LoneStriker commited on
Commit
7a84db1
1 Parent(s): e4314dd

ExLLaMA V2 quant of zephyr-7b-beta-4.0bpw-h6-exl2

Browse files
README.md ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: zephyr-7b-beta
6
+ results: []
7
+ license: mit
8
+ datasets:
9
+ - HuggingFaceH4/ultrachat_200k
10
+ - HuggingFaceH4/ultrafeedback_binarized
11
+ language:
12
+ - en
13
+ base_model: mistralai/Mistral-7B-v0.1
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ <img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
20
+
21
+
22
+ # Model Card for Zephyr 7B β
23
+
24
+ Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so and should only be used for educational and research purposes. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
25
+
26
+
27
+ ## Model description
28
+
29
+ - **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
30
+ - **Language(s) (NLP):** Primarily English
31
+ - **License:** MIT
32
+ - **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
33
+
34
+ ### Model Sources
35
+
36
+ <!-- Provide the basic links for the model. -->
37
+
38
+ - **Repository:** https://github.com/huggingface/alignment-handbook
39
+ - **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
40
+ - **Chatbot Arena:** Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org
41
+
42
+ ## Performance
43
+
44
+ At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks:
45
+
46
+ | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
47
+ |-------------|-----|----|---------------|--------------|
48
+ | StableLM-Tuned-α | 7B| dSFT |2.75| -|
49
+ | MPT-Chat | 7B |dSFT |5.42| -|
50
+ | Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
51
+ | Mistral-Instructv0.1 | 7B| - | 6.84 |-|
52
+ | Zephyr-7b-α |7B| dDPO| 6.88| -|
53
+ | **Zephyr-7b-β** 🪁 | **7B** | **dDPO** | **7.34** | **90.60** |
54
+ | Falcon-Instruct | 40B |dSFT |5.17 |45.71|
55
+ | Guanaco | 65B | SFT |6.41| 71.80|
56
+ | Llama2-Chat | 70B |RLHF |6.86| 92.66|
57
+ | Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
58
+ | WizardLM v1.0 | 70B |dSFT |7.71 |-|
59
+ | Xwin-LM v0.1 | 70B |dPPO |- |95.57|
60
+ | GPT-3.5-turbo | - |RLHF |7.94 |89.37|
61
+ | Claude 2 | - |RLHF |8.06| 91.36|
62
+ | GPT-4 | -| RLHF |8.99| 95.28|
63
+
64
+ In particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:
65
+
66
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6200d0a443eb0913fa2df7cc/raxvt5ma16d7T23my34WC.png)
67
+
68
+ However, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.
69
+
70
+
71
+ ## Intended uses & limitations
72
+
73
+ The model was initially fine-tuned on a filtered and preprocessed of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
74
+ We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities.
75
+
76
+ You can find the datasets used for training Zephyr-7B-β [here](https://huggingface.co/collections/HuggingFaceH4/zephyr-7b-6538c6d6d5ddd1cbb1744a66)
77
+
78
+ Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
79
+
80
+ ```python
81
+ # Install transformers from source - only needed for versions <= v4.34
82
+ # pip install git+https://github.com/huggingface/transformers.git
83
+ # pip install accelerate
84
+
85
+ import torch
86
+ from transformers import pipeline
87
+
88
+ pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")
89
+
90
+ # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
91
+ messages = [
92
+ {
93
+ "role": "system",
94
+ "content": "You are a friendly chatbot who always responds in the style of a pirate",
95
+ },
96
+ {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
97
+ ]
98
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
99
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
100
+ print(outputs[0]["generated_text"])
101
+ # <|system|>
102
+ # You are a friendly chatbot who always responds in the style of a pirate.</s>
103
+ # <|user|>
104
+ # How many helicopters can a human eat in one sitting?</s>
105
+ # <|assistant|>
106
+ # Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
107
+ ```
108
+
109
+ ## Bias, Risks, and Limitations
110
+
111
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
112
+
113
+ Zephyr-7B-β has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
114
+ It is also unknown what the size and composition of the corpus was used to train the base model (`mistralai/Mistral-7B-v0.1`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [Falcon 180B model card](https://huggingface.co/tiiuae/falcon-180B#training-data) for an example of this.
115
+
116
+
117
+ ## Training and evaluation data
118
+
119
+ During DPO training, this model achieves the following results on the evaluation set:
120
+
121
+ - Loss: 0.7496
122
+ - Rewards/chosen: -4.5221
123
+ - Rewards/rejected: -8.3184
124
+ - Rewards/accuracies: 0.7812
125
+ - Rewards/margins: 3.7963
126
+ - Logps/rejected: -340.1541
127
+ - Logps/chosen: -299.4561
128
+ - Logits/rejected: -2.3081
129
+ - Logits/chosen: -2.3531
130
+
131
+
132
+ ### Training hyperparameters
133
+
134
+ The following hyperparameters were used during training:
135
+ - learning_rate: 5e-07
136
+ - train_batch_size: 2
137
+ - eval_batch_size: 4
138
+ - seed: 42
139
+ - distributed_type: multi-GPU
140
+ - num_devices: 16
141
+ - total_train_batch_size: 32
142
+ - total_eval_batch_size: 64
143
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
144
+ - lr_scheduler_type: linear
145
+ - lr_scheduler_warmup_ratio: 0.1
146
+ - num_epochs: 3.0
147
+
148
+ ### Training results
149
+
150
+ The table below shows the full set of DPO training metrics:
151
+
152
+
153
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
154
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
155
+ | 0.6284 | 0.05 | 100 | 0.6098 | 0.0425 | -0.1872 | 0.7344 | 0.2297 | -258.8416 | -253.8099 | -2.7976 | -2.8234 |
156
+ | 0.4908 | 0.1 | 200 | 0.5426 | -0.0279 | -0.6842 | 0.75 | 0.6563 | -263.8124 | -254.5145 | -2.7719 | -2.7960 |
157
+ | 0.5264 | 0.15 | 300 | 0.5324 | 0.0414 | -0.9793 | 0.7656 | 1.0207 | -266.7627 | -253.8209 | -2.7892 | -2.8122 |
158
+ | 0.5536 | 0.21 | 400 | 0.4957 | -0.0185 | -1.5276 | 0.7969 | 1.5091 | -272.2460 | -254.4203 | -2.8542 | -2.8764 |
159
+ | 0.5362 | 0.26 | 500 | 0.5031 | -0.2630 | -1.5917 | 0.7812 | 1.3287 | -272.8869 | -256.8653 | -2.8702 | -2.8958 |
160
+ | 0.5966 | 0.31 | 600 | 0.5963 | -0.2993 | -1.6491 | 0.7812 | 1.3499 | -273.4614 | -257.2279 | -2.8778 | -2.8986 |
161
+ | 0.5014 | 0.36 | 700 | 0.5382 | -0.2859 | -1.4750 | 0.75 | 1.1891 | -271.7204 | -257.0942 | -2.7659 | -2.7869 |
162
+ | 0.5334 | 0.41 | 800 | 0.5677 | -0.4289 | -1.8968 | 0.7969 | 1.4679 | -275.9378 | -258.5242 | -2.7053 | -2.7265 |
163
+ | 0.5251 | 0.46 | 900 | 0.5772 | -0.2116 | -1.3107 | 0.7344 | 1.0991 | -270.0768 | -256.3507 | -2.8463 | -2.8662 |
164
+ | 0.5205 | 0.52 | 1000 | 0.5262 | -0.3792 | -1.8585 | 0.7188 | 1.4793 | -275.5552 | -258.0276 | -2.7893 | -2.7979 |
165
+ | 0.5094 | 0.57 | 1100 | 0.5433 | -0.6279 | -1.9368 | 0.7969 | 1.3089 | -276.3377 | -260.5136 | -2.7453 | -2.7536 |
166
+ | 0.5837 | 0.62 | 1200 | 0.5349 | -0.3780 | -1.9584 | 0.7656 | 1.5804 | -276.5542 | -258.0154 | -2.7643 | -2.7756 |
167
+ | 0.5214 | 0.67 | 1300 | 0.5732 | -1.0055 | -2.2306 | 0.7656 | 1.2251 | -279.2761 | -264.2903 | -2.6986 | -2.7113 |
168
+ | 0.6914 | 0.72 | 1400 | 0.5137 | -0.6912 | -2.1775 | 0.7969 | 1.4863 | -278.7448 | -261.1467 | -2.7166 | -2.7275 |
169
+ | 0.4655 | 0.77 | 1500 | 0.5090 | -0.7987 | -2.2930 | 0.7031 | 1.4943 | -279.8999 | -262.2220 | -2.6651 | -2.6838 |
170
+ | 0.5731 | 0.83 | 1600 | 0.5312 | -0.8253 | -2.3520 | 0.7812 | 1.5268 | -280.4902 | -262.4876 | -2.6543 | -2.6728 |
171
+ | 0.5233 | 0.88 | 1700 | 0.5206 | -0.4573 | -2.0951 | 0.7812 | 1.6377 | -277.9205 | -258.8084 | -2.6870 | -2.7097 |
172
+ | 0.5593 | 0.93 | 1800 | 0.5231 | -0.5508 | -2.2000 | 0.7969 | 1.6492 | -278.9703 | -259.7433 | -2.6221 | -2.6519 |
173
+ | 0.4967 | 0.98 | 1900 | 0.5290 | -0.5340 | -1.9570 | 0.8281 | 1.4230 | -276.5395 | -259.5749 | -2.6564 | -2.6878 |
174
+ | 0.0921 | 1.03 | 2000 | 0.5368 | -1.1376 | -3.1615 | 0.7812 | 2.0239 | -288.5854 | -265.6111 | -2.6040 | -2.6345 |
175
+ | 0.0733 | 1.08 | 2100 | 0.5453 | -1.1045 | -3.4451 | 0.7656 | 2.3406 | -291.4208 | -265.2799 | -2.6289 | -2.6595 |
176
+ | 0.0972 | 1.14 | 2200 | 0.5571 | -1.6915 | -3.9823 | 0.8125 | 2.2908 | -296.7934 | -271.1505 | -2.6471 | -2.6709 |
177
+ | 0.1058 | 1.19 | 2300 | 0.5789 | -1.0621 | -3.8941 | 0.7969 | 2.8319 | -295.9106 | -264.8563 | -2.5527 | -2.5798 |
178
+ | 0.2423 | 1.24 | 2400 | 0.5455 | -1.1963 | -3.5590 | 0.7812 | 2.3627 | -292.5599 | -266.1981 | -2.5414 | -2.5784 |
179
+ | 0.1177 | 1.29 | 2500 | 0.5889 | -1.8141 | -4.3942 | 0.7969 | 2.5801 | -300.9120 | -272.3761 | -2.4802 | -2.5189 |
180
+ | 0.1213 | 1.34 | 2600 | 0.5683 | -1.4608 | -3.8420 | 0.8125 | 2.3812 | -295.3901 | -268.8436 | -2.4774 | -2.5207 |
181
+ | 0.0889 | 1.39 | 2700 | 0.5890 | -1.6007 | -3.7337 | 0.7812 | 2.1330 | -294.3068 | -270.2423 | -2.4123 | -2.4522 |
182
+ | 0.0995 | 1.45 | 2800 | 0.6073 | -1.5519 | -3.8362 | 0.8281 | 2.2843 | -295.3315 | -269.7538 | -2.4685 | -2.5050 |
183
+ | 0.1145 | 1.5 | 2900 | 0.5790 | -1.7939 | -4.2876 | 0.8438 | 2.4937 | -299.8461 | -272.1744 | -2.4272 | -2.4674 |
184
+ | 0.0644 | 1.55 | 3000 | 0.5735 | -1.7285 | -4.2051 | 0.8125 | 2.4766 | -299.0209 | -271.5201 | -2.4193 | -2.4574 |
185
+ | 0.0798 | 1.6 | 3100 | 0.5537 | -1.7226 | -4.2850 | 0.8438 | 2.5624 | -299.8200 | -271.4610 | -2.5367 | -2.5696 |
186
+ | 0.1013 | 1.65 | 3200 | 0.5575 | -1.5715 | -3.9813 | 0.875 | 2.4098 | -296.7825 | -269.9498 | -2.4926 | -2.5267 |
187
+ | 0.1254 | 1.7 | 3300 | 0.5905 | -1.6412 | -4.4703 | 0.8594 | 2.8291 | -301.6730 | -270.6473 | -2.5017 | -2.5340 |
188
+ | 0.085 | 1.76 | 3400 | 0.6133 | -1.9159 | -4.6760 | 0.8438 | 2.7601 | -303.7296 | -273.3941 | -2.4614 | -2.4960 |
189
+ | 0.065 | 1.81 | 3500 | 0.6074 | -1.8237 | -4.3525 | 0.8594 | 2.5288 | -300.4951 | -272.4724 | -2.4597 | -2.5004 |
190
+ | 0.0755 | 1.86 | 3600 | 0.5836 | -1.9252 | -4.4005 | 0.8125 | 2.4753 | -300.9748 | -273.4872 | -2.4327 | -2.4716 |
191
+ | 0.0746 | 1.91 | 3700 | 0.5789 | -1.9280 | -4.4906 | 0.8125 | 2.5626 | -301.8762 | -273.5149 | -2.4686 | -2.5115 |
192
+ | 0.1348 | 1.96 | 3800 | 0.6015 | -1.8658 | -4.2428 | 0.8281 | 2.3769 | -299.3976 | -272.8936 | -2.4943 | -2.5393 |
193
+ | 0.0217 | 2.01 | 3900 | 0.6122 | -2.3335 | -4.9229 | 0.8281 | 2.5894 | -306.1988 | -277.5699 | -2.4841 | -2.5272 |
194
+ | 0.0219 | 2.07 | 4000 | 0.6522 | -2.9890 | -6.0164 | 0.8281 | 3.0274 | -317.1334 | -284.1248 | -2.4105 | -2.4545 |
195
+ | 0.0119 | 2.12 | 4100 | 0.6922 | -3.4777 | -6.6749 | 0.7969 | 3.1972 | -323.7187 | -289.0121 | -2.4272 | -2.4699 |
196
+ | 0.0153 | 2.17 | 4200 | 0.6993 | -3.2406 | -6.6775 | 0.7969 | 3.4369 | -323.7453 | -286.6413 | -2.4047 | -2.4465 |
197
+ | 0.011 | 2.22 | 4300 | 0.7178 | -3.7991 | -7.4397 | 0.7656 | 3.6406 | -331.3667 | -292.2260 | -2.3843 | -2.4290 |
198
+ | 0.0072 | 2.27 | 4400 | 0.6840 | -3.3269 | -6.8021 | 0.8125 | 3.4752 | -324.9908 | -287.5042 | -2.4095 | -2.4536 |
199
+ | 0.0197 | 2.32 | 4500 | 0.7013 | -3.6890 | -7.3014 | 0.8125 | 3.6124 | -329.9841 | -291.1250 | -2.4118 | -2.4543 |
200
+ | 0.0182 | 2.37 | 4600 | 0.7476 | -3.8994 | -7.5366 | 0.8281 | 3.6372 | -332.3356 | -293.2291 | -2.4163 | -2.4565 |
201
+ | 0.0125 | 2.43 | 4700 | 0.7199 | -4.0560 | -7.5765 | 0.8438 | 3.5204 | -332.7345 | -294.7952 | -2.3699 | -2.4100 |
202
+ | 0.0082 | 2.48 | 4800 | 0.7048 | -3.6613 | -7.1356 | 0.875 | 3.4743 | -328.3255 | -290.8477 | -2.3925 | -2.4303 |
203
+ | 0.0118 | 2.53 | 4900 | 0.6976 | -3.7908 | -7.3152 | 0.8125 | 3.5244 | -330.1224 | -292.1431 | -2.3633 | -2.4047 |
204
+ | 0.0118 | 2.58 | 5000 | 0.7198 | -3.9049 | -7.5557 | 0.8281 | 3.6508 | -332.5271 | -293.2844 | -2.3764 | -2.4194 |
205
+ | 0.006 | 2.63 | 5100 | 0.7506 | -4.2118 | -7.9149 | 0.8125 | 3.7032 | -336.1194 | -296.3530 | -2.3407 | -2.3860 |
206
+ | 0.0143 | 2.68 | 5200 | 0.7408 | -4.2433 | -7.9802 | 0.8125 | 3.7369 | -336.7721 | -296.6682 | -2.3509 | -2.3946 |
207
+ | 0.0057 | 2.74 | 5300 | 0.7552 | -4.3392 | -8.0831 | 0.7969 | 3.7439 | -337.8013 | -297.6275 | -2.3388 | -2.3842 |
208
+ | 0.0138 | 2.79 | 5400 | 0.7404 | -4.2395 | -7.9762 | 0.8125 | 3.7367 | -336.7322 | -296.6304 | -2.3286 | -2.3737 |
209
+ | 0.0079 | 2.84 | 5500 | 0.7525 | -4.4466 | -8.2196 | 0.7812 | 3.7731 | -339.1662 | -298.7007 | -2.3200 | -2.3641 |
210
+ | 0.0077 | 2.89 | 5600 | 0.7520 | -4.5586 | -8.3485 | 0.7969 | 3.7899 | -340.4545 | -299.8206 | -2.3078 | -2.3517 |
211
+ | 0.0094 | 2.94 | 5700 | 0.7527 | -4.5542 | -8.3509 | 0.7812 | 3.7967 | -340.4790 | -299.7773 | -2.3062 | -2.3510 |
212
+ | 0.0054 | 2.99 | 5800 | 0.7520 | -4.5169 | -8.3079 | 0.7812 | 3.7911 | -340.0493 | -299.4038 | -2.3081 | -2.3530 |
213
+
214
+
215
+ ### Framework versions
216
+
217
+ - Transformers 4.35.0.dev0
218
+ - Pytorch 2.0.1+cu118
219
+ - Datasets 2.12.0
220
+ - Tokenizers 0.14.0
221
+
222
+ ## Citation
223
+
224
+ If you find Zephyr-7B-β is useful in your work, please cite it with:
225
+
226
+ ```
227
+ @misc{tunstall2023zephyr,
228
+ title={Zephyr: Direct Distillation of LM Alignment},
229
+ author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
230
+ year={2023},
231
+ eprint={2310.16944},
232
+ archivePrefix={arXiv},
233
+ primaryClass={cs.LG}
234
+ }
235
+ ```
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.353081703186035,
4
+ "eval_logits/rejected": -2.308103084564209,
5
+ "eval_logps/chosen": -299.4560546875,
6
+ "eval_logps/rejected": -340.154052734375,
7
+ "eval_loss": 0.7496059536933899,
8
+ "eval_rewards/accuracies": 0.78125,
9
+ "eval_rewards/chosen": -4.522095203399658,
10
+ "eval_rewards/margins": 3.7963125705718994,
11
+ "eval_rewards/rejected": -8.318408012390137,
12
+ "eval_runtime": 48.0152,
13
+ "eval_samples": 1000,
14
+ "eval_samples_per_second": 20.827,
15
+ "eval_steps_per_second": 0.333,
16
+ "train_loss": 0.2172969928600547,
17
+ "train_runtime": 23865.9828,
18
+ "train_samples": 61966,
19
+ "train_samples_per_second": 7.789,
20
+ "train_steps_per_second": 0.243
21
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.353081703186035,
4
+ "eval_logits/rejected": -2.308103084564209,
5
+ "eval_logps/chosen": -299.4560546875,
6
+ "eval_logps/rejected": -340.154052734375,
7
+ "eval_loss": 0.7496059536933899,
8
+ "eval_rewards/accuracies": 0.78125,
9
+ "eval_rewards/chosen": -4.522095203399658,
10
+ "eval_rewards/margins": 3.7963125705718994,
11
+ "eval_rewards/rejected": -8.318408012390137,
12
+ "eval_runtime": 48.0152,
13
+ "eval_samples": 1000,
14
+ "eval_samples_per_second": 20.827,
15
+ "eval_steps_per_second": 0.333
16
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.0.dev0"
6
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00008-of-00008.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
296
+ "model.norm.weight": "model-00008-of-00008.safetensors"
297
+ }
298
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a43ee8bf27b2ce1ea50f39bdf6084fe7d500c6be040c2c4fc50a3e341555555
3
+ size 3863327744
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "</s>",
37
+ "legacy": true,
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "</s>",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "truncation_side": "left",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.2172969928600547,
4
+ "train_runtime": 23865.9828,
5
+ "train_samples": 61966,
6
+ "train_samples_per_second": 7.789,
7
+ "train_steps_per_second": 0.243
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff