hardlyworking commited on
Commit
76f4753
·
verified ·
1 Parent(s): fde8cd0

End of training

Browse files
Files changed (1) hide show
  1. README.md +192 -190
README.md CHANGED
@@ -1,208 +1,210 @@
1
  ---
2
- base_model: model
3
  library_name: peft
4
- pipeline_tag: text-generation
5
  tags:
6
  - axolotl
7
  - base_model:adapter:model
8
  - lora
9
  - transformers
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
- # Model Card for Model ID
13
-
14
- <!-- Provide a quick summary of what the model is/does. -->
15
-
16
-
17
-
18
- ## Model Details
19
-
20
- ### Model Description
21
-
22
- <!-- Provide a longer summary of what this model is. -->
23
-
24
-
25
-
26
- - **Developed by:** [More Information Needed]
27
- - **Funded by [optional]:** [More Information Needed]
28
- - **Shared by [optional]:** [More Information Needed]
29
- - **Model type:** [More Information Needed]
30
- - **Language(s) (NLP):** [More Information Needed]
31
- - **License:** [More Information Needed]
32
- - **Finetuned from model [optional]:** [More Information Needed]
33
-
34
- ### Model Sources [optional]
35
-
36
- <!-- Provide the basic links for the model. -->
37
-
38
- - **Repository:** [More Information Needed]
39
- - **Paper [optional]:** [More Information Needed]
40
- - **Demo [optional]:** [More Information Needed]
41
-
42
- ## Uses
43
-
44
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
-
46
- ### Direct Use
47
-
48
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
-
50
- [More Information Needed]
51
-
52
- ### Downstream Use [optional]
53
-
54
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
-
56
- [More Information Needed]
57
-
58
- ### Out-of-Scope Use
59
-
60
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
-
62
- [More Information Needed]
63
-
64
- ## Bias, Risks, and Limitations
65
-
66
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
-
68
- [More Information Needed]
69
-
70
- ### Recommendations
71
-
72
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
-
74
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
-
76
- ## How to Get Started with the Model
77
-
78
- Use the code below to get started with the model.
79
-
80
- [More Information Needed]
81
-
82
- ## Training Details
83
-
84
- ### Training Data
85
-
86
- <!-- 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. -->
87
-
88
- [More Information Needed]
89
-
90
- ### Training Procedure
91
-
92
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
-
94
- #### Preprocessing [optional]
95
-
96
- [More Information Needed]
97
-
98
-
99
- #### Training Hyperparameters
100
 
101
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
102
 
103
- #### Speeds, Sizes, Times [optional]
104
-
105
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
-
107
- [More Information Needed]
108
-
109
- ## Evaluation
110
-
111
- <!-- This section describes the evaluation protocols and provides the results. -->
112
-
113
- ### Testing Data, Factors & Metrics
114
-
115
- #### Testing Data
116
-
117
- <!-- This should link to a Dataset Card if possible. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Factors
122
-
123
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
-
125
- [More Information Needed]
126
-
127
- #### Metrics
128
-
129
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
-
131
- [More Information Needed]
132
-
133
- ### Results
134
-
135
- [More Information Needed]
136
-
137
- #### Summary
138
-
139
-
140
-
141
- ## Model Examination [optional]
142
-
143
- <!-- Relevant interpretability work for the model goes here -->
144
-
145
- [More Information Needed]
146
-
147
- ## Environmental Impact
148
-
149
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
-
151
- 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).
152
-
153
- - **Hardware Type:** [More Information Needed]
154
- - **Hours used:** [More Information Needed]
155
- - **Cloud Provider:** [More Information Needed]
156
- - **Compute Region:** [More Information Needed]
157
- - **Carbon Emitted:** [More Information Needed]
158
-
159
- ## Technical Specifications [optional]
160
-
161
- ### Model Architecture and Objective
162
-
163
- [More Information Needed]
164
-
165
- ### Compute Infrastructure
166
-
167
- [More Information Needed]
168
-
169
- #### Hardware
170
-
171
- [More Information Needed]
172
-
173
- #### Software
174
-
175
- [More Information Needed]
176
-
177
- ## Citation [optional]
178
-
179
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
-
181
- **BibTeX:**
182
-
183
- [More Information Needed]
184
-
185
- **APA:**
186
-
187
- [More Information Needed]
188
-
189
- ## Glossary [optional]
190
-
191
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
-
193
- [More Information Needed]
194
-
195
- ## More Information [optional]
196
 
197
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
 
199
- ## Model Card Authors [optional]
200
 
201
- [More Information Needed]
202
 
203
- ## Model Card Contact
204
 
205
- [More Information Needed]
206
  ### Framework versions
207
 
208
- - PEFT 0.17.0
 
 
 
 
 
1
  ---
 
2
  library_name: peft
 
3
  tags:
4
  - axolotl
5
  - base_model:adapter:model
6
  - lora
7
  - transformers
8
+ datasets:
9
+ - PocketDoc/Dans-Prosemaxx-RepRemover-1
10
+ - PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
11
+ - Delta-Vector/Orion-Personamaxx-RP-Deslopped-V1
12
+ - Delta-Vector/Orion-PIPPA-Cleaned-V2
13
+ - Delta-Vector/Orion-Creative_Writing-Complexity
14
+ - Delta-Vector/Orion-OpenCAI-ShareGPT
15
+ - GreenerPastures/AllYourBase5k
16
+ pipeline_tag: text-generation
17
+ base_model: model
18
+ model-index:
19
+ - name: MS32-3
20
+ results: []
21
  ---
22
 
23
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
24
+ should probably proofread and complete it, then remove this comment. -->
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
 
26
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
27
+ <details><summary>See axolotl config</summary>
28
 
29
+ axolotl version: `0.12.0.dev0`
30
+ ```yaml
31
+ base_model: model
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
 
33
+ hub_model_id: hardlyworking/MS32-3
34
+ hub_strategy: "all_checkpoints"
35
+ push_dataset_to_hub:
36
+ hf_use_auth_token: true
37
+
38
+ plugins:
39
+ - axolotl.integrations.liger.LigerPlugin
40
+ - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
41
+ liger_rope: true
42
+ liger_rms_norm: true
43
+ liger_layer_norm: true
44
+ liger_glu_activation: true
45
+ liger_fused_linear_cross_entropy: false
46
+ cut_cross_entropy: true
47
+
48
+ load_in_8bit: false
49
+ load_in_4bit: true
50
+
51
+ chat_template: mistral_v7_tekken
52
+ datasets:
53
+ - path: PocketDoc/Dans-Prosemaxx-RepRemover-1
54
+ type: chat_template
55
+ split: train
56
+ field_messages: conversations
57
+ message_property_mappings:
58
+ role: from
59
+ content: value
60
+ user: human
61
+ assistant: gpt
62
+ - path: PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
63
+ type: chat_template
64
+ split: train
65
+ field_messages: conversations
66
+ message_property_mappings:
67
+ role: from
68
+ content: value
69
+ user: human
70
+ assistant: gpt
71
+ - path: Delta-Vector/Orion-Personamaxx-RP-Deslopped-V1
72
+ type: chat_template
73
+ split: train
74
+ field_messages: conversations
75
+ message_property_mappings:
76
+ role: from
77
+ content: value
78
+ user: human
79
+ assistant: gpt
80
+ - path: Delta-Vector/Orion-PIPPA-Cleaned-V2
81
+ type: chat_template
82
+ split: train
83
+ field_messages: conversations
84
+ message_property_mappings:
85
+ role: from
86
+ content: value
87
+ user: human
88
+ assistant: gpt
89
+ - path: Delta-Vector/Orion-Creative_Writing-Complexity
90
+ type: chat_template
91
+ split: train
92
+ field_messages: conversations
93
+ message_property_mappings:
94
+ role: from
95
+ content: value
96
+ user: human
97
+ assistant: gpt
98
+ - path: Delta-Vector/Orion-OpenCAI-ShareGPT
99
+ type: chat_template
100
+ split: train
101
+ field_messages: conversations
102
+ message_property_mappings:
103
+ role: from
104
+ content: value
105
+ user: human
106
+ assistant: gpt
107
+ - path: GreenerPastures/AllYourBase5k
108
+ type: chat_template
109
+ split: train
110
+ field_messages: conversations
111
+ message_property_mappings:
112
+ role: from
113
+ content: value
114
+ user: human
115
+ assistant: gpt
116
+
117
+ val_set_size: 0.0
118
+ output_dir: ./outputs/out
119
+
120
+ adapter: qlora
121
+ lora_r: 64
122
+ lora_alpha: 32
123
+ lora_dropout: 0.0
124
+ lora_target_linear: true
125
+ peft_use_rslora: true
126
+
127
+
128
+ sequence_len: 8192
129
+ sample_packing: true
130
+ eval_sample_packing: true
131
+ pad_to_sequence_len: true
132
+
133
+ wandb_project: MS32-3
134
+ wandb_entity:
135
+ wandb_watch:
136
+ wandb_name: MS32-3
137
+ wandb_log_model:
138
+
139
+ gradient_accumulation_steps: 32
140
+ micro_batch_size: 1
141
+ num_epochs: 1
142
+ optimizer: adamw_bnb_8bit
143
+ lr_scheduler: cosine
144
+ learning_rate: 4e-5
145
+ max_grad_norm: 1.0
146
+
147
+ bf16: auto
148
+ tf32: true
149
+
150
+ gradient_checkpointing: true
151
+ gradient_checkpointing_kwargs:
152
+ use_reentrant: false
153
+ unsloth: true
154
+ resume_from_checkpoint:
155
+ logging_steps: 1
156
+ flash_attention: true
157
+
158
+ warmup_ratio: 0.1
159
+ evals_per_epoch:
160
+ saves_per_epoch: 4
161
+ weight_decay: 0.0025
162
+ special_tokens:
163
+
164
+ ```
165
+
166
+ </details><br>
167
+
168
+ # MS32-3
169
+
170
+ This model was trained from scratch on the PocketDoc/Dans-Prosemaxx-RepRemover-1, the PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2, the Delta-Vector/Orion-Personamaxx-RP-Deslopped-V1, the Delta-Vector/Orion-PIPPA-Cleaned-V2, the Delta-Vector/Orion-Creative_Writing-Complexity, the Delta-Vector/Orion-OpenCAI-ShareGPT and the GreenerPastures/AllYourBase5k datasets.
171
+
172
+ ## Model description
173
+
174
+ More information needed
175
+
176
+ ## Intended uses & limitations
177
+
178
+ More information needed
179
+
180
+ ## Training and evaluation data
181
+
182
+ More information needed
183
+
184
+ ## Training procedure
185
+
186
+ ### Training hyperparameters
187
+
188
+ The following hyperparameters were used during training:
189
+ - learning_rate: 4e-05
190
+ - train_batch_size: 1
191
+ - eval_batch_size: 1
192
+ - seed: 42
193
+ - gradient_accumulation_steps: 32
194
+ - total_train_batch_size: 32
195
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
196
+ - lr_scheduler_type: cosine
197
+ - lr_scheduler_warmup_steps: 10
198
+ - training_steps: 100
199
 
200
+ ### Training results
201
 
 
202
 
 
203
 
 
204
  ### Framework versions
205
 
206
+ - PEFT 0.17.0
207
+ - Transformers 4.55.0
208
+ - Pytorch 2.7.1+cu126
209
+ - Datasets 4.0.0
210
+ - Tokenizers 0.21.4