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
7a79c4e
·
verified ·
1 Parent(s): a13601d

Training in progress, step 9500, 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 sha256:0d538c3e4fc4ffa061c770ad80f948b6fe52a3c1cfdceefa4d7d235b2b8bc1e8
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181b12e25a68f3ff531be3c38c08908d3de3767f51dd9b71ab7236af100114b0
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d14d186391e1ccb0fc62f468e95c0ba250a4ec9c643090ffcd6cf7462f143a8a
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6947cb57ef98d2f5a6f25e4c4436ab45e5fbfe8032684285d1d11079742712e1
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:241c3f190553a159822c91da59a115205000a23b9d05c3e54cf35764fffba33c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a83d1ca69590c446ff24d17236c152b37e20876b2e60a40575af0a565b5bbb
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c509bd3e5fac674b9ba176cbf7752fe31874a5d86b221fb4760c1dc243899a
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad4ba90ddde1f3c2c621be4c01e0e4e2397fda9cf68c68a0fcd1aa269bd6e44
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729dc858ba5180ba4b30a770b18a43487caa76db2369fd0722b26be3ba9a3c3e
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
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,
@@ -332,6 +332,24 @@
332
  "eval_steps_per_second": 3.451,
333
  "eval_weighted_f1": 0.9593746302255395,
334
  "step": 9000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
335
  }
336
  ],
337
  "logging_steps": 500,
@@ -351,7 +369,7 @@
351
  "attributes": {}
352
  }
353
  },
354
- "total_flos": 3.789262525430438e+16,
355
  "train_batch_size": 128,
356
  "trial_name": null,
357
  "trial_params": null
 
1
  {
2
+ "best_global_step": 9500,
3
+ "best_metric": 0.9661621621621621,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-9500",
5
+ "epoch": 1.6430857044019718,
6
  "eval_steps": 500,
7
+ "global_step": 9500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
332
  "eval_steps_per_second": 3.451,
333
  "eval_weighted_f1": 0.9593746302255395,
334
  "step": 9000
335
+ },
336
+ {
337
+ "epoch": 1.6430857044019718,
338
+ "grad_norm": 1.4031856060028076,
339
+ "learning_rate": 2.261904761904762e-05,
340
+ "loss": 0.1167,
341
+ "step": 9500
342
+ },
343
+ {
344
+ "epoch": 1.6430857044019718,
345
+ "eval_accuracy": 0.9661621621621621,
346
+ "eval_loss": 0.125877246260643,
347
+ "eval_macro_f1": 0.5795209016258601,
348
+ "eval_runtime": 418.9995,
349
+ "eval_samples_per_second": 883.056,
350
+ "eval_steps_per_second": 3.451,
351
+ "eval_weighted_f1": 0.9600300931445321,
352
+ "step": 9500
353
  }
354
  ],
355
  "logging_steps": 500,
 
369
  "attributes": {}
370
  }
371
  },
372
+ "total_flos": 3.999794837289638e+16,
373
  "train_batch_size": 128,
374
  "trial_name": null,
375
  "trial_params": null