Hugging Face's logo

Mathildeholst
/
classifier-clinc-MBbase-distilled

Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
Mathildeholst commited on
Commit
f06d610
·
verified ·
1 Parent(s): 8b39342

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-500/model.safetensors +1 -1
  3. run-0/checkpoint-500/optimizer.pt +1 -1
  4. run-0/checkpoint-500/trainer_state.json +10 -10
  5. run-0/checkpoint-500/training_args.bin +1 -1
  6. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8193fee56dc53365e927c2d9fd3ea0bc4cc3a1e83f2ea8b008b1691e9f019cba
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2bf4b1ee900ba2c7a93b0d3003dbb5b2f1930cd1a1d5dc722a1c2fff3dcc3e
3
  size 598898116
run-0/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:594dc3eb7e83101e00195da0be1273b89a2f388b3c459b62ade9d582ca3b8e4c
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2bf4b1ee900ba2c7a93b0d3003dbb5b2f1930cd1a1d5dc722a1c2fff3dcc3e
3
  size 598898116
run-0/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3317e0c4cd32d09e86909f9212906def4b138e102b142295f928db51c498d8b5
3
  size 1197886411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b918121e298b277b5ae748988c44f9bd52ed6641c68b8cdc2218335e74884a9c
3
  size 1197886411
run-0/checkpoint-500/trainer_state.json CHANGED
@@ -11,18 +11,18 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.8970967741935484,
15
- "eval_loss": 2.0391886234283447,
16
- "eval_runtime": 17.7829,
17
- "eval_samples_per_second": 174.325,
18
- "eval_steps_per_second": 5.455,
19
  "step": 477
20
  },
21
  {
22
  "epoch": 1.0482180293501049,
23
- "grad_norm": 21.700918197631836,
24
  "learning_rate": 1.302585604472397e-05,
25
- "loss": 8.2637,
26
  "step": 500
27
  }
28
  ],
@@ -43,12 +43,12 @@
43
  "attributes": {}
44
  }
45
  },
46
- "total_flos": 224151802852992.0,
47
  "train_batch_size": 32,
48
  "trial_name": null,
49
  "trial_params": {
50
- "alpha": 0.04124860013748177,
51
  "num_train_epochs": 3,
52
- "temperature": 2.878079794128767
53
  }
54
  }
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.8764516129032258,
15
+ "eval_loss": 2.150498628616333,
16
+ "eval_runtime": 17.8438,
17
+ "eval_samples_per_second": 173.73,
18
+ "eval_steps_per_second": 5.436,
19
  "step": 477
20
  },
21
  {
22
  "epoch": 1.0482180293501049,
23
+ "grad_norm": 27.51361083984375,
24
  "learning_rate": 1.302585604472397e-05,
25
+ "loss": 5.9093,
26
  "step": 500
27
  }
28
  ],
 
43
  "attributes": {}
44
  }
45
  },
46
+ "total_flos": 407413063774080.0,
47
  "train_batch_size": 32,
48
  "trial_name": null,
49
  "trial_params": {
50
+ "alpha": 0.8979553244778209,
51
  "num_train_epochs": 3,
52
+ "temperature": 4.375187631815162
53
  }
54
  }
run-0/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6300c874dd8d560d51ee9bf55d460b2a5df3fbfe9fa1e724e25742d02b9d2b07
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b487dd7dd7a79406e30f85b1328021e4bfb070d1b507d4249e6c45909667ea
3
  size 5905
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e06f1bb4bc4cbbd72bb74742f00db632f86b3856c71e606f51ec5790460bfd7
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b487dd7dd7a79406e30f85b1328021e4bfb070d1b507d4249e6c45909667ea
3
  size 5905