Training in progress, step 2850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656b339f848f4a5e39a2f325df5573bc98a1ce1de9df8113a07cd8eeae54367e
+oid sha256:01a330ed632b021642148062b09d22bb079b73a39c22d87b4a866893ac04d712
 size 29034840

last-checkpoint/global_step2850/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fe4a2c735a04b54f2ad7e515f79d5744cbe9f8cd188ad98ce2cec5eb4279a7
+size 43429616

last-checkpoint/global_step2850/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8baf9fa8afcf57a447a5eba2eb736a87d1c5a4a46f8bf569112a16ee452f4a68
+size 43429616

last-checkpoint/global_step2850/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e06a2fa0989959de6ce4c155e0fc226e7f4cfa015e32b83a6fc4007d3246f3
+size 43429616

last-checkpoint/global_step2850/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14341d8679cc02bf357ae30fd671c5bafae090d513ab2cb8f5e6db57f60be75f
+size 43429616

last-checkpoint/global_step2850/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6812b284fbf3417e77fd86a27d65a3311729d5aa0ad1760be1c080039b6a22c
+size 637299

last-checkpoint/global_step2850/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a961275b937b710afe74a7a3b9fd6a401f9924641e566c39654df096230565
+size 637171

last-checkpoint/global_step2850/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911e755a27628af9831ca453ecfd7f1f364d53b6ef98c992957c2fffb659a58c
+size 637171

last-checkpoint/global_step2850/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20554ce78011d819cef737623a9e66ee3291f99e51e1ff343f472c5d5f41a0bb
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2800
+global_step2850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49db5a9fd0c84d580c671e52905ebeffc155b36537e76ff966d2e82906708999
+oid sha256:ff8dba2341c0517760edfde50521977f02a5bd982ffd3bc03de6109439c4f478
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ca224562d8d97aaa131b3516288bb99f68d7dcf62170494326662bda0bb206
+oid sha256:d2bf831df9fbade9ac2a8db79798bc2a7b1afb85a78a6e463ec7a7db4acc0f8e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e86a11c89dba78d60e1b2a1855a651b90a5a22ef131ce65d26af83668c154e
+oid sha256:8602ff0a0fa366d46b61c0ef2b23ce468387898cf2bc1027e5450de73ddf647f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd63019c923e9692431619aced46b91aaf3fd22e1c22ec0a64347f2fe635a0e
+oid sha256:4bb51d675cf23603b1b765cd645f53d6b66ddb104d56d48674e9c798e086f696
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a7c605cf80a46d2e0c661d5469c16671b681f268e3ecd5d1d64188653910db
+oid sha256:28cb8f1d536b1fc196e353ec37fd07d574fab0a464ddd8b31c73c59dcab3c03b
 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": 0.7210919392222508,
+  "epoch": 0.7339685809940767,
   "eval_steps": 50,
-  "global_step": 2800,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4991,11 +4991,100 @@
       "eval_steps_per_second": 0.789,
       "num_input_tokens_seen": 29402040,
       "step": 2800
+    },
+    {
+      "epoch": 0.7223796033994334,
+      "grad_norm": 3.561696884073749,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.2538,
+      "num_input_tokens_seen": 29455456,
+      "step": 2805
+    },
+    {
+      "epoch": 0.723667267576616,
+      "grad_norm": 2.941091025150912,
+      "learning_rate": 8.009177137203794e-06,
+      "loss": 0.3374,
+      "num_input_tokens_seen": 29507136,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7249549317537987,
+      "grad_norm": 1.7626408698187983,
+      "learning_rate": 7.877671276687898e-06,
+      "loss": 0.3303,
+      "num_input_tokens_seen": 29558760,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7262425959309812,
+      "grad_norm": 2.788131053787238,
+      "learning_rate": 7.747161615458902e-06,
+      "loss": 0.2834,
+      "num_input_tokens_seen": 29612000,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7275302601081638,
+      "grad_norm": 3.8899073323572444,
+      "learning_rate": 7.617651240089546e-06,
+      "loss": 0.2746,
+      "num_input_tokens_seen": 29664472,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7288179242853464,
+      "grad_norm": 1.3611659955678468,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 0.315,
+      "num_input_tokens_seen": 29716440,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7301055884625289,
+      "grad_norm": 5.373259186650034,
+      "learning_rate": 7.361640574981937e-06,
+      "loss": 0.2877,
+      "num_input_tokens_seen": 29769248,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7313932526397116,
+      "grad_norm": 2.796854999712465,
+      "learning_rate": 7.2351463399336735e-06,
+      "loss": 0.2953,
+      "num_input_tokens_seen": 29821968,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7326809168168942,
+      "grad_norm": 6.039730307609144,
+      "learning_rate": 7.109663499981834e-06,
+      "loss": 0.2709,
+      "num_input_tokens_seen": 29875104,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7339685809940767,
+      "grad_norm": 4.572150266141393,
+      "learning_rate": 6.985195022814067e-06,
+      "loss": 0.3024,
+      "num_input_tokens_seen": 29928032,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7339685809940767,
+      "eval_loss": 0.47043517231941223,
+      "eval_runtime": 37.451,
+      "eval_samples_per_second": 3.204,
+      "eval_steps_per_second": 0.801,
+      "num_input_tokens_seen": 29928032,
+      "step": 2850
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 29402040,
+  "num_input_tokens_seen": 29928032,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -5010,7 +5099,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1939869403709440.0,
+  "total_flos": 1974549322924032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null