Hugging Face's logo

VQA-DeepLearning
/
gemma_2_lora_E2b

Transformers
Safetensors
Generated from Trainer
unsloth
sft
trl
Model card Files
xet
 Community
HoangVuSnape commited on
Commit
27db80a
·
verified ·
1 Parent(s): 23b62c2

Training in progress, step 50, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +18 -53
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243afe13b8f7ac02a2de4c471bfddfd7550ff18062abdca28e6f0aa42e46f6c9
3
  size 119548152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f00321c53fa88823cc86ce5b643253810afc2bd373424cfcb5a76cf5cb0cd9
3
  size 119548152
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40eac6306a71df615dbb9f067f2753b5afb4d8708d0183fbdbb8b8b1e4cd13ad
3
  size 61495181
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4912cd02c621dbf65f2f8ce9cb20291a21f6181a38b4c0363417d74732b75f56
3
  size 61495181
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94c00658d824d839e37a5c57ecea61b532722e37885f84da53f64ef55b444877
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218aea9ed006a13e9f4fca8f999bc53d641c17be32296144dc57ba9553c21a78
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba579c51934cb0081af1cef8f2325237069970f127311ca36603dc32077d9154
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0577d256f9bcf47f54437e06329276dcb1395ae02d0747da815272e814009dce
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,82 +2,47 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.22308979364194087,
6
  "eval_steps": 500,
7
- "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
  "epoch": 0.022308979364194088,
14
- "grad_norm": 8.05798625946045,
15
- "learning_rate": 0.0001999777729859618,
16
- "loss": 3.8334781646728517,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.044617958728388175,
21
- "grad_norm": 1.6715857982635498,
22
- "learning_rate": 0.00019958290088291011,
23
- "loss": 1.101065731048584,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.06692693809258227,
28
- "grad_norm": 1.0383472442626953,
29
- "learning_rate": 0.00019869633954726807,
30
- "loss": 0.728734827041626,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 0.08923591745677635,
35
- "grad_norm": 0.9646288752555847,
36
- "learning_rate": 0.00019732246636369605,
37
- "loss": 0.6313149452209472,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 0.11154489682097044,
42
- "grad_norm": 0.8490267395973206,
43
- "learning_rate": 0.0001954680648125438,
44
- "loss": 0.6139058113098145,
45
  "step": 50
46
- },
47
- {
48
- "epoch": 0.13385387618516453,
49
- "grad_norm": 0.8779762387275696,
50
- "learning_rate": 0.00019314229097650742,
51
- "loss": 0.5535756111145019,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.1561628555493586,
56
- "grad_norm": 0.8322303891181946,
57
- "learning_rate": 0.00019035662833259432,
58
- "loss": 0.5122283935546875,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.1784718349135527,
63
- "grad_norm": 0.5753958225250244,
64
- "learning_rate": 0.00018712483105261005,
65
- "loss": 0.44754557609558104,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.2007808142777468,
70
- "grad_norm": 0.7920306324958801,
71
- "learning_rate": 0.00018346285609212025,
72
- "loss": 0.4128209114074707,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.22308979364194087,
77
- "grad_norm": 0.6400466561317444,
78
- "learning_rate": 0.0001793887844031972,
79
- "loss": 0.4159227848052979,
80
- "step": 100
81
  }
82
  ],
83
  "logging_steps": 10,
@@ -97,7 +62,7 @@
97
  "attributes": {}
98
  }
99
  },
100
- "total_flos": 1609636050452544.0,
101
  "train_batch_size": 1,
102
  "trial_name": null,
103
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.11154489682097044,
6
  "eval_steps": 500,
7
+ "global_step": 50,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
  "epoch": 0.022308979364194088,
14
+ "grad_norm": 0.47332054376602173,
15
+ "learning_rate": 0.0001998790061807298,
16
+ "loss": 0.4195059299468994,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.044617958728388175,
21
+ "grad_norm": 0.6206803917884827,
22
+ "learning_rate": 0.00019928708812698545,
23
+ "loss": 0.36927917003631594,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.06692693809258227,
28
+ "grad_norm": 0.5743476748466492,
29
+ "learning_rate": 0.00019820494141215104,
30
+ "loss": 0.3785541296005249,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 0.08923591745677635,
35
+ "grad_norm": 0.49116021394729614,
36
+ "learning_rate": 0.00019663790912106393,
37
+ "loss": 0.36582486629486083,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 0.11154489682097044,
42
+ "grad_norm": 0.6498185992240906,
43
+ "learning_rate": 0.00019459372845456705,
44
+ "loss": 0.3734700679779053,
45
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
 
62
  "attributes": {}
63
  }
64
  },
65
+ "total_flos": 881973407003136.0,
66
  "train_batch_size": 1,
67
  "trial_name": null,
68
  "trial_params": null