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
220f773
·
verified ·
1 Parent(s): 8860a01

Training in progress, step 500

Browse files
Files changed (7) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-500/model.safetensors +1 -1
  3. run-1/checkpoint-500/optimizer.pt +1 -1
  4. run-1/checkpoint-500/scheduler.pt +1 -1
  5. run-1/checkpoint-500/trainer_state.json +10 -10
  6. run-1/checkpoint-500/training_args.bin +1 -1
  7. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c29e69efe43ed7629b2be39505fafa23e90dc9160e8986cbf2eb88575b94788
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9a360c7833fba30902201ea4b82e8e9547878c34661e78a8e0880108a807ef
3
  size 598898116
run-1/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a15199142fc8907f3308a7c8deb4db712235397cb74011491eae5a44db1efc1
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9a360c7833fba30902201ea4b82e8e9547878c34661e78a8e0880108a807ef
3
  size 598898116
run-1/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9c173ac3b6f5e8cc97f33103a3521318b502cb077c26445f9041061747f7a78
3
  size 1197886411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641f5af3f8a881b84c166ea8edd889c2750b1e99c4ba8edc176b064aecb83cbb
3
  size 1197886411
run-1/checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5aea2a4c12ecebbc4232d88b1bb48a10a0c81d431fc8be5878e5d1a32c56802
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a09f9c36dde0a0a453a032a4c54a8e4cc9521c107df7189c063a10d22468170
3
  size 1465
run-1/checkpoint-500/trainer_state.json CHANGED
@@ -11,8 +11,8 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.9106451612903226,
15
- "eval_loss": 1.2346638441085815,
16
  "eval_runtime": 17.8427,
17
  "eval_samples_per_second": 173.741,
18
  "eval_steps_per_second": 5.436,
@@ -20,16 +20,16 @@
20
  },
21
  {
22
  "epoch": 1.0482180293501049,
23
- "grad_norm": 5.996705532073975,
24
- "learning_rate": 1.4769392033542977e-05,
25
- "loss": 2.5873,
26
  "step": 500
27
  }
28
  ],
29
  "logging_steps": 500,
30
- "max_steps": 1908,
31
  "num_input_tokens_seen": 0,
32
- "num_train_epochs": 4,
33
  "save_steps": 500,
34
  "stateful_callbacks": {
35
  "TrainerControl": {
@@ -47,8 +47,8 @@
47
  "train_batch_size": 32,
48
  "trial_name": null,
49
  "trial_params": {
50
- "alpha": 0.7876581623719218,
51
- "num_train_epochs": 4,
52
- "temperature": 9.39699170345036
53
  }
54
  }
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.9058064516129032,
15
+ "eval_loss": 1.5853207111358643,
16
  "eval_runtime": 17.8427,
17
  "eval_samples_per_second": 173.741,
18
  "eval_steps_per_second": 5.436,
 
20
  },
21
  {
22
  "epoch": 1.0482180293501049,
23
+ "grad_norm": 33.00371551513672,
24
+ "learning_rate": 1.302585604472397e-05,
25
+ "loss": 7.739,
26
  "step": 500
27
  }
28
  ],
29
  "logging_steps": 500,
30
+ "max_steps": 1431,
31
  "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 3,
33
  "save_steps": 500,
34
  "stateful_callbacks": {
35
  "TrainerControl": {
 
47
  "train_batch_size": 32,
48
  "trial_name": null,
49
  "trial_params": {
50
+ "alpha": 0.7491575974351798,
51
+ "num_train_epochs": 3,
52
+ "temperature": 2.381189801203997
53
  }
54
  }
run-1/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d682f742ee6575a5764dafb19cc0b570af0f61c3d9c96e2a5d8800d13aaab38c
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c5aa2e0f6144ff85d55658e39492889cffe974c1ae7f2b9e963705c16ca39d
3
  size 5905
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20b487dd7dd7a79406e30f85b1328021e4bfb070d1b507d4249e6c45909667ea
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c5aa2e0f6144ff85d55658e39492889cffe974c1ae7f2b9e963705c16ca39d
3
  size 5905