ben81828 commited on
Commit
4a57caf
·
verified ·
1 Parent(s): 05a525f

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:b99b8b6736c9551b7572fb855984029765a2e7449d447f3321e71447af523fc8
3
  size 18516456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c3ac7da08d446d1e9f20eb9182580b5c74675d4321465f97ce8b96cb262f6a
3
  size 18516456
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 sha256:06b7baa6b0ba0f6bb9a16a3e6e7af7c736fa58becfcedebbad6a5a26adbaa816
3
+ size 27700976
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:f29285bd4be2170ee090e0b4e56ac0d0f373f905c009ccd8f382b1b30b983e56
3
+ size 27700976
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 sha256:67ad8b8ce26006035c62a394fbff0283cc66176ddc5231f0d11be3f7c9f80e0e
3
+ size 27700976
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 sha256:29f824bd1152ffa7c4a7e1d3a922d06a80d7ec879c40ad10cd023a5036ecbadb
3
+ size 27700976
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 sha256:9b527e6e7b855a71ebc43d115f80ebf6fe7b12bad22106531d38884c2d484f09
3
+ size 411571
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:d7cf47e9360a06e0676c77bb957a4b1674967c3071885dc3ee3d25b0dcd7616d
3
+ size 411507
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 sha256:78fbf21fe2dd9b212623bc5d3f496995a60ba92d569ce24eb020c322e15bd1d2
3
+ size 411507
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:e3d39933836da5c4cb0f9a81b17ec3b4c96c47a924cf5c1c72126b3627124a51
3
+ size 411507
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 sha256:75979a52de119ed6c9cd6063ded2b7d6cb6c4870db4a05a6cc6a997d1fa9b653
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff02966f5e9ff1944d3a06acaf420bd5bf127f85a91f6b1b2b1649b32fc1fd58
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.8908902406692505,
3
  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-300",
4
- "epoch": 0.1545197012619109,
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": 0.885,
542
  "num_input_tokens_seen": 3508888,
543
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
544
  }
545
  ],
546
  "logging_steps": 5,
547
  "max_steps": 3400,
548
- "num_input_tokens_seen": 3508888,
549
  "num_train_epochs": 2,
550
  "save_steps": 50,
551
  "stateful_callbacks": {
@@ -560,7 +649,7 @@
560
  "attributes": {}
561
  }
562
  },
563
- "total_flos": 196997011734528.0,
564
  "train_batch_size": 1,
565
  "trial_name": null,
566
  "trial_params": null
 
1
  {
2
  "best_metric": 0.8908902406692505,
3
  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-300",
4
+ "epoch": 0.1802729848055627,
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": 0.885,
542
  "num_input_tokens_seen": 3508888,
543
  "step": 300
544
+ },
545
+ {
546
+ "epoch": 0.15709502961627608,
547
+ "grad_norm": 0.23111596622064604,
548
+ "learning_rate": 9.956959413129585e-05,
549
+ "loss": 0.9056,
550
+ "num_input_tokens_seen": 3567368,
551
+ "step": 305
552
+ },
553
+ {
554
+ "epoch": 0.15967035797064125,
555
+ "grad_norm": 0.3918406894807393,
556
+ "learning_rate": 9.953717199596598e-05,
557
+ "loss": 0.8982,
558
+ "num_input_tokens_seen": 3625848,
559
+ "step": 310
560
+ },
561
+ {
562
+ "epoch": 0.16224568632500644,
563
+ "grad_norm": 0.22081666860189372,
564
+ "learning_rate": 9.95035782992122e-05,
565
+ "loss": 0.8968,
566
+ "num_input_tokens_seen": 3684336,
567
+ "step": 315
568
+ },
569
+ {
570
+ "epoch": 0.16482101467937163,
571
+ "grad_norm": 0.18024383676398176,
572
+ "learning_rate": 9.94688138355304e-05,
573
+ "loss": 0.8975,
574
+ "num_input_tokens_seen": 3742800,
575
+ "step": 320
576
+ },
577
+ {
578
+ "epoch": 0.1673963430337368,
579
+ "grad_norm": 0.3866897344302321,
580
+ "learning_rate": 9.943287942710527e-05,
581
+ "loss": 0.9061,
582
+ "num_input_tokens_seen": 3801280,
583
+ "step": 325
584
+ },
585
+ {
586
+ "epoch": 0.16997167138810199,
587
+ "grad_norm": 0.4804151381712559,
588
+ "learning_rate": 9.939577592379088e-05,
589
+ "loss": 0.8948,
590
+ "num_input_tokens_seen": 3859792,
591
+ "step": 330
592
+ },
593
+ {
594
+ "epoch": 0.17254699974246718,
595
+ "grad_norm": 0.35878231707669056,
596
+ "learning_rate": 9.935750420309055e-05,
597
+ "loss": 0.9063,
598
+ "num_input_tokens_seen": 3918272,
599
+ "step": 335
600
+ },
601
+ {
602
+ "epoch": 0.17512232809683234,
603
+ "grad_norm": 0.8713957774909928,
604
+ "learning_rate": 9.931806517013612e-05,
605
+ "loss": 0.8952,
606
+ "num_input_tokens_seen": 3976760,
607
+ "step": 340
608
+ },
609
+ {
610
+ "epoch": 0.17769765645119753,
611
+ "grad_norm": 0.6671526212854116,
612
+ "learning_rate": 9.927745975766654e-05,
613
+ "loss": 0.9136,
614
+ "num_input_tokens_seen": 4035240,
615
+ "step": 345
616
+ },
617
+ {
618
+ "epoch": 0.1802729848055627,
619
+ "grad_norm": 0.28702679234521244,
620
+ "learning_rate": 9.923568892600578e-05,
621
+ "loss": 0.9075,
622
+ "num_input_tokens_seen": 4093688,
623
+ "step": 350
624
+ },
625
+ {
626
+ "epoch": 0.1802729848055627,
627
+ "eval_loss": 0.89204341173172,
628
+ "eval_runtime": 16.5819,
629
+ "eval_samples_per_second": 3.618,
630
+ "eval_steps_per_second": 0.905,
631
+ "num_input_tokens_seen": 4093688,
632
+ "step": 350
633
  }
634
  ],
635
  "logging_steps": 5,
636
  "max_steps": 3400,
637
+ "num_input_tokens_seen": 4093688,
638
  "num_train_epochs": 2,
639
  "save_steps": 50,
640
  "stateful_callbacks": {
 
649
  "attributes": {}
650
  }
651
  },
652
+ "total_flos": 229835067359232.0,
653
  "train_batch_size": 1,
654
  "trial_name": null,
655
  "trial_params": null