Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106639657de8130d1e743113412b2f3457d62959f493921313086761b4423ed9
+oid sha256:7f75c51d9ca969a9d3cbb26206d8c3751152111b430ee8f78c774b9d99426948
 size 29034840

last-checkpoint/global_step2100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7aa16dee243b34185cf056e35e50a3678c95dbbbc5f9fd1110ebf3b61fbcbd
+size 43429616

last-checkpoint/global_step2100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126ebc8a1d461eb6971e0fe5db0deed7713d984269085c10b7479e2d2a342936
+size 43429616

last-checkpoint/global_step2100/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:e47df0dcaf62d79ebb54425a75af03024182dc6d216cfc938c6349ced6b15d46
+size 43429616

last-checkpoint/global_step2100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d234070e3b5451c249b57b9d521faa0b72267c278a1ff149317bed3f637f667
+size 43429616

last-checkpoint/global_step2100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeda14a8789d1fd88f7eebe00675f2572359184439f7c4c60b672fbdb030c435
+size 637299

last-checkpoint/global_step2100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec295f73f879f7574e82192c1ccc1329fd81288043991b95b358440fd8f90f7
+size 637171

last-checkpoint/global_step2100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abae9bad6bb987038dcd73f0e19d994e45cae40e20cd055d436706a0b5fe6064
+size 637171

last-checkpoint/global_step2100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bfaf44e1fb94ad73e3fc28120b85b71fc1b7b472586a7f8b29d56ad2e71f3c
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2050
+global_step2100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a695de1db3382235d3f8ae213672491aa2fdc3ba3be96403a089077ad3c2bf
+oid sha256:5d1ddd7e7b4dc44903837b0414e4659f8383cd8f16b41dd396d4eaf5b9829f79
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2025b170fa1d4693537c2d73f89a6495c58940d033678742a74810c0154a6a7
+oid sha256:eeddfb77fe4d3b495c4e08307767e08df90e96ef241c3eb80d5f75adec393e80
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0865c4d7d921b23a22c91c2f3b2c6cca03dae0eb27c43dee575c9602605c94d6
+oid sha256:9e6260196fabb00061b1f1c8de6288382570dc14d02d2aa308050ca858880a97
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4ec19d9df4417359523e8cc4d27875614c1021ebcc6391b27632aa7897b7ea
+oid sha256:ea023bc5b1def54e0c49389175c0fae812f5f764c502525ce775d993d5ab2c03
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc2918e410c169f1230e99c777b80638166c2769acb78c23195e4c48ca5b249
+oid sha256:41ca6ff868655333e43bb2ded3dfe8c66b7ed82fa8a98bace2e730c42bb9959b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4194311797618866,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-1800",
-  "epoch": 0.5279423126448622,
+  "epoch": 0.5408189544166881,
   "eval_steps": 50,
-  "global_step": 2050,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3656,11 +3656,100 @@
       "eval_steps_per_second": 0.786,
       "num_input_tokens_seen": 21527496,
       "step": 2050
+    },
+    {
+      "epoch": 0.5292299768220448,
+      "grad_norm": 2.354802898537749,
+      "learning_rate": 3.7019906676411446e-05,
+      "loss": 0.3937,
+      "num_input_tokens_seen": 21579816,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5305176409992274,
+      "grad_norm": 6.103564629763687,
+      "learning_rate": 3.678524023788735e-05,
+      "loss": 0.4039,
+      "num_input_tokens_seen": 21631776,
+      "step": 2060
+    },
+    {
+      "epoch": 0.53180530517641,
+      "grad_norm": 3.5285927755997655,
+      "learning_rate": 3.6550886330380665e-05,
+      "loss": 0.3501,
+      "num_input_tokens_seen": 21683608,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5330929693535926,
+      "grad_norm": 4.520457201010945,
+      "learning_rate": 3.631685049639586e-05,
+      "loss": 0.3334,
+      "num_input_tokens_seen": 21735672,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5343806335307751,
+      "grad_norm": 2.4877611413408554,
+      "learning_rate": 3.608313827091493e-05,
+      "loss": 0.3292,
+      "num_input_tokens_seen": 21787592,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5356682977079578,
+      "grad_norm": 1.8075536605690385,
+      "learning_rate": 3.5849755181266474e-05,
+      "loss": 0.3616,
+      "num_input_tokens_seen": 21840448,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5369559618851404,
+      "grad_norm": 10.058001239765861,
+      "learning_rate": 3.5616706746995026e-05,
+      "loss": 0.3082,
+      "num_input_tokens_seen": 21893096,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5382436260623229,
+      "grad_norm": 5.955966804633529,
+      "learning_rate": 3.538399847973036e-05,
+      "loss": 0.293,
+      "num_input_tokens_seen": 21945184,
+      "step": 2090
+    },
+    {
+      "epoch": 0.5395312902395055,
+      "grad_norm": 5.3172870269416554,
+      "learning_rate": 3.515163588305735e-05,
+      "loss": 0.3835,
+      "num_input_tokens_seen": 21998016,
+      "step": 2095
+    },
+    {
+      "epoch": 0.5408189544166881,
+      "grad_norm": 10.736456867600818,
+      "learning_rate": 3.491962445238569e-05,
+      "loss": 0.3983,
+      "num_input_tokens_seen": 22050376,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5408189544166881,
+      "eval_loss": 0.481829971075058,
+      "eval_runtime": 37.9835,
+      "eval_samples_per_second": 3.159,
+      "eval_steps_per_second": 0.79,
+      "num_input_tokens_seen": 22050376,
+      "step": 2100
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 21527496,
+  "num_input_tokens_seen": 22050376,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3675,7 +3764,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1420233038888960.0,
+  "total_flos": 1454769949900800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null