Hugging Face's logo

Shaer-AI
/
ARBERT-base-submeter-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
NourFakih commited on
Commit
edd1774
·
verified ·
1 Parent(s): 59fc1b9

Training in progress, step 9000, checkpoint

Browse files
Files changed (6) 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/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +24 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a69da797b91f150e7fcd691c5ef84ea08d8bb1bb96b57b022954521a2834331
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d538c3e4fc4ffa061c770ad80f948b6fe52a3c1cfdceefa4d7d235b2b8bc1e8
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee61b09be180b57917ebcd2abdec50c65ee7386897f52f6099a8a201900363dd
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14d186391e1ccb0fc62f468e95c0ba250a4ec9c643090ffcd6cf7462f143a8a
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e14abb68a69b1d3b6d7aa43acf2e900d6d4bf6e4c47d7389f68b812c5983af2c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241c3f190553a159822c91da59a115205000a23b9d05c3e54cf35764fffba33c
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:793190053d1293f4ec72cd72bea61df6e622ffbc2a94ef18fbadb35cfca4423b
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e830af27401c6dbafa250f1dbae41b4878f5981f0bf0a06f9a0fd838e21b57
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad4ba90ddde1f3c2c621be4c01e0e4e2397fda9cf68c68a0fcd1aa269bd6e44
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 8500,
3
- "best_metric": 0.9651378378378378,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-8500",
5
- "epoch": 1.470120211017902,
6
  "eval_steps": 500,
7
- "global_step": 8500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -314,6 +314,24 @@
314
  "eval_steps_per_second": 3.455,
315
  "eval_weighted_f1": 0.9587555599089429,
316
  "step": 8500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  }
318
  ],
319
  "logging_steps": 500,
@@ -333,7 +351,7 @@
333
  "attributes": {}
334
  }
335
  },
336
- "total_flos": 3.5787302135712384e+16,
337
  "train_batch_size": 128,
338
  "trial_name": null,
339
  "trial_params": null
 
1
  {
2
+ "best_global_step": 9000,
3
+ "best_metric": 0.965654054054054,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-9000",
5
+ "epoch": 1.556602957709937,
6
  "eval_steps": 500,
7
+ "global_step": 9000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
314
  "eval_steps_per_second": 3.455,
315
  "eval_weighted_f1": 0.9587555599089429,
316
  "step": 8500
317
+ },
318
+ {
319
+ "epoch": 1.556602957709937,
320
+ "grad_norm": 3.425612211227417,
321
+ "learning_rate": 2.406030208693647e-05,
322
+ "loss": 0.118,
323
+ "step": 9000
324
+ },
325
+ {
326
+ "epoch": 1.556602957709937,
327
+ "eval_accuracy": 0.965654054054054,
328
+ "eval_loss": 0.1270706057548523,
329
+ "eval_macro_f1": 0.5691587584053437,
330
+ "eval_runtime": 419.0634,
331
+ "eval_samples_per_second": 882.921,
332
+ "eval_steps_per_second": 3.451,
333
+ "eval_weighted_f1": 0.9593746302255395,
334
+ "step": 9000
335
  }
336
  ],
337
  "logging_steps": 500,
 
351
  "attributes": {}
352
  }
353
  },
354
+ "total_flos": 3.789262525430438e+16,
355
  "train_batch_size": 128,
356
  "trial_name": null,
357
  "trial_params": null