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
57be2b9
·
verified ·
1 Parent(s): b24daec

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:b5c60f390a2a09c2d06f316d2eb971ceaae9536585000f507723f926c22f62c4
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17889f4429a43a5a0a4d569909ac577582a885c693d0236337e042289408a8a
3
  size 437958624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf2a19a8032edc40bb658d66547edff470d09254585ba9f3c328c5e1b984375
3
  size 113448011
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b1649f3264bda47e5bbbe75576d81db33ff4754130670de728c70f06143143
3
  size 113448011
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 sha256:3026a6862398ced41e03f502f101f7ea90db137e7358354f2ae702c428eaf49c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14d00f72886e8ec8d937b16720d48c02e9423351bcc4d3bf797290ffccd4584
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 782,
3
- "best_metric": 0.4083733856678009,
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": 53.71,
24
  "eval_steps_per_second": 1.68,
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": 0.39844831824302673,
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": 53.71,
24
  "eval_steps_per_second": 1.68,
25
  "step": 782
26
+ },
27
+ {
28
+ "epoch": 1.278772378516624,
29
+ "grad_norm": 2.6754071712493896,
30
+ "learning_rate": 1.489002557544757e-05,
31
+ "loss": 0.4587330322265625,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 1.918158567774936,
36
+ "grad_norm": 5.257985591888428,
37
+ "learning_rate": 1.2332480818414323e-05,
38
+ "loss": 0.42192544555664063,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_loss": 0.39844831824302673,
44
+ "eval_runtime": 464.9715,
45
+ "eval_samples_per_second": 53.767,
46
+ "eval_steps_per_second": 1.682,
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