Hugging Face's logo

redis
/
langcache-embed-experimental

Sentence Similarity
sentence-transformers
Safetensors
English
bert
biencoder
text-classification
sentence-pair-classification
semantic-similarity
semantic-search
retrieval
reranking
Generated from Trainer
dataset_size:9233417
loss:ArcFaceInBatchLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
radoslavralev commited on
Commit
1c2d42f
·
verified ·
1 Parent(s): bdeb1c4

Add new SentenceTransformer model

Browse files
Files changed (2) hide show
  1. README.md +318 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -81,28 +81,28 @@ model-index:
81
  type: test
82
  metrics:
83
  - type: cosine_accuracy@1
84
- value: 0.44070346359110285
85
  name: Cosine Accuracy@1
86
  - type: cosine_precision@1
87
- value: 0.44070346359110285
88
  name: Cosine Precision@1
89
  - type: cosine_recall@1
90
- value: 0.42648577181064024
91
  name: Cosine Recall@1
92
  - type: cosine_ndcg@10
93
- value: 0.627438499402098
94
  name: Cosine Ndcg@10
95
  - type: cosine_mrr@1
96
- value: 0.44070346359110285
97
  name: Cosine Mrr@1
98
  - type: cosine_map@100
99
- value: 0.5750186225138979
100
  name: Cosine Map@100
101
  - type: cosine_auc_precision_cache_hit_ratio
102
- value: 0.27246772094744054
103
  name: Cosine Auc Precision Cache Hit Ratio
104
  - type: cosine_auc_similarity_distribution
105
- value: 0.40850809564840007
106
  name: Cosine Auc Similarity Distribution
107
  ---
108
 
@@ -167,9 +167,9 @@ print(embeddings.shape)
167
  # Get the similarity scores for the embeddings
168
  similarities = model.similarity(embeddings, embeddings)
169
  print(similarities)
170
- # tensor([[1.0000, 0.9844, 0.9844],
171
- # [0.9844, 0.9961, 0.9922],
172
- # [0.9844, 0.9922, 0.9961]], dtype=torch.bfloat16)
173
  ```
174
 
175
  <!--
@@ -207,14 +207,14 @@ You can finetune this model on your own dataset.
207
 
208
  | Metric | Value |
209
  |:-------------------------------------|:-----------|
210
- | cosine_accuracy@1 | 0.4407 |
211
- | cosine_precision@1 | 0.4407 |
212
- | cosine_recall@1 | 0.4265 |
213
- | **cosine_ndcg@10** | **0.6274** |
214
- | cosine_mrr@1 | 0.4407 |
215
- | cosine_map@100 | 0.575 |
216
- | cosine_auc_precision_cache_hit_ratio | 0.2725 |
217
- | cosine_auc_similarity_distribution | 0.4085 |
218
 
219
  <!--
220
  ## Bias, Risks and Limitations
@@ -284,11 +284,307 @@ You can finetune this model on your own dataset.
284
  }
285
  ```
286
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
287
  ### Training Logs
288
- | Epoch | Step | test_cosine_ndcg@10 |
289
- |:-----:|:----:|:-------------------:|
290
- | -1 | -1 | 0.6274 |
291
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
292
 
293
  ### Framework Versions
294
  - Python: 3.12.3
 
81
  type: test
82
  metrics:
83
  - type: cosine_accuracy@1
84
+ value: 0.6070776173931731
85
  name: Cosine Accuracy@1
86
  - type: cosine_precision@1
87
+ value: 0.6070776173931731
88
  name: Cosine Precision@1
89
  - type: cosine_recall@1
90
+ value: 0.588632794022045
91
  name: Cosine Recall@1
92
  - type: cosine_ndcg@10
93
+ value: 0.7755359823507149
94
  name: Cosine Ndcg@10
95
  - type: cosine_mrr@1
96
+ value: 0.6070776173931731
97
  name: Cosine Mrr@1
98
  - type: cosine_map@100
99
+ value: 0.7291245351244533
100
  name: Cosine Map@100
101
  - type: cosine_auc_precision_cache_hit_ratio
102
+ value: 0.348058858138603
103
  name: Cosine Auc Precision Cache Hit Ratio
104
  - type: cosine_auc_similarity_distribution
105
+ value: 0.21125989323367672
106
  name: Cosine Auc Similarity Distribution
107
  ---
108
 
 
167
  # Get the similarity scores for the embeddings
168
  similarities = model.similarity(embeddings, embeddings)
169
  print(similarities)
170
+ # tensor([[1.0000, 0.9609, 0.4414],
171
+ # [0.9609, 1.0000, 0.4395],
172
+ # [0.4414, 0.4395, 1.0000]], dtype=torch.bfloat16)
173
  ```
174
 
175
  <!--
 
207
 
208
  | Metric | Value |
209
  |:-------------------------------------|:-----------|
210
+ | cosine_accuracy@1 | 0.6071 |
211
+ | cosine_precision@1 | 0.6071 |
212
+ | cosine_recall@1 | 0.5886 |
213
+ | **cosine_ndcg@10** | **0.7755** |
214
+ | cosine_mrr@1 | 0.6071 |
215
+ | cosine_map@100 | 0.7291 |
216
+ | cosine_auc_precision_cache_hit_ratio | 0.3481 |
217
+ | cosine_auc_similarity_distribution | 0.2113 |
218
 
219
  <!--
220
  ## Bias, Risks and Limitations
 
284
  }
285
  ```
286
 
287
+ ### Training Hyperparameters
288
+ #### Non-Default Hyperparameters
289
+
290
+ - `eval_strategy`: steps
291
+ - `per_device_train_batch_size`: 100
292
+ - `per_device_eval_batch_size`: 100
293
+ - `weight_decay`: 0.001
294
+ - `adam_beta2`: 0.98
295
+ - `adam_epsilon`: 1e-06
296
+ - `max_steps`: 75000
297
+ - `warmup_ratio`: 0.1
298
+ - `load_best_model_at_end`: True
299
+ - `optim`: stable_adamw
300
+ - `ddp_find_unused_parameters`: False
301
+ - `push_to_hub`: True
302
+ - `hub_model_id`: redis/langcache-embed-experimental
303
+ - `batch_sampler`: no_duplicates
304
+
305
+ #### All Hyperparameters
306
+ <details><summary>Click to expand</summary>
307
+
308
+ - `overwrite_output_dir`: False
309
+ - `do_predict`: False
310
+ - `eval_strategy`: steps
311
+ - `prediction_loss_only`: True
312
+ - `per_device_train_batch_size`: 100
313
+ - `per_device_eval_batch_size`: 100
314
+ - `per_gpu_train_batch_size`: None
315
+ - `per_gpu_eval_batch_size`: None
316
+ - `gradient_accumulation_steps`: 1
317
+ - `eval_accumulation_steps`: None
318
+ - `torch_empty_cache_steps`: None
319
+ - `learning_rate`: 5e-05
320
+ - `weight_decay`: 0.001
321
+ - `adam_beta1`: 0.9
322
+ - `adam_beta2`: 0.98
323
+ - `adam_epsilon`: 1e-06
324
+ - `max_grad_norm`: 1.0
325
+ - `num_train_epochs`: 3.0
326
+ - `max_steps`: 75000
327
+ - `lr_scheduler_type`: linear
328
+ - `lr_scheduler_kwargs`: {}
329
+ - `warmup_ratio`: 0.1
330
+ - `warmup_steps`: 0
331
+ - `log_level`: passive
332
+ - `log_level_replica`: warning
333
+ - `log_on_each_node`: True
334
+ - `logging_nan_inf_filter`: True
335
+ - `save_safetensors`: True
336
+ - `save_on_each_node`: False
337
+ - `save_only_model`: False
338
+ - `restore_callback_states_from_checkpoint`: False
339
+ - `no_cuda`: False
340
+ - `use_cpu`: False
341
+ - `use_mps_device`: False
342
+ - `seed`: 42
343
+ - `data_seed`: None
344
+ - `jit_mode_eval`: False
345
+ - `use_ipex`: False
346
+ - `bf16`: False
347
+ - `fp16`: False
348
+ - `fp16_opt_level`: O1
349
+ - `half_precision_backend`: auto
350
+ - `bf16_full_eval`: False
351
+ - `fp16_full_eval`: False
352
+ - `tf32`: None
353
+ - `local_rank`: 0
354
+ - `ddp_backend`: None
355
+ - `tpu_num_cores`: None
356
+ - `tpu_metrics_debug`: False
357
+ - `debug`: []
358
+ - `dataloader_drop_last`: False
359
+ - `dataloader_num_workers`: 0
360
+ - `dataloader_prefetch_factor`: None
361
+ - `past_index`: -1
362
+ - `disable_tqdm`: False
363
+ - `remove_unused_columns`: True
364
+ - `label_names`: None
365
+ - `load_best_model_at_end`: True
366
+ - `ignore_data_skip`: False
367
+ - `fsdp`: []
368
+ - `fsdp_min_num_params`: 0
369
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
370
+ - `fsdp_transformer_layer_cls_to_wrap`: None
371
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
372
+ - `parallelism_config`: None
373
+ - `deepspeed`: None
374
+ - `label_smoothing_factor`: 0.0
375
+ - `optim`: stable_adamw
376
+ - `optim_args`: None
377
+ - `adafactor`: False
378
+ - `group_by_length`: False
379
+ - `length_column_name`: length
380
+ - `ddp_find_unused_parameters`: False
381
+ - `ddp_bucket_cap_mb`: None
382
+ - `ddp_broadcast_buffers`: False
383
+ - `dataloader_pin_memory`: True
384
+ - `dataloader_persistent_workers`: False
385
+ - `skip_memory_metrics`: True
386
+ - `use_legacy_prediction_loop`: False
387
+ - `push_to_hub`: True
388
+ - `resume_from_checkpoint`: None
389
+ - `hub_model_id`: redis/langcache-embed-experimental
390
+ - `hub_strategy`: every_save
391
+ - `hub_private_repo`: None
392
+ - `hub_always_push`: False
393
+ - `hub_revision`: None
394
+ - `gradient_checkpointing`: False
395
+ - `gradient_checkpointing_kwargs`: None
396
+ - `include_inputs_for_metrics`: False
397
+ - `include_for_metrics`: []
398
+ - `eval_do_concat_batches`: True
399
+ - `fp16_backend`: auto
400
+ - `push_to_hub_model_id`: None
401
+ - `push_to_hub_organization`: None
402
+ - `mp_parameters`:
403
+ - `auto_find_batch_size`: False
404
+ - `full_determinism`: False
405
+ - `torchdynamo`: None
406
+ - `ray_scope`: last
407
+ - `ddp_timeout`: 1800
408
+ - `torch_compile`: False
409
+ - `torch_compile_backend`: None
410
+ - `torch_compile_mode`: None
411
+ - `include_tokens_per_second`: False
412
+ - `include_num_input_tokens_seen`: False
413
+ - `neftune_noise_alpha`: None
414
+ - `optim_target_modules`: None
415
+ - `batch_eval_metrics`: False
416
+ - `eval_on_start`: False
417
+ - `use_liger_kernel`: False
418
+ - `liger_kernel_config`: None
419
+ - `eval_use_gather_object`: False
420
+ - `average_tokens_across_devices`: False
421
+ - `prompts`: None
422
+ - `batch_sampler`: no_duplicates
423
+ - `multi_dataset_batch_sampler`: proportional
424
+ - `router_mapping`: {}
425
+ - `learning_rate_mapping`: {}
426
+
427
+ </details>
428
+
429
  ### Training Logs
430
+ <details><summary>Click to expand</summary>
 
 
431
 
432
+ | Epoch | Step | Training Loss | Validation Loss | test_cosine_ndcg@10 |
433
+ |:----------:|:---------:|:-------------:|:---------------:|:-------------------:|
434
+ | -1 | -1 | - | - | 0.6274 |
435
+ | 0.0054 | 500 | 2.0433 | 0.5003 | 0.7156 |
436
+ | 0.0108 | 1000 | 0.2913 | 0.3804 | 0.7423 |
437
+ | 0.0162 | 1500 | 0.1876 | 0.3343 | 0.7526 |
438
+ | 0.0217 | 2000 | 0.1484 | 0.3172 | 0.7528 |
439
+ | 0.0271 | 2500 | 0.132 | 0.2945 | 0.7569 |
440
+ | 0.0325 | 3000 | 0.1161 | 0.2822 | 0.7636 |
441
+ | 0.0379 | 3500 | 0.1105 | 0.2918 | 0.7580 |
442
+ | 0.0433 | 4000 | 0.1072 | 0.2820 | 0.7597 |
443
+ | 0.0487 | 4500 | 0.1061 | 0.2483 | 0.7661 |
444
+ | 0.0542 | 5000 | 0.0991 | 0.2671 | 0.7600 |
445
+ | 0.0596 | 5500 | 0.0971 | 0.2843 | 0.7595 |
446
+ | 0.0650 | 6000 | 0.0953 | 0.2448 | 0.7640 |
447
+ | 0.0704 | 6500 | 0.1015 | 0.3021 | 0.7632 |
448
+ | 0.0758 | 7000 | 0.0985 | 0.2744 | 0.7616 |
449
+ | 0.0812 | 7500 | 0.1009 | 0.2764 | 0.7615 |
450
+ | 0.0866 | 8000 | 0.0984 | 0.2865 | 0.7608 |
451
+ | 0.0921 | 8500 | 0.0947 | 0.3062 | 0.7600 |
452
+ | 0.0975 | 9000 | 0.0914 | 0.2997 | 0.7584 |
453
+ | 0.1029 | 9500 | 0.0896 | 0.2484 | 0.7617 |
454
+ | 0.1083 | 10000 | 0.0846 | 0.2850 | 0.7594 |
455
+ | 0.1137 | 10500 | 0.0907 | 0.2896 | 0.7571 |
456
+ | 0.1191 | 11000 | 0.0859 | 0.2657 | 0.7599 |
457
+ | 0.1245 | 11500 | 0.0875 | 0.2509 | 0.7620 |
458
+ | 0.1300 | 12000 | 0.0849 | 0.2728 | 0.7620 |
459
+ | 0.1354 | 12500 | 0.0788 | 0.2707 | 0.7587 |
460
+ | 0.1408 | 13000 | 0.0804 | 0.2985 | 0.7567 |
461
+ | 0.1462 | 13500 | 0.0815 | 0.2526 | 0.7620 |
462
+ | 0.1516 | 14000 | 0.0783 | 0.2441 | 0.7655 |
463
+ | 0.1570 | 14500 | 0.0791 | 0.2707 | 0.7645 |
464
+ | 0.1625 | 15000 | 0.0797 | 0.2781 | 0.7576 |
465
+ | 0.1679 | 15500 | 0.077 | 0.2624 | 0.7595 |
466
+ | 0.1733 | 16000 | 0.0742 | 0.2882 | 0.7620 |
467
+ | 0.1787 | 16500 | 0.0739 | 0.2654 | 0.7630 |
468
+ | 0.1841 | 17000 | 0.0695 | 0.2832 | 0.7607 |
469
+ | 0.1895 | 17500 | 0.0726 | 0.2595 | 0.7627 |
470
+ | 0.1949 | 18000 | 0.0739 | 0.2376 | 0.7653 |
471
+ | 0.2004 | 18500 | 0.0751 | 0.2671 | 0.7652 |
472
+ | 0.2058 | 19000 | 0.0717 | 0.3013 | 0.7595 |
473
+ | 0.2112 | 19500 | 0.0696 | 0.2538 | 0.7671 |
474
+ | 0.2166 | 20000 | 0.0659 | 0.2569 | 0.7612 |
475
+ | 0.2220 | 20500 | 0.0669 | 0.2595 | 0.7648 |
476
+ | 0.2274 | 21000 | 0.0679 | 0.2231 | 0.7664 |
477
+ | 0.2328 | 21500 | 0.0657 | 0.2732 | 0.7636 |
478
+ | 0.2383 | 22000 | 0.0703 | 0.2658 | 0.7674 |
479
+ | 0.2437 | 22500 | 0.0636 | 0.2582 | 0.7676 |
480
+ | 0.2491 | 23000 | 0.0688 | 0.2586 | 0.7682 |
481
+ | 0.2545 | 23500 | 0.0598 | 0.2612 | 0.7675 |
482
+ | 0.2599 | 24000 | 0.0664 | 0.2581 | 0.7655 |
483
+ | 0.2653 | 24500 | 0.0621 | 0.2393 | 0.7642 |
484
+ | 0.2708 | 25000 | 0.0641 | 0.2309 | 0.7673 |
485
+ | 0.2762 | 25500 | 0.0624 | 0.2346 | 0.7700 |
486
+ | 0.2816 | 26000 | 0.0595 | 0.2179 | 0.7671 |
487
+ | 0.2870 | 26500 | 0.0605 | 0.2332 | 0.7664 |
488
+ | 0.2924 | 27000 | 0.0609 | 0.2227 | 0.7678 |
489
+ | 0.2978 | 27500 | 0.0621 | 0.2312 | 0.7688 |
490
+ | 0.3032 | 28000 | 0.0626 | 0.2404 | 0.7680 |
491
+ | 0.3087 | 28500 | 0.063 | 0.2429 | 0.7672 |
492
+ | 0.3141 | 29000 | 0.0601 | 0.2275 | 0.7671 |
493
+ | 0.3195 | 29500 | 0.0617 | 0.2235 | 0.7663 |
494
+ | 0.3249 | 30000 | 0.0581 | 0.2370 | 0.7698 |
495
+ | 0.3303 | 30500 | 0.06 | 0.2450 | 0.7652 |
496
+ | 0.3357 | 31000 | 0.0591 | 0.2851 | 0.7638 |
497
+ | 0.3411 | 31500 | 0.0585 | 0.2718 | 0.7664 |
498
+ | 0.3466 | 32000 | 0.0563 | 0.2532 | 0.7664 |
499
+ | 0.3520 | 32500 | 0.059 | 0.2330 | 0.7689 |
500
+ | 0.3574 | 33000 | 0.0545 | 0.2158 | 0.7695 |
501
+ | 0.3628 | 33500 | 0.0567 | 0.2263 | 0.7672 |
502
+ | 0.3682 | 34000 | 0.0566 | 0.2338 | 0.7682 |
503
+ | 0.3736 | 34500 | 0.0586 | 0.2244 | 0.7696 |
504
+ | 0.3791 | 35000 | 0.0559 | 0.2474 | 0.7671 |
505
+ | 0.3845 | 35500 | 0.053 | 0.2332 | 0.7687 |
506
+ | 0.3899 | 36000 | 0.0507 | 0.2258 | 0.7679 |
507
+ | 0.3953 | 36500 | 0.0527 | 0.2240 | 0.7712 |
508
+ | 0.4007 | 37000 | 0.0545 | 0.2229 | 0.7700 |
509
+ | 0.4061 | 37500 | 0.0558 | 0.2119 | 0.7704 |
510
+ | 0.4115 | 38000 | 0.0538 | 0.2611 | 0.7693 |
511
+ | 0.4170 | 38500 | 0.0549 | 0.2336 | 0.7686 |
512
+ | 0.4224 | 39000 | 0.0501 | 0.2316 | 0.7687 |
513
+ | 0.4278 | 39500 | 0.0497 | 0.2289 | 0.7697 |
514
+ | 0.4332 | 40000 | 0.0512 | 0.2299 | 0.7683 |
515
+ | 0.4386 | 40500 | 0.0511 | 0.2654 | 0.7704 |
516
+ | 0.4440 | 41000 | 0.0498 | 0.2272 | 0.7731 |
517
+ | 0.4495 | 41500 | 0.053 | 0.2327 | 0.7696 |
518
+ | 0.4549 | 42000 | 0.0487 | 0.2380 | 0.7715 |
519
+ | 0.4603 | 42500 | 0.0518 | 0.2230 | 0.7724 |
520
+ | 0.4657 | 43000 | 0.0488 | 0.2249 | 0.7703 |
521
+ | 0.4711 | 43500 | 0.0529 | 0.2452 | 0.7716 |
522
+ | 0.4765 | 44000 | 0.0497 | 0.2341 | 0.7720 |
523
+ | 0.4819 | 44500 | 0.0486 | 0.2480 | 0.7696 |
524
+ | 0.4874 | 45000 | 0.0518 | 0.2349 | 0.7715 |
525
+ | 0.4928 | 45500 | 0.0471 | 0.2237 | 0.7720 |
526
+ | 0.4982 | 46000 | 0.0483 | 0.2299 | 0.7712 |
527
+ | 0.5036 | 46500 | 0.0462 | 0.2184 | 0.7705 |
528
+ | 0.5090 | 47000 | 0.0497 | 0.2335 | 0.7718 |
529
+ | 0.5144 | 47500 | 0.05 | 0.2302 | 0.7697 |
530
+ | 0.5198 | 48000 | 0.0488 | 0.2252 | 0.7701 |
531
+ | 0.5253 | 48500 | 0.045 | 0.2291 | 0.7687 |
532
+ | 0.5307 | 49000 | 0.048 | 0.2135 | 0.7698 |
533
+ | 0.5361 | 49500 | 0.0442 | 0.2215 | 0.7704 |
534
+ | 0.5415 | 50000 | 0.0479 | 0.2233 | 0.7707 |
535
+ | 0.5469 | 50500 | 0.0464 | 0.2275 | 0.7713 |
536
+ | 0.5523 | 51000 | 0.0454 | 0.2175 | 0.7717 |
537
+ | 0.5578 | 51500 | 0.0477 | 0.2152 | 0.7719 |
538
+ | 0.5632 | 52000 | 0.0463 | 0.2364 | 0.7701 |
539
+ | 0.5686 | 52500 | 0.0433 | 0.2430 | 0.7736 |
540
+ | 0.5740 | 53000 | 0.0454 | 0.2328 | 0.7708 |
541
+ | 0.5794 | 53500 | 0.0472 | 0.2283 | 0.7722 |
542
+ | 0.5848 | 54000 | 0.0447 | 0.2320 | 0.7720 |
543
+ | 0.5902 | 54500 | 0.0445 | 0.2404 | 0.7689 |
544
+ | 0.5957 | 55000 | 0.0429 | 0.2353 | 0.7693 |
545
+ | 0.6011 | 55500 | 0.0422 | 0.2366 | 0.7722 |
546
+ | 0.6065 | 56000 | 0.0436 | 0.2321 | 0.7720 |
547
+ | 0.6119 | 56500 | 0.0453 | 0.2250 | 0.7723 |
548
+ | 0.6173 | 57000 | 0.0431 | 0.2219 | 0.7733 |
549
+ | 0.6227 | 57500 | 0.0421 | 0.2244 | 0.7723 |
550
+ | 0.6281 | 58000 | 0.0434 | 0.2137 | 0.7728 |
551
+ | 0.6336 | 58500 | 0.0416 | 0.2181 | 0.7743 |
552
+ | 0.6390 | 59000 | 0.0412 | 0.2230 | 0.7717 |
553
+ | 0.6444 | 59500 | 0.0436 | 0.2116 | 0.7737 |
554
+ | 0.6498 | 60000 | 0.0404 | 0.2114 | 0.7736 |
555
+ | 0.6552 | 60500 | 0.041 | 0.2095 | 0.7736 |
556
+ | 0.6606 | 61000 | 0.0408 | 0.2079 | 0.7741 |
557
+ | 0.6661 | 61500 | 0.0408 | 0.2040 | 0.7756 |
558
+ | 0.6715 | 62000 | 0.0404 | 0.2098 | 0.7733 |
559
+ | 0.6769 | 62500 | 0.0418 | 0.2105 | 0.7741 |
560
+ | 0.6823 | 63000 | 0.0402 | 0.2081 | 0.7741 |
561
+ | 0.6877 | 63500 | 0.0394 | 0.2120 | 0.7742 |
562
+ | 0.6931 | 64000 | 0.0418 | 0.2129 | 0.7742 |
563
+ | 0.6985 | 64500 | 0.0406 | 0.2145 | 0.7753 |
564
+ | 0.7040 | 65000 | 0.0382 | 0.2257 | 0.7741 |
565
+ | 0.7094 | 65500 | 0.0373 | 0.2250 | 0.7756 |
566
+ | 0.7148 | 66000 | 0.0382 | 0.2269 | 0.7732 |
567
+ | **0.7202** | **66500** | **0.0405** | **0.2087** | **0.7764** |
568
+ | 0.7256 | 67000 | 0.042 | 0.2114 | 0.7753 |
569
+ | 0.7310 | 67500 | 0.0389 | 0.2138 | 0.7748 |
570
+ | 0.7364 | 68000 | 0.0339 | 0.2084 | 0.7761 |
571
+ | 0.7419 | 68500 | 0.0379 | 0.2090 | 0.7760 |
572
+ | 0.7473 | 69000 | 0.0369 | 0.2161 | 0.7742 |
573
+ | 0.7527 | 69500 | 0.0354 | 0.2226 | 0.7748 |
574
+ | 0.7581 | 70000 | 0.0396 | 0.2191 | 0.7753 |
575
+ | 0.7635 | 70500 | 0.0356 | 0.2195 | 0.7759 |
576
+ | 0.7689 | 71000 | 0.0359 | 0.2182 | 0.7760 |
577
+ | 0.7744 | 71500 | 0.0389 | 0.2187 | 0.7753 |
578
+ | 0.7798 | 72000 | 0.0366 | 0.2194 | 0.7753 |
579
+ | 0.7852 | 72500 | 0.0351 | 0.2198 | 0.7749 |
580
+ | 0.7906 | 73000 | 0.038 | 0.2175 | 0.7754 |
581
+ | 0.7960 | 73500 | 0.0378 | 0.2172 | 0.7756 |
582
+ | 0.8014 | 74000 | 0.0376 | 0.2174 | 0.7754 |
583
+ | 0.8068 | 74500 | 0.038 | 0.2176 | 0.7753 |
584
+ | 0.8123 | 75000 | 0.0379 | 0.2174 | 0.7755 |
585
+
586
+ * The bold row denotes the saved checkpoint.
587
+ </details>
588
 
589
  ### Framework Versions
590
  - Python: 3.12.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48e2a1a598b7d9d75eb9376d781d959044609905644916a262d6526ed13942e0
3
  size 789580328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2304eb08c679af236a8a9179f0e08d478a4d1958873dd0990efbc0ca883decab
3
  size 789580328