Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +62 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +9 -0
- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +34 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state_0.pth +3 -0
- checkpoint-100/rng_state_1.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +38 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer_config.json +0 -0
- checkpoint-100/trainer_state.json +193 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/README.md +202 -0
- checkpoint-200/adapter_config.json +34 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state_0.pth +3 -0
- checkpoint-200/rng_state_1.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +38 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer_config.json +0 -0
- checkpoint-200/trainer_state.json +353 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/README.md +202 -0
- checkpoint-300/adapter_config.json +34 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state_0.pth +3 -0
- checkpoint-300/rng_state_1.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +38 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer_config.json +0 -0
- checkpoint-300/trainer_state.json +513 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-312/README.md +202 -0
- checkpoint-312/adapter_config.json +34 -0
- checkpoint-312/adapter_model.safetensors +3 -0
- checkpoint-312/optimizer.pt +3 -0
- checkpoint-312/rng_state_0.pth +3 -0
- checkpoint-312/rng_state_1.pth +3 -0
- checkpoint-312/scheduler.pt +3 -0
- checkpoint-312/special_tokens_map.json +38 -0
- checkpoint-312/tokenizer.json +0 -0
- checkpoint-312/tokenizer_config.json +0 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/CodeQwen1.5-7B-Chat
|
3 |
+
library_name: peft
|
4 |
+
license: other
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- lora
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-07-30-09-22-49
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# train_2024-07-30-09-22-49
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat) on the alpaca_finance dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 2
|
44 |
+
- gradient_accumulation_steps: 32
|
45 |
+
- total_train_batch_size: 64
|
46 |
+
- total_eval_batch_size: 16
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- num_epochs: 1.0
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- PEFT 0.12.0
|
59 |
+
- Transformers 4.43.3
|
60 |
+
- Pytorch 2.2.2+cu121
|
61 |
+
- Datasets 2.16.0
|
62 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_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 sha256:7e073ccabe42b118a635f726ffc9b1e75555230df4c876eb6bef9a0907ec9c2f
|
3 |
+
size 80144136
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9984,
|
3 |
+
"num_input_tokens_seen": 4974128,
|
4 |
+
"total_flos": 2.056832720704635e+17,
|
5 |
+
"train_loss": 2.5180979997683792,
|
6 |
+
"train_runtime": 14081.4059,
|
7 |
+
"train_samples_per_second": 1.42,
|
8 |
+
"train_steps_per_second": 0.022
|
9 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/CodeQwen1.5-7B-Chat
|
3 |
+
library_name: peft
|
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 0.12.0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7999bb661c456683453b534dda3776f186de53f050fe23308eb6710014cdd95c
|
3 |
+
size 80144136
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abbe00fb431f9677245fb9a05c61287a5536476e68da60b2dd1d5071b940edc3
|
3 |
+
size 160546898
|
checkpoint-100/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
|
3 |
+
size 14512
|
checkpoint-100/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
|
3 |
+
size 14512
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db19d5f82c8e209abcc21a69b82a57aeda11c164a7ca57df1501e44c35224e2b
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>"
|
9 |
+
],
|
10 |
+
"bos_token": {
|
11 |
+
"content": "<|endoftext|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<fim_pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"unk_token": {
|
32 |
+
"content": "<unk>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
}
|
38 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.32,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016,
|
13 |
+
"grad_norm": 0.3705686628818512,
|
14 |
+
"learning_rate": 0.00019987329060020616,
|
15 |
+
"loss": 2.7276,
|
16 |
+
"num_input_tokens_seen": 78104,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.032,
|
21 |
+
"grad_norm": 0.28178921341896057,
|
22 |
+
"learning_rate": 0.00019949348350626456,
|
23 |
+
"loss": 2.6452,
|
24 |
+
"num_input_tokens_seen": 157384,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.048,
|
29 |
+
"grad_norm": 0.1864372342824936,
|
30 |
+
"learning_rate": 0.00019886154122075343,
|
31 |
+
"loss": 2.5708,
|
32 |
+
"num_input_tokens_seen": 240256,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.064,
|
37 |
+
"grad_norm": 0.1788010597229004,
|
38 |
+
"learning_rate": 0.00019797906520422677,
|
39 |
+
"loss": 2.5831,
|
40 |
+
"num_input_tokens_seen": 319032,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.08,
|
45 |
+
"grad_norm": 0.23142138123512268,
|
46 |
+
"learning_rate": 0.00019684829181681234,
|
47 |
+
"loss": 2.6138,
|
48 |
+
"num_input_tokens_seen": 397992,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.096,
|
53 |
+
"grad_norm": 0.21496976912021637,
|
54 |
+
"learning_rate": 0.00019547208665085457,
|
55 |
+
"loss": 2.5461,
|
56 |
+
"num_input_tokens_seen": 479904,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.112,
|
61 |
+
"grad_norm": 0.2536880671977997,
|
62 |
+
"learning_rate": 0.0001938539372689649,
|
63 |
+
"loss": 2.5797,
|
64 |
+
"num_input_tokens_seen": 555448,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.128,
|
69 |
+
"grad_norm": 0.39764249324798584,
|
70 |
+
"learning_rate": 0.00019199794436588243,
|
71 |
+
"loss": 2.5482,
|
72 |
+
"num_input_tokens_seen": 630888,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.144,
|
77 |
+
"grad_norm": 0.29237431287765503,
|
78 |
+
"learning_rate": 0.00018990881137654258,
|
79 |
+
"loss": 2.4726,
|
80 |
+
"num_input_tokens_seen": 709456,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.16,
|
85 |
+
"grad_norm": 0.24707558751106262,
|
86 |
+
"learning_rate": 0.0001875918325566888,
|
87 |
+
"loss": 2.5557,
|
88 |
+
"num_input_tokens_seen": 788504,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.176,
|
93 |
+
"grad_norm": 0.24359019100666046,
|
94 |
+
"learning_rate": 0.00018505287956623297,
|
95 |
+
"loss": 2.5357,
|
96 |
+
"num_input_tokens_seen": 864984,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.192,
|
101 |
+
"grad_norm": 0.23572562634944916,
|
102 |
+
"learning_rate": 0.00018229838658936564,
|
103 |
+
"loss": 2.4798,
|
104 |
+
"num_input_tokens_seen": 939136,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.208,
|
109 |
+
"grad_norm": 0.41712337732315063,
|
110 |
+
"learning_rate": 0.00017933533402912354,
|
111 |
+
"loss": 2.5619,
|
112 |
+
"num_input_tokens_seen": 1018024,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.224,
|
117 |
+
"grad_norm": 0.2777227759361267,
|
118 |
+
"learning_rate": 0.00017617123081773591,
|
119 |
+
"loss": 2.5334,
|
120 |
+
"num_input_tokens_seen": 1095072,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.24,
|
125 |
+
"grad_norm": 0.25098717212677,
|
126 |
+
"learning_rate": 0.00017281409538757883,
|
127 |
+
"loss": 2.5199,
|
128 |
+
"num_input_tokens_seen": 1172824,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.256,
|
133 |
+
"grad_norm": 0.24321608245372772,
|
134 |
+
"learning_rate": 0.00016927243535095997,
|
135 |
+
"loss": 2.4897,
|
136 |
+
"num_input_tokens_seen": 1244688,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.272,
|
141 |
+
"grad_norm": 0.25580549240112305,
|
142 |
+
"learning_rate": 0.0001655552259402295,
|
143 |
+
"loss": 2.513,
|
144 |
+
"num_input_tokens_seen": 1321104,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.288,
|
149 |
+
"grad_norm": 0.24990542232990265,
|
150 |
+
"learning_rate": 0.00016167188726285434,
|
151 |
+
"loss": 2.5533,
|
152 |
+
"num_input_tokens_seen": 1402456,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.304,
|
157 |
+
"grad_norm": 0.26301833987236023,
|
158 |
+
"learning_rate": 0.00015763226042909455,
|
159 |
+
"loss": 2.5297,
|
160 |
+
"num_input_tokens_seen": 1483648,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.32,
|
165 |
+
"grad_norm": 0.23519474267959595,
|
166 |
+
"learning_rate": 0.0001534465826127801,
|
167 |
+
"loss": 2.518,
|
168 |
+
"num_input_tokens_seen": 1560608,
|
169 |
+
"step": 100
|
170 |
+
}
|
171 |
+
],
|
172 |
+
"logging_steps": 5,
|
173 |
+
"max_steps": 312,
|
174 |
+
"num_input_tokens_seen": 1560608,
|
175 |
+
"num_train_epochs": 1,
|
176 |
+
"save_steps": 100,
|
177 |
+
"stateful_callbacks": {
|
178 |
+
"TrainerControl": {
|
179 |
+
"args": {
|
180 |
+
"should_epoch_stop": false,
|
181 |
+
"should_evaluate": false,
|
182 |
+
"should_log": false,
|
183 |
+
"should_save": true,
|
184 |
+
"should_training_stop": false
|
185 |
+
},
|
186 |
+
"attributes": {}
|
187 |
+
}
|
188 |
+
},
|
189 |
+
"total_flos": 6.453210669226394e+16,
|
190 |
+
"train_batch_size": 1,
|
191 |
+
"trial_name": null,
|
192 |
+
"trial_params": null
|
193 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a11e34958bb0166a27197cc6b1af0b4918fc0bb571b674f64d1bed0d949d03fe
|
3 |
+
size 5368
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/CodeQwen1.5-7B-Chat
|
3 |
+
library_name: peft
|
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 0.12.0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee988893364c38dee1a400f2d758e08986c16761348a3f7f2f709abd2531a8d5
|
3 |
+
size 80144136
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56d5a55a8d2384f839dcf5c2df1cc51fb9fadc35b2958ec26b99c9602b8ae1f5
|
3 |
+
size 160546898
|
checkpoint-200/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
|
3 |
+
size 14512
|
checkpoint-200/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
|
3 |
+
size 14512
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1672929cbd1b23a6c0955975e4aa190f3ae3bcbc48783ce2a380161c2e528bc5
|
3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>"
|
9 |
+
],
|
10 |
+
"bos_token": {
|
11 |
+
"content": "<|endoftext|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<fim_pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"unk_token": {
|
32 |
+
"content": "<unk>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
}
|
38 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.64,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016,
|
13 |
+
"grad_norm": 0.3705686628818512,
|
14 |
+
"learning_rate": 0.00019987329060020616,
|
15 |
+
"loss": 2.7276,
|
16 |
+
"num_input_tokens_seen": 78104,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.032,
|
21 |
+
"grad_norm": 0.28178921341896057,
|
22 |
+
"learning_rate": 0.00019949348350626456,
|
23 |
+
"loss": 2.6452,
|
24 |
+
"num_input_tokens_seen": 157384,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.048,
|
29 |
+
"grad_norm": 0.1864372342824936,
|
30 |
+
"learning_rate": 0.00019886154122075343,
|
31 |
+
"loss": 2.5708,
|
32 |
+
"num_input_tokens_seen": 240256,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.064,
|
37 |
+
"grad_norm": 0.1788010597229004,
|
38 |
+
"learning_rate": 0.00019797906520422677,
|
39 |
+
"loss": 2.5831,
|
40 |
+
"num_input_tokens_seen": 319032,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.08,
|
45 |
+
"grad_norm": 0.23142138123512268,
|
46 |
+
"learning_rate": 0.00019684829181681234,
|
47 |
+
"loss": 2.6138,
|
48 |
+
"num_input_tokens_seen": 397992,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.096,
|
53 |
+
"grad_norm": 0.21496976912021637,
|
54 |
+
"learning_rate": 0.00019547208665085457,
|
55 |
+
"loss": 2.5461,
|
56 |
+
"num_input_tokens_seen": 479904,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.112,
|
61 |
+
"grad_norm": 0.2536880671977997,
|
62 |
+
"learning_rate": 0.0001938539372689649,
|
63 |
+
"loss": 2.5797,
|
64 |
+
"num_input_tokens_seen": 555448,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.128,
|
69 |
+
"grad_norm": 0.39764249324798584,
|
70 |
+
"learning_rate": 0.00019199794436588243,
|
71 |
+
"loss": 2.5482,
|
72 |
+
"num_input_tokens_seen": 630888,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.144,
|
77 |
+
"grad_norm": 0.29237431287765503,
|
78 |
+
"learning_rate": 0.00018990881137654258,
|
79 |
+
"loss": 2.4726,
|
80 |
+
"num_input_tokens_seen": 709456,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.16,
|
85 |
+
"grad_norm": 0.24707558751106262,
|
86 |
+
"learning_rate": 0.0001875918325566888,
|
87 |
+
"loss": 2.5557,
|
88 |
+
"num_input_tokens_seen": 788504,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.176,
|
93 |
+
"grad_norm": 0.24359019100666046,
|
94 |
+
"learning_rate": 0.00018505287956623297,
|
95 |
+
"loss": 2.5357,
|
96 |
+
"num_input_tokens_seen": 864984,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.192,
|
101 |
+
"grad_norm": 0.23572562634944916,
|
102 |
+
"learning_rate": 0.00018229838658936564,
|
103 |
+
"loss": 2.4798,
|
104 |
+
"num_input_tokens_seen": 939136,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.208,
|
109 |
+
"grad_norm": 0.41712337732315063,
|
110 |
+
"learning_rate": 0.00017933533402912354,
|
111 |
+
"loss": 2.5619,
|
112 |
+
"num_input_tokens_seen": 1018024,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.224,
|
117 |
+
"grad_norm": 0.2777227759361267,
|
118 |
+
"learning_rate": 0.00017617123081773591,
|
119 |
+
"loss": 2.5334,
|
120 |
+
"num_input_tokens_seen": 1095072,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.24,
|
125 |
+
"grad_norm": 0.25098717212677,
|
126 |
+
"learning_rate": 0.00017281409538757883,
|
127 |
+
"loss": 2.5199,
|
128 |
+
"num_input_tokens_seen": 1172824,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.256,
|
133 |
+
"grad_norm": 0.24321608245372772,
|
134 |
+
"learning_rate": 0.00016927243535095997,
|
135 |
+
"loss": 2.4897,
|
136 |
+
"num_input_tokens_seen": 1244688,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.272,
|
141 |
+
"grad_norm": 0.25580549240112305,
|
142 |
+
"learning_rate": 0.0001655552259402295,
|
143 |
+
"loss": 2.513,
|
144 |
+
"num_input_tokens_seen": 1321104,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.288,
|
149 |
+
"grad_norm": 0.24990542232990265,
|
150 |
+
"learning_rate": 0.00016167188726285434,
|
151 |
+
"loss": 2.5533,
|
152 |
+
"num_input_tokens_seen": 1402456,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.304,
|
157 |
+
"grad_norm": 0.26301833987236023,
|
158 |
+
"learning_rate": 0.00015763226042909455,
|
159 |
+
"loss": 2.5297,
|
160 |
+
"num_input_tokens_seen": 1483648,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.32,
|
165 |
+
"grad_norm": 0.23519474267959595,
|
166 |
+
"learning_rate": 0.0001534465826127801,
|
167 |
+
"loss": 2.518,
|
168 |
+
"num_input_tokens_seen": 1560608,
|
169 |
+
"step": 100
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.336,
|
173 |
+
"grad_norm": 0.26162955164909363,
|
174 |
+
"learning_rate": 0.00014912546110838775,
|
175 |
+
"loss": 2.5537,
|
176 |
+
"num_input_tokens_seen": 1640728,
|
177 |
+
"step": 105
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.352,
|
181 |
+
"grad_norm": 0.2565276026725769,
|
182 |
+
"learning_rate": 0.00014467984645016258,
|
183 |
+
"loss": 2.489,
|
184 |
+
"num_input_tokens_seen": 1722440,
|
185 |
+
"step": 110
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.368,
|
189 |
+
"grad_norm": 0.3414108455181122,
|
190 |
+
"learning_rate": 0.00014012100466140578,
|
191 |
+
"loss": 2.5448,
|
192 |
+
"num_input_tokens_seen": 1805984,
|
193 |
+
"step": 115
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.384,
|
197 |
+
"grad_norm": 0.2590246796607971,
|
198 |
+
"learning_rate": 0.00013546048870425356,
|
199 |
+
"loss": 2.4148,
|
200 |
+
"num_input_tokens_seen": 1890592,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.4,
|
205 |
+
"grad_norm": 0.2765924036502838,
|
206 |
+
"learning_rate": 0.00013071010920229909,
|
207 |
+
"loss": 2.5512,
|
208 |
+
"num_input_tokens_seen": 1971272,
|
209 |
+
"step": 125
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.416,
|
213 |
+
"grad_norm": 0.2582058906555176,
|
214 |
+
"learning_rate": 0.00012588190451025207,
|
215 |
+
"loss": 2.5264,
|
216 |
+
"num_input_tokens_seen": 2053352,
|
217 |
+
"step": 130
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.432,
|
221 |
+
"grad_norm": 0.2416098713874817,
|
222 |
+
"learning_rate": 0.00012098811020648475,
|
223 |
+
"loss": 2.5525,
|
224 |
+
"num_input_tokens_seen": 2132624,
|
225 |
+
"step": 135
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.448,
|
229 |
+
"grad_norm": 0.3602483868598938,
|
230 |
+
"learning_rate": 0.00011604112808577603,
|
231 |
+
"loss": 2.5029,
|
232 |
+
"num_input_tokens_seen": 2210376,
|
233 |
+
"step": 140
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.464,
|
237 |
+
"grad_norm": 0.2507006824016571,
|
238 |
+
"learning_rate": 0.000111053494730832,
|
239 |
+
"loss": 2.5546,
|
240 |
+
"num_input_tokens_seen": 2292896,
|
241 |
+
"step": 145
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.48,
|
245 |
+
"grad_norm": 0.32158130407333374,
|
246 |
+
"learning_rate": 0.00010603784974222861,
|
247 |
+
"loss": 2.5431,
|
248 |
+
"num_input_tokens_seen": 2376432,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.496,
|
253 |
+
"grad_norm": 0.3036045730113983,
|
254 |
+
"learning_rate": 0.00010100690370728755,
|
255 |
+
"loss": 2.4882,
|
256 |
+
"num_input_tokens_seen": 2451848,
|
257 |
+
"step": 155
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.512,
|
261 |
+
"grad_norm": 0.31646254658699036,
|
262 |
+
"learning_rate": 9.597340598905852e-05,
|
263 |
+
"loss": 2.4319,
|
264 |
+
"num_input_tokens_seen": 2532816,
|
265 |
+
"step": 160
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.528,
|
269 |
+
"grad_norm": 0.2881500720977783,
|
270 |
+
"learning_rate": 9.095011241703623e-05,
|
271 |
+
"loss": 2.4688,
|
272 |
+
"num_input_tokens_seen": 2616160,
|
273 |
+
"step": 165
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.544,
|
277 |
+
"grad_norm": 0.27659812569618225,
|
278 |
+
"learning_rate": 8.594975296149076e-05,
|
279 |
+
"loss": 2.5149,
|
280 |
+
"num_input_tokens_seen": 2694864,
|
281 |
+
"step": 170
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.56,
|
285 |
+
"grad_norm": 0.4290514290332794,
|
286 |
+
"learning_rate": 8.098499947332934e-05,
|
287 |
+
"loss": 2.4754,
|
288 |
+
"num_input_tokens_seen": 2770464,
|
289 |
+
"step": 175
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.576,
|
293 |
+
"grad_norm": 0.28775912523269653,
|
294 |
+
"learning_rate": 7.606843357124426e-05,
|
295 |
+
"loss": 2.4875,
|
296 |
+
"num_input_tokens_seen": 2852888,
|
297 |
+
"step": 180
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.592,
|
301 |
+
"grad_norm": 0.2709747850894928,
|
302 |
+
"learning_rate": 7.121251475752539e-05,
|
303 |
+
"loss": 2.563,
|
304 |
+
"num_input_tokens_seen": 2933520,
|
305 |
+
"step": 185
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.608,
|
309 |
+
"grad_norm": 0.3473074734210968,
|
310 |
+
"learning_rate": 6.642954884333955e-05,
|
311 |
+
"loss": 2.4903,
|
312 |
+
"num_input_tokens_seen": 3011656,
|
313 |
+
"step": 190
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.624,
|
317 |
+
"grad_norm": 0.28855767846107483,
|
318 |
+
"learning_rate": 6.173165676349103e-05,
|
319 |
+
"loss": 2.5325,
|
320 |
+
"num_input_tokens_seen": 3088960,
|
321 |
+
"step": 195
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.64,
|
325 |
+
"grad_norm": 0.27710187435150146,
|
326 |
+
"learning_rate": 5.713074385969457e-05,
|
327 |
+
"loss": 2.4344,
|
328 |
+
"num_input_tokens_seen": 3165160,
|
329 |
+
"step": 200
|
330 |
+
}
|
331 |
+
],
|
332 |
+
"logging_steps": 5,
|
333 |
+
"max_steps": 312,
|
334 |
+
"num_input_tokens_seen": 3165160,
|
335 |
+
"num_train_epochs": 1,
|
336 |
+
"save_steps": 100,
|
337 |
+
"stateful_callbacks": {
|
338 |
+
"TrainerControl": {
|
339 |
+
"args": {
|
340 |
+
"should_epoch_stop": false,
|
341 |
+
"should_evaluate": false,
|
342 |
+
"should_log": false,
|
343 |
+
"should_save": true,
|
344 |
+
"should_training_stop": false
|
345 |
+
},
|
346 |
+
"attributes": {}
|
347 |
+
}
|
348 |
+
},
|
349 |
+
"total_flos": 1.30881325463765e+17,
|
350 |
+
"train_batch_size": 1,
|
351 |
+
"trial_name": null,
|
352 |
+
"trial_params": null
|
353 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a11e34958bb0166a27197cc6b1af0b4918fc0bb571b674f64d1bed0d949d03fe
|
3 |
+
size 5368
|
checkpoint-300/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/CodeQwen1.5-7B-Chat
|
3 |
+
library_name: peft
|
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 0.12.0
|
checkpoint-300/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a93eb4fb52d911ba38388ae2500a4b98bde499258c2f31c8125fbd3b03c5cd2d
|
3 |
+
size 80144136
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d3bddffd22dcaf20069a4514e9e8932bf5ccdb0bd0f9b6996febf2ef7e789c0
|
3 |
+
size 160546898
|
checkpoint-300/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
|
3 |
+
size 14512
|
checkpoint-300/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
|
3 |
+
size 14512
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1d0a8fa4f4f33edaee237d6f99d4cc867fb2e10c314d06eddcbd7defb0675e9
|
3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>"
|
9 |
+
],
|
10 |
+
"bos_token": {
|
11 |
+
"content": "<|endoftext|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<fim_pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"unk_token": {
|
32 |
+
"content": "<unk>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
}
|
38 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-300/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,513 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.96,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016,
|
13 |
+
"grad_norm": 0.3705686628818512,
|
14 |
+
"learning_rate": 0.00019987329060020616,
|
15 |
+
"loss": 2.7276,
|
16 |
+
"num_input_tokens_seen": 78104,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.032,
|
21 |
+
"grad_norm": 0.28178921341896057,
|
22 |
+
"learning_rate": 0.00019949348350626456,
|
23 |
+
"loss": 2.6452,
|
24 |
+
"num_input_tokens_seen": 157384,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.048,
|
29 |
+
"grad_norm": 0.1864372342824936,
|
30 |
+
"learning_rate": 0.00019886154122075343,
|
31 |
+
"loss": 2.5708,
|
32 |
+
"num_input_tokens_seen": 240256,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.064,
|
37 |
+
"grad_norm": 0.1788010597229004,
|
38 |
+
"learning_rate": 0.00019797906520422677,
|
39 |
+
"loss": 2.5831,
|
40 |
+
"num_input_tokens_seen": 319032,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.08,
|
45 |
+
"grad_norm": 0.23142138123512268,
|
46 |
+
"learning_rate": 0.00019684829181681234,
|
47 |
+
"loss": 2.6138,
|
48 |
+
"num_input_tokens_seen": 397992,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.096,
|
53 |
+
"grad_norm": 0.21496976912021637,
|
54 |
+
"learning_rate": 0.00019547208665085457,
|
55 |
+
"loss": 2.5461,
|
56 |
+
"num_input_tokens_seen": 479904,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.112,
|
61 |
+
"grad_norm": 0.2536880671977997,
|
62 |
+
"learning_rate": 0.0001938539372689649,
|
63 |
+
"loss": 2.5797,
|
64 |
+
"num_input_tokens_seen": 555448,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.128,
|
69 |
+
"grad_norm": 0.39764249324798584,
|
70 |
+
"learning_rate": 0.00019199794436588243,
|
71 |
+
"loss": 2.5482,
|
72 |
+
"num_input_tokens_seen": 630888,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.144,
|
77 |
+
"grad_norm": 0.29237431287765503,
|
78 |
+
"learning_rate": 0.00018990881137654258,
|
79 |
+
"loss": 2.4726,
|
80 |
+
"num_input_tokens_seen": 709456,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.16,
|
85 |
+
"grad_norm": 0.24707558751106262,
|
86 |
+
"learning_rate": 0.0001875918325566888,
|
87 |
+
"loss": 2.5557,
|
88 |
+
"num_input_tokens_seen": 788504,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.176,
|
93 |
+
"grad_norm": 0.24359019100666046,
|
94 |
+
"learning_rate": 0.00018505287956623297,
|
95 |
+
"loss": 2.5357,
|
96 |
+
"num_input_tokens_seen": 864984,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.192,
|
101 |
+
"grad_norm": 0.23572562634944916,
|
102 |
+
"learning_rate": 0.00018229838658936564,
|
103 |
+
"loss": 2.4798,
|
104 |
+
"num_input_tokens_seen": 939136,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.208,
|
109 |
+
"grad_norm": 0.41712337732315063,
|
110 |
+
"learning_rate": 0.00017933533402912354,
|
111 |
+
"loss": 2.5619,
|
112 |
+
"num_input_tokens_seen": 1018024,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.224,
|
117 |
+
"grad_norm": 0.2777227759361267,
|
118 |
+
"learning_rate": 0.00017617123081773591,
|
119 |
+
"loss": 2.5334,
|
120 |
+
"num_input_tokens_seen": 1095072,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.24,
|
125 |
+
"grad_norm": 0.25098717212677,
|
126 |
+
"learning_rate": 0.00017281409538757883,
|
127 |
+
"loss": 2.5199,
|
128 |
+
"num_input_tokens_seen": 1172824,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.256,
|
133 |
+
"grad_norm": 0.24321608245372772,
|
134 |
+
"learning_rate": 0.00016927243535095997,
|
135 |
+
"loss": 2.4897,
|
136 |
+
"num_input_tokens_seen": 1244688,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.272,
|
141 |
+
"grad_norm": 0.25580549240112305,
|
142 |
+
"learning_rate": 0.0001655552259402295,
|
143 |
+
"loss": 2.513,
|
144 |
+
"num_input_tokens_seen": 1321104,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.288,
|
149 |
+
"grad_norm": 0.24990542232990265,
|
150 |
+
"learning_rate": 0.00016167188726285434,
|
151 |
+
"loss": 2.5533,
|
152 |
+
"num_input_tokens_seen": 1402456,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.304,
|
157 |
+
"grad_norm": 0.26301833987236023,
|
158 |
+
"learning_rate": 0.00015763226042909455,
|
159 |
+
"loss": 2.5297,
|
160 |
+
"num_input_tokens_seen": 1483648,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.32,
|
165 |
+
"grad_norm": 0.23519474267959595,
|
166 |
+
"learning_rate": 0.0001534465826127801,
|
167 |
+
"loss": 2.518,
|
168 |
+
"num_input_tokens_seen": 1560608,
|
169 |
+
"step": 100
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.336,
|
173 |
+
"grad_norm": 0.26162955164909363,
|
174 |
+
"learning_rate": 0.00014912546110838775,
|
175 |
+
"loss": 2.5537,
|
176 |
+
"num_input_tokens_seen": 1640728,
|
177 |
+
"step": 105
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.352,
|
181 |
+
"grad_norm": 0.2565276026725769,
|
182 |
+
"learning_rate": 0.00014467984645016258,
|
183 |
+
"loss": 2.489,
|
184 |
+
"num_input_tokens_seen": 1722440,
|
185 |
+
"step": 110
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.368,
|
189 |
+
"grad_norm": 0.3414108455181122,
|
190 |
+
"learning_rate": 0.00014012100466140578,
|
191 |
+
"loss": 2.5448,
|
192 |
+
"num_input_tokens_seen": 1805984,
|
193 |
+
"step": 115
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.384,
|
197 |
+
"grad_norm": 0.2590246796607971,
|
198 |
+
"learning_rate": 0.00013546048870425356,
|
199 |
+
"loss": 2.4148,
|
200 |
+
"num_input_tokens_seen": 1890592,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.4,
|
205 |
+
"grad_norm": 0.2765924036502838,
|
206 |
+
"learning_rate": 0.00013071010920229909,
|
207 |
+
"loss": 2.5512,
|
208 |
+
"num_input_tokens_seen": 1971272,
|
209 |
+
"step": 125
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.416,
|
213 |
+
"grad_norm": 0.2582058906555176,
|
214 |
+
"learning_rate": 0.00012588190451025207,
|
215 |
+
"loss": 2.5264,
|
216 |
+
"num_input_tokens_seen": 2053352,
|
217 |
+
"step": 130
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.432,
|
221 |
+
"grad_norm": 0.2416098713874817,
|
222 |
+
"learning_rate": 0.00012098811020648475,
|
223 |
+
"loss": 2.5525,
|
224 |
+
"num_input_tokens_seen": 2132624,
|
225 |
+
"step": 135
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.448,
|
229 |
+
"grad_norm": 0.3602483868598938,
|
230 |
+
"learning_rate": 0.00011604112808577603,
|
231 |
+
"loss": 2.5029,
|
232 |
+
"num_input_tokens_seen": 2210376,
|
233 |
+
"step": 140
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.464,
|
237 |
+
"grad_norm": 0.2507006824016571,
|
238 |
+
"learning_rate": 0.000111053494730832,
|
239 |
+
"loss": 2.5546,
|
240 |
+
"num_input_tokens_seen": 2292896,
|
241 |
+
"step": 145
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.48,
|
245 |
+
"grad_norm": 0.32158130407333374,
|
246 |
+
"learning_rate": 0.00010603784974222861,
|
247 |
+
"loss": 2.5431,
|
248 |
+
"num_input_tokens_seen": 2376432,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.496,
|
253 |
+
"grad_norm": 0.3036045730113983,
|
254 |
+
"learning_rate": 0.00010100690370728755,
|
255 |
+
"loss": 2.4882,
|
256 |
+
"num_input_tokens_seen": 2451848,
|
257 |
+
"step": 155
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.512,
|
261 |
+
"grad_norm": 0.31646254658699036,
|
262 |
+
"learning_rate": 9.597340598905852e-05,
|
263 |
+
"loss": 2.4319,
|
264 |
+
"num_input_tokens_seen": 2532816,
|
265 |
+
"step": 160
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.528,
|
269 |
+
"grad_norm": 0.2881500720977783,
|
270 |
+
"learning_rate": 9.095011241703623e-05,
|
271 |
+
"loss": 2.4688,
|
272 |
+
"num_input_tokens_seen": 2616160,
|
273 |
+
"step": 165
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.544,
|
277 |
+
"grad_norm": 0.27659812569618225,
|
278 |
+
"learning_rate": 8.594975296149076e-05,
|
279 |
+
"loss": 2.5149,
|
280 |
+
"num_input_tokens_seen": 2694864,
|
281 |
+
"step": 170
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.56,
|
285 |
+
"grad_norm": 0.4290514290332794,
|
286 |
+
"learning_rate": 8.098499947332934e-05,
|
287 |
+
"loss": 2.4754,
|
288 |
+
"num_input_tokens_seen": 2770464,
|
289 |
+
"step": 175
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.576,
|
293 |
+
"grad_norm": 0.28775912523269653,
|
294 |
+
"learning_rate": 7.606843357124426e-05,
|
295 |
+
"loss": 2.4875,
|
296 |
+
"num_input_tokens_seen": 2852888,
|
297 |
+
"step": 180
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.592,
|
301 |
+
"grad_norm": 0.2709747850894928,
|
302 |
+
"learning_rate": 7.121251475752539e-05,
|
303 |
+
"loss": 2.563,
|
304 |
+
"num_input_tokens_seen": 2933520,
|
305 |
+
"step": 185
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.608,
|
309 |
+
"grad_norm": 0.3473074734210968,
|
310 |
+
"learning_rate": 6.642954884333955e-05,
|
311 |
+
"loss": 2.4903,
|
312 |
+
"num_input_tokens_seen": 3011656,
|
313 |
+
"step": 190
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.624,
|
317 |
+
"grad_norm": 0.28855767846107483,
|
318 |
+
"learning_rate": 6.173165676349103e-05,
|
319 |
+
"loss": 2.5325,
|
320 |
+
"num_input_tokens_seen": 3088960,
|
321 |
+
"step": 195
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.64,
|
325 |
+
"grad_norm": 0.27710187435150146,
|
326 |
+
"learning_rate": 5.713074385969457e-05,
|
327 |
+
"loss": 2.4344,
|
328 |
+
"num_input_tokens_seen": 3165160,
|
329 |
+
"step": 200
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.656,
|
333 |
+
"grad_norm": 0.3773224651813507,
|
334 |
+
"learning_rate": 5.263846971020108e-05,
|
335 |
+
"loss": 2.4747,
|
336 |
+
"num_input_tokens_seen": 3242128,
|
337 |
+
"step": 205
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.672,
|
341 |
+
"grad_norm": 0.3007236123085022,
|
342 |
+
"learning_rate": 4.826621858223431e-05,
|
343 |
+
"loss": 2.4753,
|
344 |
+
"num_input_tokens_seen": 3323840,
|
345 |
+
"step": 210
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.688,
|
349 |
+
"grad_norm": 0.2919347286224365,
|
350 |
+
"learning_rate": 4.40250705821178e-05,
|
351 |
+
"loss": 2.513,
|
352 |
+
"num_input_tokens_seen": 3404144,
|
353 |
+
"step": 215
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.704,
|
357 |
+
"grad_norm": 0.26084381341934204,
|
358 |
+
"learning_rate": 3.99257735762021e-05,
|
359 |
+
"loss": 2.5244,
|
360 |
+
"num_input_tokens_seen": 3481992,
|
361 |
+
"step": 220
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.72,
|
365 |
+
"grad_norm": 0.3810001611709595,
|
366 |
+
"learning_rate": 3.597871595375121e-05,
|
367 |
+
"loss": 2.4893,
|
368 |
+
"num_input_tokens_seen": 3562480,
|
369 |
+
"step": 225
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.736,
|
373 |
+
"grad_norm": 0.2814476191997528,
|
374 |
+
"learning_rate": 3.219390030081091e-05,
|
375 |
+
"loss": 2.5374,
|
376 |
+
"num_input_tokens_seen": 3648552,
|
377 |
+
"step": 230
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.752,
|
381 |
+
"grad_norm": 0.2949189841747284,
|
382 |
+
"learning_rate": 2.858091805177554e-05,
|
383 |
+
"loss": 2.4568,
|
384 |
+
"num_input_tokens_seen": 3720616,
|
385 |
+
"step": 235
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.768,
|
389 |
+
"grad_norm": 0.32114091515541077,
|
390 |
+
"learning_rate": 2.514892518288988e-05,
|
391 |
+
"loss": 2.4686,
|
392 |
+
"num_input_tokens_seen": 3804368,
|
393 |
+
"step": 240
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.784,
|
397 |
+
"grad_norm": 0.30282753705978394,
|
398 |
+
"learning_rate": 2.1906619009284257e-05,
|
399 |
+
"loss": 2.5268,
|
400 |
+
"num_input_tokens_seen": 3880720,
|
401 |
+
"step": 245
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.8,
|
405 |
+
"grad_norm": 0.25529351830482483,
|
406 |
+
"learning_rate": 1.8862216144342692e-05,
|
407 |
+
"loss": 2.4932,
|
408 |
+
"num_input_tokens_seen": 3970064,
|
409 |
+
"step": 250
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.816,
|
413 |
+
"grad_norm": 0.25532060861587524,
|
414 |
+
"learning_rate": 1.6023431677260214e-05,
|
415 |
+
"loss": 2.4882,
|
416 |
+
"num_input_tokens_seen": 4052712,
|
417 |
+
"step": 255
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.832,
|
421 |
+
"grad_norm": 0.32484114170074463,
|
422 |
+
"learning_rate": 1.339745962155613e-05,
|
423 |
+
"loss": 2.5897,
|
424 |
+
"num_input_tokens_seen": 4133104,
|
425 |
+
"step": 260
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.848,
|
429 |
+
"grad_norm": 0.2640307545661926,
|
430 |
+
"learning_rate": 1.0990954684091558e-05,
|
431 |
+
"loss": 2.4555,
|
432 |
+
"num_input_tokens_seen": 4213160,
|
433 |
+
"step": 265
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.864,
|
437 |
+
"grad_norm": 0.6774325370788574,
|
438 |
+
"learning_rate": 8.810015400790994e-06,
|
439 |
+
"loss": 2.5311,
|
440 |
+
"num_input_tokens_seen": 4294240,
|
441 |
+
"step": 270
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.88,
|
445 |
+
"grad_norm": 0.3231619596481323,
|
446 |
+
"learning_rate": 6.860168681805945e-06,
|
447 |
+
"loss": 2.4318,
|
448 |
+
"num_input_tokens_seen": 4373680,
|
449 |
+
"step": 275
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.896,
|
453 |
+
"grad_norm": 0.29059651494026184,
|
454 |
+
"learning_rate": 5.146355805285452e-06,
|
455 |
+
"loss": 2.4513,
|
456 |
+
"num_input_tokens_seen": 4452712,
|
457 |
+
"step": 280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.912,
|
461 |
+
"grad_norm": 0.4263499975204468,
|
462 |
+
"learning_rate": 3.6729198952483724e-06,
|
463 |
+
"loss": 2.4889,
|
464 |
+
"num_input_tokens_seen": 4531416,
|
465 |
+
"step": 285
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.928,
|
469 |
+
"grad_norm": 0.3342815935611725,
|
470 |
+
"learning_rate": 2.4435949152906145e-06,
|
471 |
+
"loss": 2.5461,
|
472 |
+
"num_input_tokens_seen": 4617984,
|
473 |
+
"step": 290
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.944,
|
477 |
+
"grad_norm": 0.2988833785057068,
|
478 |
+
"learning_rate": 1.4614962060194304e-06,
|
479 |
+
"loss": 2.4965,
|
480 |
+
"num_input_tokens_seen": 4698024,
|
481 |
+
"step": 295
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.96,
|
485 |
+
"grad_norm": 0.2836878299713135,
|
486 |
+
"learning_rate": 7.291125901946027e-07,
|
487 |
+
"loss": 2.5403,
|
488 |
+
"num_input_tokens_seen": 4779504,
|
489 |
+
"step": 300
|
490 |
+
}
|
491 |
+
],
|
492 |
+
"logging_steps": 5,
|
493 |
+
"max_steps": 312,
|
494 |
+
"num_input_tokens_seen": 4779504,
|
495 |
+
"num_train_epochs": 1,
|
496 |
+
"save_steps": 100,
|
497 |
+
"stateful_callbacks": {
|
498 |
+
"TrainerControl": {
|
499 |
+
"args": {
|
500 |
+
"should_epoch_stop": false,
|
501 |
+
"should_evaluate": false,
|
502 |
+
"should_log": false,
|
503 |
+
"should_save": true,
|
504 |
+
"should_training_stop": false
|
505 |
+
},
|
506 |
+
"attributes": {}
|
507 |
+
}
|
508 |
+
},
|
509 |
+
"total_flos": 1.9763544932430643e+17,
|
510 |
+
"train_batch_size": 1,
|
511 |
+
"trial_name": null,
|
512 |
+
"trial_params": null
|
513 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a11e34958bb0166a27197cc6b1af0b4918fc0bb571b674f64d1bed0d949d03fe
|
3 |
+
size 5368
|
checkpoint-312/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/CodeQwen1.5-7B-Chat
|
3 |
+
library_name: peft
|
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 0.12.0
|
checkpoint-312/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-312/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e073ccabe42b118a635f726ffc9b1e75555230df4c876eb6bef9a0907ec9c2f
|
3 |
+
size 80144136
|
checkpoint-312/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc22c2ffbdef912954b1c7a91fba73d75e78dcba6f2abe00f751c8ca2f6331be
|
3 |
+
size 160546898
|
checkpoint-312/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
|
3 |
+
size 14512
|
checkpoint-312/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
|
3 |
+
size 14512
|
checkpoint-312/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07515c2b046d99c3743a994e794dd47b173671b79b64b92ecc764813da2c450b
|
3 |
+
size 1064
|
checkpoint-312/special_tokens_map.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>"
|
9 |
+
],
|
10 |
+
"bos_token": {
|
11 |
+
"content": "<|endoftext|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<fim_pad>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"unk_token": {
|
32 |
+
"content": "<unk>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
}
|
38 |
+
}
|
checkpoint-312/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-312/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|