Hugging Face's logo

mgh6
/
TCS_MLM_All

Fill-Mask
Transformers
TensorBoard
Safetensors
esm
Model card Files Metrics Community
mgh6 commited on
Commit
a64d059
·
verified ·
1 Parent(s): c82364a

Training in progress, step 1050, 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 +4 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa6629809084d1e0509d4cc289b87169dfa3c861eb012cb080133c56d08207b9
3
  size 136000488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f9f05f0d51862408872c7f39c3304a5dbe6e7b1bfb850ae87c21c3fd4a31a1
3
  size 136000488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1908de56824c88e293a5e966e8bc8e8f85075aeb828d353732f2c6728fb86b3
3
  size 268176506
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77010a02025f23460f44ee5f9ee4894941c69bd1d0cd8f0565db387c5b76cdf
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 sha256:1ca8c345ce95ec23bc2370ba6a62dd7ae760ebb2dcd90f0e2732ef0d124176db
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aecda3fc7ab7178f3a7bfdf72d7cbbcd66cc9a0cd8be63629867c6107f19df52
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:ec90df4419bc1788183d4b14708fe72f6455a84f3d58e7a9984c89581a48157e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74eed98a8a1337f31ffec47d419b68752c39d4af2c2730d91240b4a18b979e36
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:c1698f2a3c275181ded2c6f52ffcec238e637f047d2463fda1dc456783c969fd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17f7d82cc351e2d14d89879afa702e7e413b848aea9ebd3db011dcff13ceca0
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 sha256:4d359f360893dcdb0304a82318ef91c90d17ea356410731fe6784d4cb1aae8f5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b67d054240e3475182ed0e508a255651db4425fd8d9944c28a90048969cd846
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ef20705a321e73d88ef11b6e524f85650644866cb653bf90dea905b2590f2fe
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d9ef09d028e93bd79af7307479f118ee3859e0554fd1a84988842441322036
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.0223731994628906,
3
  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
4
- "epoch": 9.523809523809524,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -180,12 +180,12 @@
180
  "should_evaluate": false,
181
  "should_log": false,
182
  "should_save": true,
183
- "should_training_stop": false
184
  },
185
  "attributes": {}
186
  }
187
  },
188
- "total_flos": 2.93172722794496e+16,
189
  "train_batch_size": 64,
190
  "trial_name": null,
191
  "trial_params": null
 
1
  {
2
  "best_metric": 1.0223731994628906,
3
  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
4
+ "epoch": 10.0,
5
  "eval_steps": 100,
6
+ "global_step": 1050,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
180
  "should_evaluate": false,
181
  "should_log": false,
182
  "should_save": true,
183
+ "should_training_stop": true
184
  },
185
  "attributes": {}
186
  }
187
  },
188
+ "total_flos": 3.078313589342208e+16,
189
  "train_batch_size": 64,
190
  "trial_name": null,
191
  "trial_params": null