ben81828 commited on
Commit
47fd6e5
·
verified ·
1 Parent(s): 4eaf721

Training in progress, step 350, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3488ed0fb4ad1bfe3deeb7b60e2d4b46bb9460eb8c5462016334f7b9afa958fc
3
  size 29034840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c7ee3fff01ccc34d52689d6b0a0f69c7bba11fef8f035de5c213e712b0aa8c
3
  size 29034840
last-checkpoint/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:115d9d5574d6f192d13d8453c99a84436a87338747f085b6c9ce2f346ba98f8e
3
+ size 43429616
last-checkpoint/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b0693c53df01e468a5c6cb16794ea7eb144c2fa3cf7cd69cf1251079be8bb0
3
+ size 43429616
last-checkpoint/global_step350/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20ccd70aaa356245d10521130ce71e1995ee63ae841370c1cd21f5a235f2b67
3
+ size 43429616
last-checkpoint/global_step350/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f10e5e3a3076a1471f11f1185ab256a7cf5a3ec521c2057f1fe77a36468262e
3
+ size 43429616
last-checkpoint/global_step350/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e380c94b13ff3da8d3edcefaf29989368f65a3c889035e4764bb6f0691e904ae
3
+ size 637299
last-checkpoint/global_step350/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:822c816c04ed580c6ac0cb6f5c7e9af964d660feb89a273c0559ef761e4f419a
3
+ size 637171
last-checkpoint/global_step350/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2f0cd1cbef37cff971a6b56d3f4c089792956c12ae34538f2ac26d7b48defe
3
+ size 637171
last-checkpoint/global_step350/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6ddd247edd9703e5de301433d1a0344a31e0ef35f5cb594af9acdf11917280
3
+ size 637171
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step300
 
1
+ global_step350
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef002048764051a71fb00f8f978e9ec32b780dc850bdb059af362cc56494234b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee97cd82dba4d425fdd8dfdb88d4a43d0d4b1979b5c81ab4a24914fb00d4f332
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37194a6d48612e1a46a2d5d317ead97c70d9fc4569b0118fcd5f84c3dc9daa5a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91dad95440fb85dc4a31745642117165c1a72173b2e389679ea8c0b2b6fcd7e2
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17c179483659a784aa1ace2427daff48c556a6bcc3c330e6f3274e4dc95e4b49
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98698326b023c2af02c94f18726ce52c7f7a6fe290734dd7edbe99bc807fcfa0
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b56857c9b117629f35af2c3d64f522d33a9d8aa94faa81ec6956380a895118c4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708e7c6b5bf8a327e688779ebc08830ce249928bcb1ff5c82b1b1d0bf6d2660b
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df871e59adfbbd58ab4f29f7fa664061939f1a6feaaa1cb06019e33c27436071
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d599041d87ad45b8804f766f89f2a165a0fb27c19b2b7170a0970b76e6a885f5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8601770997047424,
3
- "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily/lora/sft/checkpoint-300",
4
- "epoch": 0.8333333333333334,
5
  "eval_steps": 50,
6
- "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -541,11 +541,100 @@
541
  "eval_steps_per_second": 0.788,
542
  "num_input_tokens_seen": 4678776,
543
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
544
  }
545
  ],
546
  "logging_steps": 5,
547
  "max_steps": 720,
548
- "num_input_tokens_seen": 4678776,
549
  "num_train_epochs": 2,
550
  "save_steps": 50,
551
  "stateful_callbacks": {
@@ -560,7 +649,7 @@
560
  "attributes": {}
561
  }
562
  },
563
- "total_flos": 316329976922112.0,
564
  "train_batch_size": 1,
565
  "trial_name": null,
566
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.830344021320343,
3
+ "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily/lora/sft/checkpoint-350",
4
+ "epoch": 0.9722222222222222,
5
  "eval_steps": 50,
6
+ "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
541
  "eval_steps_per_second": 0.788,
542
  "num_input_tokens_seen": 4678776,
543
  "step": 300
544
+ },
545
+ {
546
+ "epoch": 0.8472222222222222,
547
+ "grad_norm": 3.824074793385472,
548
+ "learning_rate": 7.135035909907358e-05,
549
+ "loss": 0.8838,
550
+ "num_input_tokens_seen": 4756744,
551
+ "step": 305
552
+ },
553
+ {
554
+ "epoch": 0.8611111111111112,
555
+ "grad_norm": 1.8566349178683659,
556
+ "learning_rate": 7.024821410163368e-05,
557
+ "loss": 0.8843,
558
+ "num_input_tokens_seen": 4834648,
559
+ "step": 310
560
+ },
561
+ {
562
+ "epoch": 0.875,
563
+ "grad_norm": 1.8800583465943999,
564
+ "learning_rate": 6.91341716182545e-05,
565
+ "loss": 0.8637,
566
+ "num_input_tokens_seen": 4912632,
567
+ "step": 315
568
+ },
569
+ {
570
+ "epoch": 0.8888888888888888,
571
+ "grad_norm": 2.339387141795884,
572
+ "learning_rate": 6.800888624023553e-05,
573
+ "loss": 0.8714,
574
+ "num_input_tokens_seen": 4990632,
575
+ "step": 320
576
+ },
577
+ {
578
+ "epoch": 0.9027777777777778,
579
+ "grad_norm": 1.650009361432866,
580
+ "learning_rate": 6.687301916499871e-05,
581
+ "loss": 0.8581,
582
+ "num_input_tokens_seen": 5068632,
583
+ "step": 325
584
+ },
585
+ {
586
+ "epoch": 0.9166666666666666,
587
+ "grad_norm": 2.8384085546182294,
588
+ "learning_rate": 6.572723780758069e-05,
589
+ "loss": 0.8655,
590
+ "num_input_tokens_seen": 5146648,
591
+ "step": 330
592
+ },
593
+ {
594
+ "epoch": 0.9305555555555556,
595
+ "grad_norm": 6.227674605881871,
596
+ "learning_rate": 6.457221540847176e-05,
597
+ "loss": 0.8721,
598
+ "num_input_tokens_seen": 5224624,
599
+ "step": 335
600
+ },
601
+ {
602
+ "epoch": 0.9444444444444444,
603
+ "grad_norm": 3.498647817420285,
604
+ "learning_rate": 6.340863063803188e-05,
605
+ "loss": 0.8563,
606
+ "num_input_tokens_seen": 5302600,
607
+ "step": 340
608
+ },
609
+ {
610
+ "epoch": 0.9583333333333334,
611
+ "grad_norm": 4.211929847119524,
612
+ "learning_rate": 6.22371671977162e-05,
613
+ "loss": 0.8634,
614
+ "num_input_tokens_seen": 5380600,
615
+ "step": 345
616
+ },
617
+ {
618
+ "epoch": 0.9722222222222222,
619
+ "grad_norm": 3.696407127177043,
620
+ "learning_rate": 6.105851341834439e-05,
621
+ "loss": 0.8526,
622
+ "num_input_tokens_seen": 5458520,
623
+ "step": 350
624
+ },
625
+ {
626
+ "epoch": 0.9722222222222222,
627
+ "eval_loss": 0.830344021320343,
628
+ "eval_runtime": 46.3813,
629
+ "eval_samples_per_second": 3.148,
630
+ "eval_steps_per_second": 0.798,
631
+ "num_input_tokens_seen": 5458520,
632
+ "step": 350
633
  }
634
  ],
635
  "logging_steps": 5,
636
  "max_steps": 720,
637
+ "num_input_tokens_seen": 5458520,
638
  "num_train_epochs": 2,
639
  "save_steps": 50,
640
  "stateful_callbacks": {
 
649
  "attributes": {}
650
  }
651
  },
652
+ "total_flos": 369059492790272.0,
653
  "train_batch_size": 1,
654
  "trial_name": null,
655
  "trial_params": null