Hugging Face's logo

PedramR
/
ASR_Post-processing

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
PedramR commited on
Commit
1da965f
·
verified ·
1 Parent(s): 86a8689

checkpoint-350

Browse files
Files changed (9) hide show
  1. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/README.md +0 -0
  2. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/adapter_config.json +0 -0
  3. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/adapter_model.safetensors +1 -1
  4. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/optimizer.pt +1 -1
  5. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/rng_state.pth +1 -1
  6. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/scheduler.pt +1 -1
  7. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/trainer_state.json +46 -3
  8. verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/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-300 → checkpoint-350}/README.md RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/adapter_config.json RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4fa7ae17b2f05b7af9e449e561e0197025f5b067ee186b263e59370fac50df3
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddac6deecf7e73629cb935c257095e1019153b63410a2455e741032aa917cd2d
3
  size 134604152
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1b375d1d90416d333adb8eae939dd2a9b0bd62ec4f08f987f35a3f67f8abeb9
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5057d1f547730b07e1b381250e6e2e54294839950de3e60b3c56540b8fbaec
3
  size 269426431
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45acf99c56b55aba32fc5d6dd3792f86d57ad4b9d765e544f39d9a717f32c9c3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ef091d8dd69e078b8a5bd5316b99d0d10dcd4b36b290fc3dfe49b5b23f5c6d0
3
  size 14645
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a77c0652392301021f9fa41b6c909f0f649f2c1dc97aa0e1404793fdc2d3e77e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:982cbfe2a8f579cec75c48d5bf634e310dc96d796937d2153598572ead96f6ad
3
  size 1465
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/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": 1.0345423143350605,
6
  "eval_steps": 50,
7
- "global_step": 300,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -266,6 +266,49 @@
266
  "eval_samples_per_second": 118.017,
267
  "eval_steps_per_second": 15.195,
268
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
269
  }
270
  ],
271
  "logging_steps": 10,
@@ -285,7 +328,7 @@
285
  "attributes": {}
286
  }
287
  },
288
- "total_flos": 9473439594436608.0,
289
  "train_batch_size": 8,
290
  "trial_name": null,
291
  "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": 1.2072538860103628,
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,
 
266
  "eval_samples_per_second": 118.017,
267
  "eval_steps_per_second": 15.195,
268
  "step": 300
269
+ },
270
+ {
271
+ "epoch": 1.069084628670121,
272
+ "grad_norm": 2.7725467681884766,
273
+ "learning_rate": 4.918330308529946e-05,
274
+ "loss": 0.08072454929351806,
275
+ "step": 310
276
+ },
277
+ {
278
+ "epoch": 1.1036269430051813,
279
+ "grad_norm": 1.7649929523468018,
280
+ "learning_rate": 4.736842105263158e-05,
281
+ "loss": 0.160854709148407,
282
+ "step": 320
283
+ },
284
+ {
285
+ "epoch": 1.1381692573402418,
286
+ "grad_norm": 1.2601549625396729,
287
+ "learning_rate": 4.55535390199637e-05,
288
+ "loss": 0.053943085670471194,
289
+ "step": 330
290
+ },
291
+ {
292
+ "epoch": 1.1727115716753023,
293
+ "grad_norm": 2.121206283569336,
294
+ "learning_rate": 4.373865698729583e-05,
295
+ "loss": 0.12994797229766847,
296
+ "step": 340
297
+ },
298
+ {
299
+ "epoch": 1.2072538860103628,
300
+ "grad_norm": 0.8693338632583618,
301
+ "learning_rate": 4.192377495462795e-05,
302
+ "loss": 0.1275896906852722,
303
+ "step": 350
304
+ },
305
+ {
306
+ "epoch": 1.2072538860103628,
307
+ "eval_loss": 0.18902312219142914,
308
+ "eval_runtime": 1.9734,
309
+ "eval_samples_per_second": 118.072,
310
+ "eval_steps_per_second": 15.202,
311
+ "step": 350
312
  }
313
  ],
314
  "logging_steps": 10,
 
328
  "attributes": {}
329
  }
330
  },
331
+ "total_flos": 1.1050567866691584e+16,
332
  "train_batch_size": 8,
333
  "trial_name": null,
334
  "trial_params": null
verifier-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/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 sha256:81842c697a26ec113f61b611cf6af004701819dba73d9b4691dd418f04619931
3
- size 13331
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130345b575faa4c681fccee0afc03bf0d7384bbde6cd4f366a1874fe4eedf191
3
+ size 14657