Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a907044372c6e0d364bef10eddc568cb0dc263b2ee9cfe224809c3000cb0b54
+oid sha256:e47b9a2cfb5d827890098fe64e850aeaac9bcd5c19d855922f5746d06e17ed00
 size 18516456

last-checkpoint/global_step1100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8d76c18886c8ab16831ad77d620fbbcd417833f48486712dbde1107b5583f3
+size 27700976

last-checkpoint/global_step1100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4379c13db812765f56f289b4981653ea2ba9f9f6921812b5ea2a67950ba65f4
+size 27700976

last-checkpoint/global_step1100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aaae9b5f0c8b4dc6e09a322d7258de41c77452cb23081dee5c162cd3a238e77
+size 27700976

last-checkpoint/global_step1100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815b17e7f8a0ce04a26097aeee64e3e65fc4862240bcc1d28ee7f8d25a081e7b
+size 27700976

last-checkpoint/global_step1100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368fbb4161e1067a9968bb59d3601f3d9eb6f3bab5f932e4b49fc97de2b0a311
+size 411571

last-checkpoint/global_step1100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbd3965e4a65d712a26fcd12c1ae310db2461b1a58537a8a10514bce45c4ae1
+size 411507

last-checkpoint/global_step1100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31cee3c13358fcc7e8a75b09cf8f44b82125253654955e740e76e4111806633e
+size 411507

last-checkpoint/global_step1100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98867ee24d8986d407c6dd8e4d8117dd091c6272eecf26b96dcc5f96203ae387
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step1050
+global_step1100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67db742b8aa1744a8224bf2a1f79d89caff63b15f78a455d92bb666df82183ea
+oid sha256:9d9fea52fb92cc51e76feeb2b139ce35723c0cb651da383e4f7eec2606ed6c2a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f9acb7e6f8bbfb305c3601c71eb6189af24942fab5f99046412c03bb10c3eb
+oid sha256:1b5820ebfcc2e1cfe1ad2619a05ea9a484ff21635e13e386bf14abd302f2c0f7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:713783338342f7486f6f186abd03c5963a0d22368f403efb2bf903ed083d2b64
+oid sha256:eb8d96a68e732fca41980516622a50990bbd3ee989e72076a35c8608d9b4d136
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83aaec0b5b7d8a2da4577075066cf434ce6e9feb9327edbea6677a2e51d76466
+oid sha256:ce6f1db6d09f4d89a9b2bd8dc8eeb99f1fada2ec04376e23b5a7a13004994005
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccde9da0d23fd32800f01283cdb6c677def9ab43edb7232a9c4c4e9101a14cc0
+oid sha256:1d0c7456eafeee3179566bb381c9153771d7e0f21738d2398944d053915d0651
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8446129560470581,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1050",
-  "epoch": 0.5408189544166881,
+  "best_metric": 0.7743102312088013,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1100",
+  "epoch": 0.56657223796034,
   "eval_steps": 50,
-  "global_step": 1050,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1876,11 +1876,100 @@
       "eval_steps_per_second": 0.935,
       "num_input_tokens_seen": 12281072,
       "step": 1050
+    },
+    {
+      "epoch": 0.5433942827710533,
+      "grad_norm": 0.5518554447099218,
+      "learning_rate": 8.259242386389973e-05,
+      "loss": 0.8602,
+      "num_input_tokens_seen": 12339544,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5459696111254185,
+      "grad_norm": 0.7300911438509382,
+      "learning_rate": 8.240764101059912e-05,
+      "loss": 0.8615,
+      "num_input_tokens_seen": 12397992,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5485449394797837,
+      "grad_norm": 0.7364983085887583,
+      "learning_rate": 8.222209171180883e-05,
+      "loss": 0.8732,
+      "num_input_tokens_seen": 12456480,
+      "step": 1065
+    },
+    {
+      "epoch": 0.5511202678341488,
+      "grad_norm": 0.4840408774949972,
+      "learning_rate": 8.203578035579715e-05,
+      "loss": 0.8691,
+      "num_input_tokens_seen": 12515000,
+      "step": 1070
+    },
+    {
+      "epoch": 0.553695596188514,
+      "grad_norm": 0.516278691776577,
+      "learning_rate": 8.184871134885513e-05,
+      "loss": 0.8544,
+      "num_input_tokens_seen": 12573504,
+      "step": 1075
+    },
+    {
+      "epoch": 0.5562709245428792,
+      "grad_norm": 0.8626943002609527,
+      "learning_rate": 8.166088911519235e-05,
+      "loss": 0.8501,
+      "num_input_tokens_seen": 12632008,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5588462528972444,
+      "grad_norm": 0.7409465187036862,
+      "learning_rate": 8.147231809683236e-05,
+      "loss": 0.8646,
+      "num_input_tokens_seen": 12690520,
+      "step": 1085
+    },
+    {
+      "epoch": 0.5614215812516096,
+      "grad_norm": 0.5736639247313171,
+      "learning_rate": 8.128300275350756e-05,
+      "loss": 0.8327,
+      "num_input_tokens_seen": 12749032,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5639969096059748,
+      "grad_norm": 0.7720514157947642,
+      "learning_rate": 8.109294756255375e-05,
+      "loss": 0.8218,
+      "num_input_tokens_seen": 12807504,
+      "step": 1095
+    },
+    {
+      "epoch": 0.56657223796034,
+      "grad_norm": 0.9129011996506371,
+      "learning_rate": 8.090215701880419e-05,
+      "loss": 0.8427,
+      "num_input_tokens_seen": 12865992,
+      "step": 1100
+    },
+    {
+      "epoch": 0.56657223796034,
+      "eval_loss": 0.7743102312088013,
+      "eval_runtime": 16.1034,
+      "eval_samples_per_second": 3.726,
+      "eval_steps_per_second": 0.931,
+      "num_input_tokens_seen": 12865992,
+      "step": 1100
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 12281072,
+  "num_input_tokens_seen": 12865992,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1895,7 +1984,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 689597635100672.0,
+  "total_flos": 722443216093184.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null