First model version
Browse files- README.md +202 -1
- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- checkpoint-1000/README.md +204 -0
- checkpoint-1000/adapter_config.json +27 -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 +321 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/README.md +204 -0
- checkpoint-1500/adapter_config.json +27 -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 +471 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/README.md +204 -0
- checkpoint-2000/adapter_config.json +27 -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 +621 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/README.md +204 -0
- checkpoint-2500/adapter_config.json +27 -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 +771 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-500/README.md +204 -0
- checkpoint-500/adapter_config.json +27 -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 +171 -0
- checkpoint-500/training_args.bin +3 -0
- runs/Feb21_12-28-15_nlembhrwvg/events.out.tfevents.1708518496.nlembhrwvg.3321.0 +3 -0
README.md
CHANGED
@@ -1,3 +1,204 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38fcb0c0cf2b5bd87f5a86ad197eb49decdea2a50aea40a865f369c77d995725
|
3 |
+
size 16794200
|
checkpoint-1000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-1000/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fc5518035e8aa44feddfbf4c1c57dbcc68de8f5e581e901370460ef4a4a53e0
|
3 |
+
size 16794200
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28e0b9d329968adcb42229721e696c073aeaccb9961c5a513bebe28f3e54fb85
|
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:f5ad943695e09dcf5db89819e886b20b83210face7bf7094ec5d6794769cb65f
|
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 +1,321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"learning_rate": 1.9875000000000002e-05,
|
14 |
+
"loss": 1.9446,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.41,
|
19 |
+
"learning_rate": 1.9736111111111115e-05,
|
20 |
+
"loss": 1.7941,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.62,
|
25 |
+
"learning_rate": 1.9597222222222224e-05,
|
26 |
+
"loss": 1.5361,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.83,
|
31 |
+
"learning_rate": 1.9458333333333333e-05,
|
32 |
+
"loss": 1.1041,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.03,
|
37 |
+
"learning_rate": 1.9319444444444446e-05,
|
38 |
+
"loss": 0.6053,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.24,
|
43 |
+
"learning_rate": 1.918055555555556e-05,
|
44 |
+
"loss": 0.4088,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.45,
|
49 |
+
"learning_rate": 1.9041666666666668e-05,
|
50 |
+
"loss": 0.3813,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.65,
|
55 |
+
"learning_rate": 1.890277777777778e-05,
|
56 |
+
"loss": 0.3733,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.86,
|
61 |
+
"learning_rate": 1.876388888888889e-05,
|
62 |
+
"loss": 0.3678,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.07,
|
67 |
+
"learning_rate": 1.8625000000000002e-05,
|
68 |
+
"loss": 0.3604,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.27,
|
73 |
+
"learning_rate": 1.8486111111111115e-05,
|
74 |
+
"loss": 0.3368,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.48,
|
79 |
+
"learning_rate": 1.8347222222222224e-05,
|
80 |
+
"loss": 0.3356,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.69,
|
85 |
+
"learning_rate": 1.8208333333333333e-05,
|
86 |
+
"loss": 0.3439,
|
87 |
+
"step": 260
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.89,
|
91 |
+
"learning_rate": 1.8069444444444446e-05,
|
92 |
+
"loss": 0.3277,
|
93 |
+
"step": 280
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.1,
|
97 |
+
"learning_rate": 1.793055555555556e-05,
|
98 |
+
"loss": 0.3288,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.31,
|
103 |
+
"learning_rate": 1.7791666666666668e-05,
|
104 |
+
"loss": 0.3227,
|
105 |
+
"step": 320
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.51,
|
109 |
+
"learning_rate": 1.765277777777778e-05,
|
110 |
+
"loss": 0.3213,
|
111 |
+
"step": 340
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.72,
|
115 |
+
"learning_rate": 1.751388888888889e-05,
|
116 |
+
"loss": 0.3128,
|
117 |
+
"step": 360
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 3.93,
|
121 |
+
"learning_rate": 1.7375000000000002e-05,
|
122 |
+
"loss": 0.3071,
|
123 |
+
"step": 380
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.13,
|
127 |
+
"learning_rate": 1.7236111111111115e-05,
|
128 |
+
"loss": 0.3022,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.34,
|
133 |
+
"learning_rate": 1.7097222222222224e-05,
|
134 |
+
"loss": 0.2968,
|
135 |
+
"step": 420
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.54,
|
139 |
+
"learning_rate": 1.6958333333333333e-05,
|
140 |
+
"loss": 0.3023,
|
141 |
+
"step": 440
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 4.75,
|
145 |
+
"learning_rate": 1.6819444444444446e-05,
|
146 |
+
"loss": 0.2889,
|
147 |
+
"step": 460
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.96,
|
151 |
+
"learning_rate": 1.668055555555556e-05,
|
152 |
+
"loss": 0.2763,
|
153 |
+
"step": 480
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 5.16,
|
157 |
+
"learning_rate": 1.6541666666666668e-05,
|
158 |
+
"loss": 0.2778,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 5.37,
|
163 |
+
"learning_rate": 1.6402777777777777e-05,
|
164 |
+
"loss": 0.2689,
|
165 |
+
"step": 520
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 5.58,
|
169 |
+
"learning_rate": 1.626388888888889e-05,
|
170 |
+
"loss": 0.2732,
|
171 |
+
"step": 540
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 5.78,
|
175 |
+
"learning_rate": 1.6125000000000002e-05,
|
176 |
+
"loss": 0.2604,
|
177 |
+
"step": 560
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.99,
|
181 |
+
"learning_rate": 1.5986111111111115e-05,
|
182 |
+
"loss": 0.2608,
|
183 |
+
"step": 580
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 6.2,
|
187 |
+
"learning_rate": 1.5847222222222224e-05,
|
188 |
+
"loss": 0.2356,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 6.4,
|
193 |
+
"learning_rate": 1.5708333333333333e-05,
|
194 |
+
"loss": 0.2414,
|
195 |
+
"step": 620
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 6.61,
|
199 |
+
"learning_rate": 1.5569444444444446e-05,
|
200 |
+
"loss": 0.2339,
|
201 |
+
"step": 640
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 6.82,
|
205 |
+
"learning_rate": 1.543055555555556e-05,
|
206 |
+
"loss": 0.2394,
|
207 |
+
"step": 660
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 7.02,
|
211 |
+
"learning_rate": 1.5291666666666668e-05,
|
212 |
+
"loss": 0.223,
|
213 |
+
"step": 680
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 7.23,
|
217 |
+
"learning_rate": 1.5152777777777779e-05,
|
218 |
+
"loss": 0.2155,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 7.44,
|
223 |
+
"learning_rate": 1.501388888888889e-05,
|
224 |
+
"loss": 0.2099,
|
225 |
+
"step": 720
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 7.64,
|
229 |
+
"learning_rate": 1.4875000000000002e-05,
|
230 |
+
"loss": 0.2041,
|
231 |
+
"step": 740
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 7.85,
|
235 |
+
"learning_rate": 1.4736111111111113e-05,
|
236 |
+
"loss": 0.2067,
|
237 |
+
"step": 760
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 8.06,
|
241 |
+
"learning_rate": 1.4597222222222223e-05,
|
242 |
+
"loss": 0.193,
|
243 |
+
"step": 780
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 8.26,
|
247 |
+
"learning_rate": 1.4458333333333334e-05,
|
248 |
+
"loss": 0.1802,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 8.47,
|
253 |
+
"learning_rate": 1.4319444444444446e-05,
|
254 |
+
"loss": 0.1828,
|
255 |
+
"step": 820
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 8.68,
|
259 |
+
"learning_rate": 1.4180555555555557e-05,
|
260 |
+
"loss": 0.1754,
|
261 |
+
"step": 840
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 8.88,
|
265 |
+
"learning_rate": 1.4041666666666666e-05,
|
266 |
+
"loss": 0.1745,
|
267 |
+
"step": 860
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 9.09,
|
271 |
+
"learning_rate": 1.3902777777777779e-05,
|
272 |
+
"loss": 0.1692,
|
273 |
+
"step": 880
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 9.3,
|
277 |
+
"learning_rate": 1.376388888888889e-05,
|
278 |
+
"loss": 0.1648,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 9.5,
|
283 |
+
"learning_rate": 1.3625e-05,
|
284 |
+
"loss": 0.1463,
|
285 |
+
"step": 920
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 9.71,
|
289 |
+
"learning_rate": 1.3486111111111113e-05,
|
290 |
+
"loss": 0.1525,
|
291 |
+
"step": 940
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 9.92,
|
295 |
+
"learning_rate": 1.3347222222222223e-05,
|
296 |
+
"loss": 0.1458,
|
297 |
+
"step": 960
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 10.12,
|
301 |
+
"learning_rate": 1.3208333333333334e-05,
|
302 |
+
"loss": 0.137,
|
303 |
+
"step": 980
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 10.33,
|
307 |
+
"learning_rate": 1.3069444444444446e-05,
|
308 |
+
"loss": 0.1318,
|
309 |
+
"step": 1000
|
310 |
+
}
|
311 |
+
],
|
312 |
+
"logging_steps": 20,
|
313 |
+
"max_steps": 2880,
|
314 |
+
"num_input_tokens_seen": 0,
|
315 |
+
"num_train_epochs": 30,
|
316 |
+
"save_steps": 500,
|
317 |
+
"total_flos": 3.168717993764045e+17,
|
318 |
+
"train_batch_size": 1,
|
319 |
+
"trial_name": null,
|
320 |
+
"trial_params": null
|
321 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687ee61d860f794218b437b86ef3d4e7d89241cf9246f5eee16a51278e5f8b65
|
3 |
+
size 4728
|
checkpoint-1500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-1500/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66b2439bb685db6956c69d2f335b5ba7c01c605f2f4ad87146dbf2b891716001
|
3 |
+
size 16794200
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8fc5592d1aeea5adf47e6014d214b136339f323499dce79d07c3640b110454d
|
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:f84b46eeca1b5376f343e8a268ddca89fdff53a6b4f0532d24c5e016c897f921
|
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 +1,471 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"learning_rate": 1.9875000000000002e-05,
|
14 |
+
"loss": 1.9446,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.41,
|
19 |
+
"learning_rate": 1.9736111111111115e-05,
|
20 |
+
"loss": 1.7941,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.62,
|
25 |
+
"learning_rate": 1.9597222222222224e-05,
|
26 |
+
"loss": 1.5361,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.83,
|
31 |
+
"learning_rate": 1.9458333333333333e-05,
|
32 |
+
"loss": 1.1041,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.03,
|
37 |
+
"learning_rate": 1.9319444444444446e-05,
|
38 |
+
"loss": 0.6053,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.24,
|
43 |
+
"learning_rate": 1.918055555555556e-05,
|
44 |
+
"loss": 0.4088,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.45,
|
49 |
+
"learning_rate": 1.9041666666666668e-05,
|
50 |
+
"loss": 0.3813,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.65,
|
55 |
+
"learning_rate": 1.890277777777778e-05,
|
56 |
+
"loss": 0.3733,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.86,
|
61 |
+
"learning_rate": 1.876388888888889e-05,
|
62 |
+
"loss": 0.3678,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.07,
|
67 |
+
"learning_rate": 1.8625000000000002e-05,
|
68 |
+
"loss": 0.3604,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.27,
|
73 |
+
"learning_rate": 1.8486111111111115e-05,
|
74 |
+
"loss": 0.3368,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.48,
|
79 |
+
"learning_rate": 1.8347222222222224e-05,
|
80 |
+
"loss": 0.3356,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.69,
|
85 |
+
"learning_rate": 1.8208333333333333e-05,
|
86 |
+
"loss": 0.3439,
|
87 |
+
"step": 260
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.89,
|
91 |
+
"learning_rate": 1.8069444444444446e-05,
|
92 |
+
"loss": 0.3277,
|
93 |
+
"step": 280
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.1,
|
97 |
+
"learning_rate": 1.793055555555556e-05,
|
98 |
+
"loss": 0.3288,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.31,
|
103 |
+
"learning_rate": 1.7791666666666668e-05,
|
104 |
+
"loss": 0.3227,
|
105 |
+
"step": 320
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.51,
|
109 |
+
"learning_rate": 1.765277777777778e-05,
|
110 |
+
"loss": 0.3213,
|
111 |
+
"step": 340
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.72,
|
115 |
+
"learning_rate": 1.751388888888889e-05,
|
116 |
+
"loss": 0.3128,
|
117 |
+
"step": 360
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 3.93,
|
121 |
+
"learning_rate": 1.7375000000000002e-05,
|
122 |
+
"loss": 0.3071,
|
123 |
+
"step": 380
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.13,
|
127 |
+
"learning_rate": 1.7236111111111115e-05,
|
128 |
+
"loss": 0.3022,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.34,
|
133 |
+
"learning_rate": 1.7097222222222224e-05,
|
134 |
+
"loss": 0.2968,
|
135 |
+
"step": 420
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.54,
|
139 |
+
"learning_rate": 1.6958333333333333e-05,
|
140 |
+
"loss": 0.3023,
|
141 |
+
"step": 440
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 4.75,
|
145 |
+
"learning_rate": 1.6819444444444446e-05,
|
146 |
+
"loss": 0.2889,
|
147 |
+
"step": 460
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.96,
|
151 |
+
"learning_rate": 1.668055555555556e-05,
|
152 |
+
"loss": 0.2763,
|
153 |
+
"step": 480
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 5.16,
|
157 |
+
"learning_rate": 1.6541666666666668e-05,
|
158 |
+
"loss": 0.2778,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 5.37,
|
163 |
+
"learning_rate": 1.6402777777777777e-05,
|
164 |
+
"loss": 0.2689,
|
165 |
+
"step": 520
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 5.58,
|
169 |
+
"learning_rate": 1.626388888888889e-05,
|
170 |
+
"loss": 0.2732,
|
171 |
+
"step": 540
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 5.78,
|
175 |
+
"learning_rate": 1.6125000000000002e-05,
|
176 |
+
"loss": 0.2604,
|
177 |
+
"step": 560
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.99,
|
181 |
+
"learning_rate": 1.5986111111111115e-05,
|
182 |
+
"loss": 0.2608,
|
183 |
+
"step": 580
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 6.2,
|
187 |
+
"learning_rate": 1.5847222222222224e-05,
|
188 |
+
"loss": 0.2356,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 6.4,
|
193 |
+
"learning_rate": 1.5708333333333333e-05,
|
194 |
+
"loss": 0.2414,
|
195 |
+
"step": 620
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 6.61,
|
199 |
+
"learning_rate": 1.5569444444444446e-05,
|
200 |
+
"loss": 0.2339,
|
201 |
+
"step": 640
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 6.82,
|
205 |
+
"learning_rate": 1.543055555555556e-05,
|
206 |
+
"loss": 0.2394,
|
207 |
+
"step": 660
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 7.02,
|
211 |
+
"learning_rate": 1.5291666666666668e-05,
|
212 |
+
"loss": 0.223,
|
213 |
+
"step": 680
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 7.23,
|
217 |
+
"learning_rate": 1.5152777777777779e-05,
|
218 |
+
"loss": 0.2155,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 7.44,
|
223 |
+
"learning_rate": 1.501388888888889e-05,
|
224 |
+
"loss": 0.2099,
|
225 |
+
"step": 720
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 7.64,
|
229 |
+
"learning_rate": 1.4875000000000002e-05,
|
230 |
+
"loss": 0.2041,
|
231 |
+
"step": 740
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 7.85,
|
235 |
+
"learning_rate": 1.4736111111111113e-05,
|
236 |
+
"loss": 0.2067,
|
237 |
+
"step": 760
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 8.06,
|
241 |
+
"learning_rate": 1.4597222222222223e-05,
|
242 |
+
"loss": 0.193,
|
243 |
+
"step": 780
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 8.26,
|
247 |
+
"learning_rate": 1.4458333333333334e-05,
|
248 |
+
"loss": 0.1802,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 8.47,
|
253 |
+
"learning_rate": 1.4319444444444446e-05,
|
254 |
+
"loss": 0.1828,
|
255 |
+
"step": 820
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 8.68,
|
259 |
+
"learning_rate": 1.4180555555555557e-05,
|
260 |
+
"loss": 0.1754,
|
261 |
+
"step": 840
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 8.88,
|
265 |
+
"learning_rate": 1.4041666666666666e-05,
|
266 |
+
"loss": 0.1745,
|
267 |
+
"step": 860
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 9.09,
|
271 |
+
"learning_rate": 1.3902777777777779e-05,
|
272 |
+
"loss": 0.1692,
|
273 |
+
"step": 880
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 9.3,
|
277 |
+
"learning_rate": 1.376388888888889e-05,
|
278 |
+
"loss": 0.1648,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 9.5,
|
283 |
+
"learning_rate": 1.3625e-05,
|
284 |
+
"loss": 0.1463,
|
285 |
+
"step": 920
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 9.71,
|
289 |
+
"learning_rate": 1.3486111111111113e-05,
|
290 |
+
"loss": 0.1525,
|
291 |
+
"step": 940
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 9.92,
|
295 |
+
"learning_rate": 1.3347222222222223e-05,
|
296 |
+
"loss": 0.1458,
|
297 |
+
"step": 960
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 10.12,
|
301 |
+
"learning_rate": 1.3208333333333334e-05,
|
302 |
+
"loss": 0.137,
|
303 |
+
"step": 980
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 10.33,
|
307 |
+
"learning_rate": 1.3069444444444446e-05,
|
308 |
+
"loss": 0.1318,
|
309 |
+
"step": 1000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 10.54,
|
313 |
+
"learning_rate": 1.2930555555555557e-05,
|
314 |
+
"loss": 0.138,
|
315 |
+
"step": 1020
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 10.74,
|
319 |
+
"learning_rate": 1.2791666666666666e-05,
|
320 |
+
"loss": 0.1282,
|
321 |
+
"step": 1040
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 10.95,
|
325 |
+
"learning_rate": 1.2652777777777779e-05,
|
326 |
+
"loss": 0.1277,
|
327 |
+
"step": 1060
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 11.16,
|
331 |
+
"learning_rate": 1.251388888888889e-05,
|
332 |
+
"loss": 0.1201,
|
333 |
+
"step": 1080
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 11.36,
|
337 |
+
"learning_rate": 1.2375000000000001e-05,
|
338 |
+
"loss": 0.1189,
|
339 |
+
"step": 1100
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 11.57,
|
343 |
+
"learning_rate": 1.2236111111111114e-05,
|
344 |
+
"loss": 0.1153,
|
345 |
+
"step": 1120
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 11.78,
|
349 |
+
"learning_rate": 1.2097222222222223e-05,
|
350 |
+
"loss": 0.1164,
|
351 |
+
"step": 1140
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 11.98,
|
355 |
+
"learning_rate": 1.1958333333333334e-05,
|
356 |
+
"loss": 0.1062,
|
357 |
+
"step": 1160
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 12.19,
|
361 |
+
"learning_rate": 1.1819444444444446e-05,
|
362 |
+
"loss": 0.107,
|
363 |
+
"step": 1180
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 12.4,
|
367 |
+
"learning_rate": 1.1680555555555557e-05,
|
368 |
+
"loss": 0.1,
|
369 |
+
"step": 1200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 12.6,
|
373 |
+
"learning_rate": 1.1541666666666667e-05,
|
374 |
+
"loss": 0.1017,
|
375 |
+
"step": 1220
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 12.81,
|
379 |
+
"learning_rate": 1.1402777777777777e-05,
|
380 |
+
"loss": 0.0984,
|
381 |
+
"step": 1240
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 13.01,
|
385 |
+
"learning_rate": 1.126388888888889e-05,
|
386 |
+
"loss": 0.0948,
|
387 |
+
"step": 1260
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 13.22,
|
391 |
+
"learning_rate": 1.1125000000000001e-05,
|
392 |
+
"loss": 0.0886,
|
393 |
+
"step": 1280
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 13.43,
|
397 |
+
"learning_rate": 1.0986111111111114e-05,
|
398 |
+
"loss": 0.0908,
|
399 |
+
"step": 1300
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 13.63,
|
403 |
+
"learning_rate": 1.0847222222222223e-05,
|
404 |
+
"loss": 0.0907,
|
405 |
+
"step": 1320
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 13.84,
|
409 |
+
"learning_rate": 1.0708333333333334e-05,
|
410 |
+
"loss": 0.0886,
|
411 |
+
"step": 1340
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 14.05,
|
415 |
+
"learning_rate": 1.0569444444444445e-05,
|
416 |
+
"loss": 0.0835,
|
417 |
+
"step": 1360
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 14.25,
|
421 |
+
"learning_rate": 1.0430555555555557e-05,
|
422 |
+
"loss": 0.0809,
|
423 |
+
"step": 1380
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 14.46,
|
427 |
+
"learning_rate": 1.0291666666666667e-05,
|
428 |
+
"loss": 0.0793,
|
429 |
+
"step": 1400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 14.67,
|
433 |
+
"learning_rate": 1.0152777777777778e-05,
|
434 |
+
"loss": 0.0788,
|
435 |
+
"step": 1420
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 14.87,
|
439 |
+
"learning_rate": 1.001388888888889e-05,
|
440 |
+
"loss": 0.0769,
|
441 |
+
"step": 1440
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 15.08,
|
445 |
+
"learning_rate": 9.875000000000001e-06,
|
446 |
+
"loss": 0.0738,
|
447 |
+
"step": 1460
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 15.29,
|
451 |
+
"learning_rate": 9.736111111111112e-06,
|
452 |
+
"loss": 0.0747,
|
453 |
+
"step": 1480
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 15.49,
|
457 |
+
"learning_rate": 9.597222222222223e-06,
|
458 |
+
"loss": 0.0656,
|
459 |
+
"step": 1500
|
460 |
+
}
|
461 |
+
],
|
462 |
+
"logging_steps": 20,
|
463 |
+
"max_steps": 2880,
|
464 |
+
"num_input_tokens_seen": 0,
|
465 |
+
"num_train_epochs": 30,
|
466 |
+
"save_steps": 500,
|
467 |
+
"total_flos": 4.752565455957197e+17,
|
468 |
+
"train_batch_size": 1,
|
469 |
+
"trial_name": null,
|
470 |
+
"trial_params": null
|
471 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687ee61d860f794218b437b86ef3d4e7d89241cf9246f5eee16a51278e5f8b65
|
3 |
+
size 4728
|
checkpoint-2000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-2000/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d94153f92e575afbd797b637896577de5c991c1f1dee7ba8ebf0ffa17fc1414b
|
3 |
+
size 16794200
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0c2d6afa5a1972eb5194af407ad24a0157211115d72bc58cb8bc735a4c973c1
|
3 |
+
size 33662074
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:250ca088ed79ffd598a0a3b2bce7c0bf0702fbeadf775eddb97cf4c44bca4c28
|
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 +1,621 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"learning_rate": 1.9875000000000002e-05,
|
14 |
+
"loss": 1.9446,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.41,
|
19 |
+
"learning_rate": 1.9736111111111115e-05,
|
20 |
+
"loss": 1.7941,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.62,
|
25 |
+
"learning_rate": 1.9597222222222224e-05,
|
26 |
+
"loss": 1.5361,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.83,
|
31 |
+
"learning_rate": 1.9458333333333333e-05,
|
32 |
+
"loss": 1.1041,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.03,
|
37 |
+
"learning_rate": 1.9319444444444446e-05,
|
38 |
+
"loss": 0.6053,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.24,
|
43 |
+
"learning_rate": 1.918055555555556e-05,
|
44 |
+
"loss": 0.4088,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.45,
|
49 |
+
"learning_rate": 1.9041666666666668e-05,
|
50 |
+
"loss": 0.3813,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.65,
|
55 |
+
"learning_rate": 1.890277777777778e-05,
|
56 |
+
"loss": 0.3733,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.86,
|
61 |
+
"learning_rate": 1.876388888888889e-05,
|
62 |
+
"loss": 0.3678,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.07,
|
67 |
+
"learning_rate": 1.8625000000000002e-05,
|
68 |
+
"loss": 0.3604,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.27,
|
73 |
+
"learning_rate": 1.8486111111111115e-05,
|
74 |
+
"loss": 0.3368,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.48,
|
79 |
+
"learning_rate": 1.8347222222222224e-05,
|
80 |
+
"loss": 0.3356,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.69,
|
85 |
+
"learning_rate": 1.8208333333333333e-05,
|
86 |
+
"loss": 0.3439,
|
87 |
+
"step": 260
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.89,
|
91 |
+
"learning_rate": 1.8069444444444446e-05,
|
92 |
+
"loss": 0.3277,
|
93 |
+
"step": 280
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.1,
|
97 |
+
"learning_rate": 1.793055555555556e-05,
|
98 |
+
"loss": 0.3288,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.31,
|
103 |
+
"learning_rate": 1.7791666666666668e-05,
|
104 |
+
"loss": 0.3227,
|
105 |
+
"step": 320
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.51,
|
109 |
+
"learning_rate": 1.765277777777778e-05,
|
110 |
+
"loss": 0.3213,
|
111 |
+
"step": 340
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.72,
|
115 |
+
"learning_rate": 1.751388888888889e-05,
|
116 |
+
"loss": 0.3128,
|
117 |
+
"step": 360
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 3.93,
|
121 |
+
"learning_rate": 1.7375000000000002e-05,
|
122 |
+
"loss": 0.3071,
|
123 |
+
"step": 380
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.13,
|
127 |
+
"learning_rate": 1.7236111111111115e-05,
|
128 |
+
"loss": 0.3022,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.34,
|
133 |
+
"learning_rate": 1.7097222222222224e-05,
|
134 |
+
"loss": 0.2968,
|
135 |
+
"step": 420
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.54,
|
139 |
+
"learning_rate": 1.6958333333333333e-05,
|
140 |
+
"loss": 0.3023,
|
141 |
+
"step": 440
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 4.75,
|
145 |
+
"learning_rate": 1.6819444444444446e-05,
|
146 |
+
"loss": 0.2889,
|
147 |
+
"step": 460
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.96,
|
151 |
+
"learning_rate": 1.668055555555556e-05,
|
152 |
+
"loss": 0.2763,
|
153 |
+
"step": 480
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 5.16,
|
157 |
+
"learning_rate": 1.6541666666666668e-05,
|
158 |
+
"loss": 0.2778,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 5.37,
|
163 |
+
"learning_rate": 1.6402777777777777e-05,
|
164 |
+
"loss": 0.2689,
|
165 |
+
"step": 520
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 5.58,
|
169 |
+
"learning_rate": 1.626388888888889e-05,
|
170 |
+
"loss": 0.2732,
|
171 |
+
"step": 540
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 5.78,
|
175 |
+
"learning_rate": 1.6125000000000002e-05,
|
176 |
+
"loss": 0.2604,
|
177 |
+
"step": 560
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.99,
|
181 |
+
"learning_rate": 1.5986111111111115e-05,
|
182 |
+
"loss": 0.2608,
|
183 |
+
"step": 580
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 6.2,
|
187 |
+
"learning_rate": 1.5847222222222224e-05,
|
188 |
+
"loss": 0.2356,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 6.4,
|
193 |
+
"learning_rate": 1.5708333333333333e-05,
|
194 |
+
"loss": 0.2414,
|
195 |
+
"step": 620
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 6.61,
|
199 |
+
"learning_rate": 1.5569444444444446e-05,
|
200 |
+
"loss": 0.2339,
|
201 |
+
"step": 640
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 6.82,
|
205 |
+
"learning_rate": 1.543055555555556e-05,
|
206 |
+
"loss": 0.2394,
|
207 |
+
"step": 660
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 7.02,
|
211 |
+
"learning_rate": 1.5291666666666668e-05,
|
212 |
+
"loss": 0.223,
|
213 |
+
"step": 680
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 7.23,
|
217 |
+
"learning_rate": 1.5152777777777779e-05,
|
218 |
+
"loss": 0.2155,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 7.44,
|
223 |
+
"learning_rate": 1.501388888888889e-05,
|
224 |
+
"loss": 0.2099,
|
225 |
+
"step": 720
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 7.64,
|
229 |
+
"learning_rate": 1.4875000000000002e-05,
|
230 |
+
"loss": 0.2041,
|
231 |
+
"step": 740
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 7.85,
|
235 |
+
"learning_rate": 1.4736111111111113e-05,
|
236 |
+
"loss": 0.2067,
|
237 |
+
"step": 760
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 8.06,
|
241 |
+
"learning_rate": 1.4597222222222223e-05,
|
242 |
+
"loss": 0.193,
|
243 |
+
"step": 780
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 8.26,
|
247 |
+
"learning_rate": 1.4458333333333334e-05,
|
248 |
+
"loss": 0.1802,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 8.47,
|
253 |
+
"learning_rate": 1.4319444444444446e-05,
|
254 |
+
"loss": 0.1828,
|
255 |
+
"step": 820
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 8.68,
|
259 |
+
"learning_rate": 1.4180555555555557e-05,
|
260 |
+
"loss": 0.1754,
|
261 |
+
"step": 840
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 8.88,
|
265 |
+
"learning_rate": 1.4041666666666666e-05,
|
266 |
+
"loss": 0.1745,
|
267 |
+
"step": 860
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 9.09,
|
271 |
+
"learning_rate": 1.3902777777777779e-05,
|
272 |
+
"loss": 0.1692,
|
273 |
+
"step": 880
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 9.3,
|
277 |
+
"learning_rate": 1.376388888888889e-05,
|
278 |
+
"loss": 0.1648,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 9.5,
|
283 |
+
"learning_rate": 1.3625e-05,
|
284 |
+
"loss": 0.1463,
|
285 |
+
"step": 920
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 9.71,
|
289 |
+
"learning_rate": 1.3486111111111113e-05,
|
290 |
+
"loss": 0.1525,
|
291 |
+
"step": 940
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 9.92,
|
295 |
+
"learning_rate": 1.3347222222222223e-05,
|
296 |
+
"loss": 0.1458,
|
297 |
+
"step": 960
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 10.12,
|
301 |
+
"learning_rate": 1.3208333333333334e-05,
|
302 |
+
"loss": 0.137,
|
303 |
+
"step": 980
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 10.33,
|
307 |
+
"learning_rate": 1.3069444444444446e-05,
|
308 |
+
"loss": 0.1318,
|
309 |
+
"step": 1000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 10.54,
|
313 |
+
"learning_rate": 1.2930555555555557e-05,
|
314 |
+
"loss": 0.138,
|
315 |
+
"step": 1020
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 10.74,
|
319 |
+
"learning_rate": 1.2791666666666666e-05,
|
320 |
+
"loss": 0.1282,
|
321 |
+
"step": 1040
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 10.95,
|
325 |
+
"learning_rate": 1.2652777777777779e-05,
|
326 |
+
"loss": 0.1277,
|
327 |
+
"step": 1060
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 11.16,
|
331 |
+
"learning_rate": 1.251388888888889e-05,
|
332 |
+
"loss": 0.1201,
|
333 |
+
"step": 1080
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 11.36,
|
337 |
+
"learning_rate": 1.2375000000000001e-05,
|
338 |
+
"loss": 0.1189,
|
339 |
+
"step": 1100
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 11.57,
|
343 |
+
"learning_rate": 1.2236111111111114e-05,
|
344 |
+
"loss": 0.1153,
|
345 |
+
"step": 1120
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 11.78,
|
349 |
+
"learning_rate": 1.2097222222222223e-05,
|
350 |
+
"loss": 0.1164,
|
351 |
+
"step": 1140
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 11.98,
|
355 |
+
"learning_rate": 1.1958333333333334e-05,
|
356 |
+
"loss": 0.1062,
|
357 |
+
"step": 1160
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 12.19,
|
361 |
+
"learning_rate": 1.1819444444444446e-05,
|
362 |
+
"loss": 0.107,
|
363 |
+
"step": 1180
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 12.4,
|
367 |
+
"learning_rate": 1.1680555555555557e-05,
|
368 |
+
"loss": 0.1,
|
369 |
+
"step": 1200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 12.6,
|
373 |
+
"learning_rate": 1.1541666666666667e-05,
|
374 |
+
"loss": 0.1017,
|
375 |
+
"step": 1220
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 12.81,
|
379 |
+
"learning_rate": 1.1402777777777777e-05,
|
380 |
+
"loss": 0.0984,
|
381 |
+
"step": 1240
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 13.01,
|
385 |
+
"learning_rate": 1.126388888888889e-05,
|
386 |
+
"loss": 0.0948,
|
387 |
+
"step": 1260
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 13.22,
|
391 |
+
"learning_rate": 1.1125000000000001e-05,
|
392 |
+
"loss": 0.0886,
|
393 |
+
"step": 1280
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 13.43,
|
397 |
+
"learning_rate": 1.0986111111111114e-05,
|
398 |
+
"loss": 0.0908,
|
399 |
+
"step": 1300
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 13.63,
|
403 |
+
"learning_rate": 1.0847222222222223e-05,
|
404 |
+
"loss": 0.0907,
|
405 |
+
"step": 1320
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 13.84,
|
409 |
+
"learning_rate": 1.0708333333333334e-05,
|
410 |
+
"loss": 0.0886,
|
411 |
+
"step": 1340
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 14.05,
|
415 |
+
"learning_rate": 1.0569444444444445e-05,
|
416 |
+
"loss": 0.0835,
|
417 |
+
"step": 1360
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 14.25,
|
421 |
+
"learning_rate": 1.0430555555555557e-05,
|
422 |
+
"loss": 0.0809,
|
423 |
+
"step": 1380
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 14.46,
|
427 |
+
"learning_rate": 1.0291666666666667e-05,
|
428 |
+
"loss": 0.0793,
|
429 |
+
"step": 1400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 14.67,
|
433 |
+
"learning_rate": 1.0152777777777778e-05,
|
434 |
+
"loss": 0.0788,
|
435 |
+
"step": 1420
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 14.87,
|
439 |
+
"learning_rate": 1.001388888888889e-05,
|
440 |
+
"loss": 0.0769,
|
441 |
+
"step": 1440
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 15.08,
|
445 |
+
"learning_rate": 9.875000000000001e-06,
|
446 |
+
"loss": 0.0738,
|
447 |
+
"step": 1460
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 15.29,
|
451 |
+
"learning_rate": 9.736111111111112e-06,
|
452 |
+
"loss": 0.0747,
|
453 |
+
"step": 1480
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 15.49,
|
457 |
+
"learning_rate": 9.597222222222223e-06,
|
458 |
+
"loss": 0.0656,
|
459 |
+
"step": 1500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 15.7,
|
463 |
+
"learning_rate": 9.458333333333334e-06,
|
464 |
+
"loss": 0.0735,
|
465 |
+
"step": 1520
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 15.91,
|
469 |
+
"learning_rate": 9.319444444444445e-06,
|
470 |
+
"loss": 0.0693,
|
471 |
+
"step": 1540
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 16.11,
|
475 |
+
"learning_rate": 9.180555555555556e-06,
|
476 |
+
"loss": 0.0646,
|
477 |
+
"step": 1560
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 16.32,
|
481 |
+
"learning_rate": 9.041666666666667e-06,
|
482 |
+
"loss": 0.0658,
|
483 |
+
"step": 1580
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 16.53,
|
487 |
+
"learning_rate": 8.902777777777778e-06,
|
488 |
+
"loss": 0.063,
|
489 |
+
"step": 1600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 16.73,
|
493 |
+
"learning_rate": 8.76388888888889e-06,
|
494 |
+
"loss": 0.0652,
|
495 |
+
"step": 1620
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 16.94,
|
499 |
+
"learning_rate": 8.625000000000001e-06,
|
500 |
+
"loss": 0.0624,
|
501 |
+
"step": 1640
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 17.15,
|
505 |
+
"learning_rate": 8.486111111111112e-06,
|
506 |
+
"loss": 0.0597,
|
507 |
+
"step": 1660
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 17.35,
|
511 |
+
"learning_rate": 8.347222222222223e-06,
|
512 |
+
"loss": 0.0597,
|
513 |
+
"step": 1680
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 17.56,
|
517 |
+
"learning_rate": 8.208333333333334e-06,
|
518 |
+
"loss": 0.0549,
|
519 |
+
"step": 1700
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 17.77,
|
523 |
+
"learning_rate": 8.069444444444445e-06,
|
524 |
+
"loss": 0.0574,
|
525 |
+
"step": 1720
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 17.97,
|
529 |
+
"learning_rate": 7.930555555555556e-06,
|
530 |
+
"loss": 0.0575,
|
531 |
+
"step": 1740
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 18.18,
|
535 |
+
"learning_rate": 7.791666666666667e-06,
|
536 |
+
"loss": 0.0561,
|
537 |
+
"step": 1760
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 18.39,
|
541 |
+
"learning_rate": 7.652777777777778e-06,
|
542 |
+
"loss": 0.0541,
|
543 |
+
"step": 1780
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 18.59,
|
547 |
+
"learning_rate": 7.51388888888889e-06,
|
548 |
+
"loss": 0.0528,
|
549 |
+
"step": 1800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 18.8,
|
553 |
+
"learning_rate": 7.375000000000001e-06,
|
554 |
+
"loss": 0.0525,
|
555 |
+
"step": 1820
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 19.01,
|
559 |
+
"learning_rate": 7.2361111111111115e-06,
|
560 |
+
"loss": 0.0503,
|
561 |
+
"step": 1840
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 19.21,
|
565 |
+
"learning_rate": 7.097222222222223e-06,
|
566 |
+
"loss": 0.0485,
|
567 |
+
"step": 1860
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 19.42,
|
571 |
+
"learning_rate": 6.958333333333333e-06,
|
572 |
+
"loss": 0.05,
|
573 |
+
"step": 1880
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 19.63,
|
577 |
+
"learning_rate": 6.819444444444445e-06,
|
578 |
+
"loss": 0.0501,
|
579 |
+
"step": 1900
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 19.83,
|
583 |
+
"learning_rate": 6.680555555555556e-06,
|
584 |
+
"loss": 0.0489,
|
585 |
+
"step": 1920
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 20.04,
|
589 |
+
"learning_rate": 6.541666666666667e-06,
|
590 |
+
"loss": 0.0472,
|
591 |
+
"step": 1940
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 20.25,
|
595 |
+
"learning_rate": 6.402777777777778e-06,
|
596 |
+
"loss": 0.0442,
|
597 |
+
"step": 1960
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 20.45,
|
601 |
+
"learning_rate": 6.26388888888889e-06,
|
602 |
+
"loss": 0.0498,
|
603 |
+
"step": 1980
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 20.66,
|
607 |
+
"learning_rate": 6.125000000000001e-06,
|
608 |
+
"loss": 0.0455,
|
609 |
+
"step": 2000
|
610 |
+
}
|
611 |
+
],
|
612 |
+
"logging_steps": 20,
|
613 |
+
"max_steps": 2880,
|
614 |
+
"num_input_tokens_seen": 0,
|
615 |
+
"num_train_epochs": 30,
|
616 |
+
"save_steps": 500,
|
617 |
+
"total_flos": 6.33709879909417e+17,
|
618 |
+
"train_batch_size": 1,
|
619 |
+
"trial_name": null,
|
620 |
+
"trial_params": null
|
621 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687ee61d860f794218b437b86ef3d4e7d89241cf9246f5eee16a51278e5f8b65
|
3 |
+
size 4728
|
checkpoint-2500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-2500/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f50f6c39818deb35dfb78f87f112964ef738073d4c56b63f9d29db61ed32cbf2
|
3 |
+
size 16794200
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de8980fd83e000c002e7d879818ff56f47470c537da1769271d4d9cf22afa23e
|
3 |
+
size 33662074
|
checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d571f18acb2a1d3e194595e481b7a7f51b71b18c12aad698bbec1b40679eab1
|
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 +1,771 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"learning_rate": 1.9875000000000002e-05,
|
14 |
+
"loss": 1.9446,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.41,
|
19 |
+
"learning_rate": 1.9736111111111115e-05,
|
20 |
+
"loss": 1.7941,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.62,
|
25 |
+
"learning_rate": 1.9597222222222224e-05,
|
26 |
+
"loss": 1.5361,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.83,
|
31 |
+
"learning_rate": 1.9458333333333333e-05,
|
32 |
+
"loss": 1.1041,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.03,
|
37 |
+
"learning_rate": 1.9319444444444446e-05,
|
38 |
+
"loss": 0.6053,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.24,
|
43 |
+
"learning_rate": 1.918055555555556e-05,
|
44 |
+
"loss": 0.4088,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.45,
|
49 |
+
"learning_rate": 1.9041666666666668e-05,
|
50 |
+
"loss": 0.3813,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.65,
|
55 |
+
"learning_rate": 1.890277777777778e-05,
|
56 |
+
"loss": 0.3733,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.86,
|
61 |
+
"learning_rate": 1.876388888888889e-05,
|
62 |
+
"loss": 0.3678,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.07,
|
67 |
+
"learning_rate": 1.8625000000000002e-05,
|
68 |
+
"loss": 0.3604,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.27,
|
73 |
+
"learning_rate": 1.8486111111111115e-05,
|
74 |
+
"loss": 0.3368,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.48,
|
79 |
+
"learning_rate": 1.8347222222222224e-05,
|
80 |
+
"loss": 0.3356,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.69,
|
85 |
+
"learning_rate": 1.8208333333333333e-05,
|
86 |
+
"loss": 0.3439,
|
87 |
+
"step": 260
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.89,
|
91 |
+
"learning_rate": 1.8069444444444446e-05,
|
92 |
+
"loss": 0.3277,
|
93 |
+
"step": 280
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.1,
|
97 |
+
"learning_rate": 1.793055555555556e-05,
|
98 |
+
"loss": 0.3288,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.31,
|
103 |
+
"learning_rate": 1.7791666666666668e-05,
|
104 |
+
"loss": 0.3227,
|
105 |
+
"step": 320
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.51,
|
109 |
+
"learning_rate": 1.765277777777778e-05,
|
110 |
+
"loss": 0.3213,
|
111 |
+
"step": 340
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.72,
|
115 |
+
"learning_rate": 1.751388888888889e-05,
|
116 |
+
"loss": 0.3128,
|
117 |
+
"step": 360
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 3.93,
|
121 |
+
"learning_rate": 1.7375000000000002e-05,
|
122 |
+
"loss": 0.3071,
|
123 |
+
"step": 380
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.13,
|
127 |
+
"learning_rate": 1.7236111111111115e-05,
|
128 |
+
"loss": 0.3022,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.34,
|
133 |
+
"learning_rate": 1.7097222222222224e-05,
|
134 |
+
"loss": 0.2968,
|
135 |
+
"step": 420
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.54,
|
139 |
+
"learning_rate": 1.6958333333333333e-05,
|
140 |
+
"loss": 0.3023,
|
141 |
+
"step": 440
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 4.75,
|
145 |
+
"learning_rate": 1.6819444444444446e-05,
|
146 |
+
"loss": 0.2889,
|
147 |
+
"step": 460
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.96,
|
151 |
+
"learning_rate": 1.668055555555556e-05,
|
152 |
+
"loss": 0.2763,
|
153 |
+
"step": 480
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 5.16,
|
157 |
+
"learning_rate": 1.6541666666666668e-05,
|
158 |
+
"loss": 0.2778,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 5.37,
|
163 |
+
"learning_rate": 1.6402777777777777e-05,
|
164 |
+
"loss": 0.2689,
|
165 |
+
"step": 520
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 5.58,
|
169 |
+
"learning_rate": 1.626388888888889e-05,
|
170 |
+
"loss": 0.2732,
|
171 |
+
"step": 540
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 5.78,
|
175 |
+
"learning_rate": 1.6125000000000002e-05,
|
176 |
+
"loss": 0.2604,
|
177 |
+
"step": 560
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.99,
|
181 |
+
"learning_rate": 1.5986111111111115e-05,
|
182 |
+
"loss": 0.2608,
|
183 |
+
"step": 580
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 6.2,
|
187 |
+
"learning_rate": 1.5847222222222224e-05,
|
188 |
+
"loss": 0.2356,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 6.4,
|
193 |
+
"learning_rate": 1.5708333333333333e-05,
|
194 |
+
"loss": 0.2414,
|
195 |
+
"step": 620
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 6.61,
|
199 |
+
"learning_rate": 1.5569444444444446e-05,
|
200 |
+
"loss": 0.2339,
|
201 |
+
"step": 640
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 6.82,
|
205 |
+
"learning_rate": 1.543055555555556e-05,
|
206 |
+
"loss": 0.2394,
|
207 |
+
"step": 660
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 7.02,
|
211 |
+
"learning_rate": 1.5291666666666668e-05,
|
212 |
+
"loss": 0.223,
|
213 |
+
"step": 680
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 7.23,
|
217 |
+
"learning_rate": 1.5152777777777779e-05,
|
218 |
+
"loss": 0.2155,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 7.44,
|
223 |
+
"learning_rate": 1.501388888888889e-05,
|
224 |
+
"loss": 0.2099,
|
225 |
+
"step": 720
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 7.64,
|
229 |
+
"learning_rate": 1.4875000000000002e-05,
|
230 |
+
"loss": 0.2041,
|
231 |
+
"step": 740
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 7.85,
|
235 |
+
"learning_rate": 1.4736111111111113e-05,
|
236 |
+
"loss": 0.2067,
|
237 |
+
"step": 760
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 8.06,
|
241 |
+
"learning_rate": 1.4597222222222223e-05,
|
242 |
+
"loss": 0.193,
|
243 |
+
"step": 780
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 8.26,
|
247 |
+
"learning_rate": 1.4458333333333334e-05,
|
248 |
+
"loss": 0.1802,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 8.47,
|
253 |
+
"learning_rate": 1.4319444444444446e-05,
|
254 |
+
"loss": 0.1828,
|
255 |
+
"step": 820
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 8.68,
|
259 |
+
"learning_rate": 1.4180555555555557e-05,
|
260 |
+
"loss": 0.1754,
|
261 |
+
"step": 840
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 8.88,
|
265 |
+
"learning_rate": 1.4041666666666666e-05,
|
266 |
+
"loss": 0.1745,
|
267 |
+
"step": 860
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 9.09,
|
271 |
+
"learning_rate": 1.3902777777777779e-05,
|
272 |
+
"loss": 0.1692,
|
273 |
+
"step": 880
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 9.3,
|
277 |
+
"learning_rate": 1.376388888888889e-05,
|
278 |
+
"loss": 0.1648,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 9.5,
|
283 |
+
"learning_rate": 1.3625e-05,
|
284 |
+
"loss": 0.1463,
|
285 |
+
"step": 920
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 9.71,
|
289 |
+
"learning_rate": 1.3486111111111113e-05,
|
290 |
+
"loss": 0.1525,
|
291 |
+
"step": 940
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 9.92,
|
295 |
+
"learning_rate": 1.3347222222222223e-05,
|
296 |
+
"loss": 0.1458,
|
297 |
+
"step": 960
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 10.12,
|
301 |
+
"learning_rate": 1.3208333333333334e-05,
|
302 |
+
"loss": 0.137,
|
303 |
+
"step": 980
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 10.33,
|
307 |
+
"learning_rate": 1.3069444444444446e-05,
|
308 |
+
"loss": 0.1318,
|
309 |
+
"step": 1000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 10.54,
|
313 |
+
"learning_rate": 1.2930555555555557e-05,
|
314 |
+
"loss": 0.138,
|
315 |
+
"step": 1020
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 10.74,
|
319 |
+
"learning_rate": 1.2791666666666666e-05,
|
320 |
+
"loss": 0.1282,
|
321 |
+
"step": 1040
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 10.95,
|
325 |
+
"learning_rate": 1.2652777777777779e-05,
|
326 |
+
"loss": 0.1277,
|
327 |
+
"step": 1060
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 11.16,
|
331 |
+
"learning_rate": 1.251388888888889e-05,
|
332 |
+
"loss": 0.1201,
|
333 |
+
"step": 1080
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 11.36,
|
337 |
+
"learning_rate": 1.2375000000000001e-05,
|
338 |
+
"loss": 0.1189,
|
339 |
+
"step": 1100
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 11.57,
|
343 |
+
"learning_rate": 1.2236111111111114e-05,
|
344 |
+
"loss": 0.1153,
|
345 |
+
"step": 1120
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 11.78,
|
349 |
+
"learning_rate": 1.2097222222222223e-05,
|
350 |
+
"loss": 0.1164,
|
351 |
+
"step": 1140
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 11.98,
|
355 |
+
"learning_rate": 1.1958333333333334e-05,
|
356 |
+
"loss": 0.1062,
|
357 |
+
"step": 1160
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 12.19,
|
361 |
+
"learning_rate": 1.1819444444444446e-05,
|
362 |
+
"loss": 0.107,
|
363 |
+
"step": 1180
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 12.4,
|
367 |
+
"learning_rate": 1.1680555555555557e-05,
|
368 |
+
"loss": 0.1,
|
369 |
+
"step": 1200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 12.6,
|
373 |
+
"learning_rate": 1.1541666666666667e-05,
|
374 |
+
"loss": 0.1017,
|
375 |
+
"step": 1220
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 12.81,
|
379 |
+
"learning_rate": 1.1402777777777777e-05,
|
380 |
+
"loss": 0.0984,
|
381 |
+
"step": 1240
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 13.01,
|
385 |
+
"learning_rate": 1.126388888888889e-05,
|
386 |
+
"loss": 0.0948,
|
387 |
+
"step": 1260
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 13.22,
|
391 |
+
"learning_rate": 1.1125000000000001e-05,
|
392 |
+
"loss": 0.0886,
|
393 |
+
"step": 1280
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 13.43,
|
397 |
+
"learning_rate": 1.0986111111111114e-05,
|
398 |
+
"loss": 0.0908,
|
399 |
+
"step": 1300
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 13.63,
|
403 |
+
"learning_rate": 1.0847222222222223e-05,
|
404 |
+
"loss": 0.0907,
|
405 |
+
"step": 1320
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 13.84,
|
409 |
+
"learning_rate": 1.0708333333333334e-05,
|
410 |
+
"loss": 0.0886,
|
411 |
+
"step": 1340
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 14.05,
|
415 |
+
"learning_rate": 1.0569444444444445e-05,
|
416 |
+
"loss": 0.0835,
|
417 |
+
"step": 1360
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 14.25,
|
421 |
+
"learning_rate": 1.0430555555555557e-05,
|
422 |
+
"loss": 0.0809,
|
423 |
+
"step": 1380
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 14.46,
|
427 |
+
"learning_rate": 1.0291666666666667e-05,
|
428 |
+
"loss": 0.0793,
|
429 |
+
"step": 1400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 14.67,
|
433 |
+
"learning_rate": 1.0152777777777778e-05,
|
434 |
+
"loss": 0.0788,
|
435 |
+
"step": 1420
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 14.87,
|
439 |
+
"learning_rate": 1.001388888888889e-05,
|
440 |
+
"loss": 0.0769,
|
441 |
+
"step": 1440
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 15.08,
|
445 |
+
"learning_rate": 9.875000000000001e-06,
|
446 |
+
"loss": 0.0738,
|
447 |
+
"step": 1460
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 15.29,
|
451 |
+
"learning_rate": 9.736111111111112e-06,
|
452 |
+
"loss": 0.0747,
|
453 |
+
"step": 1480
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 15.49,
|
457 |
+
"learning_rate": 9.597222222222223e-06,
|
458 |
+
"loss": 0.0656,
|
459 |
+
"step": 1500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 15.7,
|
463 |
+
"learning_rate": 9.458333333333334e-06,
|
464 |
+
"loss": 0.0735,
|
465 |
+
"step": 1520
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 15.91,
|
469 |
+
"learning_rate": 9.319444444444445e-06,
|
470 |
+
"loss": 0.0693,
|
471 |
+
"step": 1540
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 16.11,
|
475 |
+
"learning_rate": 9.180555555555556e-06,
|
476 |
+
"loss": 0.0646,
|
477 |
+
"step": 1560
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 16.32,
|
481 |
+
"learning_rate": 9.041666666666667e-06,
|
482 |
+
"loss": 0.0658,
|
483 |
+
"step": 1580
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 16.53,
|
487 |
+
"learning_rate": 8.902777777777778e-06,
|
488 |
+
"loss": 0.063,
|
489 |
+
"step": 1600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 16.73,
|
493 |
+
"learning_rate": 8.76388888888889e-06,
|
494 |
+
"loss": 0.0652,
|
495 |
+
"step": 1620
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 16.94,
|
499 |
+
"learning_rate": 8.625000000000001e-06,
|
500 |
+
"loss": 0.0624,
|
501 |
+
"step": 1640
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 17.15,
|
505 |
+
"learning_rate": 8.486111111111112e-06,
|
506 |
+
"loss": 0.0597,
|
507 |
+
"step": 1660
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 17.35,
|
511 |
+
"learning_rate": 8.347222222222223e-06,
|
512 |
+
"loss": 0.0597,
|
513 |
+
"step": 1680
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 17.56,
|
517 |
+
"learning_rate": 8.208333333333334e-06,
|
518 |
+
"loss": 0.0549,
|
519 |
+
"step": 1700
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 17.77,
|
523 |
+
"learning_rate": 8.069444444444445e-06,
|
524 |
+
"loss": 0.0574,
|
525 |
+
"step": 1720
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 17.97,
|
529 |
+
"learning_rate": 7.930555555555556e-06,
|
530 |
+
"loss": 0.0575,
|
531 |
+
"step": 1740
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 18.18,
|
535 |
+
"learning_rate": 7.791666666666667e-06,
|
536 |
+
"loss": 0.0561,
|
537 |
+
"step": 1760
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 18.39,
|
541 |
+
"learning_rate": 7.652777777777778e-06,
|
542 |
+
"loss": 0.0541,
|
543 |
+
"step": 1780
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 18.59,
|
547 |
+
"learning_rate": 7.51388888888889e-06,
|
548 |
+
"loss": 0.0528,
|
549 |
+
"step": 1800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 18.8,
|
553 |
+
"learning_rate": 7.375000000000001e-06,
|
554 |
+
"loss": 0.0525,
|
555 |
+
"step": 1820
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 19.01,
|
559 |
+
"learning_rate": 7.2361111111111115e-06,
|
560 |
+
"loss": 0.0503,
|
561 |
+
"step": 1840
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 19.21,
|
565 |
+
"learning_rate": 7.097222222222223e-06,
|
566 |
+
"loss": 0.0485,
|
567 |
+
"step": 1860
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 19.42,
|
571 |
+
"learning_rate": 6.958333333333333e-06,
|
572 |
+
"loss": 0.05,
|
573 |
+
"step": 1880
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 19.63,
|
577 |
+
"learning_rate": 6.819444444444445e-06,
|
578 |
+
"loss": 0.0501,
|
579 |
+
"step": 1900
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 19.83,
|
583 |
+
"learning_rate": 6.680555555555556e-06,
|
584 |
+
"loss": 0.0489,
|
585 |
+
"step": 1920
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 20.04,
|
589 |
+
"learning_rate": 6.541666666666667e-06,
|
590 |
+
"loss": 0.0472,
|
591 |
+
"step": 1940
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 20.25,
|
595 |
+
"learning_rate": 6.402777777777778e-06,
|
596 |
+
"loss": 0.0442,
|
597 |
+
"step": 1960
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 20.45,
|
601 |
+
"learning_rate": 6.26388888888889e-06,
|
602 |
+
"loss": 0.0498,
|
603 |
+
"step": 1980
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 20.66,
|
607 |
+
"learning_rate": 6.125000000000001e-06,
|
608 |
+
"loss": 0.0455,
|
609 |
+
"step": 2000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 20.87,
|
613 |
+
"learning_rate": 5.986111111111112e-06,
|
614 |
+
"loss": 0.0443,
|
615 |
+
"step": 2020
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 21.07,
|
619 |
+
"learning_rate": 5.847222222222223e-06,
|
620 |
+
"loss": 0.0429,
|
621 |
+
"step": 2040
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 21.28,
|
625 |
+
"learning_rate": 5.7083333333333335e-06,
|
626 |
+
"loss": 0.0453,
|
627 |
+
"step": 2060
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 21.48,
|
631 |
+
"learning_rate": 5.569444444444445e-06,
|
632 |
+
"loss": 0.0412,
|
633 |
+
"step": 2080
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 21.69,
|
637 |
+
"learning_rate": 5.430555555555555e-06,
|
638 |
+
"loss": 0.0434,
|
639 |
+
"step": 2100
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 21.9,
|
643 |
+
"learning_rate": 5.291666666666667e-06,
|
644 |
+
"loss": 0.0403,
|
645 |
+
"step": 2120
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 22.1,
|
649 |
+
"learning_rate": 5.152777777777778e-06,
|
650 |
+
"loss": 0.0412,
|
651 |
+
"step": 2140
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 22.31,
|
655 |
+
"learning_rate": 5.013888888888889e-06,
|
656 |
+
"loss": 0.0408,
|
657 |
+
"step": 2160
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 22.52,
|
661 |
+
"learning_rate": 4.875e-06,
|
662 |
+
"loss": 0.0403,
|
663 |
+
"step": 2180
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 22.72,
|
667 |
+
"learning_rate": 4.736111111111112e-06,
|
668 |
+
"loss": 0.04,
|
669 |
+
"step": 2200
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 22.93,
|
673 |
+
"learning_rate": 4.597222222222223e-06,
|
674 |
+
"loss": 0.0396,
|
675 |
+
"step": 2220
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 23.14,
|
679 |
+
"learning_rate": 4.4583333333333336e-06,
|
680 |
+
"loss": 0.0396,
|
681 |
+
"step": 2240
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 23.34,
|
685 |
+
"learning_rate": 4.319444444444445e-06,
|
686 |
+
"loss": 0.038,
|
687 |
+
"step": 2260
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 23.55,
|
691 |
+
"learning_rate": 4.180555555555556e-06,
|
692 |
+
"loss": 0.0388,
|
693 |
+
"step": 2280
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 23.76,
|
697 |
+
"learning_rate": 4.041666666666667e-06,
|
698 |
+
"loss": 0.0388,
|
699 |
+
"step": 2300
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 23.96,
|
703 |
+
"learning_rate": 3.902777777777778e-06,
|
704 |
+
"loss": 0.0368,
|
705 |
+
"step": 2320
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 24.17,
|
709 |
+
"learning_rate": 3.763888888888889e-06,
|
710 |
+
"loss": 0.0357,
|
711 |
+
"step": 2340
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 24.38,
|
715 |
+
"learning_rate": 3.625e-06,
|
716 |
+
"loss": 0.0373,
|
717 |
+
"step": 2360
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 24.58,
|
721 |
+
"learning_rate": 3.4861111111111114e-06,
|
722 |
+
"loss": 0.0373,
|
723 |
+
"step": 2380
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 24.79,
|
727 |
+
"learning_rate": 3.3472222222222223e-06,
|
728 |
+
"loss": 0.0366,
|
729 |
+
"step": 2400
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 25.0,
|
733 |
+
"learning_rate": 3.2083333333333337e-06,
|
734 |
+
"loss": 0.0343,
|
735 |
+
"step": 2420
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 25.2,
|
739 |
+
"learning_rate": 3.069444444444445e-06,
|
740 |
+
"loss": 0.0365,
|
741 |
+
"step": 2440
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 25.41,
|
745 |
+
"learning_rate": 2.930555555555556e-06,
|
746 |
+
"loss": 0.0356,
|
747 |
+
"step": 2460
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 25.62,
|
751 |
+
"learning_rate": 2.791666666666667e-06,
|
752 |
+
"loss": 0.0359,
|
753 |
+
"step": 2480
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 25.82,
|
757 |
+
"learning_rate": 2.652777777777778e-06,
|
758 |
+
"loss": 0.0341,
|
759 |
+
"step": 2500
|
760 |
+
}
|
761 |
+
],
|
762 |
+
"logging_steps": 20,
|
763 |
+
"max_steps": 2880,
|
764 |
+
"num_input_tokens_seen": 0,
|
765 |
+
"num_train_epochs": 30,
|
766 |
+
"save_steps": 500,
|
767 |
+
"total_flos": 7.921287813336269e+17,
|
768 |
+
"train_batch_size": 1,
|
769 |
+
"trial_name": null,
|
770 |
+
"trial_params": null
|
771 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687ee61d860f794218b437b86ef3d4e7d89241cf9246f5eee16a51278e5f8b65
|
3 |
+
size 4728
|
checkpoint-500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-500/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87a25e09f0c9f399e1d30109290bf1719b08d59f1bf5e78253f9112d017f4d3c
|
3 |
+
size 16794200
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:168af1bcc10570047dd881a1f01ea0218fc21539d853d7a9588aef70ef8342f8
|
3 |
+
size 33662074
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11b524d0b858fe80b11d7bb869d41b535e33978776741271092268deb8a60920
|
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 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"learning_rate": 1.9875000000000002e-05,
|
14 |
+
"loss": 1.9446,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.41,
|
19 |
+
"learning_rate": 1.9736111111111115e-05,
|
20 |
+
"loss": 1.7941,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.62,
|
25 |
+
"learning_rate": 1.9597222222222224e-05,
|
26 |
+
"loss": 1.5361,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.83,
|
31 |
+
"learning_rate": 1.9458333333333333e-05,
|
32 |
+
"loss": 1.1041,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.03,
|
37 |
+
"learning_rate": 1.9319444444444446e-05,
|
38 |
+
"loss": 0.6053,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.24,
|
43 |
+
"learning_rate": 1.918055555555556e-05,
|
44 |
+
"loss": 0.4088,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.45,
|
49 |
+
"learning_rate": 1.9041666666666668e-05,
|
50 |
+
"loss": 0.3813,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.65,
|
55 |
+
"learning_rate": 1.890277777777778e-05,
|
56 |
+
"loss": 0.3733,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.86,
|
61 |
+
"learning_rate": 1.876388888888889e-05,
|
62 |
+
"loss": 0.3678,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.07,
|
67 |
+
"learning_rate": 1.8625000000000002e-05,
|
68 |
+
"loss": 0.3604,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.27,
|
73 |
+
"learning_rate": 1.8486111111111115e-05,
|
74 |
+
"loss": 0.3368,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.48,
|
79 |
+
"learning_rate": 1.8347222222222224e-05,
|
80 |
+
"loss": 0.3356,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.69,
|
85 |
+
"learning_rate": 1.8208333333333333e-05,
|
86 |
+
"loss": 0.3439,
|
87 |
+
"step": 260
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.89,
|
91 |
+
"learning_rate": 1.8069444444444446e-05,
|
92 |
+
"loss": 0.3277,
|
93 |
+
"step": 280
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.1,
|
97 |
+
"learning_rate": 1.793055555555556e-05,
|
98 |
+
"loss": 0.3288,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.31,
|
103 |
+
"learning_rate": 1.7791666666666668e-05,
|
104 |
+
"loss": 0.3227,
|
105 |
+
"step": 320
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.51,
|
109 |
+
"learning_rate": 1.765277777777778e-05,
|
110 |
+
"loss": 0.3213,
|
111 |
+
"step": 340
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.72,
|
115 |
+
"learning_rate": 1.751388888888889e-05,
|
116 |
+
"loss": 0.3128,
|
117 |
+
"step": 360
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 3.93,
|
121 |
+
"learning_rate": 1.7375000000000002e-05,
|
122 |
+
"loss": 0.3071,
|
123 |
+
"step": 380
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.13,
|
127 |
+
"learning_rate": 1.7236111111111115e-05,
|
128 |
+
"loss": 0.3022,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.34,
|
133 |
+
"learning_rate": 1.7097222222222224e-05,
|
134 |
+
"loss": 0.2968,
|
135 |
+
"step": 420
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.54,
|
139 |
+
"learning_rate": 1.6958333333333333e-05,
|
140 |
+
"loss": 0.3023,
|
141 |
+
"step": 440
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 4.75,
|
145 |
+
"learning_rate": 1.6819444444444446e-05,
|
146 |
+
"loss": 0.2889,
|
147 |
+
"step": 460
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.96,
|
151 |
+
"learning_rate": 1.668055555555556e-05,
|
152 |
+
"loss": 0.2763,
|
153 |
+
"step": 480
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 5.16,
|
157 |
+
"learning_rate": 1.6541666666666668e-05,
|
158 |
+
"loss": 0.2778,
|
159 |
+
"step": 500
|
160 |
+
}
|
161 |
+
],
|
162 |
+
"logging_steps": 20,
|
163 |
+
"max_steps": 2880,
|
164 |
+
"num_input_tokens_seen": 0,
|
165 |
+
"num_train_epochs": 30,
|
166 |
+
"save_steps": 500,
|
167 |
+
"total_flos": 1.584297707925504e+17,
|
168 |
+
"train_batch_size": 1,
|
169 |
+
"trial_name": null,
|
170 |
+
"trial_params": null
|
171 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687ee61d860f794218b437b86ef3d4e7d89241cf9246f5eee16a51278e5f8b65
|
3 |
+
size 4728
|
runs/Feb21_12-28-15_nlembhrwvg/events.out.tfevents.1708518496.nlembhrwvg.3321.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f195165b510def72fc45e1955f4251a0a071bb5ff7f460dcf83ec3966bd5b8c
|
3 |
+
size 27762
|