PedramR commited on
Commit
84b1f3a
·
verified ·
1 Parent(s): 2f1304c

checkpoint-450

Browse files
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/README.md RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/adapter_config.json RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11f04c39b579af25ad256ad7c0435a6d51b8422664b84ae8b72e4fda65e2fefc
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b4874e89ba75d6912a8f7f2295be6307558035e1c645c9df81d4f42e7fc809
3
  size 134604152
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae94ad9ac4b91930d05f04d51bccab882a93329491f662833939b507ae3f693
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96b4e5feabc95e8a06c9990e1004823fe389165538b3e304064dc0e5b25900f
3
  size 269426431
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eada336f8e89af6a4e25204f55425e49c19523fc2ef2b49ac766eda5ff0fa42
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ca0771d2e50a5d04752d8b82b395a7f9c9ff695044c93ad7564020555b473d
3
  size 14645
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7c61abf061b77f13b4c846b80db0dac107682e7cce8934bd380f6ec85db1c14
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1309cb62bc7fa24449a1db30ffbd24ad1d334589a19b696b8ac211034f849e64
3
  size 1465
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/trainer_state.json RENAMED
@@ -2,9 +2,9 @@
2
  "best_global_step": 250,
3
  "best_metric": 0.18705631792545319,
4
  "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-250",
5
- "epoch": 1.3799654576856648,
6
  "eval_steps": 50,
7
- "global_step": 400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -352,6 +352,49 @@
352
  "eval_samples_per_second": 117.879,
353
  "eval_steps_per_second": 15.178,
354
  "step": 400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
355
  }
356
  ],
357
  "logging_steps": 10,
@@ -371,7 +414,7 @@
371
  "attributes": {}
372
  }
373
  },
374
- "total_flos": 1.262702082496512e+16,
375
  "train_batch_size": 8,
376
  "trial_name": null,
377
  "trial_params": null
 
2
  "best_global_step": 250,
3
  "best_metric": 0.18705631792545319,
4
  "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-250",
5
+ "epoch": 1.552677029360967,
6
  "eval_steps": 50,
7
+ "global_step": 450,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
352
  "eval_samples_per_second": 117.879,
353
  "eval_steps_per_second": 15.178,
354
  "step": 400
355
+ },
356
+ {
357
+ "epoch": 1.4145077720207253,
358
+ "grad_norm": 2.78829288482666,
359
+ "learning_rate": 3.103448275862069e-05,
360
+ "loss": 0.07065250873565673,
361
+ "step": 410
362
+ },
363
+ {
364
+ "epoch": 1.4490500863557858,
365
+ "grad_norm": 1.3722212314605713,
366
+ "learning_rate": 2.9219600725952817e-05,
367
+ "loss": 0.0911053717136383,
368
+ "step": 420
369
+ },
370
+ {
371
+ "epoch": 1.4835924006908463,
372
+ "grad_norm": 1.1897987127304077,
373
+ "learning_rate": 2.7404718693284935e-05,
374
+ "loss": 0.06910803318023681,
375
+ "step": 430
376
+ },
377
+ {
378
+ "epoch": 1.5181347150259068,
379
+ "grad_norm": 1.521686315536499,
380
+ "learning_rate": 2.558983666061706e-05,
381
+ "loss": 0.08308793306350708,
382
+ "step": 440
383
+ },
384
+ {
385
+ "epoch": 1.552677029360967,
386
+ "grad_norm": 4.284547328948975,
387
+ "learning_rate": 2.3774954627949183e-05,
388
+ "loss": 0.12582927942276,
389
+ "step": 450
390
+ },
391
+ {
392
+ "epoch": 1.552677029360967,
393
+ "eval_loss": 0.22368137538433075,
394
+ "eval_runtime": 1.9734,
395
+ "eval_samples_per_second": 118.068,
396
+ "eval_steps_per_second": 15.202,
397
+ "step": 450
398
  }
399
  ],
400
  "logging_steps": 10,
 
414
  "attributes": {}
415
  }
416
  },
417
+ "total_flos": 1.42035413146368e+16,
418
  "train_batch_size": 8,
419
  "trial_name": null,
420
  "trial_params": null
verifier-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/training_args.bin RENAMED
File without changes
verifier-qwen3.5-2b/tb/events.out.tfevents.1790667609.02b48645612f.2184.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76e3b2ec3e6b7ce5dbd93692cd459374ead97fea24aecf6239cae5a9ad0f254b
3
- size 15983
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f52ad67bd718903577783f8a3ad5fc8f73a1a8c6e7d9804be15e4db2feed11
3
+ size 17309