Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a040fdacc28b9de2977636cd1c1956bffb7f97df44e5bd2640662f6a98fa674b
+oid sha256:2cc88a9133bd30e9f761aeca11737097aa2bc75e291ca7a8f1b1b21cc4ee3a5a
 size 29034840

last-checkpoint/global_step700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d985b6f15413cc381cd06576e8a189c829649d7182bc4c870a1ece58675f343
+size 43429616

last-checkpoint/global_step700/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:e1659d3855a9ef0e3b05343b8679ed9b6213f31c669db88b09899390e3b0ee20
+size 43429616

last-checkpoint/global_step700/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:b9b7c38ead9e590ae0766ffa9f93ce15c90caaf9de2544f3e12b04522c5c187c
+size 43429616

last-checkpoint/global_step700/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:c1a5a1f7d2bc3c5fb7d4df15ae88afc8579c8af634c0897a4d2f635ceeeb9459
+size 43429616

last-checkpoint/global_step700/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1016e4296788968087a2a2e95f3a62ee2c6085b5340c3e92171dae571481ea55
+size 637299

last-checkpoint/global_step700/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb87f12b7ce572b38ad895ddc218de834da4bf60ec37d070e1017300431fe756
+size 637171

last-checkpoint/global_step700/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d458531685f08f79fecf5600b5b32a91ce3e7e9e5c6bf39ed77dc64a6777d6
+size 637171

last-checkpoint/global_step700/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6548dde312f71fd6a7a282d97e0df54d5ebeb16b695ea5d8f6c774bbc1ca3bb
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step650
+global_step700

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8044e4c53158c210a17648ba8f2dc2d25a25bbfc55f686015542618eb652a33e
+oid sha256:e7d74de51245105e1fbf57a6707ef3538b353952485508f6e2f8f74dc5d479d4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd85d7fa425e7888c973f1c2985ac15ca21b5e6171fe140a401c2bc75ca46ff
+oid sha256:0617c9eb6cf7df57b2e0bb53cfe17c05f0910de56fe5b14427fe39ab54a44782
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7915667371a58f1598639e0d1c20a0c59c783c14580cd040a6631eb4ea2311e
+oid sha256:ed68a365057022897d9645ee60902a77102f43215dcdf2ddd5d3842b6a8446d8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dd78929ad7f0fbf37fdb1284e8edf0424350f6e6ce1cd5a3ee78979af3d3cb
+oid sha256:63ebaa0c302cadbdfcd9f8ee2289e35ecf9c9fc8c9968fc0c05f100dac20c6b9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd94ecf5c982ee0e060d3e07a575ce03dc3b0f289b5e32a1f65d3b6366a8a0e
+oid sha256:9089a2e73aa73e2c09752311bdfa67c1ed286ab83bb4bc61dbf851e8193bb593
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5542036890983582,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-650",
-  "epoch": 0.1673963430337368,
+  "best_metric": 0.5440100431442261,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-700",
+  "epoch": 0.1802729848055627,
   "eval_steps": 50,
-  "global_step": 650,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1164,11 +1164,100 @@
       "eval_steps_per_second": 0.435,
       "num_input_tokens_seen": 6824008,
       "step": 650
+    },
+    {
+      "epoch": 0.1686840072109194,
+      "grad_norm": 3.428410481447858,
+      "learning_rate": 9.453928183013385e-05,
+      "loss": 0.5344,
+      "num_input_tokens_seen": 6875432,
+      "step": 655
+    },
+    {
+      "epoch": 0.16997167138810199,
+      "grad_norm": 2.9137495299009846,
+      "learning_rate": 9.442825912005202e-05,
+      "loss": 0.56,
+      "num_input_tokens_seen": 6927768,
+      "step": 660
+    },
+    {
+      "epoch": 0.17125933556528458,
+      "grad_norm": 4.2956604210715925,
+      "learning_rate": 9.431618567508933e-05,
+      "loss": 0.5701,
+      "num_input_tokens_seen": 6980544,
+      "step": 665
+    },
+    {
+      "epoch": 0.17254699974246718,
+      "grad_norm": 4.3977584083656405,
+      "learning_rate": 9.420306414579925e-05,
+      "loss": 0.5604,
+      "num_input_tokens_seen": 7032584,
+      "step": 670
+    },
+    {
+      "epoch": 0.17383466391964975,
+      "grad_norm": 4.48381006313936,
+      "learning_rate": 9.408889720752266e-05,
+      "loss": 0.5763,
+      "num_input_tokens_seen": 7085048,
+      "step": 675
+    },
+    {
+      "epoch": 0.17512232809683234,
+      "grad_norm": 2.189534287393346,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.5962,
+      "num_input_tokens_seen": 7137952,
+      "step": 680
+    },
+    {
+      "epoch": 0.17640999227401494,
+      "grad_norm": 3.34591241093722,
+      "learning_rate": 9.385743792892982e-05,
+      "loss": 0.5935,
+      "num_input_tokens_seen": 7190584,
+      "step": 685
+    },
+    {
+      "epoch": 0.17769765645119753,
+      "grad_norm": 2.7509902524242507,
+      "learning_rate": 9.374015106265968e-05,
+      "loss": 0.5267,
+      "num_input_tokens_seen": 7243440,
+      "step": 690
+    },
+    {
+      "epoch": 0.17898532062838013,
+      "grad_norm": 2.322454948468365,
+      "learning_rate": 9.362182973536569e-05,
+      "loss": 0.5351,
+      "num_input_tokens_seen": 7295568,
+      "step": 695
+    },
+    {
+      "epoch": 0.1802729848055627,
+      "grad_norm": 3.4615171229405046,
+      "learning_rate": 9.35024767453647e-05,
+      "loss": 0.5014,
+      "num_input_tokens_seen": 7347040,
+      "step": 700
+    },
+    {
+      "epoch": 0.1802729848055627,
+      "eval_loss": 0.5440100431442261,
+      "eval_runtime": 39.1181,
+      "eval_samples_per_second": 3.068,
+      "eval_steps_per_second": 0.767,
+      "num_input_tokens_seen": 7347040,
+      "step": 700
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 6824008,
+  "num_input_tokens_seen": 7347040,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1183,7 +1272,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 450087645085696.0,
+  "total_flos": 484589024051200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null