Hugging Face's logo

kpalczewski-displate
/
category_cleaning

Zero-Shot Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kpalczewski-displate commited on
Commit
300f91f
•
1 Parent(s): a7af5f9

End of training

Browse files
Files changed (6) hide show
  1. README.md +2 -2
  2. all_results.json +9 -9
  3. eval_results.json +5 -5
  4. runs/Mar08_15-14-28_9da45c1bcf23/events.out.tfevents.1709910909.9da45c1bcf23.91244.1 +3 -0
  5. train_results.json +5 -5
  6. trainer_state.json +72 -12
README.md CHANGED
@@ -2,7 +2,7 @@
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
- - category_cleaning
6
  model-index:
7
  - name: category_cleaning
8
  results: []
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # category_cleaning
15
 
16
- This model was trained from scratch on the category_cleaning dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 2.7922
19
 
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
+ - Displate/category_cleaning
6
  model-index:
7
  - name: category_cleaning
8
  results: []
 
13
 
14
  # category_cleaning
15
 
16
+ This model was trained from scratch on the Displate/category_cleaning dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 2.7922
19
 
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_loss": 1.2932854890823364,
4
- "eval_runtime": 0.1643,
5
- "eval_samples_per_second": 73.032,
6
- "eval_steps_per_second": 6.086,
7
- "train_loss": 1.8652879397074382,
8
- "train_runtime": 4.9548,
9
- "train_samples_per_second": 45.411,
10
- "train_steps_per_second": 1.211
11
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "eval_loss": 2.79219126701355,
4
+ "eval_runtime": 0.1416,
5
+ "eval_samples_per_second": 84.761,
6
+ "eval_steps_per_second": 7.063,
7
+ "train_loss": 0.8449213743209839,
8
+ "train_runtime": 26.655,
9
+ "train_samples_per_second": 56.275,
10
+ "train_steps_per_second": 1.501
11
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_loss": 1.2932854890823364,
4
- "eval_runtime": 0.1643,
5
- "eval_samples_per_second": 73.032,
6
- "eval_steps_per_second": 6.086
7
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "eval_loss": 2.79219126701355,
4
+ "eval_runtime": 0.1416,
5
+ "eval_samples_per_second": 84.761,
6
+ "eval_steps_per_second": 7.063
7
  }
runs/Mar08_15-14-28_9da45c1bcf23/events.out.tfevents.1709910909.9da45c1bcf23.91244.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897a9e65a28b63c22cc67ca532ba3c05c23ad6193ffba10a66c31ec66e13f17f
3
+ size 354
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 1.8652879397074382,
4
- "train_runtime": 4.9548,
5
- "train_samples_per_second": 45.411,
6
- "train_steps_per_second": 1.211
7
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.8449213743209839,
4
+ "train_runtime": 26.655,
5
+ "train_samples_per_second": 56.275,
6
+ "train_steps_per_second": 1.501
7
  }
trainer_state.json CHANGED
@@ -1,29 +1,89 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.0,
5
  "eval_steps": 10,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 3.0,
13
- "step": 6,
14
- "total_flos": 13087574542350.0,
15
- "train_loss": 1.8652879397074382,
16
- "train_runtime": 4.9548,
17
- "train_samples_per_second": 45.411,
18
- "train_steps_per_second": 1.211
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 10,
22
- "max_steps": 6,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 3,
25
  "save_steps": 500,
26
- "total_flos": 13087574542350.0,
27
  "train_batch_size": 64,
28
  "trial_name": null,
29
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
  "eval_steps": 10,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 5.0,
13
+ "grad_norm": 49.72227096557617,
14
+ "learning_rate": 3.7500000000000003e-05,
15
+ "loss": 1.5458,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 5.0,
20
+ "eval_loss": 1.9921075105667114,
21
+ "eval_runtime": 0.0842,
22
+ "eval_samples_per_second": 142.47,
23
+ "eval_steps_per_second": 11.873,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 10.0,
28
+ "grad_norm": 7.272302627563477,
29
+ "learning_rate": 2.5e-05,
30
+ "loss": 0.7085,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 10.0,
35
+ "eval_loss": 2.8139545917510986,
36
+ "eval_runtime": 0.0805,
37
+ "eval_samples_per_second": 149.037,
38
+ "eval_steps_per_second": 12.42,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 15.0,
43
+ "grad_norm": 14.296534538269043,
44
+ "learning_rate": 1.25e-05,
45
+ "loss": 0.6106,
46
+ "step": 30
47
+ },
48
+ {
49
+ "epoch": 15.0,
50
+ "eval_loss": 2.804417848587036,
51
+ "eval_runtime": 0.082,
52
+ "eval_samples_per_second": 146.276,
53
+ "eval_steps_per_second": 12.19,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 20.0,
58
+ "grad_norm": 0.8484093546867371,
59
+ "learning_rate": 0.0,
60
+ "loss": 0.5148,
61
+ "step": 40
62
+ },
63
+ {
64
+ "epoch": 20.0,
65
+ "eval_loss": 2.79219126701355,
66
+ "eval_runtime": 0.0805,
67
+ "eval_samples_per_second": 149.146,
68
+ "eval_steps_per_second": 12.429,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 20.0,
73
+ "step": 40,
74
+ "total_flos": 87250496949000.0,
75
+ "train_loss": 0.8449213743209839,
76
+ "train_runtime": 26.655,
77
+ "train_samples_per_second": 56.275,
78
+ "train_steps_per_second": 1.501
79
  }
80
  ],
81
  "logging_steps": 10,
82
+ "max_steps": 40,
83
  "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 20,
85
  "save_steps": 500,
86
+ "total_flos": 87250496949000.0,
87
  "train_batch_size": 64,
88
  "trial_name": null,
89
  "trial_params": null