borakaragul
commited on
Commit
•
1278a20
1
Parent(s):
27d9b4f
Upload folder using huggingface_hub
Browse files- README.md +202 -3
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +678 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Llama-2-7b-hf
|
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 0.12.1.dev0
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe800aff789ca3aff51aca071bb01d7e4af11cf1d321e03ca47f542e552d7bcf
|
3 |
+
size 134325882
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b65f9610756e5d54d6a44928b4a2df075fd6eabf22af38ab1762325ce1667032
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:814c5335d071ae07021d1744ec9a6235158c1a31d5d0598e1cda6bddebbe2205
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,678 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 833,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.012004801920768308,
|
13 |
+
"grad_norm": 0.3538109064102173,
|
14 |
+
"learning_rate": 9.879951980792317e-05,
|
15 |
+
"loss": 2.3075,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.024009603841536616,
|
20 |
+
"grad_norm": 0.3431814908981323,
|
21 |
+
"learning_rate": 9.759903961584634e-05,
|
22 |
+
"loss": 2.1468,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.03601440576230492,
|
27 |
+
"grad_norm": 0.6265680193901062,
|
28 |
+
"learning_rate": 9.639855942376951e-05,
|
29 |
+
"loss": 2.0353,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.04801920768307323,
|
34 |
+
"grad_norm": 0.3244292736053467,
|
35 |
+
"learning_rate": 9.519807923169268e-05,
|
36 |
+
"loss": 2.0219,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.060024009603841535,
|
41 |
+
"grad_norm": 0.6210302114486694,
|
42 |
+
"learning_rate": 9.399759903961585e-05,
|
43 |
+
"loss": 1.9809,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.07202881152460984,
|
48 |
+
"grad_norm": 0.4695661962032318,
|
49 |
+
"learning_rate": 9.279711884753903e-05,
|
50 |
+
"loss": 1.9376,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.08403361344537816,
|
55 |
+
"grad_norm": 0.27379557490348816,
|
56 |
+
"learning_rate": 9.159663865546218e-05,
|
57 |
+
"loss": 1.923,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.09603841536614646,
|
62 |
+
"grad_norm": 0.4497829079627991,
|
63 |
+
"learning_rate": 9.039615846338536e-05,
|
64 |
+
"loss": 1.9875,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.10804321728691477,
|
69 |
+
"grad_norm": 0.3675350844860077,
|
70 |
+
"learning_rate": 8.919567827130852e-05,
|
71 |
+
"loss": 1.953,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.12004801920768307,
|
76 |
+
"grad_norm": 0.293821781873703,
|
77 |
+
"learning_rate": 8.79951980792317e-05,
|
78 |
+
"loss": 1.8549,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.12004801920768307,
|
83 |
+
"eval_loss": 1.889587640762329,
|
84 |
+
"eval_runtime": 39.6181,
|
85 |
+
"eval_samples_per_second": 25.241,
|
86 |
+
"eval_steps_per_second": 4.215,
|
87 |
+
"step": 100
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.13205282112845138,
|
91 |
+
"grad_norm": 0.25892049074172974,
|
92 |
+
"learning_rate": 8.679471788715487e-05,
|
93 |
+
"loss": 1.8372,
|
94 |
+
"step": 110
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.14405762304921968,
|
98 |
+
"grad_norm": 0.33091431856155396,
|
99 |
+
"learning_rate": 8.559423769507804e-05,
|
100 |
+
"loss": 1.9107,
|
101 |
+
"step": 120
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.15606242496998798,
|
105 |
+
"grad_norm": 0.3052417039871216,
|
106 |
+
"learning_rate": 8.43937575030012e-05,
|
107 |
+
"loss": 1.8123,
|
108 |
+
"step": 130
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.16806722689075632,
|
112 |
+
"grad_norm": 0.3017849028110504,
|
113 |
+
"learning_rate": 8.319327731092437e-05,
|
114 |
+
"loss": 1.8966,
|
115 |
+
"step": 140
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.18007202881152462,
|
119 |
+
"grad_norm": 0.28657111525535583,
|
120 |
+
"learning_rate": 8.199279711884754e-05,
|
121 |
+
"loss": 1.8395,
|
122 |
+
"step": 150
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.19207683073229292,
|
126 |
+
"grad_norm": 0.3324660062789917,
|
127 |
+
"learning_rate": 8.079231692677071e-05,
|
128 |
+
"loss": 1.8841,
|
129 |
+
"step": 160
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.20408163265306123,
|
133 |
+
"grad_norm": 0.28194233775138855,
|
134 |
+
"learning_rate": 7.959183673469388e-05,
|
135 |
+
"loss": 1.8627,
|
136 |
+
"step": 170
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.21608643457382953,
|
140 |
+
"grad_norm": 0.45277833938598633,
|
141 |
+
"learning_rate": 7.839135654261706e-05,
|
142 |
+
"loss": 1.8989,
|
143 |
+
"step": 180
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.22809123649459784,
|
147 |
+
"grad_norm": 0.3656202256679535,
|
148 |
+
"learning_rate": 7.719087635054022e-05,
|
149 |
+
"loss": 1.911,
|
150 |
+
"step": 190
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.24009603841536614,
|
154 |
+
"grad_norm": 0.33644187450408936,
|
155 |
+
"learning_rate": 7.599039615846338e-05,
|
156 |
+
"loss": 1.7805,
|
157 |
+
"step": 200
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.24009603841536614,
|
161 |
+
"eval_loss": 1.8699440956115723,
|
162 |
+
"eval_runtime": 39.0269,
|
163 |
+
"eval_samples_per_second": 25.623,
|
164 |
+
"eval_steps_per_second": 4.279,
|
165 |
+
"step": 200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.25210084033613445,
|
169 |
+
"grad_norm": 0.24649439752101898,
|
170 |
+
"learning_rate": 7.478991596638657e-05,
|
171 |
+
"loss": 1.841,
|
172 |
+
"step": 210
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.26410564225690275,
|
176 |
+
"grad_norm": 0.30980348587036133,
|
177 |
+
"learning_rate": 7.358943577430972e-05,
|
178 |
+
"loss": 1.9065,
|
179 |
+
"step": 220
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.27611044417767105,
|
183 |
+
"grad_norm": 0.2731610834598541,
|
184 |
+
"learning_rate": 7.23889555822329e-05,
|
185 |
+
"loss": 1.8713,
|
186 |
+
"step": 230
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.28811524609843936,
|
190 |
+
"grad_norm": 0.3211459517478943,
|
191 |
+
"learning_rate": 7.118847539015606e-05,
|
192 |
+
"loss": 1.8719,
|
193 |
+
"step": 240
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.30012004801920766,
|
197 |
+
"grad_norm": 0.3356248736381531,
|
198 |
+
"learning_rate": 6.998799519807924e-05,
|
199 |
+
"loss": 1.8211,
|
200 |
+
"step": 250
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.31212484993997597,
|
204 |
+
"grad_norm": 0.35724079608917236,
|
205 |
+
"learning_rate": 6.878751500600241e-05,
|
206 |
+
"loss": 1.8773,
|
207 |
+
"step": 260
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.3241296518607443,
|
211 |
+
"grad_norm": 0.5718697905540466,
|
212 |
+
"learning_rate": 6.758703481392558e-05,
|
213 |
+
"loss": 1.8231,
|
214 |
+
"step": 270
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.33613445378151263,
|
218 |
+
"grad_norm": 0.32961568236351013,
|
219 |
+
"learning_rate": 6.638655462184874e-05,
|
220 |
+
"loss": 1.9494,
|
221 |
+
"step": 280
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.34813925570228094,
|
225 |
+
"grad_norm": 0.3693414628505707,
|
226 |
+
"learning_rate": 6.518607442977191e-05,
|
227 |
+
"loss": 1.835,
|
228 |
+
"step": 290
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.36014405762304924,
|
232 |
+
"grad_norm": 0.4198884665966034,
|
233 |
+
"learning_rate": 6.398559423769508e-05,
|
234 |
+
"loss": 1.8722,
|
235 |
+
"step": 300
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.36014405762304924,
|
239 |
+
"eval_loss": 1.8641259670257568,
|
240 |
+
"eval_runtime": 39.2717,
|
241 |
+
"eval_samples_per_second": 25.464,
|
242 |
+
"eval_steps_per_second": 4.252,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.37214885954381755,
|
247 |
+
"grad_norm": 0.3070141077041626,
|
248 |
+
"learning_rate": 6.278511404561825e-05,
|
249 |
+
"loss": 1.8771,
|
250 |
+
"step": 310
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.38415366146458585,
|
254 |
+
"grad_norm": 0.43982160091400146,
|
255 |
+
"learning_rate": 6.158463385354142e-05,
|
256 |
+
"loss": 1.8954,
|
257 |
+
"step": 320
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.39615846338535415,
|
261 |
+
"grad_norm": 0.2642657458782196,
|
262 |
+
"learning_rate": 6.038415366146459e-05,
|
263 |
+
"loss": 1.8977,
|
264 |
+
"step": 330
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.40816326530612246,
|
268 |
+
"grad_norm": 0.25595635175704956,
|
269 |
+
"learning_rate": 5.918367346938776e-05,
|
270 |
+
"loss": 1.8949,
|
271 |
+
"step": 340
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.42016806722689076,
|
275 |
+
"grad_norm": 0.27742770314216614,
|
276 |
+
"learning_rate": 5.7983193277310935e-05,
|
277 |
+
"loss": 1.8223,
|
278 |
+
"step": 350
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.43217286914765907,
|
282 |
+
"grad_norm": 0.2831798791885376,
|
283 |
+
"learning_rate": 5.6782713085234096e-05,
|
284 |
+
"loss": 1.8477,
|
285 |
+
"step": 360
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.44417767106842737,
|
289 |
+
"grad_norm": 0.3077690005302429,
|
290 |
+
"learning_rate": 5.558223289315727e-05,
|
291 |
+
"loss": 1.9376,
|
292 |
+
"step": 370
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.4561824729891957,
|
296 |
+
"grad_norm": 0.5014916658401489,
|
297 |
+
"learning_rate": 5.438175270108043e-05,
|
298 |
+
"loss": 1.9241,
|
299 |
+
"step": 380
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.468187274909964,
|
303 |
+
"grad_norm": 0.7313567399978638,
|
304 |
+
"learning_rate": 5.31812725090036e-05,
|
305 |
+
"loss": 1.8995,
|
306 |
+
"step": 390
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.4801920768307323,
|
310 |
+
"grad_norm": 0.26589518785476685,
|
311 |
+
"learning_rate": 5.1980792316926776e-05,
|
312 |
+
"loss": 1.95,
|
313 |
+
"step": 400
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.4801920768307323,
|
317 |
+
"eval_loss": 1.8611316680908203,
|
318 |
+
"eval_runtime": 39.4525,
|
319 |
+
"eval_samples_per_second": 25.347,
|
320 |
+
"eval_steps_per_second": 4.233,
|
321 |
+
"step": 400
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.4921968787515006,
|
325 |
+
"grad_norm": 0.293312668800354,
|
326 |
+
"learning_rate": 5.078031212484994e-05,
|
327 |
+
"loss": 1.8592,
|
328 |
+
"step": 410
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.5042016806722689,
|
332 |
+
"grad_norm": 0.35831350088119507,
|
333 |
+
"learning_rate": 4.957983193277311e-05,
|
334 |
+
"loss": 1.9295,
|
335 |
+
"step": 420
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.5162064825930373,
|
339 |
+
"grad_norm": 0.33949533104896545,
|
340 |
+
"learning_rate": 4.837935174069628e-05,
|
341 |
+
"loss": 1.8581,
|
342 |
+
"step": 430
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.5282112845138055,
|
346 |
+
"grad_norm": 0.5358735918998718,
|
347 |
+
"learning_rate": 4.717887154861945e-05,
|
348 |
+
"loss": 1.8824,
|
349 |
+
"step": 440
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.5402160864345739,
|
353 |
+
"grad_norm": 0.3915724456310272,
|
354 |
+
"learning_rate": 4.5978391356542624e-05,
|
355 |
+
"loss": 1.8699,
|
356 |
+
"step": 450
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.5522208883553421,
|
360 |
+
"grad_norm": 0.3336695730686188,
|
361 |
+
"learning_rate": 4.477791116446579e-05,
|
362 |
+
"loss": 1.9749,
|
363 |
+
"step": 460
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.5642256902761105,
|
367 |
+
"grad_norm": 0.3887428641319275,
|
368 |
+
"learning_rate": 4.3577430972388954e-05,
|
369 |
+
"loss": 1.8134,
|
370 |
+
"step": 470
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.5762304921968787,
|
374 |
+
"grad_norm": 0.26423540711402893,
|
375 |
+
"learning_rate": 4.237695078031212e-05,
|
376 |
+
"loss": 1.8495,
|
377 |
+
"step": 480
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.5882352941176471,
|
381 |
+
"grad_norm": 0.30970582365989685,
|
382 |
+
"learning_rate": 4.11764705882353e-05,
|
383 |
+
"loss": 1.8386,
|
384 |
+
"step": 490
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.6002400960384153,
|
388 |
+
"grad_norm": 0.38180047273635864,
|
389 |
+
"learning_rate": 3.9975990396158466e-05,
|
390 |
+
"loss": 1.8729,
|
391 |
+
"step": 500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.6002400960384153,
|
395 |
+
"eval_loss": 1.8590781688690186,
|
396 |
+
"eval_runtime": 39.0438,
|
397 |
+
"eval_samples_per_second": 25.612,
|
398 |
+
"eval_steps_per_second": 4.277,
|
399 |
+
"step": 500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.6122448979591837,
|
403 |
+
"grad_norm": 0.4111509621143341,
|
404 |
+
"learning_rate": 3.8775510204081634e-05,
|
405 |
+
"loss": 1.833,
|
406 |
+
"step": 510
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.6242496998799519,
|
410 |
+
"grad_norm": 0.515201210975647,
|
411 |
+
"learning_rate": 3.75750300120048e-05,
|
412 |
+
"loss": 1.8744,
|
413 |
+
"step": 520
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.6362545018007203,
|
417 |
+
"grad_norm": 0.2900288701057434,
|
418 |
+
"learning_rate": 3.637454981992797e-05,
|
419 |
+
"loss": 1.8364,
|
420 |
+
"step": 530
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 0.6482593037214885,
|
424 |
+
"grad_norm": 0.2963515520095825,
|
425 |
+
"learning_rate": 3.517406962785114e-05,
|
426 |
+
"loss": 1.8469,
|
427 |
+
"step": 540
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.6602641056422569,
|
431 |
+
"grad_norm": 0.41035813093185425,
|
432 |
+
"learning_rate": 3.3973589435774314e-05,
|
433 |
+
"loss": 1.9474,
|
434 |
+
"step": 550
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.6722689075630253,
|
438 |
+
"grad_norm": 0.246292382478714,
|
439 |
+
"learning_rate": 3.277310924369748e-05,
|
440 |
+
"loss": 1.8128,
|
441 |
+
"step": 560
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.6842737094837935,
|
445 |
+
"grad_norm": 0.3911287188529968,
|
446 |
+
"learning_rate": 3.157262905162065e-05,
|
447 |
+
"loss": 1.8663,
|
448 |
+
"step": 570
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.6962785114045619,
|
452 |
+
"grad_norm": 0.3035126328468323,
|
453 |
+
"learning_rate": 3.037214885954382e-05,
|
454 |
+
"loss": 1.8921,
|
455 |
+
"step": 580
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.7082833133253301,
|
459 |
+
"grad_norm": 0.2977759540081024,
|
460 |
+
"learning_rate": 2.917166866746699e-05,
|
461 |
+
"loss": 1.8288,
|
462 |
+
"step": 590
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 0.7202881152460985,
|
466 |
+
"grad_norm": 0.3059289753437042,
|
467 |
+
"learning_rate": 2.797118847539016e-05,
|
468 |
+
"loss": 1.8482,
|
469 |
+
"step": 600
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 0.7202881152460985,
|
473 |
+
"eval_loss": 1.8568615913391113,
|
474 |
+
"eval_runtime": 39.5808,
|
475 |
+
"eval_samples_per_second": 25.265,
|
476 |
+
"eval_steps_per_second": 4.219,
|
477 |
+
"step": 600
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.7322929171668667,
|
481 |
+
"grad_norm": 0.36612552404403687,
|
482 |
+
"learning_rate": 2.6770708283313327e-05,
|
483 |
+
"loss": 1.8577,
|
484 |
+
"step": 610
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.7442977190876351,
|
488 |
+
"grad_norm": 0.2968533933162689,
|
489 |
+
"learning_rate": 2.5570228091236498e-05,
|
490 |
+
"loss": 1.8295,
|
491 |
+
"step": 620
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.7563025210084033,
|
495 |
+
"grad_norm": 0.40536123514175415,
|
496 |
+
"learning_rate": 2.4369747899159663e-05,
|
497 |
+
"loss": 1.9242,
|
498 |
+
"step": 630
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.7683073229291717,
|
502 |
+
"grad_norm": 0.3592563271522522,
|
503 |
+
"learning_rate": 2.3169267707082835e-05,
|
504 |
+
"loss": 1.8677,
|
505 |
+
"step": 640
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.78031212484994,
|
509 |
+
"grad_norm": 0.3828364908695221,
|
510 |
+
"learning_rate": 2.1968787515006003e-05,
|
511 |
+
"loss": 1.9055,
|
512 |
+
"step": 650
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.7923169267707083,
|
516 |
+
"grad_norm": 0.26257479190826416,
|
517 |
+
"learning_rate": 2.076830732292917e-05,
|
518 |
+
"loss": 1.9383,
|
519 |
+
"step": 660
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.8043217286914766,
|
523 |
+
"grad_norm": 0.3253800570964813,
|
524 |
+
"learning_rate": 1.9567827130852343e-05,
|
525 |
+
"loss": 1.8142,
|
526 |
+
"step": 670
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.8163265306122449,
|
530 |
+
"grad_norm": 0.3129618167877197,
|
531 |
+
"learning_rate": 1.836734693877551e-05,
|
532 |
+
"loss": 1.8447,
|
533 |
+
"step": 680
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.8283313325330132,
|
537 |
+
"grad_norm": 0.32753467559814453,
|
538 |
+
"learning_rate": 1.7166866746698683e-05,
|
539 |
+
"loss": 1.8617,
|
540 |
+
"step": 690
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.8403361344537815,
|
544 |
+
"grad_norm": 0.28356197476387024,
|
545 |
+
"learning_rate": 1.5966386554621848e-05,
|
546 |
+
"loss": 1.768,
|
547 |
+
"step": 700
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.8403361344537815,
|
551 |
+
"eval_loss": 1.8553369045257568,
|
552 |
+
"eval_runtime": 39.3665,
|
553 |
+
"eval_samples_per_second": 25.402,
|
554 |
+
"eval_steps_per_second": 4.242,
|
555 |
+
"step": 700
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.8523409363745498,
|
559 |
+
"grad_norm": 0.42871856689453125,
|
560 |
+
"learning_rate": 1.4765906362545018e-05,
|
561 |
+
"loss": 1.8756,
|
562 |
+
"step": 710
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.8643457382953181,
|
566 |
+
"grad_norm": 0.32104918360710144,
|
567 |
+
"learning_rate": 1.3565426170468188e-05,
|
568 |
+
"loss": 1.8396,
|
569 |
+
"step": 720
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.8763505402160864,
|
573 |
+
"grad_norm": 0.3462695777416229,
|
574 |
+
"learning_rate": 1.2364945978391356e-05,
|
575 |
+
"loss": 1.8499,
|
576 |
+
"step": 730
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.8883553421368547,
|
580 |
+
"grad_norm": 0.38381311297416687,
|
581 |
+
"learning_rate": 1.1164465786314526e-05,
|
582 |
+
"loss": 1.8353,
|
583 |
+
"step": 740
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.9003601440576231,
|
587 |
+
"grad_norm": 0.48733091354370117,
|
588 |
+
"learning_rate": 9.963985594237696e-06,
|
589 |
+
"loss": 1.8566,
|
590 |
+
"step": 750
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.9123649459783914,
|
594 |
+
"grad_norm": 0.35725510120391846,
|
595 |
+
"learning_rate": 8.763505402160866e-06,
|
596 |
+
"loss": 1.9016,
|
597 |
+
"step": 760
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.9243697478991597,
|
601 |
+
"grad_norm": 0.2945646047592163,
|
602 |
+
"learning_rate": 7.563025210084033e-06,
|
603 |
+
"loss": 1.7727,
|
604 |
+
"step": 770
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.936374549819928,
|
608 |
+
"grad_norm": 0.2922873795032501,
|
609 |
+
"learning_rate": 6.362545018007203e-06,
|
610 |
+
"loss": 1.8482,
|
611 |
+
"step": 780
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.9483793517406963,
|
615 |
+
"grad_norm": 0.29431605339050293,
|
616 |
+
"learning_rate": 5.162064825930372e-06,
|
617 |
+
"loss": 1.8867,
|
618 |
+
"step": 790
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.9603841536614646,
|
622 |
+
"grad_norm": 0.32220232486724854,
|
623 |
+
"learning_rate": 3.9615846338535415e-06,
|
624 |
+
"loss": 1.8904,
|
625 |
+
"step": 800
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.9603841536614646,
|
629 |
+
"eval_loss": 1.854928970336914,
|
630 |
+
"eval_runtime": 39.3819,
|
631 |
+
"eval_samples_per_second": 25.392,
|
632 |
+
"eval_steps_per_second": 4.241,
|
633 |
+
"step": 800
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.9723889555822329,
|
637 |
+
"grad_norm": 0.2991810142993927,
|
638 |
+
"learning_rate": 2.7611044417767106e-06,
|
639 |
+
"loss": 1.8523,
|
640 |
+
"step": 810
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.9843937575030012,
|
644 |
+
"grad_norm": 0.3944421112537384,
|
645 |
+
"learning_rate": 1.56062424969988e-06,
|
646 |
+
"loss": 1.8502,
|
647 |
+
"step": 820
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.9963985594237695,
|
651 |
+
"grad_norm": 0.3155655264854431,
|
652 |
+
"learning_rate": 3.601440576230492e-07,
|
653 |
+
"loss": 1.9278,
|
654 |
+
"step": 830
|
655 |
+
}
|
656 |
+
],
|
657 |
+
"logging_steps": 10,
|
658 |
+
"max_steps": 833,
|
659 |
+
"num_input_tokens_seen": 0,
|
660 |
+
"num_train_epochs": 1,
|
661 |
+
"save_steps": 100,
|
662 |
+
"stateful_callbacks": {
|
663 |
+
"TrainerControl": {
|
664 |
+
"args": {
|
665 |
+
"should_epoch_stop": false,
|
666 |
+
"should_evaluate": false,
|
667 |
+
"should_log": false,
|
668 |
+
"should_save": true,
|
669 |
+
"should_training_stop": true
|
670 |
+
},
|
671 |
+
"attributes": {}
|
672 |
+
}
|
673 |
+
},
|
674 |
+
"total_flos": 1.3760243809940275e+17,
|
675 |
+
"train_batch_size": 12,
|
676 |
+
"trial_name": null,
|
677 |
+
"trial_params": null
|
678 |
+
}
|