Emil7018 commited on
Commit
5d7bad0
·
verified ·
1 Parent(s): 79de46a

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -342,6 +342,7 @@
342
  "num_hidden_layers": 22,
343
  "pad_token_id": 50283,
344
  "position_embedding_type": "absolute",
 
345
  "repad_logits_with_grad": false,
346
  "sep_token_id": 50282,
347
  "sparse_pred_ignore_index": -100,
 
342
  "num_hidden_layers": 22,
343
  "pad_token_id": 50283,
344
  "position_embedding_type": "absolute",
345
+ "problem_type": "single_label_classification",
346
  "repad_logits_with_grad": false,
347
  "sep_token_id": 50282,
348
  "sparse_pred_ignore_index": -100,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5450ac7ff38ceae0c7f8804bd02f21fac2062ca3449cd2ff0d44f4584af305f8
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5bce592f3c479083253508a74c9f5c2b63a4c297c31dfb0c1c8b284bc85f12
3
  size 598898116
run-0/checkpoint-318/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e4a628d1e7d92c82501a5df529dd449a7b7d91ec763139b62aa508c8b288977
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5bce592f3c479083253508a74c9f5c2b63a4c297c31dfb0c1c8b284bc85f12
3
  size 598898116
run-0/checkpoint-318/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6348082530784c50fa0170fdddb407b46c1fa9ffb6709e1bd91457a8bc208c8
3
  size 1197886411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231b4bbb1926a1cc766d9031ade587a41ad4204fd26a137b125c55927dc7a397
3
  size 1197886411
run-0/checkpoint-318/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccd3f3d16cf1fcf78a18f0599ff20141b09c41d51e63d99b15da0a95a3bc79f4
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8bef6dda512071503ea3bab68f0960919f4ba9156b465cc1853aaa448a81f7
3
  size 1383
run-0/checkpoint-318/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f5820fad84020b09d881b4b6d6ce78d3731e06e52d3401636c1604c2a2630f2
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633f7a108b7f060837a2327a4e3f8416e33eb696c13bf2067ef22cb46c181f2d
3
  size 1465
run-0/checkpoint-318/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "best_global_step": 318,
3
- "best_metric": 0.8897418223159607,
4
  "best_model_checkpoint": "ModernBERT-base-distilled/run-0/checkpoint-318",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
@@ -11,27 +11,26 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "grad_norm": 7.658935546875,
15
- "learning_rate": 1.5015723270440253e-05,
16
- "loss": 4.0156,
17
  "step": 318
18
  },
19
  {
20
  "epoch": 1.0,
21
- "eval_accuracy": 0.8916129032258064,
22
- "eval_f1": 0.8897418223159607,
23
- "eval_loss": 2.2384302616119385,
24
- "eval_model_preparation_time": 0.0029,
25
- "eval_runtime": 17.8082,
26
- "eval_samples_per_second": 174.077,
27
- "eval_steps_per_second": 3.65,
28
  "step": 318
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 1272,
33
  "num_input_tokens_seen": 0,
34
- "num_train_epochs": 4,
35
  "save_steps": 500,
36
  "stateful_callbacks": {
37
  "EarlyStoppingCallback": {
@@ -58,8 +57,8 @@
58
  "train_batch_size": 48,
59
  "trial_name": null,
60
  "trial_params": {
61
- "alpha": 0.0728812223134534,
62
- "num_train_epochs": 4,
63
- "temperature": 15
64
  }
65
  }
 
1
  {
2
  "best_global_step": 318,
3
+ "best_metric": 0.8782099185536261,
4
  "best_model_checkpoint": "ModernBERT-base-distilled/run-0/checkpoint-318",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "grad_norm": 6.882817268371582,
15
+ "learning_rate": 1.0031446540880504e-05,
16
+ "loss": 3.7921,
17
  "step": 318
18
  },
19
  {
20
  "epoch": 1.0,
21
+ "eval_accuracy": 0.8806451612903226,
22
+ "eval_f1": 0.8782099185536261,
23
+ "eval_loss": 2.21335768699646,
24
+ "eval_runtime": 19.6251,
25
+ "eval_samples_per_second": 157.961,
26
+ "eval_steps_per_second": 3.312,
 
27
  "step": 318
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 636,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "EarlyStoppingCallback": {
 
57
  "train_batch_size": 48,
58
  "trial_name": null,
59
  "trial_params": {
60
+ "alpha": 0.2238473023876273,
61
+ "num_train_epochs": 2,
62
+ "temperature": 16
63
  }
64
  }
run-0/checkpoint-318/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080327bf308da3daf1342344694cc74997103a3dbc9b586e2e8dc0503c895f98
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c288a49e5d462511afdcb18951b1fb2d83ef9f1ece8ef0108b7a3182e94fe32
3
  size 5905
runs/Oct11_19-55-54_cd07aeb3aeb4/events.out.tfevents.1760213284.cd07aeb3aeb4.2948.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4777732bea2f410d21c20b7cb96d7cbd49948466c7174dd29cf9efb39d8a769
3
+ size 13790
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7242c37c2cf94843077a4e237bc2ac18ed122b491c70c94c0147cf66212c758
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c288a49e5d462511afdcb18951b1fb2d83ef9f1ece8ef0108b7a3182e94fe32
3
  size 5905