Hugging Face's logo

mlfoundations-dev
/
qwen_s1ablation_diversity_sampling_27k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
reinhardh commited on
Commit
2e116fd
·
verified ·
1 Parent(s): 41f8c98

Training in progress, step 750

Browse files
Files changed (6) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +32 -0
  6. training_args.bin +2 -2
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72be4bb9604e43972dc72ef211b21856693843abc8b040fba7a4b0d0f6ed9ac4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b72e0a03170a66b4b4c45fb0f17e335677139587679140101ae70fbd9afd74f8
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f514a1fca267496e7b2d3ceeb71b20b17cf5f017917b7a6865c0251b4faa204
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b0989d867d0e8c05bc25212c1e974719b4664c240aad04c84d3dd0725d3243
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:608961552a2466e97a91248f48eb366940e50072b82a2d76bd27cc33bd74f5b7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225f479523920e94a01f625a06b478b1f5ff94617846dbfbb0f30b71adf6ef17
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12ff2cef956a74718317ffeb27b543d833a7b07df16456970b118f0290ddc466
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1258c37d5d8fbfc4431f62df566ab3877627b5ade68502fef5c584c461b06b84
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -726,3 +726,35 @@
726
  {"current_steps": 726, "total_steps": 759, "loss": 0.3794, "lr": 5.748998743166256e-08, "epoch": 2.867676102699144, "percentage": 95.65, "elapsed_time": "6:13:47", "remaining_time": "0:16:59"}
727
  {"current_steps": 727, "total_steps": 759, "loss": 0.3815, "lr": 5.4064735165506035e-08, "epoch": 2.871626069782752, "percentage": 95.78, "elapsed_time": "6:14:10", "remaining_time": "0:16:28"}
728
  {"current_steps": 728, "total_steps": 759, "loss": 0.3654, "lr": 5.0744124891748956e-08, "epoch": 2.8755760368663594, "percentage": 95.92, "elapsed_time": "6:14:33", "remaining_time": "0:15:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
726
  {"current_steps": 726, "total_steps": 759, "loss": 0.3794, "lr": 5.748998743166256e-08, "epoch": 2.867676102699144, "percentage": 95.65, "elapsed_time": "6:13:47", "remaining_time": "0:16:59"}
727
  {"current_steps": 727, "total_steps": 759, "loss": 0.3815, "lr": 5.4064735165506035e-08, "epoch": 2.871626069782752, "percentage": 95.78, "elapsed_time": "6:14:10", "remaining_time": "0:16:28"}
728
  {"current_steps": 728, "total_steps": 759, "loss": 0.3654, "lr": 5.0744124891748956e-08, "epoch": 2.8755760368663594, "percentage": 95.92, "elapsed_time": "6:14:33", "remaining_time": "0:15:56"}
729
+ {"current_steps": 729, "total_steps": 759, "loss": 0.3561, "lr": 4.7528226865107274e-08, "epoch": 2.879526003949967, "percentage": 96.05, "elapsed_time": "6:14:57", "remaining_time": "0:15:25"}
730
+ {"current_steps": 730, "total_steps": 759, "loss": 0.3741, "lr": 4.4417109124882394e-08, "epoch": 2.8834759710335747, "percentage": 96.18, "elapsed_time": "6:15:20", "remaining_time": "0:14:54"}
731
+ {"current_steps": 731, "total_steps": 759, "loss": 0.3726, "lr": 4.1410837493519595e-08, "epoch": 2.8874259381171825, "percentage": 96.31, "elapsed_time": "6:17:14", "remaining_time": "0:14:26"}
732
+ {"current_steps": 732, "total_steps": 759, "loss": 0.3851, "lr": 3.8509475575219115e-08, "epoch": 2.89137590520079, "percentage": 96.44, "elapsed_time": "6:17:37", "remaining_time": "0:13:55"}
733
+ {"current_steps": 733, "total_steps": 759, "loss": 0.3669, "lr": 3.571308475458723e-08, "epoch": 2.8953258722843978, "percentage": 96.57, "elapsed_time": "6:18:00", "remaining_time": "0:13:24"}
734
+ {"current_steps": 734, "total_steps": 759, "loss": 0.357, "lr": 3.302172419534011e-08, "epoch": 2.899275839368005, "percentage": 96.71, "elapsed_time": "6:18:23", "remaining_time": "0:12:53"}
735
+ {"current_steps": 735, "total_steps": 759, "loss": 0.3399, "lr": 3.04354508390492e-08, "epoch": 2.903225806451613, "percentage": 96.84, "elapsed_time": "6:18:46", "remaining_time": "0:12:22"}
736
+ {"current_steps": 736, "total_steps": 759, "loss": 0.368, "lr": 2.7954319403940555e-08, "epoch": 2.9071757735352204, "percentage": 96.97, "elapsed_time": "6:19:09", "remaining_time": "0:11:50"}
737
+ {"current_steps": 737, "total_steps": 759, "loss": 0.3574, "lr": 2.5578382383732446e-08, "epoch": 2.9111257406188282, "percentage": 97.1, "elapsed_time": "6:19:32", "remaining_time": "0:11:19"}
738
+ {"current_steps": 738, "total_steps": 759, "loss": 0.3805, "lr": 2.3307690046527887e-08, "epoch": 2.915075707702436, "percentage": 97.23, "elapsed_time": "6:19:55", "remaining_time": "0:10:48"}
739
+ {"current_steps": 739, "total_steps": 759, "loss": 0.3699, "lr": 2.114229043375049e-08, "epoch": 2.9190256747860435, "percentage": 97.36, "elapsed_time": "6:20:19", "remaining_time": "0:10:17"}
740
+ {"current_steps": 740, "total_steps": 759, "loss": 0.3743, "lr": 1.9082229359127512e-08, "epoch": 2.922975641869651, "percentage": 97.5, "elapsed_time": "6:20:42", "remaining_time": "0:09:46"}
741
+ {"current_steps": 741, "total_steps": 759, "loss": 0.3597, "lr": 1.7127550407721184e-08, "epoch": 2.9269256089532587, "percentage": 97.63, "elapsed_time": "6:22:06", "remaining_time": "0:09:16"}
742
+ {"current_steps": 742, "total_steps": 759, "loss": 0.3519, "lr": 1.52782949350061e-08, "epoch": 2.9308755760368665, "percentage": 97.76, "elapsed_time": "6:22:29", "remaining_time": "0:08:45"}
743
+ {"current_steps": 741, "total_steps": 759, "loss": 0.3609, "lr": 1.7127550407721184e-08, "epoch": 2.9282422646477944, "percentage": 97.63, "elapsed_time": "0:00:44", "remaining_time": "0:00:01"}
744
+ {"current_steps": 742, "total_steps": 759, "loss": 0.3483, "lr": 1.52782949350061e-08, "epoch": 2.932192231731402, "percentage": 97.76, "elapsed_time": "0:01:08", "remaining_time": "0:00:01"}
745
+ {"current_steps": 743, "total_steps": 759, "loss": 0.3577, "lr": 1.3534502065993826e-08, "epoch": 2.93614219881501, "percentage": 97.89, "elapsed_time": "0:01:33", "remaining_time": "0:00:02"}
746
+ {"current_steps": 744, "total_steps": 759, "loss": 0.3537, "lr": 1.1896208694406886e-08, "epoch": 2.9400921658986174, "percentage": 98.02, "elapsed_time": "0:01:57", "remaining_time": "0:00:02"}
747
+ {"current_steps": 745, "total_steps": 759, "loss": 0.3611, "lr": 1.0363449481896604e-08, "epoch": 2.9440421329822253, "percentage": 98.16, "elapsed_time": "0:02:22", "remaining_time": "0:00:02"}
748
+ {"current_steps": 746, "total_steps": 759, "loss": 0.3369, "lr": 8.936256857308701e-09, "epoch": 2.9479921000658327, "percentage": 98.29, "elapsed_time": "0:02:47", "remaining_time": "0:00:02"}
749
+ {"current_steps": 747, "total_steps": 759, "loss": 0.3636, "lr": 7.614661016001056e-09, "epoch": 2.9519420671494405, "percentage": 98.42, "elapsed_time": "0:03:12", "remaining_time": "0:00:03"}
750
+ {"current_steps": 748, "total_steps": 759, "loss": 0.3549, "lr": 6.398689919201451e-09, "epoch": 2.955892034233048, "percentage": 98.55, "elapsed_time": "0:03:37", "remaining_time": "0:00:03"}
751
+ {"current_steps": 749, "total_steps": 759, "loss": 0.3502, "lr": 5.288369293415807e-09, "epoch": 2.9598420013166558, "percentage": 98.68, "elapsed_time": "0:04:03", "remaining_time": "0:00:03"}
752
+ {"current_steps": 750, "total_steps": 759, "loss": 0.36, "lr": 4.283722629887521e-09, "epoch": 2.9637919684002636, "percentage": 98.81, "elapsed_time": "0:04:28", "remaining_time": "0:00:03"}
753
+ {"current_steps": 751, "total_steps": 759, "loss": 0.3594, "lr": 3.3847711840950813e-09, "epoch": 2.967741935483871, "percentage": 98.95, "elapsed_time": "0:06:37", "remaining_time": "0:00:04"}
754
+ {"current_steps": 752, "total_steps": 759, "loss": 0.3745, "lr": 2.5915339753085355e-09, "epoch": 2.9716919025674784, "percentage": 99.08, "elapsed_time": "0:07:02", "remaining_time": "0:00:03"}
755
+ {"current_steps": 753, "total_steps": 759, "loss": 0.388, "lr": 1.9040277861814836e-09, "epoch": 2.9756418696510862, "percentage": 99.21, "elapsed_time": "0:07:27", "remaining_time": "0:00:03"}
756
+ {"current_steps": 754, "total_steps": 759, "loss": 0.3546, "lr": 1.3222671623991379e-09, "epoch": 2.979591836734694, "percentage": 99.34, "elapsed_time": "0:07:53", "remaining_time": "0:00:03"}
757
+ {"current_steps": 755, "total_steps": 759, "loss": 0.353, "lr": 8.462644123696794e-10, "epoch": 2.9835418038183015, "percentage": 99.47, "elapsed_time": "0:08:18", "remaining_time": "0:00:02"}
758
+ {"current_steps": 756, "total_steps": 759, "loss": 0.3509, "lr": 4.760296069639125e-10, "epoch": 2.9874917709019093, "percentage": 99.6, "elapsed_time": "0:08:44", "remaining_time": "0:00:02"}
759
+ {"current_steps": 757, "total_steps": 759, "loss": 0.355, "lr": 2.1157057930321079e-10, "epoch": 2.9914417379855167, "percentage": 99.74, "elapsed_time": "0:09:10", "remaining_time": "0:00:01"}
760
+ {"current_steps": 758, "total_steps": 759, "loss": 0.359, "lr": 5.289292459187412e-11, "epoch": 2.9953917050691246, "percentage": 99.87, "elapsed_time": "0:09:35", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad56465bf705fcd00281ff048f4da8ec4c124ff69277c29fdc8c26dd316ae42
3
- size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a2dec218e4be041cea0ecb002e79aa9d239d8bc94e23b9041e85ad7f6808f0
3
+ size 7480