Training in progress, epoch 0
Browse files- adapter_model.safetensors +1 -1
- rewriting/adapter_config.json +30 -0
- rewriting/adapter_model.safetensors +3 -0
- rewriting/checkpoint-129/README.md +202 -0
- rewriting/checkpoint-129/adapter_config.json +30 -0
- rewriting/checkpoint-129/adapter_model.safetensors +3 -0
- rewriting/checkpoint-129/optimizer.pt +3 -0
- rewriting/checkpoint-129/rng_state.pth +3 -0
- rewriting/checkpoint-129/scheduler.pt +3 -0
- rewriting/checkpoint-129/trainer_state.json +117 -0
- rewriting/checkpoint-129/training_args.bin +3 -0
- rewriting/checkpoint-258/README.md +202 -0
- rewriting/checkpoint-258/adapter_config.json +30 -0
- rewriting/checkpoint-258/adapter_model.safetensors +3 -0
- rewriting/checkpoint-258/optimizer.pt +3 -0
- rewriting/checkpoint-258/rng_state.pth +3 -0
- rewriting/checkpoint-258/scheduler.pt +3 -0
- rewriting/checkpoint-258/trainer_state.json +208 -0
- rewriting/checkpoint-258/training_args.bin +3 -0
- rewriting/checkpoint-387/README.md +202 -0
- rewriting/checkpoint-387/adapter_config.json +30 -0
- rewriting/checkpoint-387/adapter_model.safetensors +3 -0
- rewriting/checkpoint-387/optimizer.pt +3 -0
- rewriting/checkpoint-387/rng_state.pth +3 -0
- rewriting/checkpoint-387/scheduler.pt +3 -0
- rewriting/checkpoint-387/trainer_state.json +299 -0
- rewriting/checkpoint-387/training_args.bin +3 -0
- rewriting/checkpoint-516/README.md +202 -0
- rewriting/checkpoint-516/adapter_config.json +30 -0
- rewriting/checkpoint-516/adapter_model.safetensors +3 -0
- rewriting/checkpoint-516/optimizer.pt +3 -0
- rewriting/checkpoint-516/rng_state.pth +3 -0
- rewriting/checkpoint-516/scheduler.pt +3 -0
- rewriting/checkpoint-516/trainer_state.json +390 -0
- rewriting/checkpoint-516/training_args.bin +3 -0
- rewriting/checkpoint-645/README.md +202 -0
- rewriting/checkpoint-645/adapter_config.json +30 -0
- rewriting/checkpoint-645/adapter_model.safetensors +3 -0
- rewriting/checkpoint-645/optimizer.pt +3 -0
- rewriting/checkpoint-645/rng_state.pth +3 -0
- rewriting/checkpoint-645/scheduler.pt +3 -0
- rewriting/checkpoint-645/trainer_state.json +481 -0
- rewriting/checkpoint-645/training_args.bin +3 -0
- rewriting/training_args.bin +3 -0
- training_args.bin +1 -1
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18899856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd316ceca210ecba5ef39c53a822c9060181a6c8b8c6f79328ea06899474674
|
3 |
size 18899856
|
rewriting/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
rewriting/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93f3bf189e6a80c2c431b50412f18961a6ba5d10bcc20ace082ee1c09291fda3
|
3 |
+
size 18899856
|
rewriting/checkpoint-129/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
rewriting/checkpoint-129/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
rewriting/checkpoint-129/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bc733358c040d610ff8b62d59b908cd0edc3ad822ddb5188674804ada56ddea
|
3 |
+
size 18899856
|
rewriting/checkpoint-129/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab4d3fd871abd71117fc4c60e30cd7bc7ba5e8995d2299bfcb32068c4dc80b9
|
3 |
+
size 9678714
|
rewriting/checkpoint-129/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af038dae3003dcb7e4f21e24e4b32065cd138e14d9fbedc75475788a956f7ff7
|
3 |
+
size 14244
|
rewriting/checkpoint-129/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a7906b8febfaf518941c39d2db59fbe529374eff4a8c36f5a2780c20d007158
|
3 |
+
size 1064
|
rewriting/checkpoint-129/trainer_state.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 129,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07751937984496124,
|
13 |
+
"grad_norm": 2.245417356491089,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.1087,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15503875968992248,
|
20 |
+
"grad_norm": 3.3328239917755127,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 1.7547,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23255813953488372,
|
27 |
+
"grad_norm": 1.6743243932724,
|
28 |
+
"learning_rate": 9.993684783030088e-05,
|
29 |
+
"loss": 1.3868,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31007751937984496,
|
34 |
+
"grad_norm": 1.585747480392456,
|
35 |
+
"learning_rate": 9.974755084906502e-05,
|
36 |
+
"loss": 1.1455,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3875968992248062,
|
41 |
+
"grad_norm": 1.2781128883361816,
|
42 |
+
"learning_rate": 9.94325872368957e-05,
|
43 |
+
"loss": 1.1394,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46511627906976744,
|
48 |
+
"grad_norm": 1.3732120990753174,
|
49 |
+
"learning_rate": 9.899275261921234e-05,
|
50 |
+
"loss": 1.0942,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5426356589147286,
|
55 |
+
"grad_norm": 1.4817951917648315,
|
56 |
+
"learning_rate": 9.842915805643155e-05,
|
57 |
+
"loss": 0.9934,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6201550387596899,
|
62 |
+
"grad_norm": 1.261801838874817,
|
63 |
+
"learning_rate": 9.774322723733216e-05,
|
64 |
+
"loss": 1.0093,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.6976744186046512,
|
69 |
+
"grad_norm": 1.801243782043457,
|
70 |
+
"learning_rate": 9.693669288269372e-05,
|
71 |
+
"loss": 1.0686,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.7751937984496124,
|
76 |
+
"grad_norm": 1.719342827796936,
|
77 |
+
"learning_rate": 9.601159236829352e-05,
|
78 |
+
"loss": 0.9973,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8527131782945736,
|
83 |
+
"grad_norm": 1.5797449350357056,
|
84 |
+
"learning_rate": 9.497026257831855e-05,
|
85 |
+
"loss": 1.0002,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9302325581395349,
|
90 |
+
"grad_norm": 1.790971279144287,
|
91 |
+
"learning_rate": 9.381533400219318e-05,
|
92 |
+
"loss": 0.9484,
|
93 |
+
"step": 120
|
94 |
+
}
|
95 |
+
],
|
96 |
+
"logging_steps": 10,
|
97 |
+
"max_steps": 645,
|
98 |
+
"num_input_tokens_seen": 0,
|
99 |
+
"num_train_epochs": 5,
|
100 |
+
"save_steps": 500,
|
101 |
+
"stateful_callbacks": {
|
102 |
+
"TrainerControl": {
|
103 |
+
"args": {
|
104 |
+
"should_epoch_stop": false,
|
105 |
+
"should_evaluate": false,
|
106 |
+
"should_log": false,
|
107 |
+
"should_save": true,
|
108 |
+
"should_training_stop": false
|
109 |
+
},
|
110 |
+
"attributes": {}
|
111 |
+
}
|
112 |
+
},
|
113 |
+
"total_flos": 1.3332260188028928e+16,
|
114 |
+
"train_batch_size": 4,
|
115 |
+
"trial_name": null,
|
116 |
+
"trial_params": null
|
117 |
+
}
|
rewriting/checkpoint-129/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4927757fe5693d5a3f8358383ea06db1c00891947f26a31894625d5b7a0d93d
|
3 |
+
size 5176
|
rewriting/checkpoint-258/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
rewriting/checkpoint-258/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
rewriting/checkpoint-258/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21d08046922f8a309dc2c95324b631a9e153fb35179d5b6dc611619bb2cfc6c9
|
3 |
+
size 18899856
|
rewriting/checkpoint-258/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f70e1a8a061c4dd52b19be46f5c201a11ca2930c4b16dd5f120dd6d9d04fab3
|
3 |
+
size 9678906
|
rewriting/checkpoint-258/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:992512dab76482bc68057d2d1182fed2fa70434f6b3e342a4340c0d9f76874b4
|
3 |
+
size 14244
|
rewriting/checkpoint-258/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:570200398cb37a681fb2a1e222170366104f0ac02b667616b10b76d05468c808
|
3 |
+
size 1064
|
rewriting/checkpoint-258/trainer_state.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 258,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07751937984496124,
|
13 |
+
"grad_norm": 2.245417356491089,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.1087,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15503875968992248,
|
20 |
+
"grad_norm": 3.3328239917755127,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 1.7547,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23255813953488372,
|
27 |
+
"grad_norm": 1.6743243932724,
|
28 |
+
"learning_rate": 9.993684783030088e-05,
|
29 |
+
"loss": 1.3868,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31007751937984496,
|
34 |
+
"grad_norm": 1.585747480392456,
|
35 |
+
"learning_rate": 9.974755084906502e-05,
|
36 |
+
"loss": 1.1455,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3875968992248062,
|
41 |
+
"grad_norm": 1.2781128883361816,
|
42 |
+
"learning_rate": 9.94325872368957e-05,
|
43 |
+
"loss": 1.1394,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46511627906976744,
|
48 |
+
"grad_norm": 1.3732120990753174,
|
49 |
+
"learning_rate": 9.899275261921234e-05,
|
50 |
+
"loss": 1.0942,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5426356589147286,
|
55 |
+
"grad_norm": 1.4817951917648315,
|
56 |
+
"learning_rate": 9.842915805643155e-05,
|
57 |
+
"loss": 0.9934,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6201550387596899,
|
62 |
+
"grad_norm": 1.261801838874817,
|
63 |
+
"learning_rate": 9.774322723733216e-05,
|
64 |
+
"loss": 1.0093,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.6976744186046512,
|
69 |
+
"grad_norm": 1.801243782043457,
|
70 |
+
"learning_rate": 9.693669288269372e-05,
|
71 |
+
"loss": 1.0686,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.7751937984496124,
|
76 |
+
"grad_norm": 1.719342827796936,
|
77 |
+
"learning_rate": 9.601159236829352e-05,
|
78 |
+
"loss": 0.9973,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8527131782945736,
|
83 |
+
"grad_norm": 1.5797449350357056,
|
84 |
+
"learning_rate": 9.497026257831855e-05,
|
85 |
+
"loss": 1.0002,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9302325581395349,
|
90 |
+
"grad_norm": 1.790971279144287,
|
91 |
+
"learning_rate": 9.381533400219318e-05,
|
92 |
+
"loss": 0.9484,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0077519379844961,
|
97 |
+
"grad_norm": 1.6127315759658813,
|
98 |
+
"learning_rate": 9.254972408973461e-05,
|
99 |
+
"loss": 0.979,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.0852713178294573,
|
104 |
+
"grad_norm": 1.4869861602783203,
|
105 |
+
"learning_rate": 9.117662988142138e-05,
|
106 |
+
"loss": 0.8899,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.1627906976744187,
|
111 |
+
"grad_norm": 2.101341962814331,
|
112 |
+
"learning_rate": 8.969951993239177e-05,
|
113 |
+
"loss": 0.9493,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.2403100775193798,
|
118 |
+
"grad_norm": 1.7181503772735596,
|
119 |
+
"learning_rate": 8.81221255505724e-05,
|
120 |
+
"loss": 0.8715,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3178294573643412,
|
125 |
+
"grad_norm": 2.006377696990967,
|
126 |
+
"learning_rate": 8.644843137107059e-05,
|
127 |
+
"loss": 0.8846,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.3953488372093024,
|
132 |
+
"grad_norm": 2.0157504081726074,
|
133 |
+
"learning_rate": 8.468266529064025e-05,
|
134 |
+
"loss": 0.9292,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.4728682170542635,
|
139 |
+
"grad_norm": 1.704633355140686,
|
140 |
+
"learning_rate": 8.282928778764783e-05,
|
141 |
+
"loss": 0.8883,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.550387596899225,
|
146 |
+
"grad_norm": 1.7320111989974976,
|
147 |
+
"learning_rate": 8.089298065451672e-05,
|
148 |
+
"loss": 0.874,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.627906976744186,
|
153 |
+
"grad_norm": 2.369300127029419,
|
154 |
+
"learning_rate": 7.887863517111338e-05,
|
155 |
+
"loss": 0.8688,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.7054263565891472,
|
160 |
+
"grad_norm": 1.5535732507705688,
|
161 |
+
"learning_rate": 7.679133974894983e-05,
|
162 |
+
"loss": 0.8726,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.7829457364341086,
|
167 |
+
"grad_norm": 1.9749231338500977,
|
168 |
+
"learning_rate": 7.463636707741458e-05,
|
169 |
+
"loss": 0.8252,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.8604651162790697,
|
174 |
+
"grad_norm": 2.261054277420044,
|
175 |
+
"learning_rate": 7.241916080450163e-05,
|
176 |
+
"loss": 0.846,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.937984496124031,
|
181 |
+
"grad_norm": 2.019524097442627,
|
182 |
+
"learning_rate": 7.014532178568314e-05,
|
183 |
+
"loss": 0.8104,
|
184 |
+
"step": 250
|
185 |
+
}
|
186 |
+
],
|
187 |
+
"logging_steps": 10,
|
188 |
+
"max_steps": 645,
|
189 |
+
"num_input_tokens_seen": 0,
|
190 |
+
"num_train_epochs": 5,
|
191 |
+
"save_steps": 500,
|
192 |
+
"stateful_callbacks": {
|
193 |
+
"TrainerControl": {
|
194 |
+
"args": {
|
195 |
+
"should_epoch_stop": false,
|
196 |
+
"should_evaluate": false,
|
197 |
+
"should_log": false,
|
198 |
+
"should_save": true,
|
199 |
+
"should_training_stop": false
|
200 |
+
},
|
201 |
+
"attributes": {}
|
202 |
+
}
|
203 |
+
},
|
204 |
+
"total_flos": 2.681627524713677e+16,
|
205 |
+
"train_batch_size": 4,
|
206 |
+
"trial_name": null,
|
207 |
+
"trial_params": null
|
208 |
+
}
|
rewriting/checkpoint-258/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4927757fe5693d5a3f8358383ea06db1c00891947f26a31894625d5b7a0d93d
|
3 |
+
size 5176
|
rewriting/checkpoint-387/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
rewriting/checkpoint-387/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
rewriting/checkpoint-387/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ccd505680c5a75a4a21ef099e246295413531f36f293fb7c6e6439b241058e8
|
3 |
+
size 18899856
|
rewriting/checkpoint-387/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46ba850c8d5d704404852a25cd91c1f89e0cb6fe3c5d54948bec415c511add92
|
3 |
+
size 9678906
|
rewriting/checkpoint-387/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbf6c8627f4e3e8864b0af9dc65557183f677b33f318babfb15bf5cbc1b9eb1f
|
3 |
+
size 14244
|
rewriting/checkpoint-387/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d10e05bea18d12bf1ed60692fd07eaed7acdafb85acb86067ce101a683d71a
|
3 |
+
size 1064
|
rewriting/checkpoint-387/trainer_state.json
ADDED
@@ -0,0 +1,299 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 387,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07751937984496124,
|
13 |
+
"grad_norm": 2.245417356491089,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.1087,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15503875968992248,
|
20 |
+
"grad_norm": 3.3328239917755127,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 1.7547,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23255813953488372,
|
27 |
+
"grad_norm": 1.6743243932724,
|
28 |
+
"learning_rate": 9.993684783030088e-05,
|
29 |
+
"loss": 1.3868,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31007751937984496,
|
34 |
+
"grad_norm": 1.585747480392456,
|
35 |
+
"learning_rate": 9.974755084906502e-05,
|
36 |
+
"loss": 1.1455,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3875968992248062,
|
41 |
+
"grad_norm": 1.2781128883361816,
|
42 |
+
"learning_rate": 9.94325872368957e-05,
|
43 |
+
"loss": 1.1394,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46511627906976744,
|
48 |
+
"grad_norm": 1.3732120990753174,
|
49 |
+
"learning_rate": 9.899275261921234e-05,
|
50 |
+
"loss": 1.0942,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5426356589147286,
|
55 |
+
"grad_norm": 1.4817951917648315,
|
56 |
+
"learning_rate": 9.842915805643155e-05,
|
57 |
+
"loss": 0.9934,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6201550387596899,
|
62 |
+
"grad_norm": 1.261801838874817,
|
63 |
+
"learning_rate": 9.774322723733216e-05,
|
64 |
+
"loss": 1.0093,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.6976744186046512,
|
69 |
+
"grad_norm": 1.801243782043457,
|
70 |
+
"learning_rate": 9.693669288269372e-05,
|
71 |
+
"loss": 1.0686,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.7751937984496124,
|
76 |
+
"grad_norm": 1.719342827796936,
|
77 |
+
"learning_rate": 9.601159236829352e-05,
|
78 |
+
"loss": 0.9973,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8527131782945736,
|
83 |
+
"grad_norm": 1.5797449350357056,
|
84 |
+
"learning_rate": 9.497026257831855e-05,
|
85 |
+
"loss": 1.0002,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9302325581395349,
|
90 |
+
"grad_norm": 1.790971279144287,
|
91 |
+
"learning_rate": 9.381533400219318e-05,
|
92 |
+
"loss": 0.9484,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0077519379844961,
|
97 |
+
"grad_norm": 1.6127315759658813,
|
98 |
+
"learning_rate": 9.254972408973461e-05,
|
99 |
+
"loss": 0.979,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.0852713178294573,
|
104 |
+
"grad_norm": 1.4869861602783203,
|
105 |
+
"learning_rate": 9.117662988142138e-05,
|
106 |
+
"loss": 0.8899,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.1627906976744187,
|
111 |
+
"grad_norm": 2.101341962814331,
|
112 |
+
"learning_rate": 8.969951993239177e-05,
|
113 |
+
"loss": 0.9493,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.2403100775193798,
|
118 |
+
"grad_norm": 1.7181503772735596,
|
119 |
+
"learning_rate": 8.81221255505724e-05,
|
120 |
+
"loss": 0.8715,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3178294573643412,
|
125 |
+
"grad_norm": 2.006377696990967,
|
126 |
+
"learning_rate": 8.644843137107059e-05,
|
127 |
+
"loss": 0.8846,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.3953488372093024,
|
132 |
+
"grad_norm": 2.0157504081726074,
|
133 |
+
"learning_rate": 8.468266529064025e-05,
|
134 |
+
"loss": 0.9292,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.4728682170542635,
|
139 |
+
"grad_norm": 1.704633355140686,
|
140 |
+
"learning_rate": 8.282928778764783e-05,
|
141 |
+
"loss": 0.8883,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.550387596899225,
|
146 |
+
"grad_norm": 1.7320111989974976,
|
147 |
+
"learning_rate": 8.089298065451672e-05,
|
148 |
+
"loss": 0.874,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.627906976744186,
|
153 |
+
"grad_norm": 2.369300127029419,
|
154 |
+
"learning_rate": 7.887863517111338e-05,
|
155 |
+
"loss": 0.8688,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.7054263565891472,
|
160 |
+
"grad_norm": 1.5535732507705688,
|
161 |
+
"learning_rate": 7.679133974894983e-05,
|
162 |
+
"loss": 0.8726,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.7829457364341086,
|
167 |
+
"grad_norm": 1.9749231338500977,
|
168 |
+
"learning_rate": 7.463636707741458e-05,
|
169 |
+
"loss": 0.8252,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.8604651162790697,
|
174 |
+
"grad_norm": 2.261054277420044,
|
175 |
+
"learning_rate": 7.241916080450163e-05,
|
176 |
+
"loss": 0.846,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.937984496124031,
|
181 |
+
"grad_norm": 2.019524097442627,
|
182 |
+
"learning_rate": 7.014532178568314e-05,
|
183 |
+
"loss": 0.8104,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.0155038759689923,
|
188 |
+
"grad_norm": 1.8253782987594604,
|
189 |
+
"learning_rate": 6.782059393566253e-05,
|
190 |
+
"loss": 0.8436,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.0930232558139537,
|
195 |
+
"grad_norm": 1.92261803150177,
|
196 |
+
"learning_rate": 6.545084971874738e-05,
|
197 |
+
"loss": 0.8007,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.1705426356589146,
|
202 |
+
"grad_norm": 1.959991455078125,
|
203 |
+
"learning_rate": 6.304207531449486e-05,
|
204 |
+
"loss": 0.8093,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.248062015503876,
|
209 |
+
"grad_norm": 2.0819852352142334,
|
210 |
+
"learning_rate": 6.0600355496102745e-05,
|
211 |
+
"loss": 0.7626,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.3255813953488373,
|
216 |
+
"grad_norm": 2.1029396057128906,
|
217 |
+
"learning_rate": 5.813185825974419e-05,
|
218 |
+
"loss": 0.7995,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.4031007751937983,
|
223 |
+
"grad_norm": 2.149883508682251,
|
224 |
+
"learning_rate": 5.564281924367408e-05,
|
225 |
+
"loss": 0.7867,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.4806201550387597,
|
230 |
+
"grad_norm": 2.2461025714874268,
|
231 |
+
"learning_rate": 5.313952597646568e-05,
|
232 |
+
"loss": 0.778,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.558139534883721,
|
237 |
+
"grad_norm": 2.1659789085388184,
|
238 |
+
"learning_rate": 5.062830199416764e-05,
|
239 |
+
"loss": 0.8143,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.6356589147286824,
|
244 |
+
"grad_norm": 2.3656270503997803,
|
245 |
+
"learning_rate": 4.811549086650327e-05,
|
246 |
+
"loss": 0.8017,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.7131782945736433,
|
251 |
+
"grad_norm": 2.3753740787506104,
|
252 |
+
"learning_rate": 4.560744017246284e-05,
|
253 |
+
"loss": 0.7666,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.7906976744186047,
|
258 |
+
"grad_norm": 2.221393585205078,
|
259 |
+
"learning_rate": 4.31104854657681e-05,
|
260 |
+
"loss": 0.7679,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.8682170542635657,
|
265 |
+
"grad_norm": 2.018345594406128,
|
266 |
+
"learning_rate": 4.063093427071376e-05,
|
267 |
+
"loss": 0.7507,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.945736434108527,
|
272 |
+
"grad_norm": 2.199131965637207,
|
273 |
+
"learning_rate": 3.817505014881378e-05,
|
274 |
+
"loss": 0.7413,
|
275 |
+
"step": 380
|
276 |
+
}
|
277 |
+
],
|
278 |
+
"logging_steps": 10,
|
279 |
+
"max_steps": 645,
|
280 |
+
"num_input_tokens_seen": 0,
|
281 |
+
"num_train_epochs": 5,
|
282 |
+
"save_steps": 500,
|
283 |
+
"stateful_callbacks": {
|
284 |
+
"TrainerControl": {
|
285 |
+
"args": {
|
286 |
+
"should_epoch_stop": false,
|
287 |
+
"should_evaluate": false,
|
288 |
+
"should_log": false,
|
289 |
+
"should_save": true,
|
290 |
+
"should_training_stop": false
|
291 |
+
},
|
292 |
+
"attributes": {}
|
293 |
+
}
|
294 |
+
},
|
295 |
+
"total_flos": 4.029055780857446e+16,
|
296 |
+
"train_batch_size": 4,
|
297 |
+
"trial_name": null,
|
298 |
+
"trial_params": null
|
299 |
+
}
|
rewriting/checkpoint-387/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4927757fe5693d5a3f8358383ea06db1c00891947f26a31894625d5b7a0d93d
|
3 |
+
size 5176
|
rewriting/checkpoint-516/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
rewriting/checkpoint-516/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
rewriting/checkpoint-516/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac196999b86bf828f7926573a92a8e97acea484efcb24d00ea335b0b5f77cf43
|
3 |
+
size 18899856
|
rewriting/checkpoint-516/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fccd56f7463605590eed92a1578599141e09cae5d2e37c1dc427a9f8ec64633
|
3 |
+
size 9678906
|
rewriting/checkpoint-516/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e287f148b3be4564818b33c334a126d4ad30ad46c5bc1ac1c8c539f0871945dd
|
3 |
+
size 14244
|
rewriting/checkpoint-516/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:871ffc4fd770f0c4414ede2e0cb3a9c858d864396c0b22120b8b0ecfddddb8e9
|
3 |
+
size 1064
|
rewriting/checkpoint-516/trainer_state.json
ADDED
@@ -0,0 +1,390 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 516,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07751937984496124,
|
13 |
+
"grad_norm": 2.245417356491089,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.1087,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15503875968992248,
|
20 |
+
"grad_norm": 3.3328239917755127,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 1.7547,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23255813953488372,
|
27 |
+
"grad_norm": 1.6743243932724,
|
28 |
+
"learning_rate": 9.993684783030088e-05,
|
29 |
+
"loss": 1.3868,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31007751937984496,
|
34 |
+
"grad_norm": 1.585747480392456,
|
35 |
+
"learning_rate": 9.974755084906502e-05,
|
36 |
+
"loss": 1.1455,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3875968992248062,
|
41 |
+
"grad_norm": 1.2781128883361816,
|
42 |
+
"learning_rate": 9.94325872368957e-05,
|
43 |
+
"loss": 1.1394,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46511627906976744,
|
48 |
+
"grad_norm": 1.3732120990753174,
|
49 |
+
"learning_rate": 9.899275261921234e-05,
|
50 |
+
"loss": 1.0942,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5426356589147286,
|
55 |
+
"grad_norm": 1.4817951917648315,
|
56 |
+
"learning_rate": 9.842915805643155e-05,
|
57 |
+
"loss": 0.9934,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6201550387596899,
|
62 |
+
"grad_norm": 1.261801838874817,
|
63 |
+
"learning_rate": 9.774322723733216e-05,
|
64 |
+
"loss": 1.0093,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.6976744186046512,
|
69 |
+
"grad_norm": 1.801243782043457,
|
70 |
+
"learning_rate": 9.693669288269372e-05,
|
71 |
+
"loss": 1.0686,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.7751937984496124,
|
76 |
+
"grad_norm": 1.719342827796936,
|
77 |
+
"learning_rate": 9.601159236829352e-05,
|
78 |
+
"loss": 0.9973,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8527131782945736,
|
83 |
+
"grad_norm": 1.5797449350357056,
|
84 |
+
"learning_rate": 9.497026257831855e-05,
|
85 |
+
"loss": 1.0002,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9302325581395349,
|
90 |
+
"grad_norm": 1.790971279144287,
|
91 |
+
"learning_rate": 9.381533400219318e-05,
|
92 |
+
"loss": 0.9484,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0077519379844961,
|
97 |
+
"grad_norm": 1.6127315759658813,
|
98 |
+
"learning_rate": 9.254972408973461e-05,
|
99 |
+
"loss": 0.979,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.0852713178294573,
|
104 |
+
"grad_norm": 1.4869861602783203,
|
105 |
+
"learning_rate": 9.117662988142138e-05,
|
106 |
+
"loss": 0.8899,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.1627906976744187,
|
111 |
+
"grad_norm": 2.101341962814331,
|
112 |
+
"learning_rate": 8.969951993239177e-05,
|
113 |
+
"loss": 0.9493,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.2403100775193798,
|
118 |
+
"grad_norm": 1.7181503772735596,
|
119 |
+
"learning_rate": 8.81221255505724e-05,
|
120 |
+
"loss": 0.8715,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3178294573643412,
|
125 |
+
"grad_norm": 2.006377696990967,
|
126 |
+
"learning_rate": 8.644843137107059e-05,
|
127 |
+
"loss": 0.8846,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.3953488372093024,
|
132 |
+
"grad_norm": 2.0157504081726074,
|
133 |
+
"learning_rate": 8.468266529064025e-05,
|
134 |
+
"loss": 0.9292,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.4728682170542635,
|
139 |
+
"grad_norm": 1.704633355140686,
|
140 |
+
"learning_rate": 8.282928778764783e-05,
|
141 |
+
"loss": 0.8883,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.550387596899225,
|
146 |
+
"grad_norm": 1.7320111989974976,
|
147 |
+
"learning_rate": 8.089298065451672e-05,
|
148 |
+
"loss": 0.874,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.627906976744186,
|
153 |
+
"grad_norm": 2.369300127029419,
|
154 |
+
"learning_rate": 7.887863517111338e-05,
|
155 |
+
"loss": 0.8688,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.7054263565891472,
|
160 |
+
"grad_norm": 1.5535732507705688,
|
161 |
+
"learning_rate": 7.679133974894983e-05,
|
162 |
+
"loss": 0.8726,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.7829457364341086,
|
167 |
+
"grad_norm": 1.9749231338500977,
|
168 |
+
"learning_rate": 7.463636707741458e-05,
|
169 |
+
"loss": 0.8252,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.8604651162790697,
|
174 |
+
"grad_norm": 2.261054277420044,
|
175 |
+
"learning_rate": 7.241916080450163e-05,
|
176 |
+
"loss": 0.846,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.937984496124031,
|
181 |
+
"grad_norm": 2.019524097442627,
|
182 |
+
"learning_rate": 7.014532178568314e-05,
|
183 |
+
"loss": 0.8104,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.0155038759689923,
|
188 |
+
"grad_norm": 1.8253782987594604,
|
189 |
+
"learning_rate": 6.782059393566253e-05,
|
190 |
+
"loss": 0.8436,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.0930232558139537,
|
195 |
+
"grad_norm": 1.92261803150177,
|
196 |
+
"learning_rate": 6.545084971874738e-05,
|
197 |
+
"loss": 0.8007,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.1705426356589146,
|
202 |
+
"grad_norm": 1.959991455078125,
|
203 |
+
"learning_rate": 6.304207531449486e-05,
|
204 |
+
"loss": 0.8093,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.248062015503876,
|
209 |
+
"grad_norm": 2.0819852352142334,
|
210 |
+
"learning_rate": 6.0600355496102745e-05,
|
211 |
+
"loss": 0.7626,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.3255813953488373,
|
216 |
+
"grad_norm": 2.1029396057128906,
|
217 |
+
"learning_rate": 5.813185825974419e-05,
|
218 |
+
"loss": 0.7995,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.4031007751937983,
|
223 |
+
"grad_norm": 2.149883508682251,
|
224 |
+
"learning_rate": 5.564281924367408e-05,
|
225 |
+
"loss": 0.7867,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.4806201550387597,
|
230 |
+
"grad_norm": 2.2461025714874268,
|
231 |
+
"learning_rate": 5.313952597646568e-05,
|
232 |
+
"loss": 0.778,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.558139534883721,
|
237 |
+
"grad_norm": 2.1659789085388184,
|
238 |
+
"learning_rate": 5.062830199416764e-05,
|
239 |
+
"loss": 0.8143,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.6356589147286824,
|
244 |
+
"grad_norm": 2.3656270503997803,
|
245 |
+
"learning_rate": 4.811549086650327e-05,
|
246 |
+
"loss": 0.8017,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.7131782945736433,
|
251 |
+
"grad_norm": 2.3753740787506104,
|
252 |
+
"learning_rate": 4.560744017246284e-05,
|
253 |
+
"loss": 0.7666,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.7906976744186047,
|
258 |
+
"grad_norm": 2.221393585205078,
|
259 |
+
"learning_rate": 4.31104854657681e-05,
|
260 |
+
"loss": 0.7679,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.8682170542635657,
|
265 |
+
"grad_norm": 2.018345594406128,
|
266 |
+
"learning_rate": 4.063093427071376e-05,
|
267 |
+
"loss": 0.7507,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.945736434108527,
|
272 |
+
"grad_norm": 2.199131965637207,
|
273 |
+
"learning_rate": 3.817505014881378e-05,
|
274 |
+
"loss": 0.7413,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.0232558139534884,
|
279 |
+
"grad_norm": 2.139735698699951,
|
280 |
+
"learning_rate": 3.5749036876501194e-05,
|
281 |
+
"loss": 0.8139,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.10077519379845,
|
286 |
+
"grad_norm": 2.0483205318450928,
|
287 |
+
"learning_rate": 3.335902277385067e-05,
|
288 |
+
"loss": 0.7209,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 3.1782945736434107,
|
293 |
+
"grad_norm": 2.3175625801086426,
|
294 |
+
"learning_rate": 3.101104522390995e-05,
|
295 |
+
"loss": 0.7392,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.255813953488372,
|
300 |
+
"grad_norm": 2.267725944519043,
|
301 |
+
"learning_rate": 2.8711035421746367e-05,
|
302 |
+
"loss": 0.7487,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.3333333333333335,
|
307 |
+
"grad_norm": 2.491976261138916,
|
308 |
+
"learning_rate": 2.6464803391733374e-05,
|
309 |
+
"loss": 0.7472,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 3.4108527131782944,
|
314 |
+
"grad_norm": 2.3867716789245605,
|
315 |
+
"learning_rate": 2.4278023310924673e-05,
|
316 |
+
"loss": 0.7194,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.488372093023256,
|
321 |
+
"grad_norm": 2.1725575923919678,
|
322 |
+
"learning_rate": 2.215621917559062e-05,
|
323 |
+
"loss": 0.7435,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.565891472868217,
|
328 |
+
"grad_norm": 2.362307071685791,
|
329 |
+
"learning_rate": 2.0104750847124075e-05,
|
330 |
+
"loss": 0.7257,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 3.6434108527131785,
|
335 |
+
"grad_norm": 2.3659157752990723,
|
336 |
+
"learning_rate": 1.8128800512565513e-05,
|
337 |
+
"loss": 0.7498,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.7209302325581395,
|
342 |
+
"grad_norm": 2.225560188293457,
|
343 |
+
"learning_rate": 1.6233359593948777e-05,
|
344 |
+
"loss": 0.7308,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.798449612403101,
|
349 |
+
"grad_norm": 2.4101855754852295,
|
350 |
+
"learning_rate": 1.4423216139535734e-05,
|
351 |
+
"loss": 0.7524,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 3.875968992248062,
|
356 |
+
"grad_norm": 2.295118808746338,
|
357 |
+
"learning_rate": 1.2702942728790895e-05,
|
358 |
+
"loss": 0.7239,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 3.953488372093023,
|
363 |
+
"grad_norm": 2.7008495330810547,
|
364 |
+
"learning_rate": 1.1076884921648834e-05,
|
365 |
+
"loss": 0.7305,
|
366 |
+
"step": 510
|
367 |
+
}
|
368 |
+
],
|
369 |
+
"logging_steps": 10,
|
370 |
+
"max_steps": 645,
|
371 |
+
"num_input_tokens_seen": 0,
|
372 |
+
"num_train_epochs": 5,
|
373 |
+
"save_steps": 500,
|
374 |
+
"stateful_callbacks": {
|
375 |
+
"TrainerControl": {
|
376 |
+
"args": {
|
377 |
+
"should_epoch_stop": false,
|
378 |
+
"should_evaluate": false,
|
379 |
+
"should_log": false,
|
380 |
+
"should_save": true,
|
381 |
+
"should_training_stop": false
|
382 |
+
},
|
383 |
+
"attributes": {}
|
384 |
+
}
|
385 |
+
},
|
386 |
+
"total_flos": 5.387586293602714e+16,
|
387 |
+
"train_batch_size": 4,
|
388 |
+
"trial_name": null,
|
389 |
+
"trial_params": null
|
390 |
+
}
|
rewriting/checkpoint-516/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4927757fe5693d5a3f8358383ea06db1c00891947f26a31894625d5b7a0d93d
|
3 |
+
size 5176
|
rewriting/checkpoint-645/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
rewriting/checkpoint-645/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
rewriting/checkpoint-645/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93f3bf189e6a80c2c431b50412f18961a6ba5d10bcc20ace082ee1c09291fda3
|
3 |
+
size 18899856
|
rewriting/checkpoint-645/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96e090077426df553187d351f1b5fdf73a9716c7159f8d999d82cf4930c617f2
|
3 |
+
size 9678906
|
rewriting/checkpoint-645/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e543acdc33f9f623ea1846b184de72a23ebd4444697dbe38079558e468899c2
|
3 |
+
size 14244
|
rewriting/checkpoint-645/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90993da29e5d0c75b8e815b1c79f8712c416ad01eb3e8a6c18ab6c850a704ad8
|
3 |
+
size 1064
|
rewriting/checkpoint-645/trainer_state.json
ADDED
@@ -0,0 +1,481 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 645,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07751937984496124,
|
13 |
+
"grad_norm": 2.245417356491089,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 2.1087,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15503875968992248,
|
20 |
+
"grad_norm": 3.3328239917755127,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 1.7547,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23255813953488372,
|
27 |
+
"grad_norm": 1.6743243932724,
|
28 |
+
"learning_rate": 9.993684783030088e-05,
|
29 |
+
"loss": 1.3868,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31007751937984496,
|
34 |
+
"grad_norm": 1.585747480392456,
|
35 |
+
"learning_rate": 9.974755084906502e-05,
|
36 |
+
"loss": 1.1455,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3875968992248062,
|
41 |
+
"grad_norm": 1.2781128883361816,
|
42 |
+
"learning_rate": 9.94325872368957e-05,
|
43 |
+
"loss": 1.1394,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46511627906976744,
|
48 |
+
"grad_norm": 1.3732120990753174,
|
49 |
+
"learning_rate": 9.899275261921234e-05,
|
50 |
+
"loss": 1.0942,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5426356589147286,
|
55 |
+
"grad_norm": 1.4817951917648315,
|
56 |
+
"learning_rate": 9.842915805643155e-05,
|
57 |
+
"loss": 0.9934,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6201550387596899,
|
62 |
+
"grad_norm": 1.261801838874817,
|
63 |
+
"learning_rate": 9.774322723733216e-05,
|
64 |
+
"loss": 1.0093,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.6976744186046512,
|
69 |
+
"grad_norm": 1.801243782043457,
|
70 |
+
"learning_rate": 9.693669288269372e-05,
|
71 |
+
"loss": 1.0686,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.7751937984496124,
|
76 |
+
"grad_norm": 1.719342827796936,
|
77 |
+
"learning_rate": 9.601159236829352e-05,
|
78 |
+
"loss": 0.9973,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8527131782945736,
|
83 |
+
"grad_norm": 1.5797449350357056,
|
84 |
+
"learning_rate": 9.497026257831855e-05,
|
85 |
+
"loss": 1.0002,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9302325581395349,
|
90 |
+
"grad_norm": 1.790971279144287,
|
91 |
+
"learning_rate": 9.381533400219318e-05,
|
92 |
+
"loss": 0.9484,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0077519379844961,
|
97 |
+
"grad_norm": 1.6127315759658813,
|
98 |
+
"learning_rate": 9.254972408973461e-05,
|
99 |
+
"loss": 0.979,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.0852713178294573,
|
104 |
+
"grad_norm": 1.4869861602783203,
|
105 |
+
"learning_rate": 9.117662988142138e-05,
|
106 |
+
"loss": 0.8899,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.1627906976744187,
|
111 |
+
"grad_norm": 2.101341962814331,
|
112 |
+
"learning_rate": 8.969951993239177e-05,
|
113 |
+
"loss": 0.9493,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.2403100775193798,
|
118 |
+
"grad_norm": 1.7181503772735596,
|
119 |
+
"learning_rate": 8.81221255505724e-05,
|
120 |
+
"loss": 0.8715,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.3178294573643412,
|
125 |
+
"grad_norm": 2.006377696990967,
|
126 |
+
"learning_rate": 8.644843137107059e-05,
|
127 |
+
"loss": 0.8846,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.3953488372093024,
|
132 |
+
"grad_norm": 2.0157504081726074,
|
133 |
+
"learning_rate": 8.468266529064025e-05,
|
134 |
+
"loss": 0.9292,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.4728682170542635,
|
139 |
+
"grad_norm": 1.704633355140686,
|
140 |
+
"learning_rate": 8.282928778764783e-05,
|
141 |
+
"loss": 0.8883,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.550387596899225,
|
146 |
+
"grad_norm": 1.7320111989974976,
|
147 |
+
"learning_rate": 8.089298065451672e-05,
|
148 |
+
"loss": 0.874,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.627906976744186,
|
153 |
+
"grad_norm": 2.369300127029419,
|
154 |
+
"learning_rate": 7.887863517111338e-05,
|
155 |
+
"loss": 0.8688,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.7054263565891472,
|
160 |
+
"grad_norm": 1.5535732507705688,
|
161 |
+
"learning_rate": 7.679133974894983e-05,
|
162 |
+
"loss": 0.8726,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.7829457364341086,
|
167 |
+
"grad_norm": 1.9749231338500977,
|
168 |
+
"learning_rate": 7.463636707741458e-05,
|
169 |
+
"loss": 0.8252,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.8604651162790697,
|
174 |
+
"grad_norm": 2.261054277420044,
|
175 |
+
"learning_rate": 7.241916080450163e-05,
|
176 |
+
"loss": 0.846,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.937984496124031,
|
181 |
+
"grad_norm": 2.019524097442627,
|
182 |
+
"learning_rate": 7.014532178568314e-05,
|
183 |
+
"loss": 0.8104,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.0155038759689923,
|
188 |
+
"grad_norm": 1.8253782987594604,
|
189 |
+
"learning_rate": 6.782059393566253e-05,
|
190 |
+
"loss": 0.8436,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.0930232558139537,
|
195 |
+
"grad_norm": 1.92261803150177,
|
196 |
+
"learning_rate": 6.545084971874738e-05,
|
197 |
+
"loss": 0.8007,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.1705426356589146,
|
202 |
+
"grad_norm": 1.959991455078125,
|
203 |
+
"learning_rate": 6.304207531449486e-05,
|
204 |
+
"loss": 0.8093,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.248062015503876,
|
209 |
+
"grad_norm": 2.0819852352142334,
|
210 |
+
"learning_rate": 6.0600355496102745e-05,
|
211 |
+
"loss": 0.7626,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.3255813953488373,
|
216 |
+
"grad_norm": 2.1029396057128906,
|
217 |
+
"learning_rate": 5.813185825974419e-05,
|
218 |
+
"loss": 0.7995,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.4031007751937983,
|
223 |
+
"grad_norm": 2.149883508682251,
|
224 |
+
"learning_rate": 5.564281924367408e-05,
|
225 |
+
"loss": 0.7867,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.4806201550387597,
|
230 |
+
"grad_norm": 2.2461025714874268,
|
231 |
+
"learning_rate": 5.313952597646568e-05,
|
232 |
+
"loss": 0.778,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.558139534883721,
|
237 |
+
"grad_norm": 2.1659789085388184,
|
238 |
+
"learning_rate": 5.062830199416764e-05,
|
239 |
+
"loss": 0.8143,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.6356589147286824,
|
244 |
+
"grad_norm": 2.3656270503997803,
|
245 |
+
"learning_rate": 4.811549086650327e-05,
|
246 |
+
"loss": 0.8017,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.7131782945736433,
|
251 |
+
"grad_norm": 2.3753740787506104,
|
252 |
+
"learning_rate": 4.560744017246284e-05,
|
253 |
+
"loss": 0.7666,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.7906976744186047,
|
258 |
+
"grad_norm": 2.221393585205078,
|
259 |
+
"learning_rate": 4.31104854657681e-05,
|
260 |
+
"loss": 0.7679,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.8682170542635657,
|
265 |
+
"grad_norm": 2.018345594406128,
|
266 |
+
"learning_rate": 4.063093427071376e-05,
|
267 |
+
"loss": 0.7507,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.945736434108527,
|
272 |
+
"grad_norm": 2.199131965637207,
|
273 |
+
"learning_rate": 3.817505014881378e-05,
|
274 |
+
"loss": 0.7413,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.0232558139534884,
|
279 |
+
"grad_norm": 2.139735698699951,
|
280 |
+
"learning_rate": 3.5749036876501194e-05,
|
281 |
+
"loss": 0.8139,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.10077519379845,
|
286 |
+
"grad_norm": 2.0483205318450928,
|
287 |
+
"learning_rate": 3.335902277385067e-05,
|
288 |
+
"loss": 0.7209,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 3.1782945736434107,
|
293 |
+
"grad_norm": 2.3175625801086426,
|
294 |
+
"learning_rate": 3.101104522390995e-05,
|
295 |
+
"loss": 0.7392,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.255813953488372,
|
300 |
+
"grad_norm": 2.267725944519043,
|
301 |
+
"learning_rate": 2.8711035421746367e-05,
|
302 |
+
"loss": 0.7487,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.3333333333333335,
|
307 |
+
"grad_norm": 2.491976261138916,
|
308 |
+
"learning_rate": 2.6464803391733374e-05,
|
309 |
+
"loss": 0.7472,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 3.4108527131782944,
|
314 |
+
"grad_norm": 2.3867716789245605,
|
315 |
+
"learning_rate": 2.4278023310924673e-05,
|
316 |
+
"loss": 0.7194,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.488372093023256,
|
321 |
+
"grad_norm": 2.1725575923919678,
|
322 |
+
"learning_rate": 2.215621917559062e-05,
|
323 |
+
"loss": 0.7435,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.565891472868217,
|
328 |
+
"grad_norm": 2.362307071685791,
|
329 |
+
"learning_rate": 2.0104750847124075e-05,
|
330 |
+
"loss": 0.7257,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 3.6434108527131785,
|
335 |
+
"grad_norm": 2.3659157752990723,
|
336 |
+
"learning_rate": 1.8128800512565513e-05,
|
337 |
+
"loss": 0.7498,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.7209302325581395,
|
342 |
+
"grad_norm": 2.225560188293457,
|
343 |
+
"learning_rate": 1.6233359593948777e-05,
|
344 |
+
"loss": 0.7308,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.798449612403101,
|
349 |
+
"grad_norm": 2.4101855754852295,
|
350 |
+
"learning_rate": 1.4423216139535734e-05,
|
351 |
+
"loss": 0.7524,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 3.875968992248062,
|
356 |
+
"grad_norm": 2.295118808746338,
|
357 |
+
"learning_rate": 1.2702942728790895e-05,
|
358 |
+
"loss": 0.7239,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 3.953488372093023,
|
363 |
+
"grad_norm": 2.7008495330810547,
|
364 |
+
"learning_rate": 1.1076884921648834e-05,
|
365 |
+
"loss": 0.7305,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 4.0310077519379846,
|
370 |
+
"grad_norm": 2.140915632247925,
|
371 |
+
"learning_rate": 9.549150281252633e-06,
|
372 |
+
"loss": 0.7214,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 4.108527131782946,
|
377 |
+
"grad_norm": 2.121488332748413,
|
378 |
+
"learning_rate": 8.123597997892918e-06,
|
379 |
+
"loss": 0.7247,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.186046511627907,
|
384 |
+
"grad_norm": 2.2212812900543213,
|
385 |
+
"learning_rate": 6.803829140358237e-06,
|
386 |
+
"loss": 0.6995,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 4.263565891472869,
|
391 |
+
"grad_norm": 2.381098985671997,
|
392 |
+
"learning_rate": 5.593177559322777e-06,
|
393 |
+
"loss": 0.7116,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 4.341085271317829,
|
398 |
+
"grad_norm": 2.4563639163970947,
|
399 |
+
"learning_rate": 4.494701465750217e-06,
|
400 |
+
"loss": 0.7106,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 4.4186046511627906,
|
405 |
+
"grad_norm": 2.1021621227264404,
|
406 |
+
"learning_rate": 3.511175705587433e-06,
|
407 |
+
"loss": 0.7203,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 4.496124031007752,
|
412 |
+
"grad_norm": 2.3174192905426025,
|
413 |
+
"learning_rate": 2.6450847502627884e-06,
|
414 |
+
"loss": 0.6485,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 4.573643410852713,
|
419 |
+
"grad_norm": 2.161879301071167,
|
420 |
+
"learning_rate": 1.8986164206957035e-06,
|
421 |
+
"loss": 0.7654,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.651162790697675,
|
426 |
+
"grad_norm": 2.362793207168579,
|
427 |
+
"learning_rate": 1.2736563606711382e-06,
|
428 |
+
"loss": 0.694,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 4.728682170542635,
|
433 |
+
"grad_norm": 2.0738697052001953,
|
434 |
+
"learning_rate": 7.717832735397335e-07,
|
435 |
+
"loss": 0.7161,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 4.8062015503875966,
|
440 |
+
"grad_norm": 2.522212505340576,
|
441 |
+
"learning_rate": 3.9426493427611177e-07,
|
442 |
+
"loss": 0.7234,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 4.883720930232558,
|
447 |
+
"grad_norm": 2.2969350814819336,
|
448 |
+
"learning_rate": 1.420549869693033e-07,
|
449 |
+
"loss": 0.7234,
|
450 |
+
"step": 630
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 4.961240310077519,
|
454 |
+
"grad_norm": 2.1702637672424316,
|
455 |
+
"learning_rate": 1.5790535835003008e-08,
|
456 |
+
"loss": 0.726,
|
457 |
+
"step": 640
|
458 |
+
}
|
459 |
+
],
|
460 |
+
"logging_steps": 10,
|
461 |
+
"max_steps": 645,
|
462 |
+
"num_input_tokens_seen": 0,
|
463 |
+
"num_train_epochs": 5,
|
464 |
+
"save_steps": 500,
|
465 |
+
"stateful_callbacks": {
|
466 |
+
"TrainerControl": {
|
467 |
+
"args": {
|
468 |
+
"should_epoch_stop": false,
|
469 |
+
"should_evaluate": false,
|
470 |
+
"should_log": false,
|
471 |
+
"should_save": true,
|
472 |
+
"should_training_stop": true
|
473 |
+
},
|
474 |
+
"attributes": {}
|
475 |
+
}
|
476 |
+
},
|
477 |
+
"total_flos": 6.745720297183642e+16,
|
478 |
+
"train_batch_size": 4,
|
479 |
+
"trial_name": null,
|
480 |
+
"trial_params": null
|
481 |
+
}
|
rewriting/checkpoint-645/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4927757fe5693d5a3f8358383ea06db1c00891947f26a31894625d5b7a0d93d
|
3 |
+
size 5176
|
rewriting/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4927757fe5693d5a3f8358383ea06db1c00891947f26a31894625d5b7a0d93d
|
3 |
+
size 5176
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af7b78d3e1bb1f329897b1e0e91fa44cb0a52caa0b16aefd4111ecda01d45411
|
3 |
size 5176
|