Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c0919a08fffa1587acbe31835d5a8f8669c94a21edd38c6366ed4e1822b6b15
+oid sha256:006fbddb28ccd3f24fce77178564cf32b9a0d6002aa0e149d2a632f6bc384cad
 size 29034840

last-checkpoint/global_step3100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459ce3ca820ba1c67329dd8fd2836b0a7285fc19f9ba64456fa90126662cbcfb
+size 43429616

last-checkpoint/global_step3100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695d20e01e322e423f3b86d3e1d2ee57cc166f9666f03049c87386da42551953
+size 43429616

last-checkpoint/global_step3100/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:cf081ec30b6ae77d1be0a545e0b545f01df47721153713c632ad4ebc0a3966d5
+size 43429616

last-checkpoint/global_step3100/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:bfcee3947b0e659ea58510a73a6c88b19f179fca4ba79b51a6cd4597d9505b40
+size 43429616

last-checkpoint/global_step3100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:769a527c4e6f510809f5b2b13928892b9b7024384bc00772661a2cccde5e4fa4
+size 637299

last-checkpoint/global_step3100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05589d1f79cab339f6f64907a5dbf1bd44b1e8d65a9a1f019d2ec8e2b3cd2a6
+size 637171

last-checkpoint/global_step3100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28ad7a834b66d1ee2fe12359362f2fdb764eaf9b451b44e1d6df40abfd8079c
+size 637171

last-checkpoint/global_step3100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226452aea7fb29b0cd6c8e9e340122bb65353ec4a0df00019fe9614dc4195bc6
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step3050
+global_step3100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f30f7f3c3620ccd30020e1ea4b81d1a56ee511b742c91370577d55399c14412
+oid sha256:381f090b12cbb3fcce976bd2e72d07a7786154c2848cc881d75715648e7c4dc2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440cc1f8e138e1a90606722bd350460b4460991a2f3671f46f880f5743522dca
+oid sha256:4321dc1beb6c245d4a16a8fb2bed2ce2a40d89e5a9c611c4572f63a09523846c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78d5df466f5b34e85649b90825d4b168464f6d49c668313415473184409b799
+oid sha256:5b79020117e301cd96518c9d1e3eb43a609bc85799f14bac63d9c572fc04cb89
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8be6df9e66c8bba407df289d2aa6b4422668727a1e2419037de032213393a4
+oid sha256:5429623c7323b4a820ea3d76194bc456c2affeeb1f3af8978aec5aee11b2d1ef
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65132092aa084390575a45bea99d0dcabb8005a8fae760edf38c6251571f2afa
+oid sha256:d44cc93262eaa36be09e5c05cb4a41bcbfdd9c2c86797c6c680d23dd8657e6ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4145541489124298,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-2350",
-  "epoch": 0.7854751480813804,
+  "epoch": 0.7983517898532063,
   "eval_steps": 50,
-  "global_step": 3050,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5436,11 +5436,100 @@
       "eval_steps_per_second": 0.789,
       "num_input_tokens_seen": 32030016,
       "step": 3050
+    },
+    {
+      "epoch": 0.7867628122585629,
+      "grad_norm": 1.6401540308745686,
+      "learning_rate": 2.7886498764184588e-06,
+      "loss": 0.3247,
+      "num_input_tokens_seen": 32082256,
+      "step": 3055
+    },
+    {
+      "epoch": 0.7880504764357456,
+      "grad_norm": 2.305310160123287,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.2895,
+      "num_input_tokens_seen": 32134592,
+      "step": 3060
+    },
+    {
+      "epoch": 0.7893381406129282,
+      "grad_norm": 7.79411199672483,
+      "learning_rate": 2.6307443893812843e-06,
+      "loss": 0.294,
+      "num_input_tokens_seen": 32187064,
+      "step": 3065
+    },
+    {
+      "epoch": 0.7906258047901107,
+      "grad_norm": 7.8803119684251355,
+      "learning_rate": 2.5534711536759404e-06,
+      "loss": 0.3205,
+      "num_input_tokens_seen": 32238944,
+      "step": 3070
+    },
+    {
+      "epoch": 0.7919134689672933,
+      "grad_norm": 1.651743530845747,
+      "learning_rate": 2.4773200353756798e-06,
+      "loss": 0.2726,
+      "num_input_tokens_seen": 32291528,
+      "step": 3075
+    },
+    {
+      "epoch": 0.7932011331444759,
+      "grad_norm": 5.642476416103777,
+      "learning_rate": 2.4022928354656473e-06,
+      "loss": 0.3012,
+      "num_input_tokens_seen": 32343600,
+      "step": 3080
+    },
+    {
+      "epoch": 0.7944887973216586,
+      "grad_norm": 3.639368693424175,
+      "learning_rate": 2.3283913283502044e-06,
+      "loss": 0.2712,
+      "num_input_tokens_seen": 32396128,
+      "step": 3085
+    },
+    {
+      "epoch": 0.7957764614988411,
+      "grad_norm": 6.532937861900995,
+      "learning_rate": 2.2556172618108997e-06,
+      "loss": 0.3342,
+      "num_input_tokens_seen": 32448624,
+      "step": 3090
+    },
+    {
+      "epoch": 0.7970641256760237,
+      "grad_norm": 1.4088613654984938,
+      "learning_rate": 2.183972356965125e-06,
+      "loss": 0.3132,
+      "num_input_tokens_seen": 32500664,
+      "step": 3095
+    },
+    {
+      "epoch": 0.7983517898532063,
+      "grad_norm": 3.205147557757995,
+      "learning_rate": 2.113458308225458e-06,
+      "loss": 0.2856,
+      "num_input_tokens_seen": 32553288,
+      "step": 3100
+    },
+    {
+      "epoch": 0.7983517898532063,
+      "eval_loss": 0.4740166962146759,
+      "eval_runtime": 37.5378,
+      "eval_samples_per_second": 3.197,
+      "eval_steps_per_second": 0.799,
+      "num_input_tokens_seen": 32553288,
+      "step": 3100
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 32030016,
+  "num_input_tokens_seen": 32553288,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -5455,7 +5544,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2113197121732608.0,
+  "total_flos": 2147751457718272.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null