Hugging Face's logo

BayesTensor
/
modernbert_seeker1

Text Classification
Transformers
TensorBoard
Safetensors
modernbert
Generated from Trainer
Model card Files
xet
 Metrics Community
BayesTensor commited on
Commit
e106d4e
·
verified ·
1 Parent(s): 6d9e161

Training in progress, epoch 3, checkpoint

Browse files
Files changed (5) 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/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +21 -5
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48deb9d50108a5e0b39844e65a5b8a35900a15e538d0bca0246c92e20eb8f3b3
3
  size 598442860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b082d9f7f07aa3218c210cddb092957f01f3072c9ec6bf41b03953a6ec3da23d
3
  size 598442860
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56f44df2ce15e645a446644126bccd6f675b59d2bbbb924f8c3d372560683475
3
  size 1196973562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed1975b50a000839c6999b4cbd155ecd04a9bab206b47eb28bcff6fbf95376d
3
  size 1196973562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0583b378b8c26d5f7f023d50a449b521e770802231ce3bd6f38e066ed663c29
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17bc159752e862802fb5566308be6d1ff306dc0599471317a224de8cb8930a4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.2555762427123016,
3
- "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-92",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
- "global_step": 184,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -32,6 +32,22 @@
32
  "eval_samples_per_second": 12.658,
33
  "eval_steps_per_second": 3.164,
34
  "step": 184
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  }
36
  ],
37
  "logging_steps": 100,
@@ -51,7 +67,7 @@
51
  "attributes": {}
52
  }
53
  },
54
- "total_flos": 1263208741236000.0,
55
  "train_batch_size": 4,
56
  "trial_name": null,
57
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2623751468860165,
3
+ "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 276,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
32
  "eval_samples_per_second": 12.658,
33
  "eval_steps_per_second": 3.164,
34
  "step": 184
35
+ },
36
+ {
37
+ "epoch": 2.1739130434782608,
38
+ "grad_norm": 10.296772003173828,
39
+ "learning_rate": 1.739130434782609e-05,
40
+ "loss": 1.1447,
41
+ "step": 200
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_f1": 0.2623751468860165,
46
+ "eval_loss": 1.194385051727295,
47
+ "eval_runtime": 7.2397,
48
+ "eval_samples_per_second": 12.708,
49
+ "eval_steps_per_second": 3.177,
50
+ "step": 276
51
  }
52
  ],
53
  "logging_steps": 100,
 
67
  "attributes": {}
68
  }
69
  },
70
+ "total_flos": 1894813111854000.0,
71
  "train_batch_size": 4,
72
  "trial_name": null,
73
  "trial_params": null