Upload folder using huggingface_hub
Browse files- all_runs/checkpoint-1286/README.md +202 -0
- all_runs/checkpoint-1286/adapter_config.json +34 -0
- all_runs/checkpoint-1286/adapter_model.safetensors +3 -0
- all_runs/checkpoint-1286/merges.txt +0 -0
- all_runs/checkpoint-1286/optimizer.pt +3 -0
- all_runs/checkpoint-1286/rng_state.pth +3 -0
- all_runs/checkpoint-1286/scheduler.pt +3 -0
- all_runs/checkpoint-1286/special_tokens_map.json +15 -0
- all_runs/checkpoint-1286/tokenizer.json +0 -0
- all_runs/checkpoint-1286/tokenizer_config.json +57 -0
- all_runs/checkpoint-1286/trainer_state.json +207 -0
- all_runs/checkpoint-1286/training_args.bin +3 -0
- all_runs/checkpoint-1286/vocab.json +0 -0
all_runs/checkpoint-1286/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: facebook/bart-large
|
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 0.10.0
|
all_runs/checkpoint-1286/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/bart-large",
|
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": 64,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"fc1",
|
24 |
+
"q_proj",
|
25 |
+
"dense",
|
26 |
+
"k_proj",
|
27 |
+
"out_proj",
|
28 |
+
"fc2",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "SEQ_CLS",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
all_runs/checkpoint-1286/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b8ec8961e6ac8272ea920b9692869fea0a27af675e41dd2fb5d7097bd7359f
|
3 |
+
size 34854640
|
all_runs/checkpoint-1286/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
all_runs/checkpoint-1286/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bdea05987819bf1b4cdb358e006ce59d8b27d910992f005a9d40950dbf83fa4
|
3 |
+
size 69927198
|
all_runs/checkpoint-1286/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61c40c1edd741c1e2faf6be081e9d5d99cd42d36136612b2538d0b1b19e70ff0
|
3 |
+
size 14244
|
all_runs/checkpoint-1286/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:030cf863c34ee0575e672e1e7255a7b356e0f5ebf094ecd73fbf51269aaed246
|
3 |
+
size 1064
|
all_runs/checkpoint-1286/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
all_runs/checkpoint-1286/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
all_runs/checkpoint-1286/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
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 |
+
"50264": {
|
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 |
+
"model_max_length": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
all_runs/checkpoint-1286/trainer_state.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7393184269658342,
|
3 |
+
"best_model_checkpoint": "bart-base-lora/checkpoint-1125",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1286,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.715724244771495,
|
14 |
+
"eval_f1_macro": 0.3957532686340496,
|
15 |
+
"eval_f1_micro": 0.715724244771495,
|
16 |
+
"eval_f1_weighted": 0.6834645556416842,
|
17 |
+
"eval_loss": 0.9525313973426819,
|
18 |
+
"eval_macro_fpr": 0.028501626692807605,
|
19 |
+
"eval_macro_sensitivity": 0.4415906678049911,
|
20 |
+
"eval_macro_specificity": 0.9786637894661117,
|
21 |
+
"eval_precision": 0.6787596592263883,
|
22 |
+
"eval_precision_macro": 0.38751339695744513,
|
23 |
+
"eval_recall": 0.715724244771495,
|
24 |
+
"eval_recall_macro": 0.4415906678049911,
|
25 |
+
"eval_runtime": 120.9594,
|
26 |
+
"eval_samples_per_second": 10.673,
|
27 |
+
"eval_steps_per_second": 1.339,
|
28 |
+
"eval_weighted_fpr": 0.027587762158911525,
|
29 |
+
"eval_weighted_sensitivity": 0.715724244771495,
|
30 |
+
"eval_weighted_specificity": 0.9642325972201805,
|
31 |
+
"step": 160
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.7412858249419055,
|
36 |
+
"eval_f1_macro": 0.43370046411892155,
|
37 |
+
"eval_f1_micro": 0.7412858249419055,
|
38 |
+
"eval_f1_weighted": 0.7231329193382661,
|
39 |
+
"eval_loss": 0.7733433842658997,
|
40 |
+
"eval_macro_fpr": 0.025167370687133015,
|
41 |
+
"eval_macro_sensitivity": 0.4686708989603177,
|
42 |
+
"eval_macro_specificity": 0.9805374797463638,
|
43 |
+
"eval_precision": 0.729625861926521,
|
44 |
+
"eval_precision_macro": 0.4491323101141271,
|
45 |
+
"eval_recall": 0.7412858249419055,
|
46 |
+
"eval_recall_macro": 0.4686708989603177,
|
47 |
+
"eval_runtime": 119.8649,
|
48 |
+
"eval_samples_per_second": 10.77,
|
49 |
+
"eval_steps_per_second": 1.352,
|
50 |
+
"eval_weighted_fpr": 0.024322749781532187,
|
51 |
+
"eval_weighted_sensitivity": 0.7412858249419055,
|
52 |
+
"eval_weighted_specificity": 0.9667763712535515,
|
53 |
+
"step": 321
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 3.0,
|
57 |
+
"eval_accuracy": 0.7738187451587917,
|
58 |
+
"eval_f1_macro": 0.5270593942960143,
|
59 |
+
"eval_f1_micro": 0.7738187451587917,
|
60 |
+
"eval_f1_weighted": 0.7610767338978833,
|
61 |
+
"eval_loss": 0.7104586958885193,
|
62 |
+
"eval_macro_fpr": 0.021211805484311928,
|
63 |
+
"eval_macro_sensitivity": 0.5407847836684627,
|
64 |
+
"eval_macro_specificity": 0.9830897092527341,
|
65 |
+
"eval_precision": 0.7630858215778352,
|
66 |
+
"eval_precision_macro": 0.5565386466479504,
|
67 |
+
"eval_recall": 0.7738187451587917,
|
68 |
+
"eval_recall_macro": 0.5407847836684627,
|
69 |
+
"eval_runtime": 119.5419,
|
70 |
+
"eval_samples_per_second": 10.8,
|
71 |
+
"eval_steps_per_second": 1.355,
|
72 |
+
"eval_weighted_fpr": 0.020451043563524302,
|
73 |
+
"eval_weighted_sensitivity": 0.7738187451587917,
|
74 |
+
"eval_weighted_specificity": 0.9725268936322198,
|
75 |
+
"step": 482
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 3.11,
|
79 |
+
"learning_rate": 3.958333333333333e-05,
|
80 |
+
"loss": 1.08,
|
81 |
+
"step": 500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 4.0,
|
85 |
+
"eval_accuracy": 0.7575522850503486,
|
86 |
+
"eval_f1_macro": 0.5497163954183316,
|
87 |
+
"eval_f1_micro": 0.7575522850503486,
|
88 |
+
"eval_f1_weighted": 0.7437674055775699,
|
89 |
+
"eval_loss": 0.7538753151893616,
|
90 |
+
"eval_macro_fpr": 0.023393901824967867,
|
91 |
+
"eval_macro_sensitivity": 0.5613408412198008,
|
92 |
+
"eval_macro_specificity": 0.9817091819688993,
|
93 |
+
"eval_precision": 0.7583906478192325,
|
94 |
+
"eval_precision_macro": 0.5791225123984725,
|
95 |
+
"eval_recall": 0.7575522850503486,
|
96 |
+
"eval_recall_macro": 0.5613408412198008,
|
97 |
+
"eval_runtime": 120.3095,
|
98 |
+
"eval_samples_per_second": 10.731,
|
99 |
+
"eval_steps_per_second": 1.347,
|
100 |
+
"eval_weighted_fpr": 0.022349161013923598,
|
101 |
+
"eval_weighted_sensitivity": 0.7575522850503486,
|
102 |
+
"eval_weighted_specificity": 0.9680854444831427,
|
103 |
+
"step": 643
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.0,
|
107 |
+
"eval_accuracy": 0.7831138652207591,
|
108 |
+
"eval_f1_macro": 0.6353946839596228,
|
109 |
+
"eval_f1_micro": 0.783113865220759,
|
110 |
+
"eval_f1_weighted": 0.770250750407997,
|
111 |
+
"eval_loss": 0.6978110074996948,
|
112 |
+
"eval_macro_fpr": 0.020328728105215688,
|
113 |
+
"eval_macro_sensitivity": 0.6491872351233146,
|
114 |
+
"eval_macro_specificity": 0.983610303127039,
|
115 |
+
"eval_precision": 0.790031827496624,
|
116 |
+
"eval_precision_macro": 0.7409525878258343,
|
117 |
+
"eval_recall": 0.7831138652207591,
|
118 |
+
"eval_recall_macro": 0.6491872351233146,
|
119 |
+
"eval_runtime": 119.9411,
|
120 |
+
"eval_samples_per_second": 10.764,
|
121 |
+
"eval_steps_per_second": 1.351,
|
122 |
+
"eval_weighted_fpr": 0.019398642095053348,
|
123 |
+
"eval_weighted_sensitivity": 0.7831138652207591,
|
124 |
+
"eval_weighted_specificity": 0.9710406816848265,
|
125 |
+
"step": 803
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 6.0,
|
129 |
+
"eval_accuracy": 0.8156467854376452,
|
130 |
+
"eval_f1_macro": 0.686011065139391,
|
131 |
+
"eval_f1_micro": 0.8156467854376452,
|
132 |
+
"eval_f1_weighted": 0.8087620976325791,
|
133 |
+
"eval_loss": 0.5920090675354004,
|
134 |
+
"eval_macro_fpr": 0.016634568189926056,
|
135 |
+
"eval_macro_sensitivity": 0.6889168814632094,
|
136 |
+
"eval_macro_specificity": 0.9860196319752603,
|
137 |
+
"eval_precision": 0.8053079350996695,
|
138 |
+
"eval_precision_macro": 0.7051361586363433,
|
139 |
+
"eval_recall": 0.8156467854376452,
|
140 |
+
"eval_recall_macro": 0.6889168814632094,
|
141 |
+
"eval_runtime": 121.4244,
|
142 |
+
"eval_samples_per_second": 10.632,
|
143 |
+
"eval_steps_per_second": 1.334,
|
144 |
+
"eval_weighted_fpr": 0.01588785046728972,
|
145 |
+
"eval_weighted_sensitivity": 0.8156467854376452,
|
146 |
+
"eval_weighted_specificity": 0.974647694191258,
|
147 |
+
"step": 964
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 6.22,
|
151 |
+
"learning_rate": 2.916666666666667e-05,
|
152 |
+
"loss": 0.5581,
|
153 |
+
"step": 1000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 7.0,
|
157 |
+
"eval_accuracy": 0.8187451587916343,
|
158 |
+
"eval_f1_macro": 0.7393184269658342,
|
159 |
+
"eval_f1_micro": 0.8187451587916342,
|
160 |
+
"eval_f1_weighted": 0.8146848849127107,
|
161 |
+
"eval_loss": 0.6230757236480713,
|
162 |
+
"eval_macro_fpr": 0.016206558639896132,
|
163 |
+
"eval_macro_sensitivity": 0.7424574536250088,
|
164 |
+
"eval_macro_specificity": 0.9863587851767341,
|
165 |
+
"eval_precision": 0.8177894369587694,
|
166 |
+
"eval_precision_macro": 0.7626654223433325,
|
167 |
+
"eval_recall": 0.8187451587916343,
|
168 |
+
"eval_recall_macro": 0.7424574536250088,
|
169 |
+
"eval_runtime": 122.7775,
|
170 |
+
"eval_samples_per_second": 10.515,
|
171 |
+
"eval_steps_per_second": 1.319,
|
172 |
+
"eval_weighted_fpr": 0.015566790846194785,
|
173 |
+
"eval_weighted_sensitivity": 0.8187451587916343,
|
174 |
+
"eval_weighted_specificity": 0.9766366188593788,
|
175 |
+
"step": 1125
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 8.0,
|
179 |
+
"eval_accuracy": 0.8140975987606507,
|
180 |
+
"eval_f1_macro": 0.7328585966804847,
|
181 |
+
"eval_f1_micro": 0.8140975987606507,
|
182 |
+
"eval_f1_weighted": 0.8088643288992207,
|
183 |
+
"eval_loss": 0.6290707588195801,
|
184 |
+
"eval_macro_fpr": 0.01671628651715199,
|
185 |
+
"eval_macro_sensitivity": 0.730719512015592,
|
186 |
+
"eval_macro_specificity": 0.985990627132147,
|
187 |
+
"eval_precision": 0.8133783130550384,
|
188 |
+
"eval_precision_macro": 0.7636063765511063,
|
189 |
+
"eval_recall": 0.8140975987606507,
|
190 |
+
"eval_recall_macro": 0.730719512015592,
|
191 |
+
"eval_runtime": 122.8754,
|
192 |
+
"eval_samples_per_second": 10.507,
|
193 |
+
"eval_steps_per_second": 1.318,
|
194 |
+
"eval_weighted_fpr": 0.016049217600641968,
|
195 |
+
"eval_weighted_sensitivity": 0.8140975987606507,
|
196 |
+
"eval_weighted_specificity": 0.975761808221554,
|
197 |
+
"step": 1286
|
198 |
+
}
|
199 |
+
],
|
200 |
+
"logging_steps": 500,
|
201 |
+
"max_steps": 2400,
|
202 |
+
"num_train_epochs": 15,
|
203 |
+
"save_steps": 500,
|
204 |
+
"total_flos": 4.57713898892329e+16,
|
205 |
+
"trial_name": null,
|
206 |
+
"trial_params": null
|
207 |
+
}
|
all_runs/checkpoint-1286/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cfeeb4079e0edbd60cad2df3b73a192a8e64f61f57cc52cfabb80fd9ff6105d
|
3 |
+
size 4600
|
all_runs/checkpoint-1286/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|