Hugging Face's logo

mgh6
/
TCS_MLM

Fill-Mask
Transformers
TensorBoard
Safetensors
esm
Model card Files
xet
 Metrics Community
mgh6 commited on
Commit
f679fc4
·
verified ·
1 Parent(s): 15d4b6c

Training in progress, step 2500, 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 +19 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e70d948b14eeb2738c622c9062216d0b8e2a32126d68081cae366880231148b
3
  size 136000488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf111968ecfd2182c79cddf389aace292b624f4a12fdb0bf19c9d0af2659062c
3
  size 136000488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ce78e97c8ae69598891ec67aee3926e6b331920bcd79fa081e823d88bd33450
3
  size 268176506
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3804765c23fc480a9bc5293bd84544675f9d46fa8eb789519d64c12c10c72487
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 sha256:0a930774a621d4d5d809c7d64a221ff6bd07ed23f3ed097b50736aabef7637e5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552f53b4bfd8ff78acb22151277476df50231d55d234625cfa40edaa0bf9d3a3
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 sha256:0e3d5b90f1e82706bb6a590340582d4016e7c5e4792a715e2f622fe917104775
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f943f1eeef7f7e5f3f5e29d148df316e616bd2fd831bac81ced32f2548fecd
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 sha256:953299768136249cbeaf35052c07f5beaddf92b3ed6807401fc342d1f3ce8a19
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf49525bf634d756188799e8cd0d7b30d96b1892be840b29e954ce7ba14f5594
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 sha256:605e0299f66122c6d4f906277dccc7352e4b84e55889db022b63c776ad810b8b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d607d560bac1029ae756b5a3cdb456902c25b1aaa01de4add5870301e06f0d06
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33272a1400e7968fc81a41e0dd087f4d4d92e5236ea466e9bc96e6973620ac72
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6beb8fe2c3ec1351bc7066a891a1abcb74c93ada85504874b2e06ac13e8f908
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.8264986872673035,
3
  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2400",
4
- "epoch": 3.21285140562249,
5
  "eval_steps": 100,
6
- "global_step": 2400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -367,6 +367,21 @@
367
  "eval_samples_per_second": 893.972,
368
  "eval_steps_per_second": 3.612,
369
  "step": 2400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
370
  }
371
  ],
372
  "logging_steps": 100,
@@ -381,7 +396,7 @@
381
  "early_stopping_threshold": 0.0
382
  },
383
  "attributes": {
384
- "early_stopping_patience_counter": 0
385
  }
386
  },
387
  "TrainerControl": {
@@ -395,7 +410,7 @@
395
  "attributes": {}
396
  }
397
  },
398
- "total_flos": 8.7149449838592e+16,
399
  "train_batch_size": 64,
400
  "trial_name": null,
401
  "trial_params": null
 
1
  {
2
  "best_metric": 0.8264986872673035,
3
  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2400",
4
+ "epoch": 3.3467202141900936,
5
  "eval_steps": 100,
6
+ "global_step": 2500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
367
  "eval_samples_per_second": 893.972,
368
  "eval_steps_per_second": 3.612,
369
  "step": 2400
370
+ },
371
+ {
372
+ "epoch": 3.3467202141900936,
373
+ "grad_norm": 0.21075735986232758,
374
+ "learning_rate": 0.0006653279785809906,
375
+ "loss": 0.814,
376
+ "step": 2500
377
+ },
378
+ {
379
+ "epoch": 3.3467202141900936,
380
+ "eval_loss": 0.8332136869430542,
381
+ "eval_runtime": 6.3889,
382
+ "eval_samples_per_second": 890.924,
383
+ "eval_steps_per_second": 3.6,
384
+ "step": 2500
385
  }
386
  ],
387
  "logging_steps": 100,
 
396
  "early_stopping_threshold": 0.0
397
  },
398
  "attributes": {
399
+ "early_stopping_patience_counter": 1
400
  }
401
  },
402
  "TrainerControl": {
 
410
  "attributes": {}
411
  }
412
  },
413
+ "total_flos": 9.07806769152e+16,
414
  "train_batch_size": 64,
415
  "trial_name": null,
416
  "trial_params": null