hibana2077 commited on
Commit
c5db3b6
1 Parent(s): 152dc3c

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 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilgpt2",
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
+ "c_attn"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ab457981cac4cfdeb60ebb0c473c22ff776260cb18cd1d3d853e6b7f654b76
3
+ size 1181192
checkpoint-177/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: distilgpt2
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-177/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "distilgpt2",
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
+ "c_attn"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-177/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ab457981cac4cfdeb60ebb0c473c22ff776260cb18cd1d3d853e6b7f654b76
3
+ size 1181192
checkpoint-177/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-177/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeaf3a80cd1d46a4e64bce9e1bcfe8164370d1bae8ca5ebbb8e94d3aa2ec580e
3
+ size 2369978
checkpoint-177/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-177/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5011e13d715347b91c4ad987a3cae69454bfab13d3c48edae8e3311a8bb650e
3
+ size 1064
checkpoint-177/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-177/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-177/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-177/trainer_state.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 177,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19,
13
+ "learning_rate": 1.3333333333333333e-05,
14
+ "logits/chosen": -54.362911224365234,
15
+ "logits/rejected": -50.76668930053711,
16
+ "logps/chosen": -1319.19677734375,
17
+ "logps/rejected": -33.71879577636719,
18
+ "loss": 0.6892,
19
+ "rewards/accuracies": 0.40909090638160706,
20
+ "rewards/chosen": 0.008085771463811398,
21
+ "rewards/margins": 0.007936443202197552,
22
+ "rewards/rejected": 0.0001493280433351174,
23
+ "step": 11
24
+ },
25
+ {
26
+ "epoch": 0.37,
27
+ "learning_rate": 2.9811320754716983e-05,
28
+ "logits/chosen": -54.190120697021484,
29
+ "logits/rejected": -52.07868957519531,
30
+ "logps/chosen": -1108.5838623046875,
31
+ "logps/rejected": -34.123477935791016,
32
+ "loss": 0.6329,
33
+ "rewards/accuracies": 0.8636363744735718,
34
+ "rewards/chosen": 0.12481586635112762,
35
+ "rewards/margins": 0.1290697455406189,
36
+ "rewards/rejected": -0.004253899212926626,
37
+ "step": 22
38
+ },
39
+ {
40
+ "epoch": 0.56,
41
+ "learning_rate": 2.7924528301886794e-05,
42
+ "logits/chosen": -55.231224060058594,
43
+ "logits/rejected": -52.04852294921875,
44
+ "logps/chosen": -879.3148803710938,
45
+ "logps/rejected": -34.018951416015625,
46
+ "loss": 0.5471,
47
+ "rewards/accuracies": 1.0,
48
+ "rewards/chosen": 0.3259323835372925,
49
+ "rewards/margins": 0.3459864854812622,
50
+ "rewards/rejected": -0.020054107531905174,
51
+ "step": 33
52
+ },
53
+ {
54
+ "epoch": 0.75,
55
+ "learning_rate": 2.5849056603773585e-05,
56
+ "logits/chosen": -54.642879486083984,
57
+ "logits/rejected": -50.72136306762695,
58
+ "logps/chosen": -1260.130615234375,
59
+ "logps/rejected": -32.81765365600586,
60
+ "loss": 0.3731,
61
+ "rewards/accuracies": 1.0,
62
+ "rewards/chosen": 0.9432396292686462,
63
+ "rewards/margins": 0.9746879935264587,
64
+ "rewards/rejected": -0.03144851326942444,
65
+ "step": 44
66
+ },
67
+ {
68
+ "epoch": 0.93,
69
+ "learning_rate": 2.377358490566038e-05,
70
+ "logits/chosen": -54.97840881347656,
71
+ "logits/rejected": -52.43299865722656,
72
+ "logps/chosen": -1015.5433959960938,
73
+ "logps/rejected": -34.17496109008789,
74
+ "loss": 0.3539,
75
+ "rewards/accuracies": 1.0,
76
+ "rewards/chosen": 1.0532668828964233,
77
+ "rewards/margins": 1.1037672758102417,
78
+ "rewards/rejected": -0.0505005344748497,
79
+ "step": 55
80
+ },
81
+ {
82
+ "epoch": 1.12,
83
+ "learning_rate": 2.169811320754717e-05,
84
+ "logits/chosen": -55.37051773071289,
85
+ "logits/rejected": -52.23636245727539,
86
+ "logps/chosen": -1029.4456787109375,
87
+ "logps/rejected": -34.25499725341797,
88
+ "loss": 0.2602,
89
+ "rewards/accuracies": 1.0,
90
+ "rewards/chosen": 1.5273464918136597,
91
+ "rewards/margins": 1.6002427339553833,
92
+ "rewards/rejected": -0.07289613038301468,
93
+ "step": 66
94
+ },
95
+ {
96
+ "epoch": 1.31,
97
+ "learning_rate": 1.9622641509433963e-05,
98
+ "logits/chosen": -55.24615478515625,
99
+ "logits/rejected": -51.99899673461914,
100
+ "logps/chosen": -1143.59716796875,
101
+ "logps/rejected": -35.575958251953125,
102
+ "loss": 0.2115,
103
+ "rewards/accuracies": 1.0,
104
+ "rewards/chosen": 2.0695841312408447,
105
+ "rewards/margins": 2.1615474224090576,
106
+ "rewards/rejected": -0.09196347743272781,
107
+ "step": 77
108
+ },
109
+ {
110
+ "epoch": 1.49,
111
+ "learning_rate": 1.7547169811320753e-05,
112
+ "logits/chosen": -55.43460464477539,
113
+ "logits/rejected": -50.45402908325195,
114
+ "logps/chosen": -1283.4525146484375,
115
+ "logps/rejected": -34.708351135253906,
116
+ "loss": 0.1256,
117
+ "rewards/accuracies": 1.0,
118
+ "rewards/chosen": 2.9994964599609375,
119
+ "rewards/margins": 3.1131112575531006,
120
+ "rewards/rejected": -0.11361455917358398,
121
+ "step": 88
122
+ },
123
+ {
124
+ "epoch": 1.68,
125
+ "learning_rate": 1.5471698113207547e-05,
126
+ "logits/chosen": -55.35545349121094,
127
+ "logits/rejected": -52.1571044921875,
128
+ "logps/chosen": -875.93359375,
129
+ "logps/rejected": -33.44974136352539,
130
+ "loss": 0.1917,
131
+ "rewards/accuracies": 1.0,
132
+ "rewards/chosen": 2.1976325511932373,
133
+ "rewards/margins": 2.317676544189453,
134
+ "rewards/rejected": -0.12004398554563522,
135
+ "step": 99
136
+ },
137
+ {
138
+ "epoch": 1.86,
139
+ "learning_rate": 1.339622641509434e-05,
140
+ "logits/chosen": -55.0767936706543,
141
+ "logits/rejected": -51.604347229003906,
142
+ "logps/chosen": -1365.019775390625,
143
+ "logps/rejected": -35.252044677734375,
144
+ "loss": 0.1243,
145
+ "rewards/accuracies": 1.0,
146
+ "rewards/chosen": 3.4024481773376465,
147
+ "rewards/margins": 3.554830312728882,
148
+ "rewards/rejected": -0.15238191187381744,
149
+ "step": 110
150
+ },
151
+ {
152
+ "epoch": 2.05,
153
+ "learning_rate": 1.1320754716981132e-05,
154
+ "logits/chosen": -56.40107727050781,
155
+ "logits/rejected": -54.048580169677734,
156
+ "logps/chosen": -858.4847412109375,
157
+ "logps/rejected": -34.9173698425293,
158
+ "loss": 0.1969,
159
+ "rewards/accuracies": 1.0,
160
+ "rewards/chosen": 2.170722484588623,
161
+ "rewards/margins": 2.324540138244629,
162
+ "rewards/rejected": -0.15381723642349243,
163
+ "step": 121
164
+ },
165
+ {
166
+ "epoch": 2.24,
167
+ "learning_rate": 9.245283018867924e-06,
168
+ "logits/chosen": -55.104923248291016,
169
+ "logits/rejected": -52.74159240722656,
170
+ "logps/chosen": -809.7835693359375,
171
+ "logps/rejected": -35.847755432128906,
172
+ "loss": 0.1303,
173
+ "rewards/accuracies": 1.0,
174
+ "rewards/chosen": 2.388211727142334,
175
+ "rewards/margins": 2.551792860031128,
176
+ "rewards/rejected": -0.16358119249343872,
177
+ "step": 132
178
+ },
179
+ {
180
+ "epoch": 2.42,
181
+ "learning_rate": 7.169811320754717e-06,
182
+ "logits/chosen": -55.185218811035156,
183
+ "logits/rejected": -52.399497985839844,
184
+ "logps/chosen": -959.4953002929688,
185
+ "logps/rejected": -34.56352615356445,
186
+ "loss": 0.1291,
187
+ "rewards/accuracies": 1.0,
188
+ "rewards/chosen": 2.7163705825805664,
189
+ "rewards/margins": 2.8906729221343994,
190
+ "rewards/rejected": -0.1743021458387375,
191
+ "step": 143
192
+ },
193
+ {
194
+ "epoch": 2.61,
195
+ "learning_rate": 5.094339622641509e-06,
196
+ "logits/chosen": -53.87266540527344,
197
+ "logits/rejected": -51.906978607177734,
198
+ "logps/chosen": -1213.17529296875,
199
+ "logps/rejected": -34.25074768066406,
200
+ "loss": 0.069,
201
+ "rewards/accuracies": 1.0,
202
+ "rewards/chosen": 3.6375014781951904,
203
+ "rewards/margins": 3.8169896602630615,
204
+ "rewards/rejected": -0.17948788404464722,
205
+ "step": 154
206
+ },
207
+ {
208
+ "epoch": 2.8,
209
+ "learning_rate": 3.018867924528302e-06,
210
+ "logits/chosen": -55.073856353759766,
211
+ "logits/rejected": -50.98554611206055,
212
+ "logps/chosen": -1360.9793701171875,
213
+ "logps/rejected": -36.670528411865234,
214
+ "loss": 0.1152,
215
+ "rewards/accuracies": 1.0,
216
+ "rewards/chosen": 3.9220426082611084,
217
+ "rewards/margins": 4.106159687042236,
218
+ "rewards/rejected": -0.18411725759506226,
219
+ "step": 165
220
+ },
221
+ {
222
+ "epoch": 2.98,
223
+ "learning_rate": 9.433962264150943e-07,
224
+ "logits/chosen": -55.68719482421875,
225
+ "logits/rejected": -54.916015625,
226
+ "logps/chosen": -787.702880859375,
227
+ "logps/rejected": -35.69668960571289,
228
+ "loss": 0.159,
229
+ "rewards/accuracies": 1.0,
230
+ "rewards/chosen": 2.3595094680786133,
231
+ "rewards/margins": 2.553260564804077,
232
+ "rewards/rejected": -0.19375087320804596,
233
+ "step": 176
234
+ }
235
+ ],
236
+ "logging_steps": 11,
237
+ "max_steps": 177,
238
+ "num_input_tokens_seen": 0,
239
+ "num_train_epochs": 3,
240
+ "save_steps": 500,
241
+ "total_flos": 0.0,
242
+ "train_batch_size": 2,
243
+ "trial_name": null,
244
+ "trial_params": null
245
+ }
checkpoint-177/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd403be857cd5ff0893a38db2708d3d2c7405c6b78e79def8dce5268c7b3d537
3
+ size 4728
checkpoint-177/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
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
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
requirements.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ peft==0.7.1
2
+ transformers==4.36.1
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd403be857cd5ff0893a38db2708d3d2c7405c6b78e79def8dce5268c7b3d537
3
+ size 4728
training_params.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "distilgpt2",
3
+ "project_name": "/tmp/model",
4
+ "data_path": "hibana2077/autotrain-data-test-2",
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/test-2",
45
+ "username": "hibana2077"
46
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff