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
1739f10
·
verified ·
1 Parent(s): 698387a

Training in progress, step 350, 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:f5c10ceb40d1b0466cd78446012bffed9cbe47a52eddccc2650073dc745ec36f
3
  size 116429720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac681b65c9d84eecc8d7d3c32d8e83dcc02e2d1cf5a5e601ff7ebc9bf649acf
3
  size 116429720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c8bd760ddf393b48d2f2e80614e142f25cf7d99a2dc5e2e1cb68450c8eb0855
3
  size 59409829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f10be74176eb060bd976843a93ac7e7ba630f67dd00d1939e0531e47a55a91c
3
  size 59409829
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20ea3a198ff666cb4ace1c684b598fe43fc7c3c276b83efc553a1b787e12a304
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f621c40c37c796d75663f728f7490ddcd9db068eaa82d92691bb9a37ff256f
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f534cc43ce5cdd6293073329ed75bd7e61ac7711d3f86db54188c208424b3b5
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f495f35f59a847c17a244e5340abc91efe62268df4bc0dcf87d3c037ad3157
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 300,
3
- "best_metric": 0.14639338850975037,
4
- "best_model_checkpoint": "FLICC-Qwen3.5-9B/checkpoint-300",
5
- "epoch": 1.4857496902106568,
6
  "eval_steps": 25,
7
- "global_step": 300,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -524,6 +524,92 @@
524
  "eval_samples_per_second": 8.813,
525
  "eval_steps_per_second": 2.241,
526
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
527
  }
528
  ],
529
  "logging_steps": 5,
@@ -543,7 +629,7 @@
543
  "attributes": {}
544
  }
545
  },
546
- "total_flos": 2.049903533435544e+17,
547
  "train_batch_size": 1,
548
  "trial_name": null,
549
  "trial_params": null
 
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,
 
524
  "eval_samples_per_second": 8.813,
525
  "eval_steps_per_second": 2.241,
526
  "step": 300
527
+ },
528
+ {
529
+ "epoch": 1.5105328376703842,
530
+ "grad_norm": 0.0854591578245163,
531
+ "learning_rate": 0.00010210829522778111,
532
+ "loss": 0.1377027750015259,
533
+ "step": 305
534
+ },
535
+ {
536
+ "epoch": 1.5353159851301115,
537
+ "grad_norm": 0.10446186363697052,
538
+ "learning_rate": 9.947288957961e-05,
539
+ "loss": 0.14845360517501832,
540
+ "step": 310
541
+ },
542
+ {
543
+ "epoch": 1.5600991325898388,
544
+ "grad_norm": 0.09128095954656601,
545
+ "learning_rate": 9.683785005164411e-05,
546
+ "loss": 0.14711700677871703,
547
+ "step": 315
548
+ },
549
+ {
550
+ "epoch": 1.5848822800495663,
551
+ "grad_norm": 0.09243518859148026,
552
+ "learning_rate": 9.420500688888609e-05,
553
+ "loss": 0.13097442388534547,
554
+ "step": 320
555
+ },
556
+ {
557
+ "epoch": 1.6096654275092936,
558
+ "grad_norm": 0.0917942151427269,
559
+ "learning_rate": 9.157618881078772e-05,
560
+ "loss": 0.14905989170074463,
561
+ "step": 325
562
+ },
563
+ {
564
+ "epoch": 1.6096654275092936,
565
+ "eval_loss": 0.14630599319934845,
566
+ "eval_runtime": 20.0838,
567
+ "eval_samples_per_second": 8.813,
568
+ "eval_steps_per_second": 2.241,
569
+ "step": 325
570
+ },
571
+ {
572
+ "epoch": 1.6344485749690212,
573
+ "grad_norm": 0.09442687779664993,
574
+ "learning_rate": 8.895322174105881e-05,
575
+ "loss": 0.13518500328063965,
576
+ "step": 330
577
+ },
578
+ {
579
+ "epoch": 1.6592317224287485,
580
+ "grad_norm": 0.09125228226184845,
581
+ "learning_rate": 8.633792753941733e-05,
582
+ "loss": 0.14012304544448853,
583
+ "step": 335
584
+ },
585
+ {
586
+ "epoch": 1.6840148698884758,
587
+ "grad_norm": 0.0936419740319252,
588
+ "learning_rate": 8.373212273616282e-05,
589
+ "loss": 0.14055389165878296,
590
+ "step": 340
591
+ },
592
+ {
593
+ "epoch": 1.7087980173482031,
594
+ "grad_norm": 0.08522295951843262,
595
+ "learning_rate": 8.113761727045105e-05,
596
+ "loss": 0.14256774187088012,
597
+ "step": 345
598
+ },
599
+ {
600
+ "epoch": 1.7335811648079305,
601
+ "grad_norm": 0.09176695346832275,
602
+ "learning_rate": 7.855621323314736e-05,
603
+ "loss": 0.13572851419448853,
604
+ "step": 350
605
+ },
606
+ {
607
+ "epoch": 1.7335811648079305,
608
+ "eval_loss": 0.1453624814748764,
609
+ "eval_runtime": 20.065,
610
+ "eval_samples_per_second": 8.821,
611
+ "eval_steps_per_second": 2.243,
612
+ "step": 350
613
  }
614
  ],
615
  "logging_steps": 5,
 
629
  "attributes": {}
630
  }
631
  },
632
+ "total_flos": 2.39143785403464e+17,
633
  "train_batch_size": 1,
634
  "trial_name": null,
635
  "trial_params": null