theoracle commited on
Commit
2844319
1 Parent(s): 96baf0d

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-4040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2b",
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
+ "up_proj",
23
+ "gate_proj",
24
+ "o_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "k_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca547a361a90013863d28dfaa5885873fe7adcad4a3e01d801eb60a3de92fcd
3
+ size 78480072
checkpoint-4040/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: google/gemma-2b
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
+ ### Framework versions
201
+
202
+ - PEFT 0.9.0
checkpoint-4040/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2b",
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
+ "up_proj",
23
+ "gate_proj",
24
+ "o_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "k_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
checkpoint-4040/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca547a361a90013863d28dfaa5885873fe7adcad4a3e01d801eb60a3de92fcd
3
+ size 78480072
checkpoint-4040/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4b2836ed2b16fb09b5d8e1a1e327403e334dc27880767e249ba647e409e1c7
3
+ size 157104826
checkpoint-4040/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-4040/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558827980d72547dab3996c8477bd8ca92d3995995bca613a1fb28c743f1d820
3
+ size 14244
checkpoint-4040/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c228739c5078729a78b85e506a3169a7a4556d92c9abdc788dd4bb10220d27db
3
+ size 1064
checkpoint-4040/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-4040/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
3
+ size 17477553
checkpoint-4040/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
checkpoint-4040/tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<bos>",
39
+ "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 %}",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "<eos>",
42
+ "legacy": null,
43
+ "model_max_length": 2048,
44
+ "pad_token": "<pad>",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "GemmaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }
checkpoint-4040/trainer_state.json ADDED
@@ -0,0 +1,371 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4040,
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
+ "grad_norm": 13.334685325622559,
14
+ "learning_rate": 5.7178217821782184e-06,
15
+ "loss": 2.6835,
16
+ "step": 80
17
+ },
18
+ {
19
+ "epoch": 0.4,
20
+ "grad_norm": 1.5441126823425293,
21
+ "learning_rate": 1.1584158415841584e-05,
22
+ "loss": 2.3047,
23
+ "step": 160
24
+ },
25
+ {
26
+ "epoch": 0.59,
27
+ "grad_norm": 1.4855196475982666,
28
+ "learning_rate": 1.7524752475247524e-05,
29
+ "loss": 2.0103,
30
+ "step": 240
31
+ },
32
+ {
33
+ "epoch": 0.79,
34
+ "grad_norm": 2.429617166519165,
35
+ "learning_rate": 2.3465346534653467e-05,
36
+ "loss": 1.7695,
37
+ "step": 320
38
+ },
39
+ {
40
+ "epoch": 0.99,
41
+ "grad_norm": 1.6394236087799072,
42
+ "learning_rate": 2.9405940594059407e-05,
43
+ "loss": 1.7141,
44
+ "step": 400
45
+ },
46
+ {
47
+ "epoch": 1.19,
48
+ "grad_norm": 4.821674823760986,
49
+ "learning_rate": 2.9405940594059407e-05,
50
+ "loss": 1.6202,
51
+ "step": 480
52
+ },
53
+ {
54
+ "epoch": 1.39,
55
+ "grad_norm": 1.7676095962524414,
56
+ "learning_rate": 2.8745874587458746e-05,
57
+ "loss": 1.5316,
58
+ "step": 560
59
+ },
60
+ {
61
+ "epoch": 1.58,
62
+ "grad_norm": 1.9537432193756104,
63
+ "learning_rate": 2.8085808580858088e-05,
64
+ "loss": 1.5497,
65
+ "step": 640
66
+ },
67
+ {
68
+ "epoch": 1.78,
69
+ "grad_norm": 1.6451698541641235,
70
+ "learning_rate": 2.7425742574257424e-05,
71
+ "loss": 1.5092,
72
+ "step": 720
73
+ },
74
+ {
75
+ "epoch": 1.98,
76
+ "grad_norm": 1.8162490129470825,
77
+ "learning_rate": 2.6765676567656766e-05,
78
+ "loss": 1.4958,
79
+ "step": 800
80
+ },
81
+ {
82
+ "epoch": 2.18,
83
+ "grad_norm": 1.7349311113357544,
84
+ "learning_rate": 2.610561056105611e-05,
85
+ "loss": 1.4255,
86
+ "step": 880
87
+ },
88
+ {
89
+ "epoch": 2.38,
90
+ "grad_norm": 2.0465753078460693,
91
+ "learning_rate": 2.5445544554455447e-05,
92
+ "loss": 1.4322,
93
+ "step": 960
94
+ },
95
+ {
96
+ "epoch": 2.57,
97
+ "grad_norm": 2.079873561859131,
98
+ "learning_rate": 2.4785478547854786e-05,
99
+ "loss": 1.391,
100
+ "step": 1040
101
+ },
102
+ {
103
+ "epoch": 2.77,
104
+ "grad_norm": 1.8764556646347046,
105
+ "learning_rate": 2.4125412541254125e-05,
106
+ "loss": 1.4254,
107
+ "step": 1120
108
+ },
109
+ {
110
+ "epoch": 2.97,
111
+ "grad_norm": 2.345323324203491,
112
+ "learning_rate": 2.3465346534653467e-05,
113
+ "loss": 1.4177,
114
+ "step": 1200
115
+ },
116
+ {
117
+ "epoch": 3.17,
118
+ "grad_norm": 2.4153122901916504,
119
+ "learning_rate": 2.2805280528052803e-05,
120
+ "loss": 1.31,
121
+ "step": 1280
122
+ },
123
+ {
124
+ "epoch": 3.37,
125
+ "grad_norm": 2.362084150314331,
126
+ "learning_rate": 2.2145214521452145e-05,
127
+ "loss": 1.2966,
128
+ "step": 1360
129
+ },
130
+ {
131
+ "epoch": 3.56,
132
+ "grad_norm": 2.2319586277008057,
133
+ "learning_rate": 2.1485148514851487e-05,
134
+ "loss": 1.3684,
135
+ "step": 1440
136
+ },
137
+ {
138
+ "epoch": 3.76,
139
+ "grad_norm": 2.043566942214966,
140
+ "learning_rate": 2.0825082508250826e-05,
141
+ "loss": 1.392,
142
+ "step": 1520
143
+ },
144
+ {
145
+ "epoch": 3.96,
146
+ "grad_norm": 2.2719879150390625,
147
+ "learning_rate": 2.0165016501650165e-05,
148
+ "loss": 1.3083,
149
+ "step": 1600
150
+ },
151
+ {
152
+ "epoch": 4.16,
153
+ "grad_norm": 2.6207830905914307,
154
+ "learning_rate": 1.9504950495049504e-05,
155
+ "loss": 1.252,
156
+ "step": 1680
157
+ },
158
+ {
159
+ "epoch": 4.36,
160
+ "grad_norm": 2.797555446624756,
161
+ "learning_rate": 1.8844884488448846e-05,
162
+ "loss": 1.2673,
163
+ "step": 1760
164
+ },
165
+ {
166
+ "epoch": 4.55,
167
+ "grad_norm": 2.4675941467285156,
168
+ "learning_rate": 1.8184818481848185e-05,
169
+ "loss": 1.2311,
170
+ "step": 1840
171
+ },
172
+ {
173
+ "epoch": 4.75,
174
+ "grad_norm": 2.450917959213257,
175
+ "learning_rate": 1.7524752475247524e-05,
176
+ "loss": 1.2466,
177
+ "step": 1920
178
+ },
179
+ {
180
+ "epoch": 4.95,
181
+ "grad_norm": 2.9076478481292725,
182
+ "learning_rate": 1.6864686468646866e-05,
183
+ "loss": 1.3578,
184
+ "step": 2000
185
+ },
186
+ {
187
+ "epoch": 5.15,
188
+ "grad_norm": 2.909982681274414,
189
+ "learning_rate": 1.6204620462046205e-05,
190
+ "loss": 1.2384,
191
+ "step": 2080
192
+ },
193
+ {
194
+ "epoch": 5.35,
195
+ "grad_norm": 2.7267675399780273,
196
+ "learning_rate": 1.5544554455445548e-05,
197
+ "loss": 1.1951,
198
+ "step": 2160
199
+ },
200
+ {
201
+ "epoch": 5.54,
202
+ "grad_norm": 3.54055118560791,
203
+ "learning_rate": 1.4884488448844885e-05,
204
+ "loss": 1.2141,
205
+ "step": 2240
206
+ },
207
+ {
208
+ "epoch": 5.74,
209
+ "grad_norm": 2.72868275642395,
210
+ "learning_rate": 1.4224422442244225e-05,
211
+ "loss": 1.2374,
212
+ "step": 2320
213
+ },
214
+ {
215
+ "epoch": 5.94,
216
+ "grad_norm": 2.7000038623809814,
217
+ "learning_rate": 1.3564356435643564e-05,
218
+ "loss": 1.2645,
219
+ "step": 2400
220
+ },
221
+ {
222
+ "epoch": 6.14,
223
+ "grad_norm": 3.291171073913574,
224
+ "learning_rate": 1.2904290429042905e-05,
225
+ "loss": 1.1701,
226
+ "step": 2480
227
+ },
228
+ {
229
+ "epoch": 6.34,
230
+ "grad_norm": 2.9283392429351807,
231
+ "learning_rate": 1.2244224422442244e-05,
232
+ "loss": 1.1559,
233
+ "step": 2560
234
+ },
235
+ {
236
+ "epoch": 6.53,
237
+ "grad_norm": 3.4444239139556885,
238
+ "learning_rate": 1.1584158415841584e-05,
239
+ "loss": 1.1984,
240
+ "step": 2640
241
+ },
242
+ {
243
+ "epoch": 6.73,
244
+ "grad_norm": 3.4505791664123535,
245
+ "learning_rate": 1.0924092409240923e-05,
246
+ "loss": 1.1956,
247
+ "step": 2720
248
+ },
249
+ {
250
+ "epoch": 6.93,
251
+ "grad_norm": 3.7554521560668945,
252
+ "learning_rate": 1.0264026402640264e-05,
253
+ "loss": 1.1743,
254
+ "step": 2800
255
+ },
256
+ {
257
+ "epoch": 7.13,
258
+ "grad_norm": 3.4612154960632324,
259
+ "learning_rate": 9.603960396039604e-06,
260
+ "loss": 1.1505,
261
+ "step": 2880
262
+ },
263
+ {
264
+ "epoch": 7.33,
265
+ "grad_norm": 3.5600943565368652,
266
+ "learning_rate": 8.943894389438945e-06,
267
+ "loss": 1.1334,
268
+ "step": 2960
269
+ },
270
+ {
271
+ "epoch": 7.52,
272
+ "grad_norm": 3.4435224533081055,
273
+ "learning_rate": 8.283828382838284e-06,
274
+ "loss": 1.1477,
275
+ "step": 3040
276
+ },
277
+ {
278
+ "epoch": 7.72,
279
+ "grad_norm": 3.559251546859741,
280
+ "learning_rate": 7.6237623762376246e-06,
281
+ "loss": 1.1525,
282
+ "step": 3120
283
+ },
284
+ {
285
+ "epoch": 7.92,
286
+ "grad_norm": 4.093379497528076,
287
+ "learning_rate": 6.9636963696369635e-06,
288
+ "loss": 1.1258,
289
+ "step": 3200
290
+ },
291
+ {
292
+ "epoch": 8.12,
293
+ "grad_norm": 3.836825370788574,
294
+ "learning_rate": 6.303630363036304e-06,
295
+ "loss": 1.092,
296
+ "step": 3280
297
+ },
298
+ {
299
+ "epoch": 8.32,
300
+ "grad_norm": 3.719158411026001,
301
+ "learning_rate": 5.643564356435644e-06,
302
+ "loss": 1.1118,
303
+ "step": 3360
304
+ },
305
+ {
306
+ "epoch": 8.51,
307
+ "grad_norm": 4.2379374504089355,
308
+ "learning_rate": 4.9834983498349835e-06,
309
+ "loss": 1.1066,
310
+ "step": 3440
311
+ },
312
+ {
313
+ "epoch": 8.71,
314
+ "grad_norm": 4.96703577041626,
315
+ "learning_rate": 4.323432343234323e-06,
316
+ "loss": 1.1161,
317
+ "step": 3520
318
+ },
319
+ {
320
+ "epoch": 8.91,
321
+ "grad_norm": 9.020540237426758,
322
+ "learning_rate": 3.6633663366336635e-06,
323
+ "loss": 1.129,
324
+ "step": 3600
325
+ },
326
+ {
327
+ "epoch": 9.11,
328
+ "grad_norm": 3.624774217605591,
329
+ "learning_rate": 3.003300330033003e-06,
330
+ "loss": 1.097,
331
+ "step": 3680
332
+ },
333
+ {
334
+ "epoch": 9.31,
335
+ "grad_norm": 3.6332197189331055,
336
+ "learning_rate": 2.3432343234323434e-06,
337
+ "loss": 1.074,
338
+ "step": 3760
339
+ },
340
+ {
341
+ "epoch": 9.5,
342
+ "grad_norm": 4.2010579109191895,
343
+ "learning_rate": 1.683168316831683e-06,
344
+ "loss": 1.0808,
345
+ "step": 3840
346
+ },
347
+ {
348
+ "epoch": 9.7,
349
+ "grad_norm": 3.434506416320801,
350
+ "learning_rate": 1.023102310231023e-06,
351
+ "loss": 1.0774,
352
+ "step": 3920
353
+ },
354
+ {
355
+ "epoch": 9.9,
356
+ "grad_norm": 4.213884353637695,
357
+ "learning_rate": 3.63036303630363e-07,
358
+ "loss": 1.1134,
359
+ "step": 4000
360
+ }
361
+ ],
362
+ "logging_steps": 80,
363
+ "max_steps": 4040,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 10,
366
+ "save_steps": 500,
367
+ "total_flos": 9.936130988310528e+16,
368
+ "train_batch_size": 2,
369
+ "trial_name": null,
370
+ "trial_params": null
371
+ }
checkpoint-4040/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01b788f9e02180205714be9ffaf71e03e73d17a8fac23577a11f17d3dd94ef2
3
+ size 4920
handler.py ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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(path, trust_remote_code=True)
20
+ model.resize_token_embeddings(len(tokenizer))
21
+ model = PeftModel.from_pretrained(model, path)
22
+ model = model.merge_and_unload()
23
+ self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
24
+
25
+ def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
26
+ inputs = data.pop("inputs", data)
27
+ parameters = data.pop("parameters", None)
28
+ if parameters is not None:
29
+ prediction = self.pipeline(inputs, **parameters)
30
+ else:
31
+ prediction = self.pipeline(inputs)
32
+ return prediction
requirements.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ peft==0.9.0
2
+ transformers==4.38.1
runs/Mar06_21-38-30_r-theoracle-commodore2-9vrjlg93-0096a-fxgv1/events.out.tfevents.1709761111.r-theoracle-commodore2-9vrjlg93-0096a-fxgv1.98.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c04cf1eaff9e985491f1766572b6b6c16c750d0eb2df90b19061895b3d0d7fd
3
+ size 15967
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
3
+ size 17477553
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<bos>",
39
+ "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 %}",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "<eos>",
42
+ "legacy": null,
43
+ "model_max_length": 2048,
44
+ "pad_token": "<pad>",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "GemmaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01b788f9e02180205714be9ffaf71e03e73d17a8fac23577a11f17d3dd94ef2
3
+ size 4920
training_params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "google/gemma-2b",
3
+ "project_name": "autotrain-lsmbq-gemma64",
4
+ "data_path": "autotrain-lsmbq-gemma64/autotrain-data",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 1024,
9
+ "model_max_length": 2048,
10
+ "padding": "right",
11
+ "trainer": "default",
12
+ "use_flash_attention_2": false,
13
+ "log": "tensorboard",
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": 3e-05,
22
+ "epochs": 10,
23
+ "batch_size": 2,
24
+ "warmup_ratio": 0.1,
25
+ "gradient_accumulation": 1,
26
+ "optimizer": "adamw_torch",
27
+ "scheduler": "linear",
28
+ "weight_decay": 0.0,
29
+ "max_grad_norm": 1.0,
30
+ "seed": 42,
31
+ "chat_template": "none",
32
+ "quantization": "int4",
33
+ "target_modules": "all-linear",
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": "autotrain_prompt",
42
+ "text_column": "autotrain_text",
43
+ "rejected_text_column": "autotrain_rejected_text",
44
+ "push_to_hub": true,
45
+ "repo_id": "theoracle/autotrain-lsmbq-gemma64",
46
+ "username": "theoracle"
47
+ }