Hugging Face's logo

PedramR
/
ASR_Post-processing

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
PedramR commited on
Commit
2f1304c
·
verified ·
1 Parent(s): 1da965f

checkpoint-400

Browse files
Files changed (9) hide show
  1. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/README.md +0 -0
  2. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/adapter_config.json +0 -0
  3. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/adapter_model.safetensors +1 -1
  4. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/optimizer.pt +1 -1
  5. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/rng_state.pth +1 -1
  6. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/scheduler.pt +1 -1
  7. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/trainer_state.json +46 -3
  8. verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/training_args.bin +0 -0
  9. verifier-qwen3.5-2b/tb/events.out.tfevents.1790667609.02b48645612f.2184.0 +2 -2
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/README.md RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/adapter_config.json RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddac6deecf7e73629cb935c257095e1019153b63410a2455e741032aa917cd2d
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f04c39b579af25ad256ad7c0435a6d51b8422664b84ae8b72e4fda65e2fefc
3
  size 134604152
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e5057d1f547730b07e1b381250e6e2e54294839950de3e60b3c56540b8fbaec
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae94ad9ac4b91930d05f04d51bccab882a93329491f662833939b507ae3f693
3
  size 269426431
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ef091d8dd69e078b8a5bd5316b99d0d10dcd4b36b290fc3dfe49b5b23f5c6d0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eada336f8e89af6a4e25204f55425e49c19523fc2ef2b49ac766eda5ff0fa42
3
  size 14645
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:982cbfe2a8f579cec75c48d5bf634e310dc96d796937d2153598572ead96f6ad
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c61abf061b77f13b4c846b80db0dac107682e7cce8934bd380f6ec85db1c14
3
  size 1465
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/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": 1.2072538860103628,
6
  "eval_steps": 50,
7
- "global_step": 350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -309,6 +309,49 @@
309
  "eval_samples_per_second": 118.072,
310
  "eval_steps_per_second": 15.202,
311
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  }
313
  ],
314
  "logging_steps": 10,
@@ -328,7 +371,7 @@
328
  "attributes": {}
329
  }
330
  },
331
- "total_flos": 1.1050567866691584e+16,
332
  "train_batch_size": 8,
333
  "trial_name": null,
334
  "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": 1.3799654576856648,
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,
 
309
  "eval_samples_per_second": 118.072,
310
  "eval_steps_per_second": 15.202,
311
  "step": 350
312
+ },
313
+ {
314
+ "epoch": 1.2417962003454233,
315
+ "grad_norm": 0.798375129699707,
316
+ "learning_rate": 4.0108892921960075e-05,
317
+ "loss": 0.09207801818847657,
318
+ "step": 360
319
+ },
320
+ {
321
+ "epoch": 1.2763385146804835,
322
+ "grad_norm": 3.2508676052093506,
323
+ "learning_rate": 3.82940108892922e-05,
324
+ "loss": 0.09812392592430115,
325
+ "step": 370
326
+ },
327
+ {
328
+ "epoch": 1.310880829015544,
329
+ "grad_norm": 0.6655265688896179,
330
+ "learning_rate": 3.6479128856624326e-05,
331
+ "loss": 0.06765094995498658,
332
+ "step": 380
333
+ },
334
+ {
335
+ "epoch": 1.3454231433506045,
336
+ "grad_norm": 2.4199888706207275,
337
+ "learning_rate": 3.466424682395644e-05,
338
+ "loss": 0.07691715359687805,
339
+ "step": 390
340
+ },
341
+ {
342
+ "epoch": 1.3799654576856648,
343
+ "grad_norm": 4.429002285003662,
344
+ "learning_rate": 3.284936479128857e-05,
345
+ "loss": 0.09179953932762146,
346
+ "step": 400
347
+ },
348
+ {
349
+ "epoch": 1.3799654576856648,
350
+ "eval_loss": 0.24322113394737244,
351
+ "eval_runtime": 1.9766,
352
+ "eval_samples_per_second": 117.879,
353
+ "eval_steps_per_second": 15.178,
354
+ "step": 400
355
  }
356
  ],
357
  "logging_steps": 10,
 
371
  "attributes": {}
372
  }
373
  },
374
+ "total_flos": 1.262702082496512e+16,
375
  "train_batch_size": 8,
376
  "trial_name": null,
377
  "trial_params": null
verifier-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/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 sha256:130345b575faa4c681fccee0afc03bf0d7384bbde6cd4f366a1874fe4eedf191
3
- size 14657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e3b2ec3e6b7ce5dbd93692cd459374ead97fea24aecf6239cae5a9ad0f254b
3
+ size 15983