Jamesb1974
commited on
Upload folder using huggingface_hub
Browse files- README.md +45 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- checkpoint-1725/README.md +202 -0
- checkpoint-1725/adapter_config.json +34 -0
- checkpoint-1725/adapter_model.safetensors +3 -0
- checkpoint-1725/optimizer.pt +3 -0
- checkpoint-1725/pytorch_model.bin +3 -0
- checkpoint-1725/rng_state_0.pth +3 -0
- checkpoint-1725/rng_state_1.pth +3 -0
- checkpoint-1725/scheduler.pt +3 -0
- checkpoint-1725/special_tokens_map.json +24 -0
- checkpoint-1725/tokenizer.json +0 -0
- checkpoint-1725/tokenizer.model +3 -0
- checkpoint-1725/tokenizer_config.json +43 -0
- checkpoint-1725/trainer_state.json +504 -0
- checkpoint-1725/training_args.bin +3 -0
- runs/Mar27_01-40-04_r-jamesb1974-92gb570-u7kewtj9-d791b-rnrxv/events.out.tfevents.1711503608.r-jamesb1974-92gb570-u7kewtj9-d791b-rnrxv.103.0 +2 -2
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
- training_params.json +47 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
widget:
|
9 |
+
- messages:
|
10 |
+
- role: user
|
11 |
+
content: What is your favorite condiment?
|
12 |
+
license: other
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
18 |
+
|
19 |
+
# Usage
|
20 |
+
|
21 |
+
```python
|
22 |
+
|
23 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
24 |
+
|
25 |
+
model_path = "PATH_TO_THIS_REPO"
|
26 |
+
|
27 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
28 |
+
model = AutoModelForCausalLM.from_pretrained(
|
29 |
+
model_path,
|
30 |
+
device_map="auto",
|
31 |
+
torch_dtype='auto'
|
32 |
+
).eval()
|
33 |
+
|
34 |
+
# Prompt content: "hi"
|
35 |
+
messages = [
|
36 |
+
{"role": "user", "content": "hi"}
|
37 |
+
]
|
38 |
+
|
39 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
40 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
41 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
42 |
+
|
43 |
+
# Model response: "Hello! How can I assist you today?"
|
44 |
+
print(response)
|
45 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b58b1b30b65af0b51296e675db6a87213a6673773af798b8508627c4089ad75
|
3 |
+
size 167832240
|
checkpoint-1725/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
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 0.10.0
|
checkpoint-1725/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-1725/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b58b1b30b65af0b51296e675db6a87213a6673773af798b8508627c4089ad75
|
3 |
+
size 167832240
|
checkpoint-1725/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:039cd4b51c048451651f367d5146733c8b86209e2d9355023225a24ef9a19aed
|
3 |
+
size 335922386
|
checkpoint-1725/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-1725/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95830bb650b4d84533e7e8c0a68ead41bfe1b6472a5a58d018f6899beba92810
|
3 |
+
size 14512
|
checkpoint-1725/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b263673e892281915896ab7b26138b143ffd825a097cf423853be56ac0c8ed5d
|
3 |
+
size 14512
|
checkpoint-1725/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8ca186f3c6459daa6585ddd3660dea480906ae093f6a28b58c2d9b26fcd514c
|
3 |
+
size 1064
|
checkpoint-1725/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-1725/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1725/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-1725/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
checkpoint-1725/trainer_state.json
ADDED
@@ -0,0 +1,504 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9960920538428137,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1725,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 2.6797966957092285,
|
14 |
+
"learning_rate": 4.3352601156069365e-06,
|
15 |
+
"loss": 1.3088,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09,
|
20 |
+
"grad_norm": 1.1868915557861328,
|
21 |
+
"learning_rate": 8.670520231213873e-06,
|
22 |
+
"loss": 1.0702,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.13,
|
27 |
+
"grad_norm": 0.9078810811042786,
|
28 |
+
"learning_rate": 1.300578034682081e-05,
|
29 |
+
"loss": 0.8412,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.17,
|
34 |
+
"grad_norm": 0.8079336881637573,
|
35 |
+
"learning_rate": 1.716763005780347e-05,
|
36 |
+
"loss": 0.7059,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22,
|
41 |
+
"grad_norm": 0.9328547120094299,
|
42 |
+
"learning_rate": 2.1502890173410405e-05,
|
43 |
+
"loss": 0.661,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.26,
|
48 |
+
"grad_norm": 0.8373017907142639,
|
49 |
+
"learning_rate": 2.583815028901734e-05,
|
50 |
+
"loss": 0.6104,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3,
|
55 |
+
"grad_norm": 0.9223055839538574,
|
56 |
+
"learning_rate": 2.9980670103092784e-05,
|
57 |
+
"loss": 0.6106,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.35,
|
62 |
+
"grad_norm": 0.9315438270568848,
|
63 |
+
"learning_rate": 2.949742268041237e-05,
|
64 |
+
"loss": 0.5871,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.39,
|
69 |
+
"grad_norm": 0.9792923927307129,
|
70 |
+
"learning_rate": 2.901417525773196e-05,
|
71 |
+
"loss": 0.5831,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.43,
|
76 |
+
"grad_norm": 0.9282048344612122,
|
77 |
+
"learning_rate": 2.8530927835051546e-05,
|
78 |
+
"loss": 0.5696,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.48,
|
83 |
+
"grad_norm": 0.810558557510376,
|
84 |
+
"learning_rate": 2.8047680412371134e-05,
|
85 |
+
"loss": 0.5461,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.52,
|
90 |
+
"grad_norm": 0.9066827893257141,
|
91 |
+
"learning_rate": 2.756443298969072e-05,
|
92 |
+
"loss": 0.5739,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.56,
|
97 |
+
"grad_norm": 0.8533302545547485,
|
98 |
+
"learning_rate": 2.708118556701031e-05,
|
99 |
+
"loss": 0.5527,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.61,
|
104 |
+
"grad_norm": 0.933085560798645,
|
105 |
+
"learning_rate": 2.6597938144329897e-05,
|
106 |
+
"loss": 0.547,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.65,
|
111 |
+
"grad_norm": 0.8400581479072571,
|
112 |
+
"learning_rate": 2.6114690721649484e-05,
|
113 |
+
"loss": 0.5552,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.69,
|
118 |
+
"grad_norm": 0.8673002123832703,
|
119 |
+
"learning_rate": 2.5631443298969072e-05,
|
120 |
+
"loss": 0.5418,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.74,
|
125 |
+
"grad_norm": 0.9447078108787537,
|
126 |
+
"learning_rate": 2.514819587628866e-05,
|
127 |
+
"loss": 0.5493,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.78,
|
132 |
+
"grad_norm": 0.8309420943260193,
|
133 |
+
"learning_rate": 2.4664948453608247e-05,
|
134 |
+
"loss": 0.5432,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.83,
|
139 |
+
"grad_norm": 0.8934959769248962,
|
140 |
+
"learning_rate": 2.4181701030927838e-05,
|
141 |
+
"loss": 0.5373,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.87,
|
146 |
+
"grad_norm": 0.9148778915405273,
|
147 |
+
"learning_rate": 2.3698453608247422e-05,
|
148 |
+
"loss": 0.5268,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.91,
|
153 |
+
"grad_norm": 0.9047264456748962,
|
154 |
+
"learning_rate": 2.3215206185567013e-05,
|
155 |
+
"loss": 0.5284,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.96,
|
160 |
+
"grad_norm": 0.8317086100578308,
|
161 |
+
"learning_rate": 2.2731958762886597e-05,
|
162 |
+
"loss": 0.529,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.0,
|
167 |
+
"grad_norm": 0.9038283824920654,
|
168 |
+
"learning_rate": 2.224871134020619e-05,
|
169 |
+
"loss": 0.5157,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.04,
|
174 |
+
"grad_norm": 0.9291544556617737,
|
175 |
+
"learning_rate": 2.1765463917525773e-05,
|
176 |
+
"loss": 0.5048,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.09,
|
181 |
+
"grad_norm": 1.0017096996307373,
|
182 |
+
"learning_rate": 2.1282216494845363e-05,
|
183 |
+
"loss": 0.4917,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.13,
|
188 |
+
"grad_norm": 0.9479974508285522,
|
189 |
+
"learning_rate": 2.0798969072164948e-05,
|
190 |
+
"loss": 0.5084,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.17,
|
195 |
+
"grad_norm": 1.0082184076309204,
|
196 |
+
"learning_rate": 2.031572164948454e-05,
|
197 |
+
"loss": 0.4939,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.22,
|
202 |
+
"grad_norm": 1.033955693244934,
|
203 |
+
"learning_rate": 1.9832474226804123e-05,
|
204 |
+
"loss": 0.4877,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.26,
|
209 |
+
"grad_norm": 0.9597358107566833,
|
210 |
+
"learning_rate": 1.9349226804123714e-05,
|
211 |
+
"loss": 0.4883,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.3,
|
216 |
+
"grad_norm": 1.0226048231124878,
|
217 |
+
"learning_rate": 1.8865979381443298e-05,
|
218 |
+
"loss": 0.5101,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.35,
|
223 |
+
"grad_norm": 1.0424410104751587,
|
224 |
+
"learning_rate": 1.838273195876289e-05,
|
225 |
+
"loss": 0.4926,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.39,
|
230 |
+
"grad_norm": 0.9963483214378357,
|
231 |
+
"learning_rate": 1.7899484536082473e-05,
|
232 |
+
"loss": 0.4994,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.43,
|
237 |
+
"grad_norm": 1.0222622156143188,
|
238 |
+
"learning_rate": 1.7416237113402064e-05,
|
239 |
+
"loss": 0.5048,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.48,
|
244 |
+
"grad_norm": 0.9387053847312927,
|
245 |
+
"learning_rate": 1.693298969072165e-05,
|
246 |
+
"loss": 0.4887,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.52,
|
251 |
+
"grad_norm": 1.0436928272247314,
|
252 |
+
"learning_rate": 1.644974226804124e-05,
|
253 |
+
"loss": 0.4891,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.56,
|
258 |
+
"grad_norm": 1.111985206604004,
|
259 |
+
"learning_rate": 1.5966494845360824e-05,
|
260 |
+
"loss": 0.4988,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.61,
|
265 |
+
"grad_norm": 1.0231331586837769,
|
266 |
+
"learning_rate": 1.5483247422680414e-05,
|
267 |
+
"loss": 0.4918,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.65,
|
272 |
+
"grad_norm": 1.1055492162704468,
|
273 |
+
"learning_rate": 1.5e-05,
|
274 |
+
"loss": 0.4809,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.69,
|
279 |
+
"grad_norm": 0.9457443356513977,
|
280 |
+
"learning_rate": 1.4516752577319588e-05,
|
281 |
+
"loss": 0.4943,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.74,
|
286 |
+
"grad_norm": 1.02395498752594,
|
287 |
+
"learning_rate": 1.4033505154639176e-05,
|
288 |
+
"loss": 0.4796,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.78,
|
293 |
+
"grad_norm": 1.0263872146606445,
|
294 |
+
"learning_rate": 1.3550257731958763e-05,
|
295 |
+
"loss": 0.4821,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.82,
|
300 |
+
"grad_norm": 1.0765823125839233,
|
301 |
+
"learning_rate": 1.306701030927835e-05,
|
302 |
+
"loss": 0.4947,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.87,
|
307 |
+
"grad_norm": 1.0938082933425903,
|
308 |
+
"learning_rate": 1.2583762886597938e-05,
|
309 |
+
"loss": 0.4906,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.91,
|
314 |
+
"grad_norm": 0.9967209100723267,
|
315 |
+
"learning_rate": 1.2100515463917526e-05,
|
316 |
+
"loss": 0.4849,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.95,
|
321 |
+
"grad_norm": 1.0374945402145386,
|
322 |
+
"learning_rate": 1.1617268041237113e-05,
|
323 |
+
"loss": 0.49,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.0,
|
328 |
+
"grad_norm": 1.1183592081069946,
|
329 |
+
"learning_rate": 1.1134020618556701e-05,
|
330 |
+
"loss": 0.4794,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.04,
|
335 |
+
"grad_norm": 1.2019271850585938,
|
336 |
+
"learning_rate": 1.0650773195876289e-05,
|
337 |
+
"loss": 0.4453,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.08,
|
342 |
+
"grad_norm": 1.2778681516647339,
|
343 |
+
"learning_rate": 1.0167525773195876e-05,
|
344 |
+
"loss": 0.4535,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.13,
|
349 |
+
"grad_norm": 1.1817573308944702,
|
350 |
+
"learning_rate": 9.684278350515465e-06,
|
351 |
+
"loss": 0.4541,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.17,
|
356 |
+
"grad_norm": 1.2380177974700928,
|
357 |
+
"learning_rate": 9.201030927835053e-06,
|
358 |
+
"loss": 0.4439,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.21,
|
363 |
+
"grad_norm": 1.1232197284698486,
|
364 |
+
"learning_rate": 8.71778350515464e-06,
|
365 |
+
"loss": 0.4593,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.26,
|
370 |
+
"grad_norm": 1.2772026062011719,
|
371 |
+
"learning_rate": 8.234536082474228e-06,
|
372 |
+
"loss": 0.4437,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.3,
|
377 |
+
"grad_norm": 1.2638049125671387,
|
378 |
+
"learning_rate": 7.751288659793816e-06,
|
379 |
+
"loss": 0.4573,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.34,
|
384 |
+
"grad_norm": 1.2229359149932861,
|
385 |
+
"learning_rate": 7.2680412371134026e-06,
|
386 |
+
"loss": 0.438,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.39,
|
391 |
+
"grad_norm": 1.3568594455718994,
|
392 |
+
"learning_rate": 6.78479381443299e-06,
|
393 |
+
"loss": 0.4463,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.43,
|
398 |
+
"grad_norm": 1.3704684972763062,
|
399 |
+
"learning_rate": 6.301546391752578e-06,
|
400 |
+
"loss": 0.447,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.48,
|
405 |
+
"grad_norm": 1.3857060670852661,
|
406 |
+
"learning_rate": 5.818298969072165e-06,
|
407 |
+
"loss": 0.4586,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.52,
|
412 |
+
"grad_norm": 1.3202048540115356,
|
413 |
+
"learning_rate": 5.335051546391753e-06,
|
414 |
+
"loss": 0.4541,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.56,
|
419 |
+
"grad_norm": 1.233846664428711,
|
420 |
+
"learning_rate": 4.8518041237113405e-06,
|
421 |
+
"loss": 0.4431,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.61,
|
426 |
+
"grad_norm": 1.381267786026001,
|
427 |
+
"learning_rate": 4.368556701030928e-06,
|
428 |
+
"loss": 0.4422,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.65,
|
433 |
+
"grad_norm": 1.283376693725586,
|
434 |
+
"learning_rate": 3.885309278350516e-06,
|
435 |
+
"loss": 0.4378,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 2.69,
|
440 |
+
"grad_norm": 1.177047848701477,
|
441 |
+
"learning_rate": 3.4020618556701032e-06,
|
442 |
+
"loss": 0.4444,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.74,
|
447 |
+
"grad_norm": 1.3238096237182617,
|
448 |
+
"learning_rate": 2.918814432989691e-06,
|
449 |
+
"loss": 0.4467,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.78,
|
454 |
+
"grad_norm": 1.2902580499649048,
|
455 |
+
"learning_rate": 2.4355670103092784e-06,
|
456 |
+
"loss": 0.4478,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.82,
|
461 |
+
"grad_norm": 1.3172022104263306,
|
462 |
+
"learning_rate": 1.952319587628866e-06,
|
463 |
+
"loss": 0.4436,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.87,
|
468 |
+
"grad_norm": 1.2804652452468872,
|
469 |
+
"learning_rate": 1.4690721649484536e-06,
|
470 |
+
"loss": 0.4478,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.91,
|
475 |
+
"grad_norm": 1.3892390727996826,
|
476 |
+
"learning_rate": 9.858247422680414e-07,
|
477 |
+
"loss": 0.4533,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.95,
|
482 |
+
"grad_norm": 1.4237300157546997,
|
483 |
+
"learning_rate": 5.025773195876288e-07,
|
484 |
+
"loss": 0.4516,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 3.0,
|
489 |
+
"grad_norm": 1.5595041513442993,
|
490 |
+
"learning_rate": 1.9329896907216496e-08,
|
491 |
+
"loss": 0.4622,
|
492 |
+
"step": 1725
|
493 |
+
}
|
494 |
+
],
|
495 |
+
"logging_steps": 25,
|
496 |
+
"max_steps": 1725,
|
497 |
+
"num_input_tokens_seen": 0,
|
498 |
+
"num_train_epochs": 3,
|
499 |
+
"save_steps": 500,
|
500 |
+
"total_flos": 6.064491791741092e+17,
|
501 |
+
"train_batch_size": 1,
|
502 |
+
"trial_name": null,
|
503 |
+
"trial_params": null
|
504 |
+
}
|
checkpoint-1725/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f36ea0d666e62149219f9641924621be7b04de6cf8d73fe0546c46e80516f7a
|
3 |
+
size 4984
|
runs/Mar27_01-40-04_r-jamesb1974-92gb570-u7kewtj9-d791b-rnrxv/events.out.tfevents.1711503608.r-jamesb1974-92gb570-u7kewtj9-d791b-rnrxv.103.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4753bc3e9a8ed42bc257aa0e78e06780c68901afd6121ca5e5f3f1b91d8f5f87
|
3 |
+
size 20061
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f36ea0d666e62149219f9641924621be7b04de6cf8d73fe0546c46e80516f7a
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "mistralai/Mistral-7B-Instruct-v0.2",
|
3 |
+
"project_name": "autotrain-mist7b-instV2-ep3",
|
4 |
+
"data_path": "autotrain-mist7b-instV2-ep3/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": 3,
|
23 |
+
"batch_size": 1,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 4,
|
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": "Jamesb1974/autotrain-mist7b-instV2-ep3",
|
46 |
+
"username": "Jamesb1974"
|
47 |
+
}
|