First model version
Browse files- README.md +202 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- checkpoint-1000/README.md +202 -0
- checkpoint-1000/adapter_config.json +28 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +371 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/README.md +202 -0
- checkpoint-1500/adapter_config.json +28 -0
- checkpoint-1500/adapter_model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +546 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/README.md +202 -0
- checkpoint-2000/adapter_config.json +28 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +721 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/README.md +202 -0
- checkpoint-2500/adapter_config.json +28 -0
- checkpoint-2500/adapter_model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +896 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-500/README.md +202 -0
- checkpoint-500/adapter_config.json +28 -0
- checkpoint-500/adapter_model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +196 -0
- checkpoint-500/training_args.bin +3 -0
- runs/Mar04_05-55-16_n6vlfege1s/events.out.tfevents.1709531717.n6vlfege1s.478.0 +3 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: baffo32/decapoda-research-llama-7B-hf
|
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 0.9.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "baffo32/decapoda-research-llama-7B-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1c503cc57b2b9051920da2ee322544a0007e1d638b3e1924c85f7faa8869b71
|
3 |
+
size 16794200
|
checkpoint-1000/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: baffo32/decapoda-research-llama-7B-hf
|
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 0.9.0
|
checkpoint-1000/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "baffo32/decapoda-research-llama-7B-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9e5cf7128b6b4cc6032866caeefa0ffe1e36be5c063c480afc7eed0e3e5a17
|
3 |
+
size 16794200
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae2e509ef6bc514c9d073f4c60c6937ef0494220e34d7ff81446b7367143af6
|
3 |
+
size 33662074
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a8e1a1a2144a26b68231f7404ede59923f1b2deab179da906cc109392b45691
|
3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:224a88d2c1488ef4ea27e3c6c91be0b4c1906ba3ba18d7bb5adee58424971a6b
|
3 |
+
size 1064
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.329244673983215,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.21,
|
13 |
+
"grad_norm": 1.3856842517852783,
|
14 |
+
"learning_rate": 1.9868055555555558e-05,
|
15 |
+
"loss": 1.1287,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41,
|
20 |
+
"grad_norm": 0.4272608458995819,
|
21 |
+
"learning_rate": 1.9736111111111115e-05,
|
22 |
+
"loss": 1.0586,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.62,
|
27 |
+
"grad_norm": 0.4174883961677551,
|
28 |
+
"learning_rate": 1.9597222222222224e-05,
|
29 |
+
"loss": 1.0166,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.83,
|
34 |
+
"grad_norm": 0.35379958152770996,
|
35 |
+
"learning_rate": 1.9458333333333333e-05,
|
36 |
+
"loss": 0.8919,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.03,
|
41 |
+
"grad_norm": 0.3820742964744568,
|
42 |
+
"learning_rate": 1.9319444444444446e-05,
|
43 |
+
"loss": 0.7971,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.24,
|
48 |
+
"grad_norm": 0.34241142868995667,
|
49 |
+
"learning_rate": 1.918055555555556e-05,
|
50 |
+
"loss": 0.7466,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.45,
|
55 |
+
"grad_norm": 0.48230335116386414,
|
56 |
+
"learning_rate": 1.9041666666666668e-05,
|
57 |
+
"loss": 0.7468,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.65,
|
62 |
+
"grad_norm": 0.45057639479637146,
|
63 |
+
"learning_rate": 1.890277777777778e-05,
|
64 |
+
"loss": 0.7373,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.86,
|
69 |
+
"grad_norm": 0.43228989839553833,
|
70 |
+
"learning_rate": 1.876388888888889e-05,
|
71 |
+
"loss": 0.756,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.07,
|
76 |
+
"grad_norm": 0.460918664932251,
|
77 |
+
"learning_rate": 1.8625000000000002e-05,
|
78 |
+
"loss": 0.7186,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.27,
|
83 |
+
"grad_norm": 0.8221462368965149,
|
84 |
+
"learning_rate": 1.8486111111111115e-05,
|
85 |
+
"loss": 0.6772,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.48,
|
90 |
+
"grad_norm": 0.547721266746521,
|
91 |
+
"learning_rate": 1.8347222222222224e-05,
|
92 |
+
"loss": 0.6809,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.69,
|
97 |
+
"grad_norm": 0.6005927920341492,
|
98 |
+
"learning_rate": 1.8208333333333333e-05,
|
99 |
+
"loss": 0.6651,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.89,
|
104 |
+
"grad_norm": 0.7613247632980347,
|
105 |
+
"learning_rate": 1.8069444444444446e-05,
|
106 |
+
"loss": 0.641,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1,
|
111 |
+
"grad_norm": 0.668274462223053,
|
112 |
+
"learning_rate": 1.793055555555556e-05,
|
113 |
+
"loss": 0.6296,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.31,
|
118 |
+
"grad_norm": 0.6101451516151428,
|
119 |
+
"learning_rate": 1.7791666666666668e-05,
|
120 |
+
"loss": 0.6033,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.51,
|
125 |
+
"grad_norm": 0.8970944285392761,
|
126 |
+
"learning_rate": 1.765277777777778e-05,
|
127 |
+
"loss": 0.5939,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.72,
|
132 |
+
"grad_norm": 0.9417675137519836,
|
133 |
+
"learning_rate": 1.751388888888889e-05,
|
134 |
+
"loss": 0.5966,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.93,
|
139 |
+
"grad_norm": 1.3364688158035278,
|
140 |
+
"learning_rate": 1.7375000000000002e-05,
|
141 |
+
"loss": 0.5771,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.13,
|
146 |
+
"grad_norm": 0.7763314843177795,
|
147 |
+
"learning_rate": 1.7236111111111115e-05,
|
148 |
+
"loss": 0.5588,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.34,
|
153 |
+
"grad_norm": 1.156174659729004,
|
154 |
+
"learning_rate": 1.7097222222222224e-05,
|
155 |
+
"loss": 0.5571,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.54,
|
160 |
+
"grad_norm": 0.8457236886024475,
|
161 |
+
"learning_rate": 1.6958333333333333e-05,
|
162 |
+
"loss": 0.5431,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.75,
|
167 |
+
"grad_norm": 1.1372079849243164,
|
168 |
+
"learning_rate": 1.6819444444444446e-05,
|
169 |
+
"loss": 0.4839,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.96,
|
174 |
+
"grad_norm": 1.0457851886749268,
|
175 |
+
"learning_rate": 1.668055555555556e-05,
|
176 |
+
"loss": 0.5041,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.16,
|
181 |
+
"grad_norm": 1.1884819269180298,
|
182 |
+
"learning_rate": 1.6541666666666668e-05,
|
183 |
+
"loss": 0.468,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 5.37,
|
188 |
+
"grad_norm": 1.5204098224639893,
|
189 |
+
"learning_rate": 1.6402777777777777e-05,
|
190 |
+
"loss": 0.4778,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.58,
|
195 |
+
"grad_norm": 1.3218625783920288,
|
196 |
+
"learning_rate": 1.626388888888889e-05,
|
197 |
+
"loss": 0.4682,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.78,
|
202 |
+
"grad_norm": 1.2012380361557007,
|
203 |
+
"learning_rate": 1.6125000000000002e-05,
|
204 |
+
"loss": 0.4326,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 5.99,
|
209 |
+
"grad_norm": 1.4303064346313477,
|
210 |
+
"learning_rate": 1.5986111111111115e-05,
|
211 |
+
"loss": 0.4358,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 6.2,
|
216 |
+
"grad_norm": 1.4230263233184814,
|
217 |
+
"learning_rate": 1.5847222222222224e-05,
|
218 |
+
"loss": 0.4384,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 6.4,
|
223 |
+
"grad_norm": 1.5604521036148071,
|
224 |
+
"learning_rate": 1.5708333333333333e-05,
|
225 |
+
"loss": 0.3908,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.61,
|
230 |
+
"grad_norm": 1.7824558019638062,
|
231 |
+
"learning_rate": 1.5569444444444446e-05,
|
232 |
+
"loss": 0.4017,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.82,
|
237 |
+
"grad_norm": 1.4250575304031372,
|
238 |
+
"learning_rate": 1.543055555555556e-05,
|
239 |
+
"loss": 0.3759,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 7.02,
|
244 |
+
"grad_norm": 1.5560147762298584,
|
245 |
+
"learning_rate": 1.5291666666666668e-05,
|
246 |
+
"loss": 0.3869,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 7.23,
|
251 |
+
"grad_norm": 1.7027453184127808,
|
252 |
+
"learning_rate": 1.5152777777777779e-05,
|
253 |
+
"loss": 0.3591,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.44,
|
258 |
+
"grad_norm": 1.5872056484222412,
|
259 |
+
"learning_rate": 1.501388888888889e-05,
|
260 |
+
"loss": 0.3573,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.64,
|
265 |
+
"grad_norm": 1.5370341539382935,
|
266 |
+
"learning_rate": 1.4875000000000002e-05,
|
267 |
+
"loss": 0.3488,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.85,
|
272 |
+
"grad_norm": 1.853333830833435,
|
273 |
+
"learning_rate": 1.4736111111111113e-05,
|
274 |
+
"loss": 0.3416,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 8.06,
|
279 |
+
"grad_norm": 1.5671972036361694,
|
280 |
+
"learning_rate": 1.4597222222222223e-05,
|
281 |
+
"loss": 0.3282,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 8.26,
|
286 |
+
"grad_norm": 1.6593025922775269,
|
287 |
+
"learning_rate": 1.4458333333333334e-05,
|
288 |
+
"loss": 0.3112,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 8.47,
|
293 |
+
"grad_norm": 1.7826825380325317,
|
294 |
+
"learning_rate": 1.4319444444444446e-05,
|
295 |
+
"loss": 0.286,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 8.68,
|
300 |
+
"grad_norm": 1.5925076007843018,
|
301 |
+
"learning_rate": 1.4180555555555557e-05,
|
302 |
+
"loss": 0.3281,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.88,
|
307 |
+
"grad_norm": 1.7169785499572754,
|
308 |
+
"learning_rate": 1.4041666666666666e-05,
|
309 |
+
"loss": 0.3092,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 9.09,
|
314 |
+
"grad_norm": 1.8225599527359009,
|
315 |
+
"learning_rate": 1.3902777777777779e-05,
|
316 |
+
"loss": 0.2728,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 9.3,
|
321 |
+
"grad_norm": 2.113538980484009,
|
322 |
+
"learning_rate": 1.376388888888889e-05,
|
323 |
+
"loss": 0.2893,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 9.5,
|
328 |
+
"grad_norm": 2.0112457275390625,
|
329 |
+
"learning_rate": 1.3625e-05,
|
330 |
+
"loss": 0.277,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 9.71,
|
335 |
+
"grad_norm": 1.9079582691192627,
|
336 |
+
"learning_rate": 1.3486111111111113e-05,
|
337 |
+
"loss": 0.261,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.92,
|
342 |
+
"grad_norm": 1.793885350227356,
|
343 |
+
"learning_rate": 1.3347222222222223e-05,
|
344 |
+
"loss": 0.267,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 10.12,
|
349 |
+
"grad_norm": 1.770896315574646,
|
350 |
+
"learning_rate": 1.3208333333333334e-05,
|
351 |
+
"loss": 0.2719,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 10.33,
|
356 |
+
"grad_norm": 1.849857211112976,
|
357 |
+
"learning_rate": 1.3069444444444446e-05,
|
358 |
+
"loss": 0.2399,
|
359 |
+
"step": 1000
|
360 |
+
}
|
361 |
+
],
|
362 |
+
"logging_steps": 20,
|
363 |
+
"max_steps": 2880,
|
364 |
+
"num_input_tokens_seen": 0,
|
365 |
+
"num_train_epochs": 30,
|
366 |
+
"save_steps": 500,
|
367 |
+
"total_flos": 2.3132741104472064e+17,
|
368 |
+
"train_batch_size": 1,
|
369 |
+
"trial_name": null,
|
370 |
+
"trial_params": null
|
371 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2014fae9041d0eac19c9a012e0f34b574e3f2d7eb6062981c160b8614ac655dd
|
3 |
+
size 4920
|
checkpoint-1500/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: baffo32/decapoda-research-llama-7B-hf
|
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 0.9.0
|
checkpoint-1500/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "baffo32/decapoda-research-llama-7B-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a22f83129191bfc8b616bdf146a3607c1440c0ed99d0ba3b72042e871af2779a
|
3 |
+
size 16794200
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:478a40e19929e4c5d2b95b4a8e81a44e486175faf31c379ba58849a641c32dbb
|
3 |
+
size 33662074
|
checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d66007123980be2e711dfb5538ce7e95aaf6128d9437d3943fed5933fe707c36
|
3 |
+
size 14244
|
checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:248be0250673f76d2f181009e05936dc2f6b4b6bc5dd1631a5d29f12c6c220d2
|
3 |
+
size 1064
|
checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,546 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.493867010974823,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.21,
|
13 |
+
"grad_norm": 1.3856842517852783,
|
14 |
+
"learning_rate": 1.9868055555555558e-05,
|
15 |
+
"loss": 1.1287,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41,
|
20 |
+
"grad_norm": 0.4272608458995819,
|
21 |
+
"learning_rate": 1.9736111111111115e-05,
|
22 |
+
"loss": 1.0586,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.62,
|
27 |
+
"grad_norm": 0.4174883961677551,
|
28 |
+
"learning_rate": 1.9597222222222224e-05,
|
29 |
+
"loss": 1.0166,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.83,
|
34 |
+
"grad_norm": 0.35379958152770996,
|
35 |
+
"learning_rate": 1.9458333333333333e-05,
|
36 |
+
"loss": 0.8919,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.03,
|
41 |
+
"grad_norm": 0.3820742964744568,
|
42 |
+
"learning_rate": 1.9319444444444446e-05,
|
43 |
+
"loss": 0.7971,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.24,
|
48 |
+
"grad_norm": 0.34241142868995667,
|
49 |
+
"learning_rate": 1.918055555555556e-05,
|
50 |
+
"loss": 0.7466,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.45,
|
55 |
+
"grad_norm": 0.48230335116386414,
|
56 |
+
"learning_rate": 1.9041666666666668e-05,
|
57 |
+
"loss": 0.7468,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.65,
|
62 |
+
"grad_norm": 0.45057639479637146,
|
63 |
+
"learning_rate": 1.890277777777778e-05,
|
64 |
+
"loss": 0.7373,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.86,
|
69 |
+
"grad_norm": 0.43228989839553833,
|
70 |
+
"learning_rate": 1.876388888888889e-05,
|
71 |
+
"loss": 0.756,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.07,
|
76 |
+
"grad_norm": 0.460918664932251,
|
77 |
+
"learning_rate": 1.8625000000000002e-05,
|
78 |
+
"loss": 0.7186,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.27,
|
83 |
+
"grad_norm": 0.8221462368965149,
|
84 |
+
"learning_rate": 1.8486111111111115e-05,
|
85 |
+
"loss": 0.6772,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.48,
|
90 |
+
"grad_norm": 0.547721266746521,
|
91 |
+
"learning_rate": 1.8347222222222224e-05,
|
92 |
+
"loss": 0.6809,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.69,
|
97 |
+
"grad_norm": 0.6005927920341492,
|
98 |
+
"learning_rate": 1.8208333333333333e-05,
|
99 |
+
"loss": 0.6651,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.89,
|
104 |
+
"grad_norm": 0.7613247632980347,
|
105 |
+
"learning_rate": 1.8069444444444446e-05,
|
106 |
+
"loss": 0.641,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1,
|
111 |
+
"grad_norm": 0.668274462223053,
|
112 |
+
"learning_rate": 1.793055555555556e-05,
|
113 |
+
"loss": 0.6296,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.31,
|
118 |
+
"grad_norm": 0.6101451516151428,
|
119 |
+
"learning_rate": 1.7791666666666668e-05,
|
120 |
+
"loss": 0.6033,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.51,
|
125 |
+
"grad_norm": 0.8970944285392761,
|
126 |
+
"learning_rate": 1.765277777777778e-05,
|
127 |
+
"loss": 0.5939,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.72,
|
132 |
+
"grad_norm": 0.9417675137519836,
|
133 |
+
"learning_rate": 1.751388888888889e-05,
|
134 |
+
"loss": 0.5966,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.93,
|
139 |
+
"grad_norm": 1.3364688158035278,
|
140 |
+
"learning_rate": 1.7375000000000002e-05,
|
141 |
+
"loss": 0.5771,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.13,
|
146 |
+
"grad_norm": 0.7763314843177795,
|
147 |
+
"learning_rate": 1.7236111111111115e-05,
|
148 |
+
"loss": 0.5588,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.34,
|
153 |
+
"grad_norm": 1.156174659729004,
|
154 |
+
"learning_rate": 1.7097222222222224e-05,
|
155 |
+
"loss": 0.5571,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.54,
|
160 |
+
"grad_norm": 0.8457236886024475,
|
161 |
+
"learning_rate": 1.6958333333333333e-05,
|
162 |
+
"loss": 0.5431,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.75,
|
167 |
+
"grad_norm": 1.1372079849243164,
|
168 |
+
"learning_rate": 1.6819444444444446e-05,
|
169 |
+
"loss": 0.4839,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.96,
|
174 |
+
"grad_norm": 1.0457851886749268,
|
175 |
+
"learning_rate": 1.668055555555556e-05,
|
176 |
+
"loss": 0.5041,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.16,
|
181 |
+
"grad_norm": 1.1884819269180298,
|
182 |
+
"learning_rate": 1.6541666666666668e-05,
|
183 |
+
"loss": 0.468,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 5.37,
|
188 |
+
"grad_norm": 1.5204098224639893,
|
189 |
+
"learning_rate": 1.6402777777777777e-05,
|
190 |
+
"loss": 0.4778,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.58,
|
195 |
+
"grad_norm": 1.3218625783920288,
|
196 |
+
"learning_rate": 1.626388888888889e-05,
|
197 |
+
"loss": 0.4682,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.78,
|
202 |
+
"grad_norm": 1.2012380361557007,
|
203 |
+
"learning_rate": 1.6125000000000002e-05,
|
204 |
+
"loss": 0.4326,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 5.99,
|
209 |
+
"grad_norm": 1.4303064346313477,
|
210 |
+
"learning_rate": 1.5986111111111115e-05,
|
211 |
+
"loss": 0.4358,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 6.2,
|
216 |
+
"grad_norm": 1.4230263233184814,
|
217 |
+
"learning_rate": 1.5847222222222224e-05,
|
218 |
+
"loss": 0.4384,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 6.4,
|
223 |
+
"grad_norm": 1.5604521036148071,
|
224 |
+
"learning_rate": 1.5708333333333333e-05,
|
225 |
+
"loss": 0.3908,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.61,
|
230 |
+
"grad_norm": 1.7824558019638062,
|
231 |
+
"learning_rate": 1.5569444444444446e-05,
|
232 |
+
"loss": 0.4017,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.82,
|
237 |
+
"grad_norm": 1.4250575304031372,
|
238 |
+
"learning_rate": 1.543055555555556e-05,
|
239 |
+
"loss": 0.3759,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 7.02,
|
244 |
+
"grad_norm": 1.5560147762298584,
|
245 |
+
"learning_rate": 1.5291666666666668e-05,
|
246 |
+
"loss": 0.3869,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 7.23,
|
251 |
+
"grad_norm": 1.7027453184127808,
|
252 |
+
"learning_rate": 1.5152777777777779e-05,
|
253 |
+
"loss": 0.3591,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.44,
|
258 |
+
"grad_norm": 1.5872056484222412,
|
259 |
+
"learning_rate": 1.501388888888889e-05,
|
260 |
+
"loss": 0.3573,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.64,
|
265 |
+
"grad_norm": 1.5370341539382935,
|
266 |
+
"learning_rate": 1.4875000000000002e-05,
|
267 |
+
"loss": 0.3488,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.85,
|
272 |
+
"grad_norm": 1.853333830833435,
|
273 |
+
"learning_rate": 1.4736111111111113e-05,
|
274 |
+
"loss": 0.3416,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 8.06,
|
279 |
+
"grad_norm": 1.5671972036361694,
|
280 |
+
"learning_rate": 1.4597222222222223e-05,
|
281 |
+
"loss": 0.3282,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 8.26,
|
286 |
+
"grad_norm": 1.6593025922775269,
|
287 |
+
"learning_rate": 1.4458333333333334e-05,
|
288 |
+
"loss": 0.3112,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 8.47,
|
293 |
+
"grad_norm": 1.7826825380325317,
|
294 |
+
"learning_rate": 1.4319444444444446e-05,
|
295 |
+
"loss": 0.286,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 8.68,
|
300 |
+
"grad_norm": 1.5925076007843018,
|
301 |
+
"learning_rate": 1.4180555555555557e-05,
|
302 |
+
"loss": 0.3281,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.88,
|
307 |
+
"grad_norm": 1.7169785499572754,
|
308 |
+
"learning_rate": 1.4041666666666666e-05,
|
309 |
+
"loss": 0.3092,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 9.09,
|
314 |
+
"grad_norm": 1.8225599527359009,
|
315 |
+
"learning_rate": 1.3902777777777779e-05,
|
316 |
+
"loss": 0.2728,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 9.3,
|
321 |
+
"grad_norm": 2.113538980484009,
|
322 |
+
"learning_rate": 1.376388888888889e-05,
|
323 |
+
"loss": 0.2893,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 9.5,
|
328 |
+
"grad_norm": 2.0112457275390625,
|
329 |
+
"learning_rate": 1.3625e-05,
|
330 |
+
"loss": 0.277,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 9.71,
|
335 |
+
"grad_norm": 1.9079582691192627,
|
336 |
+
"learning_rate": 1.3486111111111113e-05,
|
337 |
+
"loss": 0.261,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.92,
|
342 |
+
"grad_norm": 1.793885350227356,
|
343 |
+
"learning_rate": 1.3347222222222223e-05,
|
344 |
+
"loss": 0.267,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 10.12,
|
349 |
+
"grad_norm": 1.770896315574646,
|
350 |
+
"learning_rate": 1.3208333333333334e-05,
|
351 |
+
"loss": 0.2719,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 10.33,
|
356 |
+
"grad_norm": 1.849857211112976,
|
357 |
+
"learning_rate": 1.3069444444444446e-05,
|
358 |
+
"loss": 0.2399,
|
359 |
+
"step": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 10.54,
|
363 |
+
"grad_norm": 1.8785293102264404,
|
364 |
+
"learning_rate": 1.2930555555555557e-05,
|
365 |
+
"loss": 0.2316,
|
366 |
+
"step": 1020
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 10.74,
|
370 |
+
"grad_norm": 1.7189656496047974,
|
371 |
+
"learning_rate": 1.2791666666666666e-05,
|
372 |
+
"loss": 0.243,
|
373 |
+
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 10.95,
|
377 |
+
"grad_norm": 1.6181199550628662,
|
378 |
+
"learning_rate": 1.2652777777777779e-05,
|
379 |
+
"loss": 0.2347,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 11.16,
|
384 |
+
"grad_norm": 2.0756866931915283,
|
385 |
+
"learning_rate": 1.251388888888889e-05,
|
386 |
+
"loss": 0.2407,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 11.36,
|
391 |
+
"grad_norm": 1.9992755651474,
|
392 |
+
"learning_rate": 1.2375000000000001e-05,
|
393 |
+
"loss": 0.2205,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 11.57,
|
398 |
+
"grad_norm": 2.19657039642334,
|
399 |
+
"learning_rate": 1.2236111111111114e-05,
|
400 |
+
"loss": 0.1992,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 11.78,
|
405 |
+
"grad_norm": 1.8114335536956787,
|
406 |
+
"learning_rate": 1.2097222222222223e-05,
|
407 |
+
"loss": 0.219,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 11.98,
|
412 |
+
"grad_norm": 1.841556429862976,
|
413 |
+
"learning_rate": 1.1958333333333334e-05,
|
414 |
+
"loss": 0.2051,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 12.19,
|
419 |
+
"grad_norm": 1.9361953735351562,
|
420 |
+
"learning_rate": 1.1819444444444446e-05,
|
421 |
+
"loss": 0.2025,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 12.4,
|
426 |
+
"grad_norm": 1.841424584388733,
|
427 |
+
"learning_rate": 1.1680555555555557e-05,
|
428 |
+
"loss": 0.2109,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 12.6,
|
433 |
+
"grad_norm": 2.569114923477173,
|
434 |
+
"learning_rate": 1.1541666666666667e-05,
|
435 |
+
"loss": 0.1933,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 12.81,
|
440 |
+
"grad_norm": 1.8263764381408691,
|
441 |
+
"learning_rate": 1.1402777777777777e-05,
|
442 |
+
"loss": 0.1814,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 13.01,
|
447 |
+
"grad_norm": 1.7250192165374756,
|
448 |
+
"learning_rate": 1.126388888888889e-05,
|
449 |
+
"loss": 0.1842,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 13.22,
|
454 |
+
"grad_norm": 1.8750269412994385,
|
455 |
+
"learning_rate": 1.1125000000000001e-05,
|
456 |
+
"loss": 0.1803,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 13.43,
|
461 |
+
"grad_norm": 2.2998244762420654,
|
462 |
+
"learning_rate": 1.0986111111111114e-05,
|
463 |
+
"loss": 0.167,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 13.63,
|
468 |
+
"grad_norm": 1.663015604019165,
|
469 |
+
"learning_rate": 1.0847222222222223e-05,
|
470 |
+
"loss": 0.1723,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 13.84,
|
475 |
+
"grad_norm": 2.0710666179656982,
|
476 |
+
"learning_rate": 1.0708333333333334e-05,
|
477 |
+
"loss": 0.1895,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 14.05,
|
482 |
+
"grad_norm": 1.8963505029678345,
|
483 |
+
"learning_rate": 1.0569444444444445e-05,
|
484 |
+
"loss": 0.1783,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 14.25,
|
489 |
+
"grad_norm": 2.3760714530944824,
|
490 |
+
"learning_rate": 1.0430555555555557e-05,
|
491 |
+
"loss": 0.1674,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 14.46,
|
496 |
+
"grad_norm": 1.8337997198104858,
|
497 |
+
"learning_rate": 1.0291666666666667e-05,
|
498 |
+
"loss": 0.1677,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 14.67,
|
503 |
+
"grad_norm": 1.8879417181015015,
|
504 |
+
"learning_rate": 1.0152777777777778e-05,
|
505 |
+
"loss": 0.1602,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 14.87,
|
510 |
+
"grad_norm": 1.9163988828659058,
|
511 |
+
"learning_rate": 1.001388888888889e-05,
|
512 |
+
"loss": 0.1536,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 15.08,
|
517 |
+
"grad_norm": 1.772133469581604,
|
518 |
+
"learning_rate": 9.875000000000001e-06,
|
519 |
+
"loss": 0.1422,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 15.29,
|
524 |
+
"grad_norm": 2.173783540725708,
|
525 |
+
"learning_rate": 9.736111111111112e-06,
|
526 |
+
"loss": 0.1634,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 15.49,
|
531 |
+
"grad_norm": 2.1147613525390625,
|
532 |
+
"learning_rate": 9.597222222222223e-06,
|
533 |
+
"loss": 0.14,
|
534 |
+
"step": 1500
|
535 |
+
}
|
536 |
+
],
|
537 |
+
"logging_steps": 20,
|
538 |
+
"max_steps": 2880,
|
539 |
+
"num_input_tokens_seen": 0,
|
540 |
+
"num_train_epochs": 30,
|
541 |
+
"save_steps": 500,
|
542 |
+
"total_flos": 3.470427063974707e+17,
|
543 |
+
"train_batch_size": 1,
|
544 |
+
"trial_name": null,
|
545 |
+
"trial_params": null
|
546 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2014fae9041d0eac19c9a012e0f34b574e3f2d7eb6062981c160b8614ac655dd
|
3 |
+
size 4920
|
checkpoint-2000/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: baffo32/decapoda-research-llama-7B-hf
|
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 0.9.0
|
checkpoint-2000/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "baffo32/decapoda-research-llama-7B-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68a2a206eca7aa29d26c4af769d253621dac83ffed938fa774286691214959d9
|
3 |
+
size 16794200
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acb8a597cb4a9629ebe9523c1f12e1ab3f2ff0f57b8097f1a3a2f509ab429c08
|
3 |
+
size 33662074
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f4b12c4bc3ebddb8f91c4da8598249a73455d2b9e0130ee986d4567b80c5369
|
3 |
+
size 14244
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d41235318dcf12670a9ee30e4a84db17652f29276a272bef0c8239eff4977d27
|
3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.65848934796643,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.21,
|
13 |
+
"grad_norm": 1.3856842517852783,
|
14 |
+
"learning_rate": 1.9868055555555558e-05,
|
15 |
+
"loss": 1.1287,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41,
|
20 |
+
"grad_norm": 0.4272608458995819,
|
21 |
+
"learning_rate": 1.9736111111111115e-05,
|
22 |
+
"loss": 1.0586,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.62,
|
27 |
+
"grad_norm": 0.4174883961677551,
|
28 |
+
"learning_rate": 1.9597222222222224e-05,
|
29 |
+
"loss": 1.0166,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.83,
|
34 |
+
"grad_norm": 0.35379958152770996,
|
35 |
+
"learning_rate": 1.9458333333333333e-05,
|
36 |
+
"loss": 0.8919,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.03,
|
41 |
+
"grad_norm": 0.3820742964744568,
|
42 |
+
"learning_rate": 1.9319444444444446e-05,
|
43 |
+
"loss": 0.7971,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.24,
|
48 |
+
"grad_norm": 0.34241142868995667,
|
49 |
+
"learning_rate": 1.918055555555556e-05,
|
50 |
+
"loss": 0.7466,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.45,
|
55 |
+
"grad_norm": 0.48230335116386414,
|
56 |
+
"learning_rate": 1.9041666666666668e-05,
|
57 |
+
"loss": 0.7468,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.65,
|
62 |
+
"grad_norm": 0.45057639479637146,
|
63 |
+
"learning_rate": 1.890277777777778e-05,
|
64 |
+
"loss": 0.7373,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.86,
|
69 |
+
"grad_norm": 0.43228989839553833,
|
70 |
+
"learning_rate": 1.876388888888889e-05,
|
71 |
+
"loss": 0.756,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.07,
|
76 |
+
"grad_norm": 0.460918664932251,
|
77 |
+
"learning_rate": 1.8625000000000002e-05,
|
78 |
+
"loss": 0.7186,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.27,
|
83 |
+
"grad_norm": 0.8221462368965149,
|
84 |
+
"learning_rate": 1.8486111111111115e-05,
|
85 |
+
"loss": 0.6772,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.48,
|
90 |
+
"grad_norm": 0.547721266746521,
|
91 |
+
"learning_rate": 1.8347222222222224e-05,
|
92 |
+
"loss": 0.6809,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.69,
|
97 |
+
"grad_norm": 0.6005927920341492,
|
98 |
+
"learning_rate": 1.8208333333333333e-05,
|
99 |
+
"loss": 0.6651,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.89,
|
104 |
+
"grad_norm": 0.7613247632980347,
|
105 |
+
"learning_rate": 1.8069444444444446e-05,
|
106 |
+
"loss": 0.641,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1,
|
111 |
+
"grad_norm": 0.668274462223053,
|
112 |
+
"learning_rate": 1.793055555555556e-05,
|
113 |
+
"loss": 0.6296,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.31,
|
118 |
+
"grad_norm": 0.6101451516151428,
|
119 |
+
"learning_rate": 1.7791666666666668e-05,
|
120 |
+
"loss": 0.6033,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.51,
|
125 |
+
"grad_norm": 0.8970944285392761,
|
126 |
+
"learning_rate": 1.765277777777778e-05,
|
127 |
+
"loss": 0.5939,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.72,
|
132 |
+
"grad_norm": 0.9417675137519836,
|
133 |
+
"learning_rate": 1.751388888888889e-05,
|
134 |
+
"loss": 0.5966,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.93,
|
139 |
+
"grad_norm": 1.3364688158035278,
|
140 |
+
"learning_rate": 1.7375000000000002e-05,
|
141 |
+
"loss": 0.5771,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.13,
|
146 |
+
"grad_norm": 0.7763314843177795,
|
147 |
+
"learning_rate": 1.7236111111111115e-05,
|
148 |
+
"loss": 0.5588,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.34,
|
153 |
+
"grad_norm": 1.156174659729004,
|
154 |
+
"learning_rate": 1.7097222222222224e-05,
|
155 |
+
"loss": 0.5571,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.54,
|
160 |
+
"grad_norm": 0.8457236886024475,
|
161 |
+
"learning_rate": 1.6958333333333333e-05,
|
162 |
+
"loss": 0.5431,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.75,
|
167 |
+
"grad_norm": 1.1372079849243164,
|
168 |
+
"learning_rate": 1.6819444444444446e-05,
|
169 |
+
"loss": 0.4839,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.96,
|
174 |
+
"grad_norm": 1.0457851886749268,
|
175 |
+
"learning_rate": 1.668055555555556e-05,
|
176 |
+
"loss": 0.5041,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.16,
|
181 |
+
"grad_norm": 1.1884819269180298,
|
182 |
+
"learning_rate": 1.6541666666666668e-05,
|
183 |
+
"loss": 0.468,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 5.37,
|
188 |
+
"grad_norm": 1.5204098224639893,
|
189 |
+
"learning_rate": 1.6402777777777777e-05,
|
190 |
+
"loss": 0.4778,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.58,
|
195 |
+
"grad_norm": 1.3218625783920288,
|
196 |
+
"learning_rate": 1.626388888888889e-05,
|
197 |
+
"loss": 0.4682,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.78,
|
202 |
+
"grad_norm": 1.2012380361557007,
|
203 |
+
"learning_rate": 1.6125000000000002e-05,
|
204 |
+
"loss": 0.4326,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 5.99,
|
209 |
+
"grad_norm": 1.4303064346313477,
|
210 |
+
"learning_rate": 1.5986111111111115e-05,
|
211 |
+
"loss": 0.4358,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 6.2,
|
216 |
+
"grad_norm": 1.4230263233184814,
|
217 |
+
"learning_rate": 1.5847222222222224e-05,
|
218 |
+
"loss": 0.4384,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 6.4,
|
223 |
+
"grad_norm": 1.5604521036148071,
|
224 |
+
"learning_rate": 1.5708333333333333e-05,
|
225 |
+
"loss": 0.3908,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.61,
|
230 |
+
"grad_norm": 1.7824558019638062,
|
231 |
+
"learning_rate": 1.5569444444444446e-05,
|
232 |
+
"loss": 0.4017,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.82,
|
237 |
+
"grad_norm": 1.4250575304031372,
|
238 |
+
"learning_rate": 1.543055555555556e-05,
|
239 |
+
"loss": 0.3759,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 7.02,
|
244 |
+
"grad_norm": 1.5560147762298584,
|
245 |
+
"learning_rate": 1.5291666666666668e-05,
|
246 |
+
"loss": 0.3869,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 7.23,
|
251 |
+
"grad_norm": 1.7027453184127808,
|
252 |
+
"learning_rate": 1.5152777777777779e-05,
|
253 |
+
"loss": 0.3591,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.44,
|
258 |
+
"grad_norm": 1.5872056484222412,
|
259 |
+
"learning_rate": 1.501388888888889e-05,
|
260 |
+
"loss": 0.3573,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.64,
|
265 |
+
"grad_norm": 1.5370341539382935,
|
266 |
+
"learning_rate": 1.4875000000000002e-05,
|
267 |
+
"loss": 0.3488,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.85,
|
272 |
+
"grad_norm": 1.853333830833435,
|
273 |
+
"learning_rate": 1.4736111111111113e-05,
|
274 |
+
"loss": 0.3416,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 8.06,
|
279 |
+
"grad_norm": 1.5671972036361694,
|
280 |
+
"learning_rate": 1.4597222222222223e-05,
|
281 |
+
"loss": 0.3282,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 8.26,
|
286 |
+
"grad_norm": 1.6593025922775269,
|
287 |
+
"learning_rate": 1.4458333333333334e-05,
|
288 |
+
"loss": 0.3112,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 8.47,
|
293 |
+
"grad_norm": 1.7826825380325317,
|
294 |
+
"learning_rate": 1.4319444444444446e-05,
|
295 |
+
"loss": 0.286,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 8.68,
|
300 |
+
"grad_norm": 1.5925076007843018,
|
301 |
+
"learning_rate": 1.4180555555555557e-05,
|
302 |
+
"loss": 0.3281,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.88,
|
307 |
+
"grad_norm": 1.7169785499572754,
|
308 |
+
"learning_rate": 1.4041666666666666e-05,
|
309 |
+
"loss": 0.3092,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 9.09,
|
314 |
+
"grad_norm": 1.8225599527359009,
|
315 |
+
"learning_rate": 1.3902777777777779e-05,
|
316 |
+
"loss": 0.2728,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 9.3,
|
321 |
+
"grad_norm": 2.113538980484009,
|
322 |
+
"learning_rate": 1.376388888888889e-05,
|
323 |
+
"loss": 0.2893,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 9.5,
|
328 |
+
"grad_norm": 2.0112457275390625,
|
329 |
+
"learning_rate": 1.3625e-05,
|
330 |
+
"loss": 0.277,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 9.71,
|
335 |
+
"grad_norm": 1.9079582691192627,
|
336 |
+
"learning_rate": 1.3486111111111113e-05,
|
337 |
+
"loss": 0.261,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.92,
|
342 |
+
"grad_norm": 1.793885350227356,
|
343 |
+
"learning_rate": 1.3347222222222223e-05,
|
344 |
+
"loss": 0.267,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 10.12,
|
349 |
+
"grad_norm": 1.770896315574646,
|
350 |
+
"learning_rate": 1.3208333333333334e-05,
|
351 |
+
"loss": 0.2719,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 10.33,
|
356 |
+
"grad_norm": 1.849857211112976,
|
357 |
+
"learning_rate": 1.3069444444444446e-05,
|
358 |
+
"loss": 0.2399,
|
359 |
+
"step": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 10.54,
|
363 |
+
"grad_norm": 1.8785293102264404,
|
364 |
+
"learning_rate": 1.2930555555555557e-05,
|
365 |
+
"loss": 0.2316,
|
366 |
+
"step": 1020
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 10.74,
|
370 |
+
"grad_norm": 1.7189656496047974,
|
371 |
+
"learning_rate": 1.2791666666666666e-05,
|
372 |
+
"loss": 0.243,
|
373 |
+
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 10.95,
|
377 |
+
"grad_norm": 1.6181199550628662,
|
378 |
+
"learning_rate": 1.2652777777777779e-05,
|
379 |
+
"loss": 0.2347,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 11.16,
|
384 |
+
"grad_norm": 2.0756866931915283,
|
385 |
+
"learning_rate": 1.251388888888889e-05,
|
386 |
+
"loss": 0.2407,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 11.36,
|
391 |
+
"grad_norm": 1.9992755651474,
|
392 |
+
"learning_rate": 1.2375000000000001e-05,
|
393 |
+
"loss": 0.2205,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 11.57,
|
398 |
+
"grad_norm": 2.19657039642334,
|
399 |
+
"learning_rate": 1.2236111111111114e-05,
|
400 |
+
"loss": 0.1992,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 11.78,
|
405 |
+
"grad_norm": 1.8114335536956787,
|
406 |
+
"learning_rate": 1.2097222222222223e-05,
|
407 |
+
"loss": 0.219,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 11.98,
|
412 |
+
"grad_norm": 1.841556429862976,
|
413 |
+
"learning_rate": 1.1958333333333334e-05,
|
414 |
+
"loss": 0.2051,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 12.19,
|
419 |
+
"grad_norm": 1.9361953735351562,
|
420 |
+
"learning_rate": 1.1819444444444446e-05,
|
421 |
+
"loss": 0.2025,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 12.4,
|
426 |
+
"grad_norm": 1.841424584388733,
|
427 |
+
"learning_rate": 1.1680555555555557e-05,
|
428 |
+
"loss": 0.2109,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 12.6,
|
433 |
+
"grad_norm": 2.569114923477173,
|
434 |
+
"learning_rate": 1.1541666666666667e-05,
|
435 |
+
"loss": 0.1933,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 12.81,
|
440 |
+
"grad_norm": 1.8263764381408691,
|
441 |
+
"learning_rate": 1.1402777777777777e-05,
|
442 |
+
"loss": 0.1814,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 13.01,
|
447 |
+
"grad_norm": 1.7250192165374756,
|
448 |
+
"learning_rate": 1.126388888888889e-05,
|
449 |
+
"loss": 0.1842,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 13.22,
|
454 |
+
"grad_norm": 1.8750269412994385,
|
455 |
+
"learning_rate": 1.1125000000000001e-05,
|
456 |
+
"loss": 0.1803,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 13.43,
|
461 |
+
"grad_norm": 2.2998244762420654,
|
462 |
+
"learning_rate": 1.0986111111111114e-05,
|
463 |
+
"loss": 0.167,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 13.63,
|
468 |
+
"grad_norm": 1.663015604019165,
|
469 |
+
"learning_rate": 1.0847222222222223e-05,
|
470 |
+
"loss": 0.1723,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 13.84,
|
475 |
+
"grad_norm": 2.0710666179656982,
|
476 |
+
"learning_rate": 1.0708333333333334e-05,
|
477 |
+
"loss": 0.1895,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 14.05,
|
482 |
+
"grad_norm": 1.8963505029678345,
|
483 |
+
"learning_rate": 1.0569444444444445e-05,
|
484 |
+
"loss": 0.1783,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 14.25,
|
489 |
+
"grad_norm": 2.3760714530944824,
|
490 |
+
"learning_rate": 1.0430555555555557e-05,
|
491 |
+
"loss": 0.1674,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 14.46,
|
496 |
+
"grad_norm": 1.8337997198104858,
|
497 |
+
"learning_rate": 1.0291666666666667e-05,
|
498 |
+
"loss": 0.1677,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 14.67,
|
503 |
+
"grad_norm": 1.8879417181015015,
|
504 |
+
"learning_rate": 1.0152777777777778e-05,
|
505 |
+
"loss": 0.1602,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 14.87,
|
510 |
+
"grad_norm": 1.9163988828659058,
|
511 |
+
"learning_rate": 1.001388888888889e-05,
|
512 |
+
"loss": 0.1536,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 15.08,
|
517 |
+
"grad_norm": 1.772133469581604,
|
518 |
+
"learning_rate": 9.875000000000001e-06,
|
519 |
+
"loss": 0.1422,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 15.29,
|
524 |
+
"grad_norm": 2.173783540725708,
|
525 |
+
"learning_rate": 9.736111111111112e-06,
|
526 |
+
"loss": 0.1634,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 15.49,
|
531 |
+
"grad_norm": 2.1147613525390625,
|
532 |
+
"learning_rate": 9.597222222222223e-06,
|
533 |
+
"loss": 0.14,
|
534 |
+
"step": 1500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 15.7,
|
538 |
+
"grad_norm": 2.0401387214660645,
|
539 |
+
"learning_rate": 9.458333333333334e-06,
|
540 |
+
"loss": 0.1498,
|
541 |
+
"step": 1520
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 15.91,
|
545 |
+
"grad_norm": 2.0865604877471924,
|
546 |
+
"learning_rate": 9.319444444444445e-06,
|
547 |
+
"loss": 0.1395,
|
548 |
+
"step": 1540
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 16.11,
|
552 |
+
"grad_norm": 1.884482502937317,
|
553 |
+
"learning_rate": 9.180555555555556e-06,
|
554 |
+
"loss": 0.1461,
|
555 |
+
"step": 1560
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 16.32,
|
559 |
+
"grad_norm": 2.2012784481048584,
|
560 |
+
"learning_rate": 9.041666666666667e-06,
|
561 |
+
"loss": 0.1297,
|
562 |
+
"step": 1580
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 16.53,
|
566 |
+
"grad_norm": 2.0317113399505615,
|
567 |
+
"learning_rate": 8.902777777777778e-06,
|
568 |
+
"loss": 0.15,
|
569 |
+
"step": 1600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 16.73,
|
573 |
+
"grad_norm": 1.4792850017547607,
|
574 |
+
"learning_rate": 8.76388888888889e-06,
|
575 |
+
"loss": 0.1359,
|
576 |
+
"step": 1620
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 16.94,
|
580 |
+
"grad_norm": 2.3025472164154053,
|
581 |
+
"learning_rate": 8.625000000000001e-06,
|
582 |
+
"loss": 0.1298,
|
583 |
+
"step": 1640
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 17.15,
|
587 |
+
"grad_norm": 1.8987499475479126,
|
588 |
+
"learning_rate": 8.486111111111112e-06,
|
589 |
+
"loss": 0.1287,
|
590 |
+
"step": 1660
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 17.35,
|
594 |
+
"grad_norm": 3.6023619174957275,
|
595 |
+
"learning_rate": 8.347222222222223e-06,
|
596 |
+
"loss": 0.1584,
|
597 |
+
"step": 1680
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 17.56,
|
601 |
+
"grad_norm": 1.6749480962753296,
|
602 |
+
"learning_rate": 8.208333333333334e-06,
|
603 |
+
"loss": 0.1071,
|
604 |
+
"step": 1700
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 17.77,
|
608 |
+
"grad_norm": 1.894116759300232,
|
609 |
+
"learning_rate": 8.069444444444445e-06,
|
610 |
+
"loss": 0.1233,
|
611 |
+
"step": 1720
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 17.97,
|
615 |
+
"grad_norm": 1.9405465126037598,
|
616 |
+
"learning_rate": 7.930555555555556e-06,
|
617 |
+
"loss": 0.1143,
|
618 |
+
"step": 1740
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 18.18,
|
622 |
+
"grad_norm": 1.8571505546569824,
|
623 |
+
"learning_rate": 7.791666666666667e-06,
|
624 |
+
"loss": 0.1197,
|
625 |
+
"step": 1760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 18.39,
|
629 |
+
"grad_norm": 1.8494367599487305,
|
630 |
+
"learning_rate": 7.652777777777778e-06,
|
631 |
+
"loss": 0.133,
|
632 |
+
"step": 1780
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 18.59,
|
636 |
+
"grad_norm": 1.8017449378967285,
|
637 |
+
"learning_rate": 7.51388888888889e-06,
|
638 |
+
"loss": 0.1036,
|
639 |
+
"step": 1800
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 18.8,
|
643 |
+
"grad_norm": 1.9734400510787964,
|
644 |
+
"learning_rate": 7.375000000000001e-06,
|
645 |
+
"loss": 0.1135,
|
646 |
+
"step": 1820
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 19.01,
|
650 |
+
"grad_norm": 1.88029944896698,
|
651 |
+
"learning_rate": 7.2361111111111115e-06,
|
652 |
+
"loss": 0.1159,
|
653 |
+
"step": 1840
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 19.21,
|
657 |
+
"grad_norm": 1.6627161502838135,
|
658 |
+
"learning_rate": 7.097222222222223e-06,
|
659 |
+
"loss": 0.1138,
|
660 |
+
"step": 1860
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 19.42,
|
664 |
+
"grad_norm": 1.9287075996398926,
|
665 |
+
"learning_rate": 6.958333333333333e-06,
|
666 |
+
"loss": 0.1154,
|
667 |
+
"step": 1880
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 19.63,
|
671 |
+
"grad_norm": 1.843787670135498,
|
672 |
+
"learning_rate": 6.819444444444445e-06,
|
673 |
+
"loss": 0.1052,
|
674 |
+
"step": 1900
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 19.83,
|
678 |
+
"grad_norm": 2.0632147789001465,
|
679 |
+
"learning_rate": 6.680555555555556e-06,
|
680 |
+
"loss": 0.1157,
|
681 |
+
"step": 1920
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 20.04,
|
685 |
+
"grad_norm": 1.6356507539749146,
|
686 |
+
"learning_rate": 6.541666666666667e-06,
|
687 |
+
"loss": 0.0993,
|
688 |
+
"step": 1940
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 20.25,
|
692 |
+
"grad_norm": 2.1572136878967285,
|
693 |
+
"learning_rate": 6.402777777777778e-06,
|
694 |
+
"loss": 0.0973,
|
695 |
+
"step": 1960
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 20.45,
|
699 |
+
"grad_norm": 1.834170937538147,
|
700 |
+
"learning_rate": 6.26388888888889e-06,
|
701 |
+
"loss": 0.0947,
|
702 |
+
"step": 1980
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 20.66,
|
706 |
+
"grad_norm": 1.80930495262146,
|
707 |
+
"learning_rate": 6.125000000000001e-06,
|
708 |
+
"loss": 0.1176,
|
709 |
+
"step": 2000
|
710 |
+
}
|
711 |
+
],
|
712 |
+
"logging_steps": 20,
|
713 |
+
"max_steps": 2880,
|
714 |
+
"num_input_tokens_seen": 0,
|
715 |
+
"num_train_epochs": 30,
|
716 |
+
"save_steps": 500,
|
717 |
+
"total_flos": 4.626131694005453e+17,
|
718 |
+
"train_batch_size": 1,
|
719 |
+
"trial_name": null,
|
720 |
+
"trial_params": null
|
721 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2014fae9041d0eac19c9a012e0f34b574e3f2d7eb6062981c160b8614ac655dd
|
3 |
+
size 4920
|
checkpoint-2500/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: baffo32/decapoda-research-llama-7B-hf
|
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 0.9.0
|
checkpoint-2500/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "baffo32/decapoda-research-llama-7B-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e68a2a41e015fdb101b63131310e222c4fb094f4a4297098a63c2f029b3951
|
3 |
+
size 16794200
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9663b125dbfbe90fd115ac708167a6547f2ab06e2df64fe622b83f9fced4a1c8
|
3 |
+
size 33662074
|
checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ba401189d3616e733f5a52e63075b81b5ec713af898e4ce563eb4e5d50da1b7
|
3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f828af5d55cd807daf6f7264f5d9538fceb56ec495d58765c74c3195249f34
|
3 |
+
size 1064
|
checkpoint-2500/trainer_state.json
ADDED
@@ -0,0 +1,896 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 25.823111684958036,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.21,
|
13 |
+
"grad_norm": 1.3856842517852783,
|
14 |
+
"learning_rate": 1.9868055555555558e-05,
|
15 |
+
"loss": 1.1287,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41,
|
20 |
+
"grad_norm": 0.4272608458995819,
|
21 |
+
"learning_rate": 1.9736111111111115e-05,
|
22 |
+
"loss": 1.0586,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.62,
|
27 |
+
"grad_norm": 0.4174883961677551,
|
28 |
+
"learning_rate": 1.9597222222222224e-05,
|
29 |
+
"loss": 1.0166,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.83,
|
34 |
+
"grad_norm": 0.35379958152770996,
|
35 |
+
"learning_rate": 1.9458333333333333e-05,
|
36 |
+
"loss": 0.8919,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.03,
|
41 |
+
"grad_norm": 0.3820742964744568,
|
42 |
+
"learning_rate": 1.9319444444444446e-05,
|
43 |
+
"loss": 0.7971,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.24,
|
48 |
+
"grad_norm": 0.34241142868995667,
|
49 |
+
"learning_rate": 1.918055555555556e-05,
|
50 |
+
"loss": 0.7466,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.45,
|
55 |
+
"grad_norm": 0.48230335116386414,
|
56 |
+
"learning_rate": 1.9041666666666668e-05,
|
57 |
+
"loss": 0.7468,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.65,
|
62 |
+
"grad_norm": 0.45057639479637146,
|
63 |
+
"learning_rate": 1.890277777777778e-05,
|
64 |
+
"loss": 0.7373,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.86,
|
69 |
+
"grad_norm": 0.43228989839553833,
|
70 |
+
"learning_rate": 1.876388888888889e-05,
|
71 |
+
"loss": 0.756,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.07,
|
76 |
+
"grad_norm": 0.460918664932251,
|
77 |
+
"learning_rate": 1.8625000000000002e-05,
|
78 |
+
"loss": 0.7186,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.27,
|
83 |
+
"grad_norm": 0.8221462368965149,
|
84 |
+
"learning_rate": 1.8486111111111115e-05,
|
85 |
+
"loss": 0.6772,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.48,
|
90 |
+
"grad_norm": 0.547721266746521,
|
91 |
+
"learning_rate": 1.8347222222222224e-05,
|
92 |
+
"loss": 0.6809,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.69,
|
97 |
+
"grad_norm": 0.6005927920341492,
|
98 |
+
"learning_rate": 1.8208333333333333e-05,
|
99 |
+
"loss": 0.6651,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.89,
|
104 |
+
"grad_norm": 0.7613247632980347,
|
105 |
+
"learning_rate": 1.8069444444444446e-05,
|
106 |
+
"loss": 0.641,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1,
|
111 |
+
"grad_norm": 0.668274462223053,
|
112 |
+
"learning_rate": 1.793055555555556e-05,
|
113 |
+
"loss": 0.6296,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.31,
|
118 |
+
"grad_norm": 0.6101451516151428,
|
119 |
+
"learning_rate": 1.7791666666666668e-05,
|
120 |
+
"loss": 0.6033,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.51,
|
125 |
+
"grad_norm": 0.8970944285392761,
|
126 |
+
"learning_rate": 1.765277777777778e-05,
|
127 |
+
"loss": 0.5939,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.72,
|
132 |
+
"grad_norm": 0.9417675137519836,
|
133 |
+
"learning_rate": 1.751388888888889e-05,
|
134 |
+
"loss": 0.5966,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.93,
|
139 |
+
"grad_norm": 1.3364688158035278,
|
140 |
+
"learning_rate": 1.7375000000000002e-05,
|
141 |
+
"loss": 0.5771,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.13,
|
146 |
+
"grad_norm": 0.7763314843177795,
|
147 |
+
"learning_rate": 1.7236111111111115e-05,
|
148 |
+
"loss": 0.5588,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.34,
|
153 |
+
"grad_norm": 1.156174659729004,
|
154 |
+
"learning_rate": 1.7097222222222224e-05,
|
155 |
+
"loss": 0.5571,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.54,
|
160 |
+
"grad_norm": 0.8457236886024475,
|
161 |
+
"learning_rate": 1.6958333333333333e-05,
|
162 |
+
"loss": 0.5431,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.75,
|
167 |
+
"grad_norm": 1.1372079849243164,
|
168 |
+
"learning_rate": 1.6819444444444446e-05,
|
169 |
+
"loss": 0.4839,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.96,
|
174 |
+
"grad_norm": 1.0457851886749268,
|
175 |
+
"learning_rate": 1.668055555555556e-05,
|
176 |
+
"loss": 0.5041,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.16,
|
181 |
+
"grad_norm": 1.1884819269180298,
|
182 |
+
"learning_rate": 1.6541666666666668e-05,
|
183 |
+
"loss": 0.468,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 5.37,
|
188 |
+
"grad_norm": 1.5204098224639893,
|
189 |
+
"learning_rate": 1.6402777777777777e-05,
|
190 |
+
"loss": 0.4778,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.58,
|
195 |
+
"grad_norm": 1.3218625783920288,
|
196 |
+
"learning_rate": 1.626388888888889e-05,
|
197 |
+
"loss": 0.4682,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.78,
|
202 |
+
"grad_norm": 1.2012380361557007,
|
203 |
+
"learning_rate": 1.6125000000000002e-05,
|
204 |
+
"loss": 0.4326,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 5.99,
|
209 |
+
"grad_norm": 1.4303064346313477,
|
210 |
+
"learning_rate": 1.5986111111111115e-05,
|
211 |
+
"loss": 0.4358,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 6.2,
|
216 |
+
"grad_norm": 1.4230263233184814,
|
217 |
+
"learning_rate": 1.5847222222222224e-05,
|
218 |
+
"loss": 0.4384,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 6.4,
|
223 |
+
"grad_norm": 1.5604521036148071,
|
224 |
+
"learning_rate": 1.5708333333333333e-05,
|
225 |
+
"loss": 0.3908,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.61,
|
230 |
+
"grad_norm": 1.7824558019638062,
|
231 |
+
"learning_rate": 1.5569444444444446e-05,
|
232 |
+
"loss": 0.4017,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.82,
|
237 |
+
"grad_norm": 1.4250575304031372,
|
238 |
+
"learning_rate": 1.543055555555556e-05,
|
239 |
+
"loss": 0.3759,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 7.02,
|
244 |
+
"grad_norm": 1.5560147762298584,
|
245 |
+
"learning_rate": 1.5291666666666668e-05,
|
246 |
+
"loss": 0.3869,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 7.23,
|
251 |
+
"grad_norm": 1.7027453184127808,
|
252 |
+
"learning_rate": 1.5152777777777779e-05,
|
253 |
+
"loss": 0.3591,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.44,
|
258 |
+
"grad_norm": 1.5872056484222412,
|
259 |
+
"learning_rate": 1.501388888888889e-05,
|
260 |
+
"loss": 0.3573,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.64,
|
265 |
+
"grad_norm": 1.5370341539382935,
|
266 |
+
"learning_rate": 1.4875000000000002e-05,
|
267 |
+
"loss": 0.3488,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.85,
|
272 |
+
"grad_norm": 1.853333830833435,
|
273 |
+
"learning_rate": 1.4736111111111113e-05,
|
274 |
+
"loss": 0.3416,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 8.06,
|
279 |
+
"grad_norm": 1.5671972036361694,
|
280 |
+
"learning_rate": 1.4597222222222223e-05,
|
281 |
+
"loss": 0.3282,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 8.26,
|
286 |
+
"grad_norm": 1.6593025922775269,
|
287 |
+
"learning_rate": 1.4458333333333334e-05,
|
288 |
+
"loss": 0.3112,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 8.47,
|
293 |
+
"grad_norm": 1.7826825380325317,
|
294 |
+
"learning_rate": 1.4319444444444446e-05,
|
295 |
+
"loss": 0.286,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 8.68,
|
300 |
+
"grad_norm": 1.5925076007843018,
|
301 |
+
"learning_rate": 1.4180555555555557e-05,
|
302 |
+
"loss": 0.3281,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.88,
|
307 |
+
"grad_norm": 1.7169785499572754,
|
308 |
+
"learning_rate": 1.4041666666666666e-05,
|
309 |
+
"loss": 0.3092,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 9.09,
|
314 |
+
"grad_norm": 1.8225599527359009,
|
315 |
+
"learning_rate": 1.3902777777777779e-05,
|
316 |
+
"loss": 0.2728,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 9.3,
|
321 |
+
"grad_norm": 2.113538980484009,
|
322 |
+
"learning_rate": 1.376388888888889e-05,
|
323 |
+
"loss": 0.2893,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 9.5,
|
328 |
+
"grad_norm": 2.0112457275390625,
|
329 |
+
"learning_rate": 1.3625e-05,
|
330 |
+
"loss": 0.277,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 9.71,
|
335 |
+
"grad_norm": 1.9079582691192627,
|
336 |
+
"learning_rate": 1.3486111111111113e-05,
|
337 |
+
"loss": 0.261,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.92,
|
342 |
+
"grad_norm": 1.793885350227356,
|
343 |
+
"learning_rate": 1.3347222222222223e-05,
|
344 |
+
"loss": 0.267,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 10.12,
|
349 |
+
"grad_norm": 1.770896315574646,
|
350 |
+
"learning_rate": 1.3208333333333334e-05,
|
351 |
+
"loss": 0.2719,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 10.33,
|
356 |
+
"grad_norm": 1.849857211112976,
|
357 |
+
"learning_rate": 1.3069444444444446e-05,
|
358 |
+
"loss": 0.2399,
|
359 |
+
"step": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 10.54,
|
363 |
+
"grad_norm": 1.8785293102264404,
|
364 |
+
"learning_rate": 1.2930555555555557e-05,
|
365 |
+
"loss": 0.2316,
|
366 |
+
"step": 1020
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 10.74,
|
370 |
+
"grad_norm": 1.7189656496047974,
|
371 |
+
"learning_rate": 1.2791666666666666e-05,
|
372 |
+
"loss": 0.243,
|
373 |
+
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 10.95,
|
377 |
+
"grad_norm": 1.6181199550628662,
|
378 |
+
"learning_rate": 1.2652777777777779e-05,
|
379 |
+
"loss": 0.2347,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 11.16,
|
384 |
+
"grad_norm": 2.0756866931915283,
|
385 |
+
"learning_rate": 1.251388888888889e-05,
|
386 |
+
"loss": 0.2407,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 11.36,
|
391 |
+
"grad_norm": 1.9992755651474,
|
392 |
+
"learning_rate": 1.2375000000000001e-05,
|
393 |
+
"loss": 0.2205,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 11.57,
|
398 |
+
"grad_norm": 2.19657039642334,
|
399 |
+
"learning_rate": 1.2236111111111114e-05,
|
400 |
+
"loss": 0.1992,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 11.78,
|
405 |
+
"grad_norm": 1.8114335536956787,
|
406 |
+
"learning_rate": 1.2097222222222223e-05,
|
407 |
+
"loss": 0.219,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 11.98,
|
412 |
+
"grad_norm": 1.841556429862976,
|
413 |
+
"learning_rate": 1.1958333333333334e-05,
|
414 |
+
"loss": 0.2051,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 12.19,
|
419 |
+
"grad_norm": 1.9361953735351562,
|
420 |
+
"learning_rate": 1.1819444444444446e-05,
|
421 |
+
"loss": 0.2025,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 12.4,
|
426 |
+
"grad_norm": 1.841424584388733,
|
427 |
+
"learning_rate": 1.1680555555555557e-05,
|
428 |
+
"loss": 0.2109,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 12.6,
|
433 |
+
"grad_norm": 2.569114923477173,
|
434 |
+
"learning_rate": 1.1541666666666667e-05,
|
435 |
+
"loss": 0.1933,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 12.81,
|
440 |
+
"grad_norm": 1.8263764381408691,
|
441 |
+
"learning_rate": 1.1402777777777777e-05,
|
442 |
+
"loss": 0.1814,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 13.01,
|
447 |
+
"grad_norm": 1.7250192165374756,
|
448 |
+
"learning_rate": 1.126388888888889e-05,
|
449 |
+
"loss": 0.1842,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 13.22,
|
454 |
+
"grad_norm": 1.8750269412994385,
|
455 |
+
"learning_rate": 1.1125000000000001e-05,
|
456 |
+
"loss": 0.1803,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 13.43,
|
461 |
+
"grad_norm": 2.2998244762420654,
|
462 |
+
"learning_rate": 1.0986111111111114e-05,
|
463 |
+
"loss": 0.167,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 13.63,
|
468 |
+
"grad_norm": 1.663015604019165,
|
469 |
+
"learning_rate": 1.0847222222222223e-05,
|
470 |
+
"loss": 0.1723,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 13.84,
|
475 |
+
"grad_norm": 2.0710666179656982,
|
476 |
+
"learning_rate": 1.0708333333333334e-05,
|
477 |
+
"loss": 0.1895,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 14.05,
|
482 |
+
"grad_norm": 1.8963505029678345,
|
483 |
+
"learning_rate": 1.0569444444444445e-05,
|
484 |
+
"loss": 0.1783,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 14.25,
|
489 |
+
"grad_norm": 2.3760714530944824,
|
490 |
+
"learning_rate": 1.0430555555555557e-05,
|
491 |
+
"loss": 0.1674,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 14.46,
|
496 |
+
"grad_norm": 1.8337997198104858,
|
497 |
+
"learning_rate": 1.0291666666666667e-05,
|
498 |
+
"loss": 0.1677,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 14.67,
|
503 |
+
"grad_norm": 1.8879417181015015,
|
504 |
+
"learning_rate": 1.0152777777777778e-05,
|
505 |
+
"loss": 0.1602,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 14.87,
|
510 |
+
"grad_norm": 1.9163988828659058,
|
511 |
+
"learning_rate": 1.001388888888889e-05,
|
512 |
+
"loss": 0.1536,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 15.08,
|
517 |
+
"grad_norm": 1.772133469581604,
|
518 |
+
"learning_rate": 9.875000000000001e-06,
|
519 |
+
"loss": 0.1422,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 15.29,
|
524 |
+
"grad_norm": 2.173783540725708,
|
525 |
+
"learning_rate": 9.736111111111112e-06,
|
526 |
+
"loss": 0.1634,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 15.49,
|
531 |
+
"grad_norm": 2.1147613525390625,
|
532 |
+
"learning_rate": 9.597222222222223e-06,
|
533 |
+
"loss": 0.14,
|
534 |
+
"step": 1500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 15.7,
|
538 |
+
"grad_norm": 2.0401387214660645,
|
539 |
+
"learning_rate": 9.458333333333334e-06,
|
540 |
+
"loss": 0.1498,
|
541 |
+
"step": 1520
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 15.91,
|
545 |
+
"grad_norm": 2.0865604877471924,
|
546 |
+
"learning_rate": 9.319444444444445e-06,
|
547 |
+
"loss": 0.1395,
|
548 |
+
"step": 1540
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 16.11,
|
552 |
+
"grad_norm": 1.884482502937317,
|
553 |
+
"learning_rate": 9.180555555555556e-06,
|
554 |
+
"loss": 0.1461,
|
555 |
+
"step": 1560
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 16.32,
|
559 |
+
"grad_norm": 2.2012784481048584,
|
560 |
+
"learning_rate": 9.041666666666667e-06,
|
561 |
+
"loss": 0.1297,
|
562 |
+
"step": 1580
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 16.53,
|
566 |
+
"grad_norm": 2.0317113399505615,
|
567 |
+
"learning_rate": 8.902777777777778e-06,
|
568 |
+
"loss": 0.15,
|
569 |
+
"step": 1600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 16.73,
|
573 |
+
"grad_norm": 1.4792850017547607,
|
574 |
+
"learning_rate": 8.76388888888889e-06,
|
575 |
+
"loss": 0.1359,
|
576 |
+
"step": 1620
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 16.94,
|
580 |
+
"grad_norm": 2.3025472164154053,
|
581 |
+
"learning_rate": 8.625000000000001e-06,
|
582 |
+
"loss": 0.1298,
|
583 |
+
"step": 1640
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 17.15,
|
587 |
+
"grad_norm": 1.8987499475479126,
|
588 |
+
"learning_rate": 8.486111111111112e-06,
|
589 |
+
"loss": 0.1287,
|
590 |
+
"step": 1660
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 17.35,
|
594 |
+
"grad_norm": 3.6023619174957275,
|
595 |
+
"learning_rate": 8.347222222222223e-06,
|
596 |
+
"loss": 0.1584,
|
597 |
+
"step": 1680
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 17.56,
|
601 |
+
"grad_norm": 1.6749480962753296,
|
602 |
+
"learning_rate": 8.208333333333334e-06,
|
603 |
+
"loss": 0.1071,
|
604 |
+
"step": 1700
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 17.77,
|
608 |
+
"grad_norm": 1.894116759300232,
|
609 |
+
"learning_rate": 8.069444444444445e-06,
|
610 |
+
"loss": 0.1233,
|
611 |
+
"step": 1720
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 17.97,
|
615 |
+
"grad_norm": 1.9405465126037598,
|
616 |
+
"learning_rate": 7.930555555555556e-06,
|
617 |
+
"loss": 0.1143,
|
618 |
+
"step": 1740
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 18.18,
|
622 |
+
"grad_norm": 1.8571505546569824,
|
623 |
+
"learning_rate": 7.791666666666667e-06,
|
624 |
+
"loss": 0.1197,
|
625 |
+
"step": 1760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 18.39,
|
629 |
+
"grad_norm": 1.8494367599487305,
|
630 |
+
"learning_rate": 7.652777777777778e-06,
|
631 |
+
"loss": 0.133,
|
632 |
+
"step": 1780
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 18.59,
|
636 |
+
"grad_norm": 1.8017449378967285,
|
637 |
+
"learning_rate": 7.51388888888889e-06,
|
638 |
+
"loss": 0.1036,
|
639 |
+
"step": 1800
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 18.8,
|
643 |
+
"grad_norm": 1.9734400510787964,
|
644 |
+
"learning_rate": 7.375000000000001e-06,
|
645 |
+
"loss": 0.1135,
|
646 |
+
"step": 1820
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 19.01,
|
650 |
+
"grad_norm": 1.88029944896698,
|
651 |
+
"learning_rate": 7.2361111111111115e-06,
|
652 |
+
"loss": 0.1159,
|
653 |
+
"step": 1840
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 19.21,
|
657 |
+
"grad_norm": 1.6627161502838135,
|
658 |
+
"learning_rate": 7.097222222222223e-06,
|
659 |
+
"loss": 0.1138,
|
660 |
+
"step": 1860
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 19.42,
|
664 |
+
"grad_norm": 1.9287075996398926,
|
665 |
+
"learning_rate": 6.958333333333333e-06,
|
666 |
+
"loss": 0.1154,
|
667 |
+
"step": 1880
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 19.63,
|
671 |
+
"grad_norm": 1.843787670135498,
|
672 |
+
"learning_rate": 6.819444444444445e-06,
|
673 |
+
"loss": 0.1052,
|
674 |
+
"step": 1900
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 19.83,
|
678 |
+
"grad_norm": 2.0632147789001465,
|
679 |
+
"learning_rate": 6.680555555555556e-06,
|
680 |
+
"loss": 0.1157,
|
681 |
+
"step": 1920
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 20.04,
|
685 |
+
"grad_norm": 1.6356507539749146,
|
686 |
+
"learning_rate": 6.541666666666667e-06,
|
687 |
+
"loss": 0.0993,
|
688 |
+
"step": 1940
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 20.25,
|
692 |
+
"grad_norm": 2.1572136878967285,
|
693 |
+
"learning_rate": 6.402777777777778e-06,
|
694 |
+
"loss": 0.0973,
|
695 |
+
"step": 1960
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 20.45,
|
699 |
+
"grad_norm": 1.834170937538147,
|
700 |
+
"learning_rate": 6.26388888888889e-06,
|
701 |
+
"loss": 0.0947,
|
702 |
+
"step": 1980
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 20.66,
|
706 |
+
"grad_norm": 1.80930495262146,
|
707 |
+
"learning_rate": 6.125000000000001e-06,
|
708 |
+
"loss": 0.1176,
|
709 |
+
"step": 2000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 20.87,
|
713 |
+
"grad_norm": 1.6790763139724731,
|
714 |
+
"learning_rate": 5.986111111111112e-06,
|
715 |
+
"loss": 0.0997,
|
716 |
+
"step": 2020
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 21.07,
|
720 |
+
"grad_norm": 1.771209478378296,
|
721 |
+
"learning_rate": 5.847222222222223e-06,
|
722 |
+
"loss": 0.1131,
|
723 |
+
"step": 2040
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 21.28,
|
727 |
+
"grad_norm": 1.8562020063400269,
|
728 |
+
"learning_rate": 5.7083333333333335e-06,
|
729 |
+
"loss": 0.1014,
|
730 |
+
"step": 2060
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 21.48,
|
734 |
+
"grad_norm": 2.914065361022949,
|
735 |
+
"learning_rate": 5.569444444444445e-06,
|
736 |
+
"loss": 0.1143,
|
737 |
+
"step": 2080
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 21.69,
|
741 |
+
"grad_norm": 1.7524240016937256,
|
742 |
+
"learning_rate": 5.430555555555555e-06,
|
743 |
+
"loss": 0.0931,
|
744 |
+
"step": 2100
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 21.9,
|
748 |
+
"grad_norm": 2.364281415939331,
|
749 |
+
"learning_rate": 5.291666666666667e-06,
|
750 |
+
"loss": 0.0869,
|
751 |
+
"step": 2120
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 22.1,
|
755 |
+
"grad_norm": 1.8760323524475098,
|
756 |
+
"learning_rate": 5.152777777777778e-06,
|
757 |
+
"loss": 0.0933,
|
758 |
+
"step": 2140
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 22.31,
|
762 |
+
"grad_norm": 1.855651617050171,
|
763 |
+
"learning_rate": 5.013888888888889e-06,
|
764 |
+
"loss": 0.0911,
|
765 |
+
"step": 2160
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 22.52,
|
769 |
+
"grad_norm": 2.1004161834716797,
|
770 |
+
"learning_rate": 4.875e-06,
|
771 |
+
"loss": 0.0941,
|
772 |
+
"step": 2180
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 22.72,
|
776 |
+
"grad_norm": 1.5337902307510376,
|
777 |
+
"learning_rate": 4.736111111111112e-06,
|
778 |
+
"loss": 0.1018,
|
779 |
+
"step": 2200
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 22.93,
|
783 |
+
"grad_norm": 1.7602789402008057,
|
784 |
+
"learning_rate": 4.597222222222223e-06,
|
785 |
+
"loss": 0.0908,
|
786 |
+
"step": 2220
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 23.14,
|
790 |
+
"grad_norm": 1.9307445287704468,
|
791 |
+
"learning_rate": 4.4583333333333336e-06,
|
792 |
+
"loss": 0.0888,
|
793 |
+
"step": 2240
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 23.34,
|
797 |
+
"grad_norm": 1.6600220203399658,
|
798 |
+
"learning_rate": 4.319444444444445e-06,
|
799 |
+
"loss": 0.0836,
|
800 |
+
"step": 2260
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 23.55,
|
804 |
+
"grad_norm": 2.088109254837036,
|
805 |
+
"learning_rate": 4.180555555555556e-06,
|
806 |
+
"loss": 0.0909,
|
807 |
+
"step": 2280
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 23.76,
|
811 |
+
"grad_norm": 1.643743872642517,
|
812 |
+
"learning_rate": 4.041666666666667e-06,
|
813 |
+
"loss": 0.0887,
|
814 |
+
"step": 2300
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 23.96,
|
818 |
+
"grad_norm": 2.0399911403656006,
|
819 |
+
"learning_rate": 3.902777777777778e-06,
|
820 |
+
"loss": 0.0912,
|
821 |
+
"step": 2320
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 24.17,
|
825 |
+
"grad_norm": 2.045422315597534,
|
826 |
+
"learning_rate": 3.763888888888889e-06,
|
827 |
+
"loss": 0.0935,
|
828 |
+
"step": 2340
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 24.38,
|
832 |
+
"grad_norm": 1.6552656888961792,
|
833 |
+
"learning_rate": 3.625e-06,
|
834 |
+
"loss": 0.0877,
|
835 |
+
"step": 2360
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 24.58,
|
839 |
+
"grad_norm": 2.5343992710113525,
|
840 |
+
"learning_rate": 3.4861111111111114e-06,
|
841 |
+
"loss": 0.0887,
|
842 |
+
"step": 2380
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 24.79,
|
846 |
+
"grad_norm": 2.4031288623809814,
|
847 |
+
"learning_rate": 3.3472222222222223e-06,
|
848 |
+
"loss": 0.0799,
|
849 |
+
"step": 2400
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 25.0,
|
853 |
+
"grad_norm": 1.4991315603256226,
|
854 |
+
"learning_rate": 3.2083333333333337e-06,
|
855 |
+
"loss": 0.0807,
|
856 |
+
"step": 2420
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 25.2,
|
860 |
+
"grad_norm": 1.7015751600265503,
|
861 |
+
"learning_rate": 3.069444444444445e-06,
|
862 |
+
"loss": 0.0742,
|
863 |
+
"step": 2440
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 25.41,
|
867 |
+
"grad_norm": 1.8738179206848145,
|
868 |
+
"learning_rate": 2.930555555555556e-06,
|
869 |
+
"loss": 0.0849,
|
870 |
+
"step": 2460
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 25.62,
|
874 |
+
"grad_norm": 1.4357935190200806,
|
875 |
+
"learning_rate": 2.791666666666667e-06,
|
876 |
+
"loss": 0.0861,
|
877 |
+
"step": 2480
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 25.82,
|
881 |
+
"grad_norm": 1.8066306114196777,
|
882 |
+
"learning_rate": 2.652777777777778e-06,
|
883 |
+
"loss": 0.0814,
|
884 |
+
"step": 2500
|
885 |
+
}
|
886 |
+
],
|
887 |
+
"logging_steps": 20,
|
888 |
+
"max_steps": 2880,
|
889 |
+
"num_input_tokens_seen": 0,
|
890 |
+
"num_train_epochs": 30,
|
891 |
+
"save_steps": 500,
|
892 |
+
"total_flos": 5.782119562320691e+17,
|
893 |
+
"train_batch_size": 1,
|
894 |
+
"trial_name": null,
|
895 |
+
"trial_params": null
|
896 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2014fae9041d0eac19c9a012e0f34b574e3f2d7eb6062981c160b8614ac655dd
|
3 |
+
size 4920
|
checkpoint-500/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: baffo32/decapoda-research-llama-7B-hf
|
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 0.9.0
|
checkpoint-500/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "baffo32/decapoda-research-llama-7B-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
checkpoint-500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be7032ca1e4a50a5843aca92fa52d3ce879aa2b0bb933dd8845e8a99a62a55d9
|
3 |
+
size 16794200
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c619c14744eb600dba5d98a633ab23ee1ec43022382cdce341acec08b58d1b1
|
3 |
+
size 33662074
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2db90426a4279b1161e4ca7b8c63e6287fe911cac12ad42a4cba8dd79de55479
|
3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:007284b2011f964240f5a9b3d3e08228f7b2eb33f1214eb62e7c07ec775e17cb
|
3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.1646223369916076,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.21,
|
13 |
+
"grad_norm": 1.3856842517852783,
|
14 |
+
"learning_rate": 1.9868055555555558e-05,
|
15 |
+
"loss": 1.1287,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41,
|
20 |
+
"grad_norm": 0.4272608458995819,
|
21 |
+
"learning_rate": 1.9736111111111115e-05,
|
22 |
+
"loss": 1.0586,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.62,
|
27 |
+
"grad_norm": 0.4174883961677551,
|
28 |
+
"learning_rate": 1.9597222222222224e-05,
|
29 |
+
"loss": 1.0166,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.83,
|
34 |
+
"grad_norm": 0.35379958152770996,
|
35 |
+
"learning_rate": 1.9458333333333333e-05,
|
36 |
+
"loss": 0.8919,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.03,
|
41 |
+
"grad_norm": 0.3820742964744568,
|
42 |
+
"learning_rate": 1.9319444444444446e-05,
|
43 |
+
"loss": 0.7971,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.24,
|
48 |
+
"grad_norm": 0.34241142868995667,
|
49 |
+
"learning_rate": 1.918055555555556e-05,
|
50 |
+
"loss": 0.7466,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.45,
|
55 |
+
"grad_norm": 0.48230335116386414,
|
56 |
+
"learning_rate": 1.9041666666666668e-05,
|
57 |
+
"loss": 0.7468,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.65,
|
62 |
+
"grad_norm": 0.45057639479637146,
|
63 |
+
"learning_rate": 1.890277777777778e-05,
|
64 |
+
"loss": 0.7373,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.86,
|
69 |
+
"grad_norm": 0.43228989839553833,
|
70 |
+
"learning_rate": 1.876388888888889e-05,
|
71 |
+
"loss": 0.756,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.07,
|
76 |
+
"grad_norm": 0.460918664932251,
|
77 |
+
"learning_rate": 1.8625000000000002e-05,
|
78 |
+
"loss": 0.7186,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.27,
|
83 |
+
"grad_norm": 0.8221462368965149,
|
84 |
+
"learning_rate": 1.8486111111111115e-05,
|
85 |
+
"loss": 0.6772,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.48,
|
90 |
+
"grad_norm": 0.547721266746521,
|
91 |
+
"learning_rate": 1.8347222222222224e-05,
|
92 |
+
"loss": 0.6809,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.69,
|
97 |
+
"grad_norm": 0.6005927920341492,
|
98 |
+
"learning_rate": 1.8208333333333333e-05,
|
99 |
+
"loss": 0.6651,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.89,
|
104 |
+
"grad_norm": 0.7613247632980347,
|
105 |
+
"learning_rate": 1.8069444444444446e-05,
|
106 |
+
"loss": 0.641,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1,
|
111 |
+
"grad_norm": 0.668274462223053,
|
112 |
+
"learning_rate": 1.793055555555556e-05,
|
113 |
+
"loss": 0.6296,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.31,
|
118 |
+
"grad_norm": 0.6101451516151428,
|
119 |
+
"learning_rate": 1.7791666666666668e-05,
|
120 |
+
"loss": 0.6033,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.51,
|
125 |
+
"grad_norm": 0.8970944285392761,
|
126 |
+
"learning_rate": 1.765277777777778e-05,
|
127 |
+
"loss": 0.5939,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.72,
|
132 |
+
"grad_norm": 0.9417675137519836,
|
133 |
+
"learning_rate": 1.751388888888889e-05,
|
134 |
+
"loss": 0.5966,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.93,
|
139 |
+
"grad_norm": 1.3364688158035278,
|
140 |
+
"learning_rate": 1.7375000000000002e-05,
|
141 |
+
"loss": 0.5771,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.13,
|
146 |
+
"grad_norm": 0.7763314843177795,
|
147 |
+
"learning_rate": 1.7236111111111115e-05,
|
148 |
+
"loss": 0.5588,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.34,
|
153 |
+
"grad_norm": 1.156174659729004,
|
154 |
+
"learning_rate": 1.7097222222222224e-05,
|
155 |
+
"loss": 0.5571,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.54,
|
160 |
+
"grad_norm": 0.8457236886024475,
|
161 |
+
"learning_rate": 1.6958333333333333e-05,
|
162 |
+
"loss": 0.5431,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.75,
|
167 |
+
"grad_norm": 1.1372079849243164,
|
168 |
+
"learning_rate": 1.6819444444444446e-05,
|
169 |
+
"loss": 0.4839,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.96,
|
174 |
+
"grad_norm": 1.0457851886749268,
|
175 |
+
"learning_rate": 1.668055555555556e-05,
|
176 |
+
"loss": 0.5041,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.16,
|
181 |
+
"grad_norm": 1.1884819269180298,
|
182 |
+
"learning_rate": 1.6541666666666668e-05,
|
183 |
+
"loss": 0.468,
|
184 |
+
"step": 500
|
185 |
+
}
|
186 |
+
],
|
187 |
+
"logging_steps": 20,
|
188 |
+
"max_steps": 2880,
|
189 |
+
"num_input_tokens_seen": 0,
|
190 |
+
"num_train_epochs": 30,
|
191 |
+
"save_steps": 500,
|
192 |
+
"total_flos": 1.1559398685499392e+17,
|
193 |
+
"train_batch_size": 1,
|
194 |
+
"trial_name": null,
|
195 |
+
"trial_params": null
|
196 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2014fae9041d0eac19c9a012e0f34b574e3f2d7eb6062981c160b8614ac655dd
|
3 |
+
size 4920
|
runs/Mar04_05-55-16_n6vlfege1s/events.out.tfevents.1709531717.n6vlfege1s.478.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d6d09b5cb2eaa480907270e8080df076105e0cf326b4ce317291e1d36e343a
|
3 |
+
size 35822
|