Hugging Face's logo

redis
/
langcache-embed-v3

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
biencoder
text-classification
sentence-pair-classification
semantic-similarity
semantic-search
retrieval
reranking
Generated from Trainer
dataset_size:1451941
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
radoslavralev commited on
Commit
e1e7f17
·
verified ·
1 Parent(s): 3024844

Add new SentenceTransformer model

Browse files
Files changed (2) hide show
  1. README.md +368 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -87,28 +87,28 @@ model-index:
87
  type: test
88
  metrics:
89
  - type: cosine_accuracy
90
- value: 0.7036165169861821
91
  name: Cosine Accuracy
92
  - type: cosine_accuracy_threshold
93
- value: 0.8524742126464844
94
  name: Cosine Accuracy Threshold
95
  - type: cosine_f1
96
- value: 0.7123780174627633
97
  name: Cosine F1
98
  - type: cosine_f1_threshold
99
- value: 0.8120777606964111
100
  name: Cosine F1 Threshold
101
  - type: cosine_precision
102
- value: 0.5992426552810817
103
  name: Cosine Precision
104
  - type: cosine_recall
105
- value: 0.8781750465549348
106
  name: Cosine Recall
107
  - type: cosine_ap
108
- value: 0.6475972261979004
109
  name: Cosine Ap
110
  - type: cosine_mcc
111
- value: 0.44221965028695587
112
  name: Cosine Mcc
113
  ---
114
 
@@ -173,9 +173,9 @@ print(embeddings.shape)
173
  # Get the similarity scores for the embeddings
174
  similarities = model.similarity(embeddings, embeddings)
175
  print(similarities)
176
- # tensor([[0.9922, 0.9922, 0.5352],
177
- # [0.9922, 0.9961, 0.5391],
178
- # [0.5352, 0.5391, 1.0000]], dtype=torch.bfloat16)
179
  ```
180
 
181
  <!--
@@ -213,14 +213,14 @@ You can finetune this model on your own dataset.
213
 
214
  | Metric | Value |
215
  |:--------------------------|:-----------|
216
- | cosine_accuracy | 0.7036 |
217
- | cosine_accuracy_threshold | 0.8525 |
218
- | cosine_f1 | 0.7124 |
219
- | cosine_f1_threshold | 0.8121 |
220
- | cosine_precision | 0.5992 |
221
- | cosine_recall | 0.8782 |
222
- | **cosine_ap** | **0.6476** |
223
- | cosine_mcc | 0.4422 |
224
 
225
  <!--
226
  ## Bias, Risks and Limitations
@@ -290,11 +290,357 @@ You can finetune this model on your own dataset.
290
  }
291
  ```
292
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
293
  ### Training Logs
294
- | Epoch | Step | test_cosine_ap |
295
- |:-----:|:----:|:--------------:|
296
- | -1 | -1 | 0.6476 |
297
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
 
299
  ### Framework Versions
300
  - Python: 3.12.3
 
87
  type: test
88
  metrics:
89
  - type: cosine_accuracy
90
+ value: 0.7276245142774221
91
  name: Cosine Accuracy
92
  - type: cosine_accuracy_threshold
93
+ value: 0.8017503619194031
94
  name: Cosine Accuracy Threshold
95
  - type: cosine_f1
96
+ value: 0.723032161181329
97
  name: Cosine F1
98
  - type: cosine_f1_threshold
99
+ value: 0.7345461845397949
100
  name: Cosine F1 Threshold
101
  - type: cosine_precision
102
+ value: 0.6233076217703221
103
  name: Cosine Precision
104
  - type: cosine_recall
105
+ value: 0.8607448789571694
106
  name: Cosine Recall
107
  - type: cosine_ap
108
+ value: 0.7251364855292874
109
  name: Cosine Ap
110
  - type: cosine_mcc
111
+ value: 0.4684913821533736
112
  name: Cosine Mcc
113
  ---
114
 
 
173
  # Get the similarity scores for the embeddings
174
  similarities = model.similarity(embeddings, embeddings)
175
  print(similarities)
176
+ # tensor([[0.9961, 0.9961, 0.1250],
177
+ # [0.9961, 0.9961, 0.1162],
178
+ # [0.1250, 0.1162, 1.0078]], dtype=torch.bfloat16)
179
  ```
180
 
181
  <!--
 
213
 
214
  | Metric | Value |
215
  |:--------------------------|:-----------|
216
+ | cosine_accuracy | 0.7276 |
217
+ | cosine_accuracy_threshold | 0.8018 |
218
+ | cosine_f1 | 0.723 |
219
+ | cosine_f1_threshold | 0.7345 |
220
+ | cosine_precision | 0.6233 |
221
+ | cosine_recall | 0.8607 |
222
+ | **cosine_ap** | **0.7251** |
223
+ | cosine_mcc | 0.4685 |
224
 
225
  <!--
226
  ## Bias, Risks and Limitations
 
290
  }
291
  ```
292
 
293
+ ### Training Hyperparameters
294
+ #### Non-Default Hyperparameters
295
+
296
+ - `eval_strategy`: steps
297
+ - `per_device_train_batch_size`: 100
298
+ - `per_device_eval_batch_size`: 100
299
+ - `learning_rate`: 0.0001
300
+ - `adam_beta2`: 0.98
301
+ - `adam_epsilon`: 1e-06
302
+ - `max_steps`: 200000
303
+ - `warmup_steps`: 1000
304
+ - `load_best_model_at_end`: True
305
+ - `optim`: adamw_torch
306
+ - `ddp_find_unused_parameters`: False
307
+ - `push_to_hub`: True
308
+ - `hub_model_id`: redis/langcache-embed-v3
309
+ - `batch_sampler`: no_duplicates
310
+
311
+ #### All Hyperparameters
312
+ <details><summary>Click to expand</summary>
313
+
314
+ - `overwrite_output_dir`: False
315
+ - `do_predict`: False
316
+ - `eval_strategy`: steps
317
+ - `prediction_loss_only`: True
318
+ - `per_device_train_batch_size`: 100
319
+ - `per_device_eval_batch_size`: 100
320
+ - `per_gpu_train_batch_size`: None
321
+ - `per_gpu_eval_batch_size`: None
322
+ - `gradient_accumulation_steps`: 1
323
+ - `eval_accumulation_steps`: None
324
+ - `torch_empty_cache_steps`: None
325
+ - `learning_rate`: 0.0001
326
+ - `weight_decay`: 0.0
327
+ - `adam_beta1`: 0.9
328
+ - `adam_beta2`: 0.98
329
+ - `adam_epsilon`: 1e-06
330
+ - `max_grad_norm`: 1.0
331
+ - `num_train_epochs`: 3.0
332
+ - `max_steps`: 200000
333
+ - `lr_scheduler_type`: linear
334
+ - `lr_scheduler_kwargs`: {}
335
+ - `warmup_ratio`: 0.0
336
+ - `warmup_steps`: 1000
337
+ - `log_level`: passive
338
+ - `log_level_replica`: warning
339
+ - `log_on_each_node`: True
340
+ - `logging_nan_inf_filter`: True
341
+ - `save_safetensors`: True
342
+ - `save_on_each_node`: False
343
+ - `save_only_model`: False
344
+ - `restore_callback_states_from_checkpoint`: False
345
+ - `no_cuda`: False
346
+ - `use_cpu`: False
347
+ - `use_mps_device`: False
348
+ - `seed`: 42
349
+ - `data_seed`: None
350
+ - `jit_mode_eval`: False
351
+ - `use_ipex`: False
352
+ - `bf16`: False
353
+ - `fp16`: False
354
+ - `fp16_opt_level`: O1
355
+ - `half_precision_backend`: auto
356
+ - `bf16_full_eval`: False
357
+ - `fp16_full_eval`: False
358
+ - `tf32`: None
359
+ - `local_rank`: 0
360
+ - `ddp_backend`: None
361
+ - `tpu_num_cores`: None
362
+ - `tpu_metrics_debug`: False
363
+ - `debug`: []
364
+ - `dataloader_drop_last`: False
365
+ - `dataloader_num_workers`: 0
366
+ - `dataloader_prefetch_factor`: None
367
+ - `past_index`: -1
368
+ - `disable_tqdm`: False
369
+ - `remove_unused_columns`: True
370
+ - `label_names`: None
371
+ - `load_best_model_at_end`: True
372
+ - `ignore_data_skip`: False
373
+ - `fsdp`: []
374
+ - `fsdp_min_num_params`: 0
375
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
376
+ - `fsdp_transformer_layer_cls_to_wrap`: None
377
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
378
+ - `parallelism_config`: None
379
+ - `deepspeed`: None
380
+ - `label_smoothing_factor`: 0.0
381
+ - `optim`: adamw_torch
382
+ - `optim_args`: None
383
+ - `adafactor`: False
384
+ - `group_by_length`: False
385
+ - `length_column_name`: length
386
+ - `ddp_find_unused_parameters`: False
387
+ - `ddp_bucket_cap_mb`: None
388
+ - `ddp_broadcast_buffers`: False
389
+ - `dataloader_pin_memory`: True
390
+ - `dataloader_persistent_workers`: False
391
+ - `skip_memory_metrics`: True
392
+ - `use_legacy_prediction_loop`: False
393
+ - `push_to_hub`: True
394
+ - `resume_from_checkpoint`: None
395
+ - `hub_model_id`: redis/langcache-embed-v3
396
+ - `hub_strategy`: every_save
397
+ - `hub_private_repo`: None
398
+ - `hub_always_push`: False
399
+ - `hub_revision`: None
400
+ - `gradient_checkpointing`: False
401
+ - `gradient_checkpointing_kwargs`: None
402
+ - `include_inputs_for_metrics`: False
403
+ - `include_for_metrics`: []
404
+ - `eval_do_concat_batches`: True
405
+ - `fp16_backend`: auto
406
+ - `push_to_hub_model_id`: None
407
+ - `push_to_hub_organization`: None
408
+ - `mp_parameters`:
409
+ - `auto_find_batch_size`: False
410
+ - `full_determinism`: False
411
+ - `torchdynamo`: None
412
+ - `ray_scope`: last
413
+ - `ddp_timeout`: 1800
414
+ - `torch_compile`: False
415
+ - `torch_compile_backend`: None
416
+ - `torch_compile_mode`: None
417
+ - `include_tokens_per_second`: False
418
+ - `include_num_input_tokens_seen`: False
419
+ - `neftune_noise_alpha`: None
420
+ - `optim_target_modules`: None
421
+ - `batch_eval_metrics`: False
422
+ - `eval_on_start`: False
423
+ - `use_liger_kernel`: False
424
+ - `liger_kernel_config`: None
425
+ - `eval_use_gather_object`: False
426
+ - `average_tokens_across_devices`: False
427
+ - `prompts`: None
428
+ - `batch_sampler`: no_duplicates
429
+ - `multi_dataset_batch_sampler`: proportional
430
+ - `router_mapping`: {}
431
+ - `learning_rate_mapping`: {}
432
+
433
+ </details>
434
+
435
  ### Training Logs
436
+ <details><summary>Click to expand</summary>
 
 
437
 
438
+ | Epoch | Step | Training Loss | Validation Loss | test_cosine_ap |
439
+ |:----------:|:--------:|:-------------:|:---------------:|:--------------:|
440
+ | -1 | -1 | - | - | 0.6476 |
441
+ | 0.2067 | 1000 | 0.0165 | 0.1033 | 0.6705 |
442
+ | 0.4133 | 2000 | 0.0067 | 0.0977 | 0.6597 |
443
+ | 0.6200 | 3000 | 0.0061 | 0.0955 | 0.6670 |
444
+ | **0.8266** | **4000** | **0.0063** | **0.0945** | **0.6678** |
445
+ | 1.0333 | 5000 | 0.0059 | 0.0950 | 0.6786 |
446
+ | 1.2399 | 6000 | 0.0054 | 0.0880 | 0.6779 |
447
+ | 1.4466 | 7000 | 0.0054 | 0.0876 | 0.6791 |
448
+ | 1.6532 | 8000 | 0.0054 | 0.0833 | 0.6652 |
449
+ | 1.8599 | 9000 | 0.0051 | 0.0821 | 0.6760 |
450
+ | 2.0665 | 10000 | 0.0048 | 0.0818 | 0.6767 |
451
+ | 2.2732 | 11000 | 0.0044 | 0.0796 | 0.6732 |
452
+ | 2.4799 | 12000 | 0.0048 | 0.0790 | 0.6717 |
453
+ | 2.6865 | 13000 | 0.0043 | 0.0804 | 0.6748 |
454
+ | 2.8932 | 14000 | 0.0048 | 0.0790 | 0.6745 |
455
+ | 3.0998 | 15000 | 0.0033 | 0.0775 | 0.6693 |
456
+ | 3.3065 | 16000 | 0.0044 | 0.0769 | 0.6767 |
457
+ | 3.5131 | 17000 | 0.005 | 0.0770 | 0.6768 |
458
+ | 3.7198 | 18000 | 0.0044 | 0.0760 | 0.6761 |
459
+ | 3.9264 | 19000 | 0.0039 | 0.0741 | 0.6799 |
460
+ | 4.1331 | 20000 | 0.0044 | 0.0750 | 0.6888 |
461
+ | 4.3397 | 21000 | 0.0041 | 0.0751 | 0.7019 |
462
+ | 4.5464 | 22000 | 0.0044 | 0.0707 | 0.7009 |
463
+ | 4.7530 | 23000 | 0.0039 | 0.0726 | 0.7041 |
464
+ | 4.9597 | 24000 | 0.0042 | 0.0712 | 0.6971 |
465
+ | 5.1664 | 25000 | 0.0038 | 0.0718 | 0.6978 |
466
+ | 5.3730 | 26000 | 0.004 | 0.0703 | 0.7035 |
467
+ | 5.5797 | 27000 | 0.004 | 0.0706 | 0.6976 |
468
+ | 5.7863 | 28000 | 0.0042 | 0.0699 | 0.6964 |
469
+ | 5.9930 | 29000 | 0.0044 | 0.0699 | 0.6911 |
470
+ | 6.1996 | 30000 | 0.0035 | 0.0702 | 0.6791 |
471
+ | 6.4063 | 31000 | 0.0035 | 0.0690 | 0.6955 |
472
+ | 6.6129 | 32000 | 0.0037 | 0.0693 | 0.6917 |
473
+ | 6.8196 | 33000 | 0.0035 | 0.0691 | 0.6972 |
474
+ | 7.0262 | 34000 | 0.004 | 0.0695 | 0.7083 |
475
+ | 7.2329 | 35000 | 0.0037 | 0.0690 | 0.6994 |
476
+ | 7.4396 | 36000 | 0.0036 | 0.0670 | 0.7060 |
477
+ | 7.6462 | 37000 | 0.0042 | 0.0682 | 0.6963 |
478
+ | 7.8529 | 38000 | 0.0037 | 0.0678 | 0.7049 |
479
+ | 8.0595 | 39000 | 0.0039 | 0.0682 | 0.7014 |
480
+ | 8.2662 | 40000 | 0.0039 | 0.0684 | 0.6969 |
481
+ | 8.4728 | 41000 | 0.0041 | 0.0677 | 0.7007 |
482
+ | 8.6795 | 42000 | 0.0038 | 0.0671 | 0.7126 |
483
+ | 8.8861 | 43000 | 0.0035 | 0.0684 | 0.7150 |
484
+ | 9.0928 | 44000 | 0.0035 | 0.0671 | 0.7043 |
485
+ | 9.2994 | 45000 | 0.0038 | 0.0681 | 0.7021 |
486
+ | 9.5061 | 46000 | 0.0038 | 0.0687 | 0.7129 |
487
+ | 9.7128 | 47000 | 0.0038 | 0.0684 | 0.7215 |
488
+ | 9.9194 | 48000 | 0.0039 | 0.0668 | 0.7179 |
489
+ | 10.1261 | 49000 | 0.0031 | 0.0661 | 0.7129 |
490
+ | 10.3327 | 50000 | 0.0033 | 0.0664 | 0.7119 |
491
+ | 10.5394 | 51000 | 0.0034 | 0.0668 | 0.7162 |
492
+ | 10.7460 | 52000 | 0.0038 | 0.0666 | 0.7181 |
493
+ | 10.9527 | 53000 | 0.0034 | 0.0674 | 0.7046 |
494
+ | 11.1593 | 54000 | 0.0034 | 0.0657 | 0.7100 |
495
+ | 11.3660 | 55000 | 0.0035 | 0.0656 | 0.7163 |
496
+ | 11.5726 | 56000 | 0.0034 | 0.0656 | 0.7003 |
497
+ | 11.7793 | 57000 | 0.0036 | 0.0643 | 0.7009 |
498
+ | 11.9859 | 58000 | 0.0038 | 0.0649 | 0.7166 |
499
+ | 12.1926 | 59000 | 0.0039 | 0.0659 | 0.7168 |
500
+ | 12.3993 | 60000 | 0.0039 | 0.0647 | 0.7080 |
501
+ | 12.6059 | 61000 | 0.0032 | 0.0649 | 0.7114 |
502
+ | 12.8126 | 62000 | 0.0034 | 0.0646 | 0.7165 |
503
+ | 13.0192 | 63000 | 0.0034 | 0.0654 | 0.7197 |
504
+ | 13.2259 | 64000 | 0.0035 | 0.0657 | 0.7179 |
505
+ | 13.4325 | 65000 | 0.0031 | 0.0652 | 0.7107 |
506
+ | 13.6392 | 66000 | 0.0032 | 0.0649 | 0.7089 |
507
+ | 13.8458 | 67000 | 0.0034 | 0.0655 | 0.7089 |
508
+ | 14.0525 | 68000 | 0.0031 | 0.0668 | 0.7163 |
509
+ | 14.2591 | 69000 | 0.0035 | 0.0644 | 0.7213 |
510
+ | 14.4658 | 70000 | 0.0035 | 0.0634 | 0.7057 |
511
+ | 14.6725 | 71000 | 0.0035 | 0.0635 | 0.7049 |
512
+ | 14.8791 | 72000 | 0.0033 | 0.0627 | 0.7094 |
513
+ | 15.0858 | 73000 | 0.0037 | 0.0620 | 0.7140 |
514
+ | 15.2924 | 74000 | 0.0035 | 0.0628 | 0.7237 |
515
+ | 15.4991 | 75000 | 0.003 | 0.0625 | 0.7127 |
516
+ | 15.7057 | 76000 | 0.0036 | 0.0635 | 0.7127 |
517
+ | 15.9124 | 77000 | 0.0037 | 0.0621 | 0.7104 |
518
+ | 16.1190 | 78000 | 0.0033 | 0.0624 | 0.7132 |
519
+ | 16.3257 | 79000 | 0.0035 | 0.0632 | 0.7132 |
520
+ | 16.5323 | 80000 | 0.003 | 0.0626 | 0.7193 |
521
+ | 16.7390 | 81000 | 0.0033 | 0.0628 | 0.7179 |
522
+ | 16.9456 | 82000 | 0.0036 | 0.0630 | 0.7210 |
523
+ | 17.1523 | 83000 | 0.0033 | 0.0628 | 0.7222 |
524
+ | 17.3590 | 84000 | 0.0034 | 0.0629 | 0.7226 |
525
+ | 17.5656 | 85000 | 0.0029 | 0.0621 | 0.7207 |
526
+ | 17.7723 | 86000 | 0.0032 | 0.0618 | 0.7182 |
527
+ | 17.9789 | 87000 | 0.0034 | 0.0620 | 0.7177 |
528
+ | 18.1856 | 88000 | 0.0034 | 0.0625 | 0.7148 |
529
+ | 18.3922 | 89000 | 0.0032 | 0.0624 | 0.7131 |
530
+ | 18.5989 | 90000 | 0.0032 | 0.0622 | 0.7126 |
531
+ | 18.8055 | 91000 | 0.0031 | 0.0617 | 0.7185 |
532
+ | 19.0122 | 92000 | 0.0032 | 0.0620 | 0.7231 |
533
+ | 19.2188 | 93000 | 0.0028 | 0.0623 | 0.7202 |
534
+ | 19.4255 | 94000 | 0.003 | 0.0625 | 0.7194 |
535
+ | 19.6322 | 95000 | 0.003 | 0.0619 | 0.7139 |
536
+ | 19.8388 | 96000 | 0.0031 | 0.0621 | 0.7151 |
537
+ | 20.0455 | 97000 | 0.0031 | 0.0617 | 0.7188 |
538
+ | 20.2521 | 98000 | 0.0031 | 0.0619 | 0.7161 |
539
+ | 20.4588 | 99000 | 0.0027 | 0.0612 | 0.7164 |
540
+ | 20.6654 | 100000 | 0.0033 | 0.0616 | 0.7173 |
541
+ | 20.8721 | 101000 | 0.0033 | 0.0614 | 0.7182 |
542
+ | 21.0787 | 102000 | 0.003 | 0.0611 | 0.7194 |
543
+ | 21.2854 | 103000 | 0.0031 | 0.0614 | 0.7191 |
544
+ | 21.4920 | 104000 | 0.0031 | 0.0615 | 0.7187 |
545
+ | 21.6987 | 105000 | 0.0035 | 0.0609 | 0.7143 |
546
+ | 21.9054 | 106000 | 0.0033 | 0.0614 | 0.7180 |
547
+ | 22.1120 | 107000 | 0.0029 | 0.0608 | 0.7215 |
548
+ | 22.3187 | 108000 | 0.0032 | 0.0609 | 0.7250 |
549
+ | 22.5253 | 109000 | 0.0029 | 0.0611 | 0.7248 |
550
+ | 22.7320 | 110000 | 0.003 | 0.0612 | 0.7224 |
551
+ | 22.9386 | 111000 | 0.0029 | 0.0612 | 0.7180 |
552
+ | 23.1453 | 112000 | 0.0032 | 0.0610 | 0.7169 |
553
+ | 23.3519 | 113000 | 0.0032 | 0.0609 | 0.7174 |
554
+ | 23.5586 | 114000 | 0.0028 | 0.0613 | 0.7204 |
555
+ | 23.7652 | 115000 | 0.0033 | 0.0613 | 0.7222 |
556
+ | 23.9719 | 116000 | 0.0033 | 0.0613 | 0.7240 |
557
+ | 24.1785 | 117000 | 0.003 | 0.0610 | 0.7244 |
558
+ | 24.3852 | 118000 | 0.0027 | 0.0613 | 0.7239 |
559
+ | 24.5919 | 119000 | 0.0028 | 0.0615 | 0.7248 |
560
+ | 24.7985 | 120000 | 0.003 | 0.0608 | 0.7259 |
561
+ | 25.0052 | 121000 | 0.0033 | 0.0605 | 0.7270 |
562
+ | 25.2118 | 122000 | 0.0035 | 0.0604 | 0.7240 |
563
+ | 25.4185 | 123000 | 0.003 | 0.0607 | 0.7245 |
564
+ | 25.6251 | 124000 | 0.003 | 0.0608 | 0.7238 |
565
+ | 25.8318 | 125000 | 0.0032 | 0.0605 | 0.7208 |
566
+ | 26.0384 | 126000 | 0.0029 | 0.0605 | 0.7208 |
567
+ | 26.2451 | 127000 | 0.0034 | 0.0603 | 0.7212 |
568
+ | 26.4517 | 128000 | 0.003 | 0.0605 | 0.7222 |
569
+ | 26.6584 | 129000 | 0.003 | 0.0604 | 0.7236 |
570
+ | 26.8651 | 130000 | 0.003 | 0.0608 | 0.7271 |
571
+ | 27.0717 | 131000 | 0.0028 | 0.0608 | 0.7242 |
572
+ | 27.2784 | 132000 | 0.0028 | 0.0612 | 0.7239 |
573
+ | 27.4850 | 133000 | 0.0025 | 0.0609 | 0.7270 |
574
+ | 27.6917 | 134000 | 0.0026 | 0.0607 | 0.7277 |
575
+ | 27.8983 | 135000 | 0.003 | 0.0608 | 0.7263 |
576
+ | 28.1050 | 136000 | 0.003 | 0.0609 | 0.7250 |
577
+ | 28.3116 | 137000 | 0.0029 | 0.0607 | 0.7262 |
578
+ | 28.5183 | 138000 | 0.0029 | 0.0609 | 0.7269 |
579
+ | 28.7249 | 139000 | 0.0029 | 0.0607 | 0.7250 |
580
+ | 28.9316 | 140000 | 0.0025 | 0.0608 | 0.7254 |
581
+ | 29.1383 | 141000 | 0.0031 | 0.0609 | 0.7262 |
582
+ | 29.3449 | 142000 | 0.0027 | 0.0606 | 0.7247 |
583
+ | 29.5516 | 143000 | 0.003 | 0.0607 | 0.7244 |
584
+ | 29.7582 | 144000 | 0.0028 | 0.0606 | 0.7240 |
585
+ | 29.9649 | 145000 | 0.0028 | 0.0605 | 0.7228 |
586
+ | 30.1715 | 146000 | 0.0032 | 0.0604 | 0.7251 |
587
+ | 30.3782 | 147000 | 0.0033 | 0.0603 | 0.7240 |
588
+ | 30.5848 | 148000 | 0.0029 | 0.0604 | 0.7242 |
589
+ | 30.7915 | 149000 | 0.0032 | 0.0603 | 0.7241 |
590
+ | 30.9981 | 150000 | 0.0028 | 0.0602 | 0.7246 |
591
+ | 31.2048 | 151000 | 0.0029 | 0.0602 | 0.7261 |
592
+ | 31.4114 | 152000 | 0.003 | 0.0602 | 0.7258 |
593
+ | 31.6181 | 153000 | 0.0031 | 0.0603 | 0.7253 |
594
+ | 31.8248 | 154000 | 0.003 | 0.0602 | 0.7250 |
595
+ | 32.0314 | 155000 | 0.0033 | 0.0602 | 0.7248 |
596
+ | 32.2381 | 156000 | 0.0031 | 0.0601 | 0.7248 |
597
+ | 32.4447 | 157000 | 0.0027 | 0.0602 | 0.7240 |
598
+ | 32.6514 | 158000 | 0.0026 | 0.0602 | 0.7243 |
599
+ | 32.8580 | 159000 | 0.0028 | 0.0602 | 0.7249 |
600
+ | 33.0647 | 160000 | 0.0033 | 0.0602 | 0.7251 |
601
+ | 33.2713 | 161000 | 0.0031 | 0.0602 | 0.7252 |
602
+ | 33.4780 | 162000 | 0.0027 | 0.0600 | 0.7247 |
603
+ | 33.6846 | 163000 | 0.0031 | 0.0601 | 0.7247 |
604
+ | 33.8913 | 164000 | 0.0032 | 0.0601 | 0.7251 |
605
+ | 34.0980 | 165000 | 0.0026 | 0.0602 | 0.7252 |
606
+ | 34.3046 | 166000 | 0.0034 | 0.0602 | 0.7252 |
607
+ | 34.5113 | 167000 | 0.0028 | 0.0602 | 0.7250 |
608
+ | 34.7179 | 168000 | 0.0029 | 0.0601 | 0.7249 |
609
+ | 34.9246 | 169000 | 0.0028 | 0.0602 | 0.7253 |
610
+ | 35.1312 | 170000 | 0.0026 | 0.0601 | 0.7249 |
611
+ | 35.3379 | 171000 | 0.0027 | 0.0601 | 0.7247 |
612
+ | 35.5445 | 172000 | 0.0031 | 0.0601 | 0.7245 |
613
+ | 35.7512 | 173000 | 0.003 | 0.0600 | 0.7245 |
614
+ | 35.9578 | 174000 | 0.003 | 0.0601 | 0.7250 |
615
+ | 36.1645 | 175000 | 0.0027 | 0.0600 | 0.7246 |
616
+ | 36.3712 | 176000 | 0.0028 | 0.0601 | 0.7248 |
617
+ | 36.5778 | 177000 | 0.0027 | 0.0601 | 0.7250 |
618
+ | 36.7845 | 178000 | 0.0028 | 0.0601 | 0.7252 |
619
+ | 36.9911 | 179000 | 0.0029 | 0.0601 | 0.7252 |
620
+ | 37.1978 | 180000 | 0.0029 | 0.0602 | 0.7251 |
621
+ | 37.4044 | 181000 | 0.0025 | 0.0601 | 0.7250 |
622
+ | 37.6111 | 182000 | 0.003 | 0.0601 | 0.7250 |
623
+ | 37.8177 | 183000 | 0.0028 | 0.0601 | 0.7251 |
624
+ | 38.0244 | 184000 | 0.0028 | 0.0601 | 0.7252 |
625
+ | 38.2310 | 185000 | 0.0034 | 0.0600 | 0.7251 |
626
+ | 38.4377 | 186000 | 0.0028 | 0.0601 | 0.7251 |
627
+ | 38.6443 | 187000 | 0.0035 | 0.0601 | 0.7250 |
628
+ | 38.8510 | 188000 | 0.003 | 0.0600 | 0.7250 |
629
+ | 39.0577 | 189000 | 0.0028 | 0.0601 | 0.7252 |
630
+ | 39.2643 | 190000 | 0.0027 | 0.0600 | 0.7250 |
631
+ | 39.4710 | 191000 | 0.0026 | 0.0601 | 0.7250 |
632
+ | 39.6776 | 192000 | 0.0028 | 0.0600 | 0.7251 |
633
+ | 39.8843 | 193000 | 0.0027 | 0.0600 | 0.7251 |
634
+ | 40.0909 | 194000 | 0.0031 | 0.0601 | 0.7252 |
635
+ | 40.2976 | 195000 | 0.0031 | 0.0600 | 0.7252 |
636
+ | 40.5042 | 196000 | 0.0029 | 0.0601 | 0.7251 |
637
+ | 40.7109 | 197000 | 0.0032 | 0.0600 | 0.7251 |
638
+ | 40.9175 | 198000 | 0.0028 | 0.0600 | 0.7251 |
639
+ | 41.1242 | 199000 | 0.0029 | 0.0600 | 0.7252 |
640
+ | 41.3309 | 200000 | 0.003 | 0.0600 | 0.7251 |
641
+
642
+ * The bold row denotes the saved checkpoint.
643
+ </details>
644
 
645
  ### Framework Versions
646
  - Python: 3.12.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c8601d215cb8c8a945b2e3836374f9935ffd687087b40d7eec6b1379051b1fe
3
  size 298041696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d620f65f36a797833828aad1edbcab0bc63cbc8e7cf5d4b7af936d5ecd305b
3
  size 298041696