Hugging Face's logo

harsith05
/
imdb_practice

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
harsith05 commited on
Commit
48a62e8
·
verified ·
1 Parent(s): d9251c9

Training in progress, epoch 2, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/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 +28 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27834de25ac118c4d59af070cc374749631b6c02121ad779b97d2752992a20b2
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538c3b6bfe3dd5a7b3c54b62f5fc71954f9a303e5e241186f5f44225b3a32ded
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47b33404bccde6e36804626114a174639c19c3befcb9f4d1980cf162b5a49201
3
  size 4741923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a03722c8a0c3282082fdc43862f4dfdfff045c8362575570f9a317662b09964
3
  size 4741923
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb7e7f0e32311ea4a34bdd12b1dc8ec66d46164a59b314eea8415d8682591cf
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d162a27fed25729344a2bcfc01d466b3fce9828a651acf58597c5f5fce3339
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8457a345e0d53a37b5f1ebb6db1120270f6a7f4b99a871d4acda8980a58382cc
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55a14f50074c8ada78f60d77af81976ea4a319a828807b0fe7148cf20eea9f51
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef3af56a55052e98aa5beb6c4c90cc3520c9d76d06c8b7bd66364a88c166c795
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778d08b3d8775920e0ddf0f813feab141bcbe1463b3aa704b47b315801d4216d
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 782,
3
- "best_metric": 1.0015039443969727,
4
- "best_model_checkpoint": "./bert-imdb-cp/checkpoint-782",
5
- "epoch": 1.0,
6
  "eval_steps": 500,
7
- "global_step": 782,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -23,6 +23,28 @@
23
  "eval_samples_per_second": 59.785,
24
  "eval_steps_per_second": 1.87,
25
  "step": 782
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  ],
28
  "logging_steps": 500,
@@ -42,7 +64,7 @@
42
  "attributes": {}
43
  }
44
  },
45
- "total_flos": 6575737273320960.0,
46
  "train_batch_size": 32,
47
  "trial_name": null,
48
  "trial_params": null
 
1
  {
2
+ "best_global_step": 1564,
3
+ "best_metric": 0.8580926656723022,
4
+ "best_model_checkpoint": "./bert-imdb-cp/checkpoint-1564",
5
+ "epoch": 2.0,
6
  "eval_steps": 500,
7
+ "global_step": 1564,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
23
  "eval_samples_per_second": 59.785,
24
  "eval_steps_per_second": 1.87,
25
  "step": 782
26
+ },
27
+ {
28
+ "epoch": 1.278772378516624,
29
+ "grad_norm": 2.3382785320281982,
30
+ "learning_rate": 7.445012787723785e-06,
31
+ "loss": 1.0520084228515625,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 1.918158567774936,
36
+ "grad_norm": 6.36515474319458,
37
+ "learning_rate": 6.166240409207161e-06,
38
+ "loss": 0.9488739624023438,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_loss": 0.8580926656723022,
44
+ "eval_runtime": 417.5511,
45
+ "eval_samples_per_second": 59.873,
46
+ "eval_steps_per_second": 1.873,
47
+ "step": 1564
48
  }
49
  ],
50
  "logging_steps": 500,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 1.314943543596288e+16,
68
  "train_batch_size": 32,
69
  "trial_name": null,
70
  "trial_params": null