Emil7018 commited on
Commit
a4c60ba
·
verified ·
1 Parent(s): dc11d1d

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbe5fc7ba60f16342a2cea677db69c8ae5f868fc72eeac6a4b913d0533dcab28
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05da4069fc52d58f023e29df4dcdd61eef9ec8db8396ec64e56917963bbb9d9
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:cc5bce592f3c479083253508a74c9f5c2b63a4c297c31dfb0c1c8b284bc85f12
3
  size 598898116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05da4069fc52d58f023e29df4dcdd61eef9ec8db8396ec64e56917963bbb9d9
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 sha256:231b4bbb1926a1cc766d9031ade587a41ad4204fd26a137b125c55927dc7a397
3
  size 1197886411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3017f0f9e1765dc23bae8577f1efa55de32e56690c998f0edf1e472bc741c30
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 sha256:0e8bef6dda512071503ea3bab68f0960919f4ba9156b465cc1853aaa448a81f7
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e642f50b65cad64c4e76d928defe85e28a1873bd062929b57f3779c4adc0d3
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 sha256:633f7a108b7f060837a2327a4e3f8416e33eb696c13bf2067ef22cb46c181f2d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5820fad84020b09d881b4b6d6ce78d3731e06e52d3401636c1604c2a2630f2
3
  size 1465
run-0/checkpoint-318/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "best_global_step": 318,
3
- "best_metric": 0.8782099185536261,
4
  "best_model_checkpoint": "ModernBERT-base-distilled/run-0/checkpoint-318",
5
  "epoch": 1.0,
6
  "eval_steps": 500,
@@ -11,26 +11,26 @@
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": {
@@ -53,12 +53,12 @@
53
  "attributes": {}
54
  }
55
  },
56
- "total_flos": 225704119111812.0,
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
  }
 
1
  {
2
  "best_global_step": 318,
3
+ "best_metric": 0.9051373620810793,
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": 7.095359802246094,
15
+ "learning_rate": 1.5015723270440253e-05,
16
+ "loss": 4.2443,
17
  "step": 318
18
  },
19
  {
20
  "epoch": 1.0,
21
+ "eval_accuracy": 0.9070967741935484,
22
+ "eval_f1": 0.9051373620810793,
23
+ "eval_loss": 2.06101655960083,
24
+ "eval_runtime": 16.6455,
25
+ "eval_samples_per_second": 186.236,
26
+ "eval_steps_per_second": 3.905,
27
  "step": 318
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 1272,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
  "save_steps": 500,
35
  "stateful_callbacks": {
36
  "EarlyStoppingCallback": {
 
53
  "attributes": {}
54
  }
55
  },
56
+ "total_flos": 331330912647588.0,
57
  "train_batch_size": 48,
58
  "trial_name": null,
59
  "trial_params": {
60
+ "alpha": 0.362336107066899,
61
+ "num_train_epochs": 4,
62
+ "temperature": 10
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 sha256:9c288a49e5d462511afdcb18951b1fb2d83ef9f1ece8ef0108b7a3182e94fe32
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57990bfcffc7508b1aa41cf9c14f9a33fd6a76ae0e5b564184c21c4e65e1398
3
  size 5905
runs/Oct11_19-55-54_cd07aeb3aeb4/events.out.tfevents.1760213687.cd07aeb3aeb4.2948.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2972b1965f5ee7fd2e6c57ed4c4222c2cce42193ee44ad4ce3f8ca3f6f472d70
3
- size 13790
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8347db70977538ed9d9e433e8a4c4278244d3788ddfb49687a6c6c6eb814aae
3
+ size 27492
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4d1f48d83021324c19290eb8526bd37db5d8c6569e5318a75916976ce927e32
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57990bfcffc7508b1aa41cf9c14f9a33fd6a76ae0e5b564184c21c4e65e1398
3
  size 5905