Hugging Face's logo

harsith05
/
imdbdata

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
harsith05 commited on
Commit
8c83956
·
verified ·
1 Parent(s): a28b95f

Training in progress, epoch 1, checkpoint

Browse files
Files changed (7) 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 +19 -48
  7. last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f719df5c83666eec61603992db9030357dd727e75dcaa3d406c75539d8fa528b
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6150ab718e56792dae4144c609ddc3646236b5d1bcd0bfb4acc9f9570a43114e
3
  size 437958648
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84d7a8fc17e0de59435c69efd2b65dd40bf467a3d067ba3c81aad134cbd9f092
3
  size 15132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595c5de21882d505de5d28e4d7ada9a42b76bb47345b5c2fa1676ad2cd52b479
3
  size 15132
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:691b3b85e42c089d2bdb72309424d3454b990e0596c27b15f218b3f6e4c39e55
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fde5d78d467270e6f38169a48e70e420d3afe1146078e423f8499685461bf22
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8243327b567e29221b3b0a60eae4c9072058f5c8b9c0d230403fabc381ad170
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713ce80c4477b3cfcc8aacd01e948331f6b151bcde4f5963a683f54fa49aa3e3
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3670c631aacd1a4f845efa5b330f928a1ce229840199ae317c17f3db16fde01e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4bdd482695b42169ef7246f76d1bdfc504014258754e59317c8db3044fb3370
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,71 +1,42 @@
1
  {
2
- "best_global_step": 3126,
3
- "best_metric": 0.6253220438957214,
4
- "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-3126",
5
- "epoch": 2.0,
6
  "eval_steps": 500,
7
- "global_step": 3126,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
  "epoch": 0.3198976327575176,
14
- "grad_norm": 1.601021409034729,
15
- "learning_rate": 1.9960000000000002e-05,
16
- "loss": 0.6662,
17
  "step": 500
18
  },
19
  {
20
  "epoch": 0.6397952655150352,
21
- "grad_norm": 3.4787182807922363,
22
- "learning_rate": 1.8635680109364324e-05,
23
- "loss": 0.6591,
24
  "step": 1000
25
  },
26
  {
27
  "epoch": 0.9596928982725528,
28
- "grad_norm": 3.4800970554351807,
29
- "learning_rate": 1.7268626110731374e-05,
30
- "loss": 0.6507,
31
  "step": 1500
32
  },
33
  {
34
  "epoch": 1.0,
35
- "eval_loss": 0.6421542167663574,
36
- "eval_runtime": 272.3617,
37
- "eval_samples_per_second": 91.79,
38
- "eval_steps_per_second": 5.739,
39
  "step": 1563
40
- },
41
- {
42
- "epoch": 1.2795905310300704,
43
- "grad_norm": 1.9906386137008667,
44
- "learning_rate": 1.5901572112098428e-05,
45
- "loss": 0.6446,
46
- "step": 2000
47
- },
48
- {
49
- "epoch": 1.599488163787588,
50
- "grad_norm": 1.4003853797912598,
51
- "learning_rate": 1.4534518113465483e-05,
52
- "loss": 0.6391,
53
- "step": 2500
54
- },
55
- {
56
- "epoch": 1.9193857965451055,
57
- "grad_norm": 1.166661024093628,
58
- "learning_rate": 1.3167464114832538e-05,
59
- "loss": 0.6377,
60
- "step": 3000
61
- },
62
- {
63
- "epoch": 2.0,
64
- "eval_loss": 0.6253220438957214,
65
- "eval_runtime": 288.1305,
66
- "eval_samples_per_second": 86.766,
67
- "eval_steps_per_second": 5.425,
68
- "step": 3126
69
  }
70
  ],
71
  "logging_steps": 500,
@@ -85,7 +56,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1.302353679597312e+16,
89
  "train_batch_size": 16,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
+ "best_global_step": 1563,
3
+ "best_metric": 0.618361234664917,
4
+ "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-1563",
5
+ "epoch": 1.0,
6
  "eval_steps": 500,
7
+ "global_step": 1563,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
  "epoch": 0.3198976327575176,
14
+ "grad_norm": 1.6426746845245361,
15
+ "learning_rate": 9.361484325015996e-06,
16
+ "loss": 0.6295,
17
  "step": 500
18
  },
19
  {
20
  "epoch": 0.6397952655150352,
21
+ "grad_norm": 3.4760828018188477,
22
+ "learning_rate": 8.72168905950096e-06,
23
+ "loss": 0.6269,
24
  "step": 1000
25
  },
26
  {
27
  "epoch": 0.9596928982725528,
28
+ "grad_norm": 3.5572147369384766,
29
+ "learning_rate": 8.081893793985925e-06,
30
+ "loss": 0.6237,
31
  "step": 1500
32
  },
33
  {
34
  "epoch": 1.0,
35
+ "eval_loss": 0.618361234664917,
36
+ "eval_runtime": 393.46,
37
+ "eval_samples_per_second": 63.539,
38
+ "eval_steps_per_second": 3.972,
39
  "step": 1563
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 500,
 
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 6515172397265280.0,
60
  "train_batch_size": 16,
61
  "trial_name": null,
62
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d3c4d5c55a91e040eab54c87900586dde022464d3a5d3fdf3a520c943ed0d08
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bb51a5a37a5d18e30f0bf5b5ebc89b2910c739252bc87dc6993eae90eab68a
3
  size 5432