Hugging Face's logo

mgh6
/
TCS_Pairing_VAE

Safetensors
Model card Files Community
mgh6 commited on
Commit
2acb0a2
•
1 Parent(s): 92b4b4c

Training in progress, step 1280

Browse files
Files changed (8) hide show
  1. model.safetensors +2 -2
  2. tmp-checkpoint-300/model.safetensors +3 -0
  3. tmp-checkpoint-300/optimizer.pt +3 -0
  4. tmp-checkpoint-300/rng_state.pth +3 -0
  5. tmp-checkpoint-300/scheduler.pt +3 -0
  6. tmp-checkpoint-300/trainer_state.json +63 -0
  7. tmp-checkpoint-300/training_args.bin +3 -0
  8. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d4780d8e2a40180d477f830935401dd2e7f70748eb0727218408bf511e5bfe
3
- size 4675160156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10644a595e8f1333d5ede8e726c10c0f288ce2dba4d4fba64d23a335acea1368
3
+ size 280149152
tmp-checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d4780d8e2a40180d477f830935401dd2e7f70748eb0727218408bf511e5bfe
3
+ size 4675160156
tmp-checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465a9633d64867d9027c669bb48ae0bb7ef18cc95f430b77e7dee626f19d3ebf
3
+ size 9214296767
tmp-checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e89ede40e0337581cc6d477777c115e9af1d2a7a90787e141c64c60488dd59
3
+ size 14503
tmp-checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108fd27506bcfe6b6f8e8ed492e133fb0a2c18a3ebd9562fe79889ca5e33a025
3
+ size 623
tmp-checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": NaN,
3
+ "best_model_checkpoint": "mgh6/TCS_Pairing_VAE/checkpoint-100",
4
+ "epoch": 0.0027706715184203476,
5
+ "eval_steps": 100,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0009999692147609064,
14
+ "loss": 12653.28,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "eval_loss": NaN,
20
+ "eval_runtime": 60.2212,
21
+ "eval_samples_per_second": 53.636,
22
+ "eval_steps_per_second": 53.636,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "learning_rate": 0.000999938429521813,
28
+ "loss": 0.0,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.0,
33
+ "eval_loss": NaN,
34
+ "eval_runtime": 62.8807,
35
+ "eval_samples_per_second": 51.367,
36
+ "eval_steps_per_second": 51.367,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "learning_rate": 0.0009999076442827194,
42
+ "loss": 0.0,
43
+ "step": 300
44
+ },
45
+ {
46
+ "epoch": 0.0,
47
+ "eval_loss": NaN,
48
+ "eval_runtime": 62.677,
49
+ "eval_samples_per_second": 51.534,
50
+ "eval_steps_per_second": 51.534,
51
+ "step": 300
52
+ }
53
+ ],
54
+ "logging_steps": 100,
55
+ "max_steps": 3248310,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 30,
58
+ "save_steps": 100,
59
+ "total_flos": 0.0,
60
+ "train_batch_size": 1,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
tmp-checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f441d83f12ce9d03d9cb6e56bf490e9442cf9d8b2c636217c83445a4bc6874
3
+ size 4271
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f441d83f12ce9d03d9cb6e56bf490e9442cf9d8b2c636217c83445a4bc6874
3
  size 4271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17591b4985849a9224798336001b49dd77f2c940ea1fa951a5141778729a83d
3
  size 4271