Hugging Face's logo

shihaozou
/
bobai-mlm-pretrain

Fill-Mask
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
shihaozou commited on
Commit
05be710
·
verified ·
1 Parent(s): 7461088

Training in progress, step 500, checkpoint

Browse files
Files changed (9) hide show
  1. last-checkpoint/config.json +1 -1
  2. last-checkpoint/model.safetensors +2 -2
  3. last-checkpoint/optimizer.pt +2 -2
  4. last-checkpoint/rng_state.pth +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/tokenizer.json +0 -0
  7. last-checkpoint/trainer_state.json +5 -47
  8. last-checkpoint/training_args.bin +1 -1
  9. last-checkpoint/vocab.txt +2 -2
last-checkpoint/config.json CHANGED
@@ -27,5 +27,5 @@
27
  "transformers_version": "4.41.2",
28
  "type_vocab_size": 2,
29
  "use_cache": true,
30
- "vocab_size": 176010
31
  }
 
27
  "transformers_version": "4.41.2",
28
  "type_vocab_size": 2,
29
  "use_cache": true,
30
+ "vocab_size": 175991
31
  }
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a202bd5af148822e1e3e07b2eba74358cbcb64475af47c8f95c2551a78d63805
3
- size 885602000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c360d853b22122494c741e378234f5dcb8fff8c95b65b8be9dd20c6904ec60a
3
+ size 885543556
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dc68bf25f63fc2820f2b6b3cf5ae7618b2dac90481a0e9aa1c0b4635646784e
3
- size 1771325498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9a70b47037089b1fc83a29f0fccb1d23b2e2cef538317eedcb35b38b9e0f2c
3
+ size 1771208634
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a00a5d457468f8e96ffffdc8c00d28024f7b75aca00e6b753bc84869b865ea3e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ff5bd3a0068b490c864320566bda7f5fdd2275d25e879fb1f4de3f45b64f79
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cbdad3847a2cf371eac01931a8217d0a1f823a0f4700aaf5a80943ae3b42e38
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ec6cc9c7b2f046f413e3061298f47cb8246946a0ef13a247b050ceda37b8fd
3
  size 1064
last-checkpoint/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/trainer_state.json CHANGED
@@ -1,61 +1,19 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.050897985893986766,
5
  "eval_steps": 500,
6
- "global_step": 3500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.00727114084199811,
13
- "grad_norm": 16.903057098388672,
14
  "learning_rate": 1.9951525727720014e-05,
15
- "loss": 7.7051,
16
  "step": 500
17
- },
18
- {
19
- "epoch": 0.01454228168399622,
20
- "grad_norm": 13.898771286010742,
21
- "learning_rate": 1.990305145544003e-05,
22
- "loss": 6.7587,
23
- "step": 1000
24
- },
25
- {
26
- "epoch": 0.021813422525994327,
27
- "grad_norm": 15.041173934936523,
28
- "learning_rate": 1.985457718316004e-05,
29
- "loss": 6.6744,
30
- "step": 1500
31
- },
32
- {
33
- "epoch": 0.02908456336799244,
34
- "grad_norm": 16.15885353088379,
35
- "learning_rate": 1.9806102910880053e-05,
36
- "loss": 6.5784,
37
- "step": 2000
38
- },
39
- {
40
- "epoch": 0.03635570420999055,
41
- "grad_norm": 10.643068313598633,
42
- "learning_rate": 1.9757628638600062e-05,
43
- "loss": 6.3891,
44
- "step": 2500
45
- },
46
- {
47
- "epoch": 0.043626845051988654,
48
- "grad_norm": 24.84389305114746,
49
- "learning_rate": 1.9709154366320078e-05,
50
- "loss": 6.3109,
51
- "step": 3000
52
- },
53
- {
54
- "epoch": 0.050897985893986766,
55
- "grad_norm": 19.950510025024414,
56
- "learning_rate": 1.966068009404009e-05,
57
- "loss": 6.2184,
58
- "step": 3500
59
  }
60
  ],
61
  "logging_steps": 500,
@@ -75,7 +33,7 @@
75
  "attributes": {}
76
  }
77
  },
78
- "total_flos": 752705153984160.0,
79
  "train_batch_size": 8,
80
  "trial_name": null,
81
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00727114084199811,
5
  "eval_steps": 500,
6
+ "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.00727114084199811,
13
+ "grad_norm": 25.571533203125,
14
  "learning_rate": 1.9951525727720014e-05,
15
+ "loss": 7.7581,
16
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
18
  ],
19
  "logging_steps": 500,
 
33
  "attributes": {}
34
  }
35
  },
36
+ "total_flos": 113609162581536.0,
37
  "train_batch_size": 8,
38
  "trial_name": null,
39
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:506a91072dc9c192fc9340a397644c79df2652fd40a31232d3381786d2600a6a
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d95f25e1de35f62e4e204ab538306ecef4ab283e65af475b969cd70e1e4be3e
3
  size 5176
last-checkpoint/vocab.txt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eb1a27fddb0f62179356fa7a776bac17897f7b576556dcb7e9e86a79e750698
3
- size 4759934
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e054944723e90105c2050b9d8316d91afe1bf990a0839482c14bf732eb3edc06
3
+ size 4759663