Hugging Face's logo

mgh6
/
TCS_MLM

Fill-Mask
Transformers
TensorBoard
Safetensors
esm
Model card Files
xet
Metrics Community
mgh6 commited on
Commit
d01cfe7
·
verified ·
1 Parent(s): 484b7d6

Training in progress, step 400, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +20 -5
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05bdb81ea9fd3fb7fee69363543e0abb627618d494a437b729ea47c50157ca52
3
  size 136000488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f27c55a6b7ff26add6ca12b66b08a03938a5264d91f6c3c0858e7cc44a0885
3
  size 136000488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e0de4cc64561a2e127a5c5a576cfa4877018690c45b21294691e3aa497459b8
3
  size 268176506
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3528c3f2886f6a6ff39794da95c97e7e9168c462ba99a0aacb9a5f7e0ee006
3
  size 268176506
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c36ff10dd2a06f64abe8c50f0195373fd0ff96ab73fe93f86c0fc6019aa6cd7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36205505ff7c8f39e1e4c85b6853d46fb51500bf0f06c3d0a59c07012b9a9832
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d74e9d8e3d06c40a9ac96856348569834b8994791b3d5aae1e2e971c3d36f89
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6477b3da99bdcdb3a930c7bf415bba4680e36c852eb3e5e5f110e648f5923ebb
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55f3a3269c586457d190d66e9d2716fd5f503d02f41c3c15109c31faad2d4e0c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196f2299243dc0bc367db6f89dcd8263fed09436b97fc4aea1759596eb3a66c3
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c00c02e75f0b8ba3dec9f97bfdfaa0f162c32f2f42503a061b77c04f924bbab3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9840f31cf2ea0e1349fc2944a1471b0767f445ae4b9229fa04546cbf3a99e9
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87c5c7a464f7359a51f160c6e7acb947388efd776aacc4351ee16aea191aa1f7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c58c1cd6178c8f979902cb0d2a83ba9e449411fde4b3ef37d83085a443371c56
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0328294038772583,
3
- "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-300",
4
- "epoch": 0.40160642570281124,
5
  "eval_steps": 100,
6
- "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,21 @@
52
  "eval_samples_per_second": 891.734,
53
  "eval_steps_per_second": 3.603,
54
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 100,
@@ -80,7 +95,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 1.0893681229824e+16,
84
  "train_batch_size": 64,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0003758668899536,
3
+ "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-400",
4
+ "epoch": 0.535475234270415,
5
  "eval_steps": 100,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 891.734,
53
  "eval_steps_per_second": 3.603,
54
  "step": 300
55
+ },
56
+ {
57
+ "epoch": 0.535475234270415,
58
+ "grad_norm": 0.21808107197284698,
59
+ "learning_rate": 0.0009464524765729585,
60
+ "loss": 1.0729,
61
+ "step": 400
62
+ },
63
+ {
64
+ "epoch": 0.535475234270415,
65
+ "eval_loss": 1.0003758668899536,
66
+ "eval_runtime": 6.3823,
67
+ "eval_samples_per_second": 891.836,
68
+ "eval_steps_per_second": 3.604,
69
+ "step": 400
70
  }
71
  ],
72
  "logging_steps": 100,
 
95
  "attributes": {}
96
  }
97
  },
98
+ "total_flos": 1.4524908306432e+16,
99
  "train_batch_size": 64,
100
  "trial_name": null,
101
  "trial_params": null