vidhi0206 commited on
Commit
c8f4a2d
·
verified ·
1 Parent(s): 4de10ac

Add SetFit model

Browse files
Files changed (3) hide show
  1. README.md +15 -15
  2. model.safetensors +1 -1
  3. model_head.pkl +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ model-index:
32
  split: test
33
  metrics:
34
  - type: accuracy
35
- value: 0.4235294117647059
36
  name: Accuracy
37
  ---
38
 
@@ -64,20 +64,20 @@ The model has been trained using an efficient few-shot learning technique that i
64
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
65
 
66
  ### Model Labels
67
- | Label | Examples |
68
- |:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
69
- | 4 | <ul><li>'this is a sincerely crafted picture that deserves to emerge from the traffic jam of holiday movies .'</li><li>'e.t. works because its flabbergasting principals , 14-year-old robert macnaughton , 6-year-old drew barrymore and 10-year-old henry thomas , convince us of the existence of the wise , wizened visitor from a faraway planet .'</li><li>'jones has delivered a solidly entertaining and moving family drama .'</li></ul> |
70
- | 0 | <ul><li>'nothing more than an amiable but unfocused bagatelle that plays like a loosely-connected string of acting-workshop exercises .'</li><li>'makes a joke out of car chases for an hour and then gives us half an hour of car chases .'</li><li>'in all the annals of the movies , few films have been this odd , inexplicable and unpleasant .'</li></ul> |
71
- | 2 | <ul><li>'in gleefully , thumpingly hyperbolic terms , it covers just about every cliche in the compendium about crass , jaded movie types and the phony baloney movie biz .'</li><li>"this may be dover kosashvili 's feature directing debut , but it looks an awful lot like life -- gritty , awkward and ironic ."</li><li>"the filmmaker 's heart is in the right place ..."</li></ul> |
72
- | 3 | <ul><li>"if you 're as happy listening to movies as you are watching them , and the slow parade of human frailty fascinates you , then you 're at the right film ."</li><li>'a bracing , unblinking work that serves as a painful elegy and sobering cautionary tale .'</li><li>"now as a former gong show addict , i 'll admit it , my only complaint is that we did n't get more re-creations of all those famous moments from the show ."</li></ul> |
73
- | 1 | <ul><li>"you 'll feel like you ate a reeses without the peanut butter ... '"</li><li>"but , like silence , it 's a movie that gets under your skin ."</li><li>'he seems to want both , but succeeds in making neither .'</li></ul> |
74
 
75
  ## Evaluation
76
 
77
  ### Metrics
78
  | Label | Accuracy |
79
  |:--------|:---------|
80
- | **all** | 0.4235 |
81
 
82
  ## Uses
83
 
@@ -129,7 +129,7 @@ preds = model("my response to the film is best described as lukewarm .")
129
  ### Training Set Metrics
130
  | Training set | Min | Median | Max |
131
  |:-------------|:----|:-------|:----|
132
- | Word count | 3 | 18.325 | 35 |
133
 
134
  | Label | Training Sample Count |
135
  |:------|:----------------------|
@@ -160,11 +160,11 @@ preds = model("my response to the film is best described as lukewarm .")
160
  ### Training Results
161
  | Epoch | Step | Training Loss | Validation Loss |
162
  |:-----:|:----:|:-------------:|:---------------:|
163
- | 0.005 | 1 | 0.3225 | - |
164
- | 0.25 | 50 | 0.2032 | - |
165
- | 0.5 | 100 | 0.0987 | - |
166
- | 0.75 | 150 | 0.062 | - |
167
- | 1.0 | 200 | 0.016 | - |
168
 
169
  ### Framework Versions
170
  - Python: 3.8.10
 
32
  split: test
33
  metrics:
34
  - type: accuracy
35
+ value: 0.38371040723981903
36
  name: Accuracy
37
  ---
38
 
 
64
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
65
 
66
  ### Model Labels
67
+ | Label | Examples |
68
+ |:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
69
+ | 2 | <ul><li>"will no doubt delight plympton 's legion of fans ; others may find 80 minutes of these shenanigans exhausting ."</li><li>"there 's no real reason to see it , and no real reason not to ."</li><li>'in the telling of a story largely untold , bui chooses to produce something that is ultimately suspiciously familiar .'</li></ul> |
70
+ | 4 | <ul><li>'stevens has a flair for dialogue comedy , the film operates nicely off the element of surprise , and the large cast is solid .'</li><li>'a thought-provoking picture .'</li><li>'arguably the best script that besson has written in years .'</li></ul> |
71
+ | 3 | <ul><li>"trapped presents a frightening and compelling ` what if ? '"</li><li>'cremaster 3 is at once a tough pill to swallow and a minor miracle of self-expression .'</li><li>"toes the fine line between cheese and earnestness remarkably well ; everything is delivered with such conviction that it 's hard not to be carried away ."</li></ul> |
72
+ | 1 | <ul><li>'the laughs are as rare as snake foo yung .'</li><li>'could this be the first major studio production shot on video tape instead of film ?'</li><li>'well , this movie proves you wrong on both counts .'</li></ul> |
73
+ | 0 | <ul><li>"... this is n't even a movie we can enjoy as mild escapism ; it is one in which fear and frustration are provoked to intolerable levels ."</li><li>'this kiddie-oriented stinker is so bad that i even caught the gum stuck under my seat trying to sneak out of the theater'</li><li>"as a remake , it 's a pale imitation ."</li></ul> |
74
 
75
  ## Evaluation
76
 
77
  ### Metrics
78
  | Label | Accuracy |
79
  |:--------|:---------|
80
+ | **all** | 0.3837 |
81
 
82
  ## Uses
83
 
 
129
  ### Training Set Metrics
130
  | Training set | Min | Median | Max |
131
  |:-------------|:----|:-------|:----|
132
+ | Word count | 3 | 16.85 | 34 |
133
 
134
  | Label | Training Sample Count |
135
  |:------|:----------------------|
 
160
  ### Training Results
161
  | Epoch | Step | Training Loss | Validation Loss |
162
  |:-----:|:----:|:-------------:|:---------------:|
163
+ | 0.005 | 1 | 0.335 | - |
164
+ | 0.25 | 50 | 0.1776 | - |
165
+ | 0.5 | 100 | 0.0768 | - |
166
+ | 0.75 | 150 | 0.0198 | - |
167
+ | 1.0 | 200 | 0.0072 | - |
168
 
169
  ### Framework Versions
170
  - Python: 3.8.10
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aabc34a2497a421e7187b9f200b4d745a96874a3de9628d5762a8a4a04f4abe3
3
  size 437967672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e5f70d7839dccce8f57cd07a66b1ff168ed9cc83e6b06f5e7161fd5e712d58
3
  size 437967672
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eecc6916659afede329d0b395e6912f53a7e404b61a3350a070754cc035b02ea
3
  size 31631
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4afe08c3989bf930041ed8363a72b35669cc71072a468c8bf6ff8633c46db488
3
  size 31631