Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
- added_tokens.json +5 -0
- checkpoint-400/README.md +238 -0
- checkpoint-400/adapter_config.json +23 -0
- checkpoint-400/adapter_model.bin +3 -0
- checkpoint-400/added_tokens.json +5 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +11 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer.model +3 -0
- checkpoint-400/tokenizer_config.json +44 -0
- checkpoint-400/trainer_state.json +79 -0
- checkpoint-400/training_args.bin +3 -0
- runs/Oct06_15-30-48_5b2d42ddb49a/events.out.tfevents.1696606249.5b2d42ddb49a.2212.0 +3 -0
- runs/Oct06_15-41-23_5b2d42ddb49a/events.out.tfevents.1696606884.5b2d42ddb49a.6040.0 +3 -0
- runs/Oct06_15-45-23_5b2d42ddb49a/events.out.tfevents.1696607123.5b2d42ddb49a.7119.0 +3 -0
- runs/Oct06_15-49-03_5b2d42ddb49a/events.out.tfevents.1696607343.5b2d42ddb49a.8125.0 +3 -0
- runs/Oct06_15-53-07_5b2d42ddb49a/events.out.tfevents.1696607587.5b2d42ddb49a.9167.0 +3 -0
- runs/Oct06_15-56-15_5b2d42ddb49a/events.out.tfevents.1696607776.5b2d42ddb49a.10043.0 +3 -0
- runs/Oct06_15-59-27_5b2d42ddb49a/events.out.tfevents.1696607968.5b2d42ddb49a.10951.0 +3 -0
- runs/Oct06_16-02-40_5b2d42ddb49a/events.out.tfevents.1696608160.5b2d42ddb49a.11825.0 +3 -0
- runs/Oct06_16-06-41_5b2d42ddb49a/events.out.tfevents.1696608402.5b2d42ddb49a.12895.0 +3 -0
- runs/Oct06_16-11-04_5b2d42ddb49a/events.out.tfevents.1696608665.5b2d42ddb49a.14015.0 +3 -0
- runs/Oct06_16-15-00_5b2d42ddb49a/events.out.tfevents.1696608900.5b2d42ddb49a.15064.0 +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- training_args.bin +3 -0
- training_params.json +1 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
widget:
|
6 |
+
- text: "I love AutoTrain because "
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Trained Using AutoTrain
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
|
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 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4019e2111cc7bd5cbc64531e70b37b1656f01463ca8d4990389c6cde22553e4d
|
3 |
+
size 27308941
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
checkpoint-400/README.md
ADDED
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: bn22/Mistral-7B-Instruct-v0.1-sharded
|
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 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data 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. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
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).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
+
## Training procedure
|
202 |
+
|
203 |
+
|
204 |
+
The following `bitsandbytes` quantization config was used during training:
|
205 |
+
- quant_method: bitsandbytes
|
206 |
+
- load_in_8bit: False
|
207 |
+
- load_in_4bit: True
|
208 |
+
- llm_int8_threshold: 6.0
|
209 |
+
- llm_int8_skip_modules: None
|
210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
211 |
+
- llm_int8_has_fp16_weight: False
|
212 |
+
- bnb_4bit_quant_type: nf4
|
213 |
+
- bnb_4bit_use_double_quant: False
|
214 |
+
- bnb_4bit_compute_dtype: float16
|
215 |
+
|
216 |
+
### Framework versions
|
217 |
+
|
218 |
+
|
219 |
+
- PEFT 0.6.0.dev0
|
220 |
+
## Training procedure
|
221 |
+
|
222 |
+
|
223 |
+
The following `bitsandbytes` quantization config was used during training:
|
224 |
+
- quant_method: bitsandbytes
|
225 |
+
- load_in_8bit: False
|
226 |
+
- load_in_4bit: True
|
227 |
+
- llm_int8_threshold: 6.0
|
228 |
+
- llm_int8_skip_modules: None
|
229 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
230 |
+
- llm_int8_has_fp16_weight: False
|
231 |
+
- bnb_4bit_quant_type: nf4
|
232 |
+
- bnb_4bit_use_double_quant: False
|
233 |
+
- bnb_4bit_compute_dtype: float16
|
234 |
+
|
235 |
+
### Framework versions
|
236 |
+
|
237 |
+
|
238 |
+
- PEFT 0.6.0.dev0
|
checkpoint-400/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
|
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 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-400/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4019e2111cc7bd5cbc64531e70b37b1656f01463ca8d4990389c6cde22553e4d
|
3 |
+
size 27308941
|
checkpoint-400/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
checkpoint-400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe172519a3ee8dfe4f6a6b659c174f2d6fb4bc3db104ad26134d03b1b32c62f
|
3 |
+
size 54633541
|
checkpoint-400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d61b78dd59e97d4678f229b0bf256b76b3111aef6634b134d729feae5dd1388c
|
3 |
+
size 14575
|
checkpoint-400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b31f08d8b35e149f41a12eed2de4457c266598e159e071ff484583bfb03d9709
|
3 |
+
size 627
|
checkpoint-400/special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"pad_token": "</s>",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-400/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-400/tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [
|
29 |
+
"<unk>",
|
30 |
+
"<s>",
|
31 |
+
"</s>"
|
32 |
+
],
|
33 |
+
"bos_token": "<s>",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 8192,
|
38 |
+
"pad_token": "</s>",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": true
|
44 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.44,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 400,
|
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": 0.000195,
|
14 |
+
"loss": 1.9236,
|
15 |
+
"step": 40
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.4,
|
19 |
+
"learning_rate": 0.00017833333333333335,
|
20 |
+
"loss": 1.709,
|
21 |
+
"step": 80
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.6,
|
25 |
+
"learning_rate": 0.00015611111111111113,
|
26 |
+
"loss": 1.7728,
|
27 |
+
"step": 120
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.8,
|
31 |
+
"learning_rate": 0.00013388888888888888,
|
32 |
+
"loss": 1.6717,
|
33 |
+
"step": 160
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"learning_rate": 0.00011166666666666668,
|
38 |
+
"loss": 1.6509,
|
39 |
+
"step": 200
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.2,
|
43 |
+
"learning_rate": 8.944444444444446e-05,
|
44 |
+
"loss": 1.7405,
|
45 |
+
"step": 240
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.4,
|
49 |
+
"learning_rate": 6.722222222222223e-05,
|
50 |
+
"loss": 1.7064,
|
51 |
+
"step": 280
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.04,
|
55 |
+
"learning_rate": 4.5e-05,
|
56 |
+
"loss": 1.7012,
|
57 |
+
"step": 320
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.24,
|
61 |
+
"learning_rate": 2.277777777777778e-05,
|
62 |
+
"loss": 1.5934,
|
63 |
+
"step": 360
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.44,
|
67 |
+
"learning_rate": 5.555555555555556e-07,
|
68 |
+
"loss": 1.6474,
|
69 |
+
"step": 400
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 40,
|
73 |
+
"max_steps": 400,
|
74 |
+
"num_train_epochs": 2,
|
75 |
+
"save_steps": 500,
|
76 |
+
"total_flos": 8.728462403567616e+16,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": null
|
79 |
+
}
|
checkpoint-400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d9885afd90ed4964bedc18202fb3dadaa57c52c5cebbd1c2e3ebf8b72c62894
|
3 |
+
size 4091
|
runs/Oct06_15-30-48_5b2d42ddb49a/events.out.tfevents.1696606249.5b2d42ddb49a.2212.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d320f3d4765bbe25916c2f451abaa9bc602d3edbf134986e852e053c98fc340
|
3 |
+
size 4184
|
runs/Oct06_15-41-23_5b2d42ddb49a/events.out.tfevents.1696606884.5b2d42ddb49a.6040.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:423998b83be168d1c116cf8ec8ae65af9cc703f15735d0d746e00726fc82bbd5
|
3 |
+
size 4184
|
runs/Oct06_15-45-23_5b2d42ddb49a/events.out.tfevents.1696607123.5b2d42ddb49a.7119.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4c1115f4b0749a40ba4df1af7f4b5b718260e9a75f8b948e4053d6df68c6c55
|
3 |
+
size 4536
|
runs/Oct06_15-49-03_5b2d42ddb49a/events.out.tfevents.1696607343.5b2d42ddb49a.8125.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f592b2f0c52208da5a8490ed8b1900e4b379f91270cc3669abf403f12cf1337
|
3 |
+
size 4536
|
runs/Oct06_15-53-07_5b2d42ddb49a/events.out.tfevents.1696607587.5b2d42ddb49a.9167.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4961fa5f62a9fd87b9033b46139ce996ab0127ae98541cd95aab9c67682132b
|
3 |
+
size 4534
|
runs/Oct06_15-56-15_5b2d42ddb49a/events.out.tfevents.1696607776.5b2d42ddb49a.10043.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d4c782801d87d1b5ac0935680450394cf21a78bbf2e4f6bf9ae4519eeb5cb84
|
3 |
+
size 4184
|
runs/Oct06_15-59-27_5b2d42ddb49a/events.out.tfevents.1696607968.5b2d42ddb49a.10951.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffe5adc599888c05074e7dd4ac7d75b8e0871dd0647fa3e751ced1c294c44476
|
3 |
+
size 4534
|
runs/Oct06_16-02-40_5b2d42ddb49a/events.out.tfevents.1696608160.5b2d42ddb49a.11825.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebc1d2efa5a14585dc8b13617b33b08b5c3ac24b974efecf6dbb5ccd9c76e3b8
|
3 |
+
size 4184
|
runs/Oct06_16-06-41_5b2d42ddb49a/events.out.tfevents.1696608402.5b2d42ddb49a.12895.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a1bf77a76a2fadc039a0e6cfadb38240bd480a1ef33a1755c9b81057ac2e31
|
3 |
+
size 4184
|
runs/Oct06_16-11-04_5b2d42ddb49a/events.out.tfevents.1696608665.5b2d42ddb49a.14015.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f91037284a61cdaacd0e3f5b29b64bbda41f76d358888817115b0d9b5cbaffe
|
3 |
+
size 4184
|
runs/Oct06_16-15-00_5b2d42ddb49a/events.out.tfevents.1696608900.5b2d42ddb49a.15064.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75d6601d5e89511ec6647b101f1bd99143407badfadaca48cbfb279e9971fcba
|
3 |
+
size 6448
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"pad_token": "</s>",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
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 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [
|
29 |
+
"<unk>",
|
30 |
+
"<s>",
|
31 |
+
"</s>"
|
32 |
+
],
|
33 |
+
"bos_token": "<s>",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 8192,
|
38 |
+
"pad_token": "</s>",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": true
|
44 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d9885afd90ed4964bedc18202fb3dadaa57c52c5cebbd1c2e3ebf8b72c62894
|
3 |
+
size 4091
|
training_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "bn22/Mistral-7B-Instruct-v0.1-sharded", "data_path": ".", "project_name": "mistral-7b-20kcontextqa-finetuned", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 2, "batch_size": 5, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 8192, "repo_id": "Dekono/mistral-7b-20kcontextqa-finetuned", "use_int4": true, "trainer": "sft", "target_modules": "q_proj,v_proj", "merge_adapter": false, "username": null, "use_flash_attention_2": false}
|