Upload 8 files
Browse filesminimal files to run model from most recent chkpt
- README.md +205 -1
- adapter_config.json +22 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1169 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,207 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: microsoft/BioGPT
|
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 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data 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. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
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).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
+
## Training procedure
|
202 |
+
|
203 |
+
|
204 |
+
### Framework versions
|
205 |
+
|
206 |
+
|
207 |
+
- PEFT 0.6.0
|
adapter_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/BioGPT",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.1,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 4,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj"
|
20 |
+
],
|
21 |
+
"task_type": "CAUSAL_LM"
|
22 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b989853110df26897aa38c114d0f24e60e775afbe6d222a785a6b305aa30cc
|
3 |
+
size 1613562
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62bfeb62df5d53684740a33db572502c144dea131c951f4cb8ad301b5c957f93
|
3 |
+
size 803902
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3f001e11b281491b5c213dd732aa2ff767ac6bd0f42be1dbcc4b40ffd598415
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e3008979cba7c2af0bd74a2f3e180bbfc246eec8835fb7def4487224cb95e10
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,1169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.988236782190741,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 94500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 1.9894594822497684e-05,
|
14 |
+
"loss": 3.6148,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.03,
|
19 |
+
"learning_rate": 1.9789189644995362e-05,
|
20 |
+
"loss": 3.3107,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.05,
|
25 |
+
"learning_rate": 1.9683784467493044e-05,
|
26 |
+
"loss": 3.2487,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.06,
|
31 |
+
"learning_rate": 1.9578379289990726e-05,
|
32 |
+
"loss": 3.1954,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.08,
|
37 |
+
"learning_rate": 1.947297411248841e-05,
|
38 |
+
"loss": 3.1585,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.09,
|
43 |
+
"learning_rate": 1.9367568934986087e-05,
|
44 |
+
"loss": 3.1312,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.11,
|
49 |
+
"learning_rate": 1.926216375748377e-05,
|
50 |
+
"loss": 3.0709,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.13,
|
55 |
+
"learning_rate": 1.9156758579981448e-05,
|
56 |
+
"loss": 3.0622,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.14,
|
61 |
+
"learning_rate": 1.905135340247913e-05,
|
62 |
+
"loss": 3.0556,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.16,
|
67 |
+
"learning_rate": 1.8945948224976815e-05,
|
68 |
+
"loss": 3.002,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.17,
|
73 |
+
"learning_rate": 1.8840543047474494e-05,
|
74 |
+
"loss": 3.0279,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.19,
|
79 |
+
"learning_rate": 1.8735137869972176e-05,
|
80 |
+
"loss": 2.9804,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.21,
|
85 |
+
"learning_rate": 1.8629732692469854e-05,
|
86 |
+
"loss": 2.988,
|
87 |
+
"step": 6500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.22,
|
91 |
+
"learning_rate": 1.8524327514967536e-05,
|
92 |
+
"loss": 2.9664,
|
93 |
+
"step": 7000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.24,
|
97 |
+
"learning_rate": 1.841892233746522e-05,
|
98 |
+
"loss": 2.9649,
|
99 |
+
"step": 7500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.25,
|
103 |
+
"learning_rate": 1.83135171599629e-05,
|
104 |
+
"loss": 2.9827,
|
105 |
+
"step": 8000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.27,
|
109 |
+
"learning_rate": 1.820811198246058e-05,
|
110 |
+
"loss": 2.9541,
|
111 |
+
"step": 8500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.28,
|
115 |
+
"learning_rate": 1.810270680495826e-05,
|
116 |
+
"loss": 2.955,
|
117 |
+
"step": 9000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.3,
|
121 |
+
"learning_rate": 1.7997301627455943e-05,
|
122 |
+
"loss": 2.9489,
|
123 |
+
"step": 9500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.32,
|
127 |
+
"learning_rate": 1.7891896449953622e-05,
|
128 |
+
"loss": 2.9415,
|
129 |
+
"step": 10000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.33,
|
133 |
+
"learning_rate": 1.7786491272451304e-05,
|
134 |
+
"loss": 2.9453,
|
135 |
+
"step": 10500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.35,
|
139 |
+
"learning_rate": 1.7681086094948986e-05,
|
140 |
+
"loss": 2.9273,
|
141 |
+
"step": 11000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.36,
|
145 |
+
"learning_rate": 1.7575680917446668e-05,
|
146 |
+
"loss": 2.935,
|
147 |
+
"step": 11500
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.38,
|
151 |
+
"learning_rate": 1.7470275739944346e-05,
|
152 |
+
"loss": 2.938,
|
153 |
+
"step": 12000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.4,
|
157 |
+
"learning_rate": 1.736487056244203e-05,
|
158 |
+
"loss": 2.9441,
|
159 |
+
"step": 12500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.41,
|
163 |
+
"learning_rate": 1.7259465384939707e-05,
|
164 |
+
"loss": 2.9091,
|
165 |
+
"step": 13000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.43,
|
169 |
+
"learning_rate": 1.715406020743739e-05,
|
170 |
+
"loss": 2.9037,
|
171 |
+
"step": 13500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.44,
|
175 |
+
"learning_rate": 1.704865502993507e-05,
|
176 |
+
"loss": 2.9112,
|
177 |
+
"step": 14000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.46,
|
181 |
+
"learning_rate": 1.6943249852432753e-05,
|
182 |
+
"loss": 2.88,
|
183 |
+
"step": 14500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.47,
|
187 |
+
"learning_rate": 1.6837844674930435e-05,
|
188 |
+
"loss": 2.9045,
|
189 |
+
"step": 15000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.49,
|
193 |
+
"learning_rate": 1.6732439497428114e-05,
|
194 |
+
"loss": 2.9221,
|
195 |
+
"step": 15500
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.51,
|
199 |
+
"learning_rate": 1.6627034319925796e-05,
|
200 |
+
"loss": 2.9079,
|
201 |
+
"step": 16000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.52,
|
205 |
+
"learning_rate": 1.6521629142423478e-05,
|
206 |
+
"loss": 2.8972,
|
207 |
+
"step": 16500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.54,
|
211 |
+
"learning_rate": 1.641622396492116e-05,
|
212 |
+
"loss": 2.8958,
|
213 |
+
"step": 17000
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.55,
|
217 |
+
"learning_rate": 1.631081878741884e-05,
|
218 |
+
"loss": 2.9097,
|
219 |
+
"step": 17500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.57,
|
223 |
+
"learning_rate": 1.620541360991652e-05,
|
224 |
+
"loss": 2.9103,
|
225 |
+
"step": 18000
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.58,
|
229 |
+
"learning_rate": 1.6100008432414203e-05,
|
230 |
+
"loss": 2.9001,
|
231 |
+
"step": 18500
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.6,
|
235 |
+
"learning_rate": 1.599460325491188e-05,
|
236 |
+
"loss": 2.8897,
|
237 |
+
"step": 19000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.62,
|
241 |
+
"learning_rate": 1.5889198077409563e-05,
|
242 |
+
"loss": 2.9011,
|
243 |
+
"step": 19500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.63,
|
247 |
+
"learning_rate": 1.5783792899907245e-05,
|
248 |
+
"loss": 2.8966,
|
249 |
+
"step": 20000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.65,
|
253 |
+
"learning_rate": 1.5678387722404927e-05,
|
254 |
+
"loss": 2.8786,
|
255 |
+
"step": 20500
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.66,
|
259 |
+
"learning_rate": 1.5572982544902606e-05,
|
260 |
+
"loss": 2.8719,
|
261 |
+
"step": 21000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.68,
|
265 |
+
"learning_rate": 1.5467577367400288e-05,
|
266 |
+
"loss": 2.8824,
|
267 |
+
"step": 21500
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.7,
|
271 |
+
"learning_rate": 1.5362172189897967e-05,
|
272 |
+
"loss": 2.8859,
|
273 |
+
"step": 22000
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.71,
|
277 |
+
"learning_rate": 1.525676701239565e-05,
|
278 |
+
"loss": 2.8539,
|
279 |
+
"step": 22500
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.73,
|
283 |
+
"learning_rate": 1.5151361834893332e-05,
|
284 |
+
"loss": 2.8895,
|
285 |
+
"step": 23000
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.74,
|
289 |
+
"learning_rate": 1.5045956657391013e-05,
|
290 |
+
"loss": 2.869,
|
291 |
+
"step": 23500
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.76,
|
295 |
+
"learning_rate": 1.4940551479888695e-05,
|
296 |
+
"loss": 2.8888,
|
297 |
+
"step": 24000
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.77,
|
301 |
+
"learning_rate": 1.4835146302386373e-05,
|
302 |
+
"loss": 2.8637,
|
303 |
+
"step": 24500
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.79,
|
307 |
+
"learning_rate": 1.4729741124884055e-05,
|
308 |
+
"loss": 2.8905,
|
309 |
+
"step": 25000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.81,
|
313 |
+
"learning_rate": 1.4624335947381736e-05,
|
314 |
+
"loss": 2.8916,
|
315 |
+
"step": 25500
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.82,
|
319 |
+
"learning_rate": 1.4518930769879418e-05,
|
320 |
+
"loss": 2.8801,
|
321 |
+
"step": 26000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.84,
|
325 |
+
"learning_rate": 1.4413525592377098e-05,
|
326 |
+
"loss": 2.8854,
|
327 |
+
"step": 26500
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.85,
|
331 |
+
"learning_rate": 1.430812041487478e-05,
|
332 |
+
"loss": 2.8838,
|
333 |
+
"step": 27000
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.87,
|
337 |
+
"learning_rate": 1.4202715237372462e-05,
|
338 |
+
"loss": 2.8701,
|
339 |
+
"step": 27500
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.89,
|
343 |
+
"learning_rate": 1.4097310059870142e-05,
|
344 |
+
"loss": 2.8749,
|
345 |
+
"step": 28000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.9,
|
349 |
+
"learning_rate": 1.3991904882367824e-05,
|
350 |
+
"loss": 2.8488,
|
351 |
+
"step": 28500
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.92,
|
355 |
+
"learning_rate": 1.3886499704865503e-05,
|
356 |
+
"loss": 2.8685,
|
357 |
+
"step": 29000
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.93,
|
361 |
+
"learning_rate": 1.3781094527363185e-05,
|
362 |
+
"loss": 2.8526,
|
363 |
+
"step": 29500
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.95,
|
367 |
+
"learning_rate": 1.3675689349860865e-05,
|
368 |
+
"loss": 2.8521,
|
369 |
+
"step": 30000
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.96,
|
373 |
+
"learning_rate": 1.3570284172358547e-05,
|
374 |
+
"loss": 2.8803,
|
375 |
+
"step": 30500
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.98,
|
379 |
+
"learning_rate": 1.3464878994856228e-05,
|
380 |
+
"loss": 2.8803,
|
381 |
+
"step": 31000
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.0,
|
385 |
+
"learning_rate": 1.335947381735391e-05,
|
386 |
+
"loss": 2.8807,
|
387 |
+
"step": 31500
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.0,
|
391 |
+
"eval_loss": 2.767564058303833,
|
392 |
+
"eval_runtime": 6452.3126,
|
393 |
+
"eval_samples_per_second": 39.209,
|
394 |
+
"eval_steps_per_second": 4.901,
|
395 |
+
"step": 31624
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.01,
|
399 |
+
"learning_rate": 1.3254068639851592e-05,
|
400 |
+
"loss": 2.8679,
|
401 |
+
"step": 32000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.03,
|
405 |
+
"learning_rate": 1.3148663462349272e-05,
|
406 |
+
"loss": 2.874,
|
407 |
+
"step": 32500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 1.04,
|
411 |
+
"learning_rate": 1.3043258284846954e-05,
|
412 |
+
"loss": 2.8517,
|
413 |
+
"step": 33000
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.06,
|
417 |
+
"learning_rate": 1.2937853107344633e-05,
|
418 |
+
"loss": 2.8499,
|
419 |
+
"step": 33500
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.08,
|
423 |
+
"learning_rate": 1.2832447929842315e-05,
|
424 |
+
"loss": 2.8693,
|
425 |
+
"step": 34000
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 1.09,
|
429 |
+
"learning_rate": 1.2727042752339995e-05,
|
430 |
+
"loss": 2.8738,
|
431 |
+
"step": 34500
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.11,
|
435 |
+
"learning_rate": 1.2621637574837677e-05,
|
436 |
+
"loss": 2.8282,
|
437 |
+
"step": 35000
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.12,
|
441 |
+
"learning_rate": 1.2516232397335358e-05,
|
442 |
+
"loss": 2.8402,
|
443 |
+
"step": 35500
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.14,
|
447 |
+
"learning_rate": 1.241082721983304e-05,
|
448 |
+
"loss": 2.8686,
|
449 |
+
"step": 36000
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.15,
|
453 |
+
"learning_rate": 1.2305422042330722e-05,
|
454 |
+
"loss": 2.8629,
|
455 |
+
"step": 36500
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 1.17,
|
459 |
+
"learning_rate": 1.2200016864828402e-05,
|
460 |
+
"loss": 2.8643,
|
461 |
+
"step": 37000
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.19,
|
465 |
+
"learning_rate": 1.2094611687326084e-05,
|
466 |
+
"loss": 2.8254,
|
467 |
+
"step": 37500
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 1.2,
|
471 |
+
"learning_rate": 1.1989206509823763e-05,
|
472 |
+
"loss": 2.8569,
|
473 |
+
"step": 38000
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.22,
|
477 |
+
"learning_rate": 1.1883801332321445e-05,
|
478 |
+
"loss": 2.8581,
|
479 |
+
"step": 38500
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.23,
|
483 |
+
"learning_rate": 1.1778396154819125e-05,
|
484 |
+
"loss": 2.8454,
|
485 |
+
"step": 39000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.25,
|
489 |
+
"learning_rate": 1.1672990977316807e-05,
|
490 |
+
"loss": 2.8462,
|
491 |
+
"step": 39500
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 1.26,
|
495 |
+
"learning_rate": 1.1567585799814487e-05,
|
496 |
+
"loss": 2.865,
|
497 |
+
"step": 40000
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 1.28,
|
501 |
+
"learning_rate": 1.146218062231217e-05,
|
502 |
+
"loss": 2.8448,
|
503 |
+
"step": 40500
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.3,
|
507 |
+
"learning_rate": 1.1356775444809851e-05,
|
508 |
+
"loss": 2.8366,
|
509 |
+
"step": 41000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 1.31,
|
513 |
+
"learning_rate": 1.1251370267307532e-05,
|
514 |
+
"loss": 2.8472,
|
515 |
+
"step": 41500
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 1.33,
|
519 |
+
"learning_rate": 1.1145965089805214e-05,
|
520 |
+
"loss": 2.8406,
|
521 |
+
"step": 42000
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.34,
|
525 |
+
"learning_rate": 1.1040559912302892e-05,
|
526 |
+
"loss": 2.8612,
|
527 |
+
"step": 42500
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.36,
|
531 |
+
"learning_rate": 1.0935154734800574e-05,
|
532 |
+
"loss": 2.8621,
|
533 |
+
"step": 43000
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 1.38,
|
537 |
+
"learning_rate": 1.0829749557298255e-05,
|
538 |
+
"loss": 2.8466,
|
539 |
+
"step": 43500
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 1.39,
|
543 |
+
"learning_rate": 1.0724344379795937e-05,
|
544 |
+
"loss": 2.8412,
|
545 |
+
"step": 44000
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.41,
|
549 |
+
"learning_rate": 1.0618939202293617e-05,
|
550 |
+
"loss": 2.8483,
|
551 |
+
"step": 44500
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 1.42,
|
555 |
+
"learning_rate": 1.0513534024791299e-05,
|
556 |
+
"loss": 2.8502,
|
557 |
+
"step": 45000
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 1.44,
|
561 |
+
"learning_rate": 1.0408128847288981e-05,
|
562 |
+
"loss": 2.8451,
|
563 |
+
"step": 45500
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.45,
|
567 |
+
"learning_rate": 1.0302723669786661e-05,
|
568 |
+
"loss": 2.8406,
|
569 |
+
"step": 46000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.47,
|
573 |
+
"learning_rate": 1.0197318492284343e-05,
|
574 |
+
"loss": 2.8499,
|
575 |
+
"step": 46500
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 1.49,
|
579 |
+
"learning_rate": 1.0091913314782022e-05,
|
580 |
+
"loss": 2.8533,
|
581 |
+
"step": 47000
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 1.5,
|
585 |
+
"learning_rate": 9.986508137279704e-06,
|
586 |
+
"loss": 2.8233,
|
587 |
+
"step": 47500
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 1.52,
|
591 |
+
"learning_rate": 9.881102959777386e-06,
|
592 |
+
"loss": 2.8373,
|
593 |
+
"step": 48000
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 1.53,
|
597 |
+
"learning_rate": 9.775697782275066e-06,
|
598 |
+
"loss": 2.8606,
|
599 |
+
"step": 48500
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 1.55,
|
603 |
+
"learning_rate": 9.670292604772747e-06,
|
604 |
+
"loss": 2.8385,
|
605 |
+
"step": 49000
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.57,
|
609 |
+
"learning_rate": 9.564887427270429e-06,
|
610 |
+
"loss": 2.8455,
|
611 |
+
"step": 49500
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.58,
|
615 |
+
"learning_rate": 9.459482249768109e-06,
|
616 |
+
"loss": 2.8701,
|
617 |
+
"step": 50000
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 1.6,
|
621 |
+
"learning_rate": 9.354077072265791e-06,
|
622 |
+
"loss": 2.8277,
|
623 |
+
"step": 50500
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 1.61,
|
627 |
+
"learning_rate": 9.248671894763471e-06,
|
628 |
+
"loss": 2.8681,
|
629 |
+
"step": 51000
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 1.63,
|
633 |
+
"learning_rate": 9.143266717261152e-06,
|
634 |
+
"loss": 2.8445,
|
635 |
+
"step": 51500
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 1.64,
|
639 |
+
"learning_rate": 9.037861539758834e-06,
|
640 |
+
"loss": 2.8545,
|
641 |
+
"step": 52000
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.66,
|
645 |
+
"learning_rate": 8.932456362256516e-06,
|
646 |
+
"loss": 2.8397,
|
647 |
+
"step": 52500
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.68,
|
651 |
+
"learning_rate": 8.827051184754196e-06,
|
652 |
+
"loss": 2.8442,
|
653 |
+
"step": 53000
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 1.69,
|
657 |
+
"learning_rate": 8.721646007251876e-06,
|
658 |
+
"loss": 2.8288,
|
659 |
+
"step": 53500
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 1.71,
|
663 |
+
"learning_rate": 8.616240829749558e-06,
|
664 |
+
"loss": 2.8278,
|
665 |
+
"step": 54000
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 1.72,
|
669 |
+
"learning_rate": 8.510835652247239e-06,
|
670 |
+
"loss": 2.835,
|
671 |
+
"step": 54500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 1.74,
|
675 |
+
"learning_rate": 8.40543047474492e-06,
|
676 |
+
"loss": 2.8464,
|
677 |
+
"step": 55000
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 1.75,
|
681 |
+
"learning_rate": 8.300025297242601e-06,
|
682 |
+
"loss": 2.8251,
|
683 |
+
"step": 55500
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 1.77,
|
687 |
+
"learning_rate": 8.194620119740281e-06,
|
688 |
+
"loss": 2.8414,
|
689 |
+
"step": 56000
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.79,
|
693 |
+
"learning_rate": 8.089214942237964e-06,
|
694 |
+
"loss": 2.8335,
|
695 |
+
"step": 56500
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 1.8,
|
699 |
+
"learning_rate": 7.983809764735646e-06,
|
700 |
+
"loss": 2.8405,
|
701 |
+
"step": 57000
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 1.82,
|
705 |
+
"learning_rate": 7.878404587233326e-06,
|
706 |
+
"loss": 2.835,
|
707 |
+
"step": 57500
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 1.83,
|
711 |
+
"learning_rate": 7.772999409731006e-06,
|
712 |
+
"loss": 2.8239,
|
713 |
+
"step": 58000
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 1.85,
|
717 |
+
"learning_rate": 7.667594232228688e-06,
|
718 |
+
"loss": 2.8322,
|
719 |
+
"step": 58500
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 1.87,
|
723 |
+
"learning_rate": 7.5621890547263685e-06,
|
724 |
+
"loss": 2.8366,
|
725 |
+
"step": 59000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 1.88,
|
729 |
+
"learning_rate": 7.45678387722405e-06,
|
730 |
+
"loss": 2.8391,
|
731 |
+
"step": 59500
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 1.9,
|
735 |
+
"learning_rate": 7.351378699721731e-06,
|
736 |
+
"loss": 2.8396,
|
737 |
+
"step": 60000
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.91,
|
741 |
+
"learning_rate": 7.245973522219411e-06,
|
742 |
+
"loss": 2.824,
|
743 |
+
"step": 60500
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 1.93,
|
747 |
+
"learning_rate": 7.140568344717092e-06,
|
748 |
+
"loss": 2.8282,
|
749 |
+
"step": 61000
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 1.94,
|
753 |
+
"learning_rate": 7.035163167214774e-06,
|
754 |
+
"loss": 2.8341,
|
755 |
+
"step": 61500
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 1.96,
|
759 |
+
"learning_rate": 6.929757989712456e-06,
|
760 |
+
"loss": 2.8247,
|
761 |
+
"step": 62000
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 1.98,
|
765 |
+
"learning_rate": 6.824352812210137e-06,
|
766 |
+
"loss": 2.837,
|
767 |
+
"step": 62500
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 1.99,
|
771 |
+
"learning_rate": 6.718947634707817e-06,
|
772 |
+
"loss": 2.8199,
|
773 |
+
"step": 63000
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 2.0,
|
777 |
+
"eval_loss": 2.7402868270874023,
|
778 |
+
"eval_runtime": 6430.6551,
|
779 |
+
"eval_samples_per_second": 39.341,
|
780 |
+
"eval_steps_per_second": 4.918,
|
781 |
+
"step": 63248
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.01,
|
785 |
+
"learning_rate": 6.613542457205498e-06,
|
786 |
+
"loss": 2.8177,
|
787 |
+
"step": 63500
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.02,
|
791 |
+
"learning_rate": 6.5081372797031795e-06,
|
792 |
+
"loss": 2.8361,
|
793 |
+
"step": 64000
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 2.04,
|
797 |
+
"learning_rate": 6.402732102200861e-06,
|
798 |
+
"loss": 2.8109,
|
799 |
+
"step": 64500
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 2.06,
|
803 |
+
"learning_rate": 6.297326924698541e-06,
|
804 |
+
"loss": 2.8399,
|
805 |
+
"step": 65000
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 2.07,
|
809 |
+
"learning_rate": 6.191921747196222e-06,
|
810 |
+
"loss": 2.8311,
|
811 |
+
"step": 65500
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 2.09,
|
815 |
+
"learning_rate": 6.086516569693904e-06,
|
816 |
+
"loss": 2.8227,
|
817 |
+
"step": 66000
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 2.1,
|
821 |
+
"learning_rate": 5.981111392191585e-06,
|
822 |
+
"loss": 2.8347,
|
823 |
+
"step": 66500
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.12,
|
827 |
+
"learning_rate": 5.8757062146892665e-06,
|
828 |
+
"loss": 2.8259,
|
829 |
+
"step": 67000
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 2.13,
|
833 |
+
"learning_rate": 5.770301037186947e-06,
|
834 |
+
"loss": 2.8554,
|
835 |
+
"step": 67500
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 2.15,
|
839 |
+
"learning_rate": 5.664895859684628e-06,
|
840 |
+
"loss": 2.8385,
|
841 |
+
"step": 68000
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 2.17,
|
845 |
+
"learning_rate": 5.559490682182309e-06,
|
846 |
+
"loss": 2.8042,
|
847 |
+
"step": 68500
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 2.18,
|
851 |
+
"learning_rate": 5.45408550467999e-06,
|
852 |
+
"loss": 2.8222,
|
853 |
+
"step": 69000
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 2.2,
|
857 |
+
"learning_rate": 5.348680327177671e-06,
|
858 |
+
"loss": 2.8209,
|
859 |
+
"step": 69500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 2.21,
|
863 |
+
"learning_rate": 5.243275149675352e-06,
|
864 |
+
"loss": 2.836,
|
865 |
+
"step": 70000
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.23,
|
869 |
+
"learning_rate": 5.137869972173034e-06,
|
870 |
+
"loss": 2.8291,
|
871 |
+
"step": 70500
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 2.25,
|
875 |
+
"learning_rate": 5.032464794670715e-06,
|
876 |
+
"loss": 2.8257,
|
877 |
+
"step": 71000
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 2.26,
|
881 |
+
"learning_rate": 4.927059617168396e-06,
|
882 |
+
"loss": 2.8353,
|
883 |
+
"step": 71500
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 2.28,
|
887 |
+
"learning_rate": 4.8216544396660766e-06,
|
888 |
+
"loss": 2.8184,
|
889 |
+
"step": 72000
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 2.29,
|
893 |
+
"learning_rate": 4.716249262163758e-06,
|
894 |
+
"loss": 2.8308,
|
895 |
+
"step": 72500
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 2.31,
|
899 |
+
"learning_rate": 4.610844084661439e-06,
|
900 |
+
"loss": 2.8321,
|
901 |
+
"step": 73000
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 2.32,
|
905 |
+
"learning_rate": 4.50543890715912e-06,
|
906 |
+
"loss": 2.8366,
|
907 |
+
"step": 73500
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.34,
|
911 |
+
"learning_rate": 4.400033729656801e-06,
|
912 |
+
"loss": 2.8133,
|
913 |
+
"step": 74000
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 2.36,
|
917 |
+
"learning_rate": 4.2946285521544825e-06,
|
918 |
+
"loss": 2.8063,
|
919 |
+
"step": 74500
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 2.37,
|
923 |
+
"learning_rate": 4.189223374652164e-06,
|
924 |
+
"loss": 2.8334,
|
925 |
+
"step": 75000
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 2.39,
|
929 |
+
"learning_rate": 4.083818197149844e-06,
|
930 |
+
"loss": 2.8103,
|
931 |
+
"step": 75500
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 2.4,
|
935 |
+
"learning_rate": 3.978413019647526e-06,
|
936 |
+
"loss": 2.8221,
|
937 |
+
"step": 76000
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 2.42,
|
941 |
+
"learning_rate": 3.873007842145206e-06,
|
942 |
+
"loss": 2.817,
|
943 |
+
"step": 76500
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 2.43,
|
947 |
+
"learning_rate": 3.7676026646428875e-06,
|
948 |
+
"loss": 2.8334,
|
949 |
+
"step": 77000
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 2.45,
|
953 |
+
"learning_rate": 3.6621974871405687e-06,
|
954 |
+
"loss": 2.8423,
|
955 |
+
"step": 77500
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 2.47,
|
959 |
+
"learning_rate": 3.5567923096382494e-06,
|
960 |
+
"loss": 2.8247,
|
961 |
+
"step": 78000
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 2.48,
|
965 |
+
"learning_rate": 3.451387132135931e-06,
|
966 |
+
"loss": 2.8373,
|
967 |
+
"step": 78500
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 2.5,
|
971 |
+
"learning_rate": 3.3459819546336118e-06,
|
972 |
+
"loss": 2.8324,
|
973 |
+
"step": 79000
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 2.51,
|
977 |
+
"learning_rate": 3.240576777131293e-06,
|
978 |
+
"loss": 2.8312,
|
979 |
+
"step": 79500
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 2.53,
|
983 |
+
"learning_rate": 3.1351715996289737e-06,
|
984 |
+
"loss": 2.8452,
|
985 |
+
"step": 80000
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 2.55,
|
989 |
+
"learning_rate": 3.029766422126655e-06,
|
990 |
+
"loss": 2.8331,
|
991 |
+
"step": 80500
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 2.56,
|
995 |
+
"learning_rate": 2.9243612446243365e-06,
|
996 |
+
"loss": 2.8209,
|
997 |
+
"step": 81000
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 2.58,
|
1001 |
+
"learning_rate": 2.8189560671220172e-06,
|
1002 |
+
"loss": 2.8289,
|
1003 |
+
"step": 81500
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 2.59,
|
1007 |
+
"learning_rate": 2.7135508896196984e-06,
|
1008 |
+
"loss": 2.8415,
|
1009 |
+
"step": 82000
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 2.61,
|
1013 |
+
"learning_rate": 2.608145712117379e-06,
|
1014 |
+
"loss": 2.8256,
|
1015 |
+
"step": 82500
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 2.62,
|
1019 |
+
"learning_rate": 2.5027405346150608e-06,
|
1020 |
+
"loss": 2.8257,
|
1021 |
+
"step": 83000
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 2.64,
|
1025 |
+
"learning_rate": 2.3973353571127415e-06,
|
1026 |
+
"loss": 2.833,
|
1027 |
+
"step": 83500
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 2.66,
|
1031 |
+
"learning_rate": 2.2919301796104227e-06,
|
1032 |
+
"loss": 2.8348,
|
1033 |
+
"step": 84000
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 2.67,
|
1037 |
+
"learning_rate": 2.186525002108104e-06,
|
1038 |
+
"loss": 2.8292,
|
1039 |
+
"step": 84500
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 2.69,
|
1043 |
+
"learning_rate": 2.081119824605785e-06,
|
1044 |
+
"loss": 2.8259,
|
1045 |
+
"step": 85000
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 2.7,
|
1049 |
+
"learning_rate": 1.9757146471034658e-06,
|
1050 |
+
"loss": 2.8319,
|
1051 |
+
"step": 85500
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 2.72,
|
1055 |
+
"learning_rate": 1.870309469601147e-06,
|
1056 |
+
"loss": 2.8094,
|
1057 |
+
"step": 86000
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 2.74,
|
1061 |
+
"learning_rate": 1.764904292098828e-06,
|
1062 |
+
"loss": 2.8276,
|
1063 |
+
"step": 86500
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 2.75,
|
1067 |
+
"learning_rate": 1.659499114596509e-06,
|
1068 |
+
"loss": 2.8325,
|
1069 |
+
"step": 87000
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 2.77,
|
1073 |
+
"learning_rate": 1.55409393709419e-06,
|
1074 |
+
"loss": 2.8247,
|
1075 |
+
"step": 87500
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 2.78,
|
1079 |
+
"learning_rate": 1.4486887595918715e-06,
|
1080 |
+
"loss": 2.8363,
|
1081 |
+
"step": 88000
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 2.8,
|
1085 |
+
"learning_rate": 1.3432835820895524e-06,
|
1086 |
+
"loss": 2.8343,
|
1087 |
+
"step": 88500
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 2.81,
|
1091 |
+
"learning_rate": 1.2378784045872334e-06,
|
1092 |
+
"loss": 2.8325,
|
1093 |
+
"step": 89000
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"epoch": 2.83,
|
1097 |
+
"learning_rate": 1.1324732270849146e-06,
|
1098 |
+
"loss": 2.8316,
|
1099 |
+
"step": 89500
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 2.85,
|
1103 |
+
"learning_rate": 1.0270680495825955e-06,
|
1104 |
+
"loss": 2.8232,
|
1105 |
+
"step": 90000
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 2.86,
|
1109 |
+
"learning_rate": 9.216628720802767e-07,
|
1110 |
+
"loss": 2.8241,
|
1111 |
+
"step": 90500
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 2.88,
|
1115 |
+
"learning_rate": 8.162576945779577e-07,
|
1116 |
+
"loss": 2.8203,
|
1117 |
+
"step": 91000
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 2.89,
|
1121 |
+
"learning_rate": 7.108525170756387e-07,
|
1122 |
+
"loss": 2.8356,
|
1123 |
+
"step": 91500
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 2.91,
|
1127 |
+
"learning_rate": 6.054473395733199e-07,
|
1128 |
+
"loss": 2.8509,
|
1129 |
+
"step": 92000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 2.92,
|
1133 |
+
"learning_rate": 5.00042162071001e-07,
|
1134 |
+
"loss": 2.8315,
|
1135 |
+
"step": 92500
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 2.94,
|
1139 |
+
"learning_rate": 3.9463698456868205e-07,
|
1140 |
+
"loss": 2.8223,
|
1141 |
+
"step": 93000
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 2.96,
|
1145 |
+
"learning_rate": 2.892318070663631e-07,
|
1146 |
+
"loss": 2.8368,
|
1147 |
+
"step": 93500
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 2.97,
|
1151 |
+
"learning_rate": 1.838266295640442e-07,
|
1152 |
+
"loss": 2.8271,
|
1153 |
+
"step": 94000
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 2.99,
|
1157 |
+
"learning_rate": 7.842145206172527e-08,
|
1158 |
+
"loss": 2.8375,
|
1159 |
+
"step": 94500
|
1160 |
+
}
|
1161 |
+
],
|
1162 |
+
"logging_steps": 500,
|
1163 |
+
"max_steps": 94872,
|
1164 |
+
"num_train_epochs": 3,
|
1165 |
+
"save_steps": 500,
|
1166 |
+
"total_flos": 7.025524751644754e+17,
|
1167 |
+
"trial_name": null,
|
1168 |
+
"trial_params": null
|
1169 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:016b9b790bf64d70e454e68cc09880a3a450d4e85678979f995976030c8bf78c
|
3 |
+
size 4536
|