ "rewards/margins": 10.058463096618652,
78
+ "rewards/rejected": -4.922704696655273,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.18,
83
+ "learning_rate": 2.0836363636363637e-05,
84
+ "logits/chosen": -2.204026699066162,
85
+ "logits/rejected": -2.377389430999756,
86
+ "logps/chosen": -6.087798118591309,
87
+ "logps/rejected": -80.18804931640625,
88
+ "loss": 0.0,
89
+ "rewards/accuracies": 1.0,
90
+ "rewards/chosen": 5.203327655792236,
91
+ "rewards/margins": 10.240509986877441,
92
+ "rewards/rejected": -5.037181854248047,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.37,
97
+ "learning_rate": 1.8654545454545454e-05,
98
+ "logits/chosen": -2.190598964691162,
99
+ "logits/rejected": -2.3737359046936035,
100
+ "logps/chosen": -5.493344306945801,
101
+ "logps/rejected": -81.6736831665039,
102
+ "loss": 0.0,
103
+ "rewards/accuracies": 1.0,
104
+ "rewards/chosen": 5.198002815246582,
105
+ "rewards/margins": 10.370179176330566,
106
+ "rewards/rejected": -5.172175884246826,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.57,
111
+ "learning_rate": 1.647272727272727e-05,
112
+ "logits/chosen": -2.198334217071533,
113
+ "logits/rejected": -2.3750014305114746,
114
+ "logps/chosen": -5.27658224105835,
115
+ "logps/rejected": -83.0462417602539,
116
+ "loss": 0.0,
117
+ "rewards/accuracies": 1.0,
118
+ "rewards/chosen": 5.275361061096191,
119
+ "rewards/margins": 10.579935073852539,
120
+ "rewards/rejected": -5.304574012756348,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.76,
125
+ "learning_rate": 1.4290909090909092e-05,
126
+ "logits/chosen": -2.1648800373077393,
127
+ "logits/rejected": -2.3531603813171387,
128
+ "logps/chosen": -5.335925579071045,
129
+ "logps/rejected": -83.67100524902344,
130
+ "loss": 0.0,
131
+ "rewards/accuracies": 1.0,
132
+ "rewards/chosen": 5.311135768890381,
133
+ "rewards/margins": 10.685991287231445,
134
+ "rewards/rejected": -5.374855041503906,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.96,
139
+ "learning_rate": 1.210909090909091e-05,
140
+ "logits/chosen": -2.1698648929595947,
141
+ "logits/rejected": -2.350588798522949,
142
+ "logps/chosen": -5.037841796875,
143
+ "logps/rejected": -84.4847183227539,
144
+ "loss": 0.0,
145
+ "rewards/accuracies": 1.0,
146
+ "rewards/chosen": 5.284677982330322,
147
+ "rewards/margins": 10.73720932006836,
148
+ "rewards/rejected": -5.4525299072265625,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.16,
153
+ "learning_rate": 9.927272727272728e-06,
154
+ "logits/chosen": -2.172761917114258,
155
+ "logits/rejected": -2.3548429012298584,
156
+ "logps/chosen": -4.5183844566345215,
157
+ "logps/rejected": -85.39585876464844,
158
+ "loss": 0.0,
159
+ "rewards/accuracies": 1.0,
160
+ "rewards/chosen": 5.35943603515625,
161
+ "rewards/margins": 10.907907485961914,
162
+ "rewards/rejected": -5.5484724044799805,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 2.35,
167
+ "learning_rate": 7.745454545454545e-06,
168
+ "logits/chosen": -2.176955223083496,
169
+ "logits/rejected": -2.3584964275360107,
170
+ "logps/chosen": -4.64106559753418,
171
+ "logps/rejected": -85.82803344726562,
172
+ "loss": 0.0,
173
+ "rewards/accuracies": 1.0,
174
+ "rewards/chosen": 5.32342004776001,
175
+ "rewards/margins": 10.914727210998535,
176
+ "rewards/rejected": -5.591307640075684,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 2.55,
181
+ "learning_rate": 5.563636363636363e-06,
182
+ "logits/chosen": -2.137197494506836,
183
+ "logits/rejected": -2.3419229984283447,
184
+ "logps/chosen": -4.342270374298096,
185
+ "logps/rejected": -85.80111694335938,
186
+ "loss": 0.0,
187
+ "rewards/accuracies": 1.0,
188
+ "rewards/chosen": 5.375523567199707,
189
+ "rewards/margins": 10.970113754272461,
190
+ "rewards/rejected": -5.594590663909912,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 2.75,
195
+ "learning_rate": 3.381818181818182e-06,
196
+ "logits/chosen": -2.18381404876709,
197
+ "logits/rejected": -2.362435817718506,
198
+ "logps/chosen": -4.8146867752075195,
199
+ "logps/rejected": -86.47946166992188,
200
+ "loss": 0.0,
201
+ "rewards/accuracies": 1.0,
202
+ "rewards/chosen": 5.325329303741455,
203
+ "rewards/margins": 10.978459358215332,
204
+ "rewards/rejected": -5.653130531311035,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 2.94,
209
+ "learning_rate": 1.2000000000000002e-06,
210
+ "logits/chosen": -2.179290294647217,
211
+ "logits/rejected": -2.3513832092285156,
212
+ "logps/chosen": -4.198988437652588,
213
+ "logps/rejected": -86.9154052734375,
214
+ "loss": 0.0,
215
+ "rewards/accuracies": 1.0,
216
+ "rewards/chosen": 5.389545917510986,
217
+ "rewards/margins": 11.077142715454102,
218
+ "rewards/rejected": -5.687596321105957,
219
+ "step": 300
220
+ }
221
+ ],
222
+ "logging_steps": 20,
223
+ "max_steps": 306,
224
+ "num_input_tokens_seen": 0,
225
+ "num_train_epochs": 3,
226
+ "save_steps": 500,
227
+ "total_flos": 0.0,
228
+ "train_batch_size": 2,
229
+ "trial_name": null,
230
+ "trial_params": null
231
+ }
checkpoint-306/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9c2c5a5d50cdb11b163d3080c4cca2b7702a1c504d741a0913a9cf77e1d08e
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": 2048,
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:df9c2c5a5d50cdb11b163d3080c4cca2b7702a1c504d741a0913a9cf77e1d08e
3
+ size 4728
training_params.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "mistralai/Mistral-7B-Instruct-v0.1",
3
+ "project_name": "/tmp/model",
4
+ "data_path": "hibana2077/autotrain-data-autotrain-67u2b-ez13i",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 1024,
9
+ "model_max_length": 2048,
10
+ "trainer": "dpo",
11
+ "use_flash_attention_2": false,
12
+ "log": "none",
13
+ "disable_gradient_checkpointing": false,
14
+ "logging_steps": -1,
15
+ "evaluation_strategy": "epoch",
16
+ "save_total_limit": 1,
17
+ "save_strategy": "epoch",
18
+ "auto_find_batch_size": false,
19
+ "mixed_precision": "fp16",
20
+ "lr": 3e-05,
21
+ "epochs": 3,
22
+ "batch_size": 2,
23
+ "warmup_ratio": 0.1,
24
+ "gradient_accumulation": 1,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "linear",
27
+ "weight_decay": 0.0,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "apply_chat_template": false,
31
+ "quantization": "int4",
32
+ "target_modules": "",
33
+ "merge_adapter": false,
34
+ "peft": true,
35
+ "lora_r": 16,
36
+ "lora_alpha": 32,
37
+ "lora_dropout": 0.05,
38
+ "model_ref": null,
39
+ "dpo_beta": 0.1,
40
+ "prompt_text_column": "autotrain_prompt",
41
+ "text_column": "autotrain_text",
42
+ "rejected_text_column": "autotrain_rejected_text",
43
+ "push_to_hub": true,
44
+ "repo_id": "hibana2077/autotrain-67u2b-ez13i",
45
+ "username": "hibana2077"
46
+ }