Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +348 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: PlanTL-GOB-ES/RoBERTalex
|
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 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "PlanTL-GOB-ES/RoBERTalex",
|
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": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"qa_outputs",
|
19 |
+
"qa_outputs"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 8,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"query",
|
27 |
+
"value"
|
28 |
+
],
|
29 |
+
"task_type": "QUESTION_ANS",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623abd13bf1a87cd95a1267342f323a8c4b8067bc813a627937b26393590a8e3
|
3 |
+
size 1192800
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51b9ca9cd5387fa7b0d8c8623876af05fbc8360a694e0513b3af34fd31e20fd5
|
3 |
+
size 2401402
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6089c2e9cce3c1365d04e68132abcc5066817ab9e1f1b0849b765a710c177e53
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae18fad851bff1b9ad6535adf0e13669badd70aed49e848c498b388a8741457
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"51999": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_len": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4500.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 100.0,
|
13 |
+
"grad_norm": 0.09399763494729996,
|
14 |
+
"learning_rate": 0.00019975640502598244,
|
15 |
+
"loss": 0.4328,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 200.0,
|
20 |
+
"grad_norm": 0.008415983989834785,
|
21 |
+
"learning_rate": 0.00019902680687415705,
|
22 |
+
"loss": 0.0012,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 300.0,
|
27 |
+
"grad_norm": 0.004644488915801048,
|
28 |
+
"learning_rate": 0.00019781476007338058,
|
29 |
+
"loss": 0.0003,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 400.0,
|
34 |
+
"grad_norm": 0.002689788118004799,
|
35 |
+
"learning_rate": 0.0001961261695938319,
|
36 |
+
"loss": 0.0002,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 500.0,
|
41 |
+
"grad_norm": 0.0023731214459985495,
|
42 |
+
"learning_rate": 0.00019396926207859084,
|
43 |
+
"loss": 0.0002,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 600.0,
|
48 |
+
"grad_norm": 0.0013438506284728646,
|
49 |
+
"learning_rate": 0.0001913545457642601,
|
50 |
+
"loss": 0.0001,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 700.0,
|
55 |
+
"grad_norm": 0.0014795837923884392,
|
56 |
+
"learning_rate": 0.00018829475928589271,
|
57 |
+
"loss": 0.0001,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 800.0,
|
62 |
+
"grad_norm": 0.0012762774713337421,
|
63 |
+
"learning_rate": 0.0001848048096156426,
|
64 |
+
"loss": 0.0001,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 900.0,
|
69 |
+
"grad_norm": 0.0009800918633118272,
|
70 |
+
"learning_rate": 0.00018090169943749476,
|
71 |
+
"loss": 0.0001,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1000.0,
|
76 |
+
"grad_norm": 0.001324972603470087,
|
77 |
+
"learning_rate": 0.0001766044443118978,
|
78 |
+
"loss": 0.0,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1100.0,
|
83 |
+
"grad_norm": 0.0007171508623287082,
|
84 |
+
"learning_rate": 0.0001719339800338651,
|
85 |
+
"loss": 0.0,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1200.0,
|
90 |
+
"grad_norm": 0.0006033563986420631,
|
91 |
+
"learning_rate": 0.00016691306063588583,
|
92 |
+
"loss": 0.0,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1300.0,
|
97 |
+
"grad_norm": 0.0005752713768742979,
|
98 |
+
"learning_rate": 0.0001615661475325658,
|
99 |
+
"loss": 0.0,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1400.0,
|
104 |
+
"grad_norm": 0.000505088537465781,
|
105 |
+
"learning_rate": 0.0001559192903470747,
|
106 |
+
"loss": 0.0,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1500.0,
|
111 |
+
"grad_norm": 0.0010271323844790459,
|
112 |
+
"learning_rate": 0.00015000000000000001,
|
113 |
+
"loss": 0.0,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1600.0,
|
118 |
+
"grad_norm": 0.0004594104248099029,
|
119 |
+
"learning_rate": 0.00014383711467890774,
|
120 |
+
"loss": 0.0,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1700.0,
|
125 |
+
"grad_norm": 0.00037568225525319576,
|
126 |
+
"learning_rate": 0.00013746065934159123,
|
127 |
+
"loss": 0.0,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1800.0,
|
132 |
+
"grad_norm": 0.0006100877653807402,
|
133 |
+
"learning_rate": 0.00013090169943749476,
|
134 |
+
"loss": 0.0,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1900.0,
|
139 |
+
"grad_norm": 0.0006700914236716926,
|
140 |
+
"learning_rate": 0.00012419218955996676,
|
141 |
+
"loss": 0.0,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2000.0,
|
146 |
+
"grad_norm": 0.0004988115979358554,
|
147 |
+
"learning_rate": 0.00011736481776669306,
|
148 |
+
"loss": 0.0,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2100.0,
|
153 |
+
"grad_norm": 0.0003406632167752832,
|
154 |
+
"learning_rate": 0.00011045284632676536,
|
155 |
+
"loss": 0.0,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 2200.0,
|
160 |
+
"grad_norm": 0.00035023069358430803,
|
161 |
+
"learning_rate": 0.00010348994967025012,
|
162 |
+
"loss": 0.0,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2300.0,
|
167 |
+
"grad_norm": 0.00035629895864985883,
|
168 |
+
"learning_rate": 9.657982181634475e-05,
|
169 |
+
"loss": 0.0003,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2400.0,
|
174 |
+
"grad_norm": 0.00036875385558232665,
|
175 |
+
"learning_rate": 8.961658694111929e-05,
|
176 |
+
"loss": 0.0,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2500.0,
|
181 |
+
"grad_norm": 0.0003993694263044745,
|
182 |
+
"learning_rate": 8.270393901057964e-05,
|
183 |
+
"loss": 0.0,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2600.0,
|
188 |
+
"grad_norm": 0.00030426381272263825,
|
189 |
+
"learning_rate": 7.587555575058649e-05,
|
190 |
+
"loss": 0.0,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2700.0,
|
195 |
+
"grad_norm": 0.0005253420677036047,
|
196 |
+
"learning_rate": 6.916470435799587e-05,
|
197 |
+
"loss": 0.0,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2800.0,
|
202 |
+
"grad_norm": 0.000337547215167433,
|
203 |
+
"learning_rate": 6.260407942621998e-05,
|
204 |
+
"loss": 0.0,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2900.0,
|
209 |
+
"grad_norm": 0.00034444258199073374,
|
210 |
+
"learning_rate": 5.622564366045472e-05,
|
211 |
+
"loss": 0.0,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3000.0,
|
216 |
+
"grad_norm": 0.00015016530232969671,
|
217 |
+
"learning_rate": 5.006047215859289e-05,
|
218 |
+
"loss": 0.0,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 3100.0,
|
223 |
+
"grad_norm": 0.00021075463155284524,
|
224 |
+
"learning_rate": 4.413860101647055e-05,
|
225 |
+
"loss": 0.0,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 3200.0,
|
230 |
+
"grad_norm": 0.00025653259945102036,
|
231 |
+
"learning_rate": 3.8488880995027786e-05,
|
232 |
+
"loss": 0.0,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 3300.0,
|
237 |
+
"grad_norm": 0.00018334439664613456,
|
238 |
+
"learning_rate": 3.313883696230119e-05,
|
239 |
+
"loss": 0.0,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 3400.0,
|
244 |
+
"grad_norm": 0.00026421225629746914,
|
245 |
+
"learning_rate": 2.8114533795033683e-05,
|
246 |
+
"loss": 0.0,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 3500.0,
|
251 |
+
"grad_norm": 0.00012184748629806563,
|
252 |
+
"learning_rate": 2.3440449393214948e-05,
|
253 |
+
"loss": 0.0,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3600.0,
|
258 |
+
"grad_norm": 0.0003666615521069616,
|
259 |
+
"learning_rate": 1.9139355426213347e-05,
|
260 |
+
"loss": 0.0,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3700.0,
|
265 |
+
"grad_norm": 0.00032034661853685975,
|
266 |
+
"learning_rate": 1.5232206391491699e-05,
|
267 |
+
"loss": 0.0,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 3800.0,
|
272 |
+
"grad_norm": 0.000288996787276119,
|
273 |
+
"learning_rate": 1.1738037526401857e-05,
|
274 |
+
"loss": 0.0,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3900.0,
|
279 |
+
"grad_norm": 0.00018436899699736387,
|
280 |
+
"learning_rate": 8.67387207042194e-06,
|
281 |
+
"loss": 0.0,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 4000.0,
|
286 |
+
"grad_norm": 0.0004207100428175181,
|
287 |
+
"learning_rate": 6.054638329644657e-06,
|
288 |
+
"loss": 0.0,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 4100.0,
|
293 |
+
"grad_norm": 0.0002757696493063122,
|
294 |
+
"learning_rate": 3.893096947570618e-06,
|
295 |
+
"loss": 0.0,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 4200.0,
|
300 |
+
"grad_norm": 0.000379523349693045,
|
301 |
+
"learning_rate": 2.1997787365358958e-06,
|
302 |
+
"loss": 0.0,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 4300.0,
|
307 |
+
"grad_norm": 0.0002130218199454248,
|
308 |
+
"learning_rate": 9.829333726529056e-07,
|
309 |
+
"loss": 0.0,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 4400.0,
|
314 |
+
"grad_norm": 0.00015009118942543864,
|
315 |
+
"learning_rate": 2.484892042176279e-07,
|
316 |
+
"loss": 0.0,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 4500.0,
|
321 |
+
"grad_norm": 0.00018362345872446895,
|
322 |
+
"learning_rate": 2.4369392592760164e-11,
|
323 |
+
"loss": 0.0,
|
324 |
+
"step": 4500
|
325 |
+
}
|
326 |
+
],
|
327 |
+
"logging_steps": 100,
|
328 |
+
"max_steps": 4500,
|
329 |
+
"num_input_tokens_seen": 0,
|
330 |
+
"num_train_epochs": 4500,
|
331 |
+
"save_steps": 500,
|
332 |
+
"stateful_callbacks": {
|
333 |
+
"TrainerControl": {
|
334 |
+
"args": {
|
335 |
+
"should_epoch_stop": false,
|
336 |
+
"should_evaluate": false,
|
337 |
+
"should_log": false,
|
338 |
+
"should_save": true,
|
339 |
+
"should_training_stop": true
|
340 |
+
},
|
341 |
+
"attributes": {}
|
342 |
+
}
|
343 |
+
},
|
344 |
+
"total_flos": 884950147584000.0,
|
345 |
+
"train_batch_size": 4,
|
346 |
+
"trial_name": null,
|
347 |
+
"trial_params": null
|
348 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:447b6d3f2b63abc0067a4d10fe4208ea0013673a66bedca2eab377118855fb62
|
3 |
+
size 5368
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|