Hugging Face's logo

C3DS
/
FLICC-Qwen3.5-9B-lora

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
hf_jobs
unsloth
sft
Model card Files
xet
 Metrics Community
iRanadheer commited on
Commit
b13af9b
·
verified ·
1 Parent(s): a63204c

Training in progress, step 400, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +92 -6
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eac681b65c9d84eecc8d7d3c32d8e83dcc02e2d1cf5a5e601ff7ebc9bf649acf
3
  size 116429720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f31f438de0fa5aa2c5a7cadf9fbf5e862872f1975898f7f59ac6a9c5c657e1d
3
  size 116429720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f10be74176eb060bd976843a93ac7e7ba630f67dd00d1939e0531e47a55a91c
3
  size 59409829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72948fe88af67b5df1f5ad3434439eb5b82df69f3e8a4b36c2fa6085f9b7742
3
  size 59409829
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97f621c40c37c796d75663f728f7490ddcd9db068eaa82d92691bb9a37ff256f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1f495f35f59a847c17a244e5340abc91efe62268df4bc0dcf87d3c037ad3157
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a4ebd8bcb2ebd8257c25c43dba0da1138cd02eec81cc8ef5dc7f61d645393f
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 350,
3
- "best_metric": 0.1453624814748764,
4
- "best_model_checkpoint": "FLICC-Qwen3.5-9B/checkpoint-350",
5
- "epoch": 1.7335811648079305,
6
  "eval_steps": 25,
7
- "global_step": 350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -610,6 +610,92 @@
610
  "eval_samples_per_second": 8.821,
611
  "eval_steps_per_second": 2.243,
612
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
613
  }
614
  ],
615
  "logging_steps": 5,
@@ -629,7 +715,7 @@
629
  "attributes": {}
630
  }
631
  },
632
- "total_flos": 2.39143785403464e+17,
633
  "train_batch_size": 1,
634
  "trial_name": null,
635
  "trial_params": null
 
1
  {
2
+ "best_global_step": 400,
3
+ "best_metric": 0.1438552290201187,
4
+ "best_model_checkpoint": "FLICC-Qwen3.5-9B/checkpoint-400",
5
+ "epoch": 1.9814126394052045,
6
  "eval_steps": 25,
7
+ "global_step": 400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
610
  "eval_samples_per_second": 8.821,
611
  "eval_steps_per_second": 2.243,
612
  "step": 350
613
+ },
614
+ {
615
+ "epoch": 1.758364312267658,
616
+ "grad_norm": 0.09987305104732513,
617
+ "learning_rate": 7.598970361513051e-05,
618
+ "loss": 0.14147673845291137,
619
+ "step": 355
620
+ },
621
+ {
622
+ "epoch": 1.7831474597273855,
623
+ "grad_norm": 0.09593646973371506,
624
+ "learning_rate": 7.343987106191785e-05,
625
+ "loss": 0.14583654403686525,
626
+ "step": 360
627
+ },
628
+ {
629
+ "epoch": 1.8079306071871128,
630
+ "grad_norm": 0.08658026158809662,
631
+ "learning_rate": 7.090848663547574e-05,
632
+ "loss": 0.1391659379005432,
633
+ "step": 365
634
+ },
635
+ {
636
+ "epoch": 1.8327137546468402,
637
+ "grad_norm": 0.08900578320026398,
638
+ "learning_rate": 6.839730858407603e-05,
639
+ "loss": 0.1330711841583252,
640
+ "step": 370
641
+ },
642
+ {
643
+ "epoch": 1.8574969021065675,
644
+ "grad_norm": 0.0947270616889,
645
+ "learning_rate": 6.590808112105232e-05,
646
+ "loss": 0.14469583034515382,
647
+ "step": 375
648
+ },
649
+ {
650
+ "epoch": 1.8574969021065675,
651
+ "eval_loss": 0.1443570852279663,
652
+ "eval_runtime": 20.0669,
653
+ "eval_samples_per_second": 8.82,
654
+ "eval_steps_per_second": 2.242,
655
+ "step": 375
656
+ },
657
+ {
658
+ "epoch": 1.8822800495662948,
659
+ "grad_norm": 0.0893881618976593,
660
+ "learning_rate": 6.344253321330476e-05,
661
+ "loss": 0.13211302757263182,
662
+ "step": 380
663
+ },
664
+ {
665
+ "epoch": 1.9070631970260223,
666
+ "grad_norm": 0.09638750553131104,
667
+ "learning_rate": 6.100237738039484e-05,
668
+ "loss": 0.14780888557434083,
669
+ "step": 385
670
+ },
671
+ {
672
+ "epoch": 1.9318463444857497,
673
+ "grad_norm": 0.09466356039047241,
674
+ "learning_rate": 5.858930850506388e-05,
675
+ "loss": 0.1425341010093689,
676
+ "step": 390
677
+ },
678
+ {
679
+ "epoch": 1.9566294919454772,
680
+ "grad_norm": 0.09821353852748871,
681
+ "learning_rate": 5.620500265600206e-05,
682
+ "loss": 0.14998058080673218,
683
+ "step": 395
684
+ },
685
+ {
686
+ "epoch": 1.9814126394052045,
687
+ "grad_norm": 0.09322469681501389,
688
+ "learning_rate": 5.385111592368486e-05,
689
+ "loss": 0.14387768507003784,
690
+ "step": 400
691
+ },
692
+ {
693
+ "epoch": 1.9814126394052045,
694
+ "eval_loss": 0.1438552290201187,
695
+ "eval_runtime": 20.1578,
696
+ "eval_samples_per_second": 8.781,
697
+ "eval_steps_per_second": 2.232,
698
+ "step": 400
699
  }
700
  ],
701
  "logging_steps": 5,
 
715
  "attributes": {}
716
  }
717
  },
718
+ "total_flos": 2.733373262406168e+17,
719
  "train_batch_size": 1,
720
  "trial_name": null,
721
  "trial_params": null