PedramR commited on
Commit
3b89dd7
·
verified ·
1 Parent(s): 84b1f3a

checkpoint-500

Browse files
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/README.md RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/adapter_config.json RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0b4874e89ba75d6912a8f7f2295be6307558035e1c645c9df81d4f42e7fc809
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f8cd14d56127cd14ffe3a31a56ff771a15aa10a99691e88677639be86db186
3
  size 134604152
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96b4e5feabc95e8a06c9990e1004823fe389165538b3e304064dc0e5b25900f
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0598c14a2cf67766087a8cdc6b285deb943d6fc08547b6561876c71319b737c2
3
  size 269426431
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76ca0771d2e50a5d04752d8b82b395a7f9c9ff695044c93ad7564020555b473d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25162bf35bb78f04cc118f6047232b828f792f880f1e976d3ddab5769b27012
3
  size 14645
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1309cb62bc7fa24449a1db30ffbd24ad1d334589a19b696b8ac211034f849e64
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6528b45050b441437de60ddf69164d8d25345267d73bd19af61eebdf168903eb
3
  size 1465
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/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": 1.552677029360967,
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,
@@ -395,6 +395,49 @@
395
  "eval_samples_per_second": 118.068,
396
  "eval_steps_per_second": 15.202,
397
  "step": 450
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
398
  }
399
  ],
400
  "logging_steps": 10,
@@ -414,7 +457,7 @@
414
  "attributes": {}
415
  }
416
  },
417
- "total_flos": 1.42035413146368e+16,
418
  "train_batch_size": 8,
419
  "trial_name": null,
420
  "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": 1.7253886010362693,
6
  "eval_steps": 50,
7
+ "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
395
  "eval_samples_per_second": 118.068,
396
  "eval_steps_per_second": 15.202,
397
  "step": 450
398
+ },
399
+ {
400
+ "epoch": 1.5872193436960278,
401
+ "grad_norm": 0.675014317035675,
402
+ "learning_rate": 2.1960072595281308e-05,
403
+ "loss": 0.12466132640838623,
404
+ "step": 460
405
+ },
406
+ {
407
+ "epoch": 1.621761658031088,
408
+ "grad_norm": 3.469187021255493,
409
+ "learning_rate": 2.014519056261343e-05,
410
+ "loss": 0.09179966449737549,
411
+ "step": 470
412
+ },
413
+ {
414
+ "epoch": 1.6563039723661486,
415
+ "grad_norm": 1.1941732168197632,
416
+ "learning_rate": 1.8330308529945555e-05,
417
+ "loss": 0.09128846526145935,
418
+ "step": 480
419
+ },
420
+ {
421
+ "epoch": 1.690846286701209,
422
+ "grad_norm": 1.672904133796692,
423
+ "learning_rate": 1.6515426497277677e-05,
424
+ "loss": 0.08639370203018189,
425
+ "step": 490
426
+ },
427
+ {
428
+ "epoch": 1.7253886010362693,
429
+ "grad_norm": 5.294003486633301,
430
+ "learning_rate": 1.47005444646098e-05,
431
+ "loss": 0.1066015362739563,
432
+ "step": 500
433
+ },
434
+ {
435
+ "epoch": 1.7253886010362693,
436
+ "eval_loss": 0.22476431727409363,
437
+ "eval_runtime": 1.9727,
438
+ "eval_samples_per_second": 118.11,
439
+ "eval_steps_per_second": 15.207,
440
+ "step": 500
441
  }
442
  ],
443
  "logging_steps": 10,
 
457
  "attributes": {}
458
  }
459
  },
460
+ "total_flos": 1.5781547495067648e+16,
461
  "train_batch_size": 8,
462
  "trial_name": null,
463
  "trial_params": null
verifier-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/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 sha256:01f52ad67bd718903577783f8a3ad5fc8f73a1a8c6e7d9804be15e4db2feed11
3
- size 17309
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb6ca5a72a919aacf7eee50a30774cac636175da4ffb78278405f902b81bbfb
3
+ size 18635