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
5b9fcef
·
verified ·
1 Parent(s): 7e4d043

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 sha256:3ec7a44c4fb9a7cb89c58ea6e7b52ef4b9f0f88fac96ed45e44e84c487ccb991
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e10cd4ce21cbffcdbd4d57e715bac4623c7344e0631c294a4b88ae85daac6fe
3
  size 437958648
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8c9bf082e97384ea8d78c1ae1a9a24272e120104f4220e2d417c3de66cf732b
3
  size 15132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69813ceb0538417f9d5aec8a3cf0df7003325bbce72c1aff75e71a95e4903e36
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 sha256:57f9090a10451cfcde8a06c7be0e254fefb5188534b2f83a624ea5b7e7728345
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 sha256:0c28abdc351c8a90f54e4f65c77f64d06f99dbfd78b3087ed5ba445ee81093fa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049572e395d6fcf22f8a706229bb092eb71db07d94600a6903903a7510df1a6c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,71 +1,42 @@
1
  {
2
- "best_global_step": 3126,
3
- "best_metric": 0.6645415425300598,
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": 1.363720417022705,
15
- "learning_rate": 9.980000000000001e-06,
16
- "loss": 0.7124,
17
  "step": 500
18
  },
19
  {
20
  "epoch": 0.6397952655150352,
21
- "grad_norm": 3.833448648452759,
22
- "learning_rate": 9.317840054682162e-06,
23
- "loss": 0.6965,
24
  "step": 1000
25
  },
26
  {
27
  "epoch": 0.9596928982725528,
28
- "grad_norm": 3.1018316745758057,
29
- "learning_rate": 8.634313055365687e-06,
30
- "loss": 0.6864,
31
  "step": 1500
32
  },
33
  {
34
  "epoch": 1.0,
35
- "eval_loss": 0.6799984574317932,
36
- "eval_runtime": 271.586,
37
- "eval_samples_per_second": 92.052,
38
- "eval_steps_per_second": 5.755,
39
  "step": 1563
40
- },
41
- {
42
- "epoch": 1.2795905310300704,
43
- "grad_norm": 1.741823673248291,
44
- "learning_rate": 7.950786056049214e-06,
45
- "loss": 0.6803,
46
- "step": 2000
47
- },
48
- {
49
- "epoch": 1.599488163787588,
50
- "grad_norm": 1.358868956565857,
51
- "learning_rate": 7.268626110731375e-06,
52
- "loss": 0.6769,
53
- "step": 2500
54
- },
55
- {
56
- "epoch": 1.9193857965451055,
57
- "grad_norm": 1.2229254245758057,
58
- "learning_rate": 6.585099111414901e-06,
59
- "loss": 0.6724,
60
- "step": 3000
61
- },
62
- {
63
- "epoch": 2.0,
64
- "eval_loss": 0.6645415425300598,
65
- "eval_runtime": 272.658,
66
- "eval_samples_per_second": 91.69,
67
- "eval_steps_per_second": 5.732,
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": 0.6421542167663574,
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": 1.601021409034729,
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
  "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:bb5f76d7c9e18d0e133606c450598e25e8558beb9c4c2be80a228255702975b0
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3c4d5c55a91e040eab54c87900586dde022464d3a5d3fdf3a520c943ed0d08
3
  size 5432