Hugging Face's logo

mgh6
/
TCS_MLM_SaProt

Fill-Mask
Transformers
TensorBoard
Safetensors
esm
Model card Files
xet
 Metrics Community
mgh6 commited on
Commit
d9a289c
·
verified ·
1 Parent(s): 404a998

Training in progress, step 300, checkpoint

Browse files
Files changed (5) 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/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +10 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30b0f309b7f4a021aeae9b8c023638b91640c0494b78df53f9799eafce8591ec
3
  size 2611614300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0fa296798d9cdcadaab6e96740003c7a0e4443525b472b72cbe0f7da282bcf
3
  size 2611614300
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cbefb9ea304174eb6b10d342f4670b2fe3cd40d03615dc555c42ec57dc27c0e
3
  size 5213028466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff00e5e52075027447d0f25e67ee29e80a073bbf0e0a33be73a27801bee378b
3
  size 5213028466
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b5a50d8043ac6976ce002b35434e69f45b0b7b1b32881ce5602e437b14e194b
3
  size 14942
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c97e55e18090da6d731a9d609491c0dc3404a5277236f2e6505dc60d9ff0699f
3
  size 14942
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eecc763d4f0407011d54bc501a4da5c4c1dfc18e161c6f252fcc58e764d0886a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77712d9502f65a409c52e12da05f15e6f1ae096bc13a5b136d2cc201ae8919c4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.04968751213074027,
5
  "eval_steps": 500,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -21,6 +21,13 @@
21
  "learning_rate": 0.000995031055900621,
22
  "loss": 1.7117682180722524e+16,
23
  "step": 200
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 100,
@@ -40,7 +47,7 @@
40
  "attributes": {}
41
  }
42
  },
43
- "total_flos": 3.889759465452339e+16,
44
  "train_batch_size": 1,
45
  "trial_name": null,
46
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0745312681961104,
5
  "eval_steps": 500,
6
+ "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
21
  "learning_rate": 0.000995031055900621,
22
  "loss": 1.7117682180722524e+16,
23
  "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.0745312681961104,
27
+ "grad_norm": 0.5384548306465149,
28
+ "learning_rate": 0.0009925465838509318,
29
+ "loss": 1.2063225853446717e+17,
30
+ "step": 300
31
  }
32
  ],
33
  "logging_steps": 100,
 
47
  "attributes": {}
48
  }
49
  },
50
+ "total_flos": 5.834639198178509e+16,
51
  "train_batch_size": 1,
52
  "trial_name": null,
53
  "trial_params": null