Training in progress, step 850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b3ad121c980fed4c4f6e332f8d74b8c34f8719af7ea7fe02d0238882dfb6ca
+oid sha256:c194e4011ebc3d53bf21924236aa69f02cd3e886bdcc096049ceabfa8e037964
 size 29034840

last-checkpoint/global_step850/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34100fa86cad3e9f6e41fe4c2d38f267a77fc9e2dd8b5fd799f7787b501bfe3e
+size 43429616

last-checkpoint/global_step850/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1e44c14b7c791b760d7023aba18ee7a5b74a7d72087679039616a97ca38679
+size 43429616

last-checkpoint/global_step850/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:cb42580270678586b4015104dd0b1978995640e143c570f30e0d2d55fddaf5d4
+size 43429616

last-checkpoint/global_step850/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:efea34847e37bfe5bb8c884f5166d8cb467598a44096ccdc7a2d925a98b3a749
+size 43429616

last-checkpoint/global_step850/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18337b921f0aba380566f71c4857b67981734dc7975b4ed43e57711a412ef28
+size 637299

last-checkpoint/global_step850/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d144742df08d3730450d7fb36709b9a81b06278b4025a5f5b7cf8306696ee8ed
+size 637171

last-checkpoint/global_step850/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1e27c63d553ea81d8a5f4f57f82e6fd2dab396822dedba339d93c3e67b54fd
+size 637171

last-checkpoint/global_step850/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4777d80a9e8c2d0c23709b7630c4e2ffc82a5624bbdac8e3a2d838a612e80caa
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step800
+global_step850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f003069486a57c6ac033f30cf4c4213eb6b7d659bab68a5a50fdb8da7c4118
+oid sha256:36c9044354f826de248840acaaec171f816609c147a664089731a0570deef948
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a016ef89b4392d083b2c15a7cf06a39bc61a759f648cf6dc03f1c32b89a526aa
+oid sha256:54f4c4013326db4e7267b656aaf72b86570f8aeee91ad39242a416cf8b963191
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b56fe0893036dc052d18d90feba4328b90ea71561942150b07406ac3d7a700e
+oid sha256:43e910793831957d8685c316138c33eef8867edf60052477dc9ad6ec0c6da901
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c203d12c2c308dab785ed672c9ca27fb6a2f72acd1e1552d1516c7b0006013
+oid sha256:7cfd0d71ef5a6c58d9f1d46851f4b1e699ca8a50ab3223cfb39668895cffeef2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d85b710a5709549c0b4daddcc052f2ed242a5d916ac9ca030c805e7ff501c88
+oid sha256:3e24eaa8963cd872c048c2c655789d678b8c3fcd1c77ca0d663feee5857d2e34
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5219093561172485,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-800",
-  "epoch": 0.20602626834921453,
+  "epoch": 0.21890291012104043,
   "eval_steps": 50,
-  "global_step": 800,
+  "global_step": 850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1431,11 +1431,100 @@
       "eval_steps_per_second": 0.755,
       "num_input_tokens_seen": 8393696,
       "step": 800
+    },
+    {
+      "epoch": 0.20731393252639713,
+      "grad_norm": 4.254130676908817,
+      "learning_rate": 9.076296203830579e-05,
+      "loss": 0.5449,
+      "num_input_tokens_seen": 8446496,
+      "step": 805
+    },
+    {
+      "epoch": 0.2086015967035797,
+      "grad_norm": 5.6525741285524145,
+      "learning_rate": 9.062166909283062e-05,
+      "loss": 0.5625,
+      "num_input_tokens_seen": 8499544,
+      "step": 810
+    },
+    {
+      "epoch": 0.2098892608807623,
+      "grad_norm": 3.8041246225911345,
+      "learning_rate": 9.047941543889014e-05,
+      "loss": 0.5564,
+      "num_input_tokens_seen": 8552568,
+      "step": 815
+    },
+    {
+      "epoch": 0.2111769250579449,
+      "grad_norm": 3.803732280546421,
+      "learning_rate": 9.033620444080428e-05,
+      "loss": 0.5487,
+      "num_input_tokens_seen": 8605560,
+      "step": 820
+    },
+    {
+      "epoch": 0.21246458923512748,
+      "grad_norm": 2.8518948364927925,
+      "learning_rate": 9.019203948553422e-05,
+      "loss": 0.5719,
+      "num_input_tokens_seen": 8657704,
+      "step": 825
+    },
+    {
+      "epoch": 0.21375225341231008,
+      "grad_norm": 3.939376115862177,
+      "learning_rate": 9.004692398260244e-05,
+      "loss": 0.5235,
+      "num_input_tokens_seen": 8711088,
+      "step": 830
+    },
+    {
+      "epoch": 0.21503991758949267,
+      "grad_norm": 6.635912128499916,
+      "learning_rate": 8.9900861364012e-05,
+      "loss": 0.5566,
+      "num_input_tokens_seen": 8763712,
+      "step": 835
+    },
+    {
+      "epoch": 0.21632758176667524,
+      "grad_norm": 3.7547407090496687,
+      "learning_rate": 8.975385508416532e-05,
+      "loss": 0.482,
+      "num_input_tokens_seen": 8815760,
+      "step": 840
+    },
+    {
+      "epoch": 0.21761524594385784,
+      "grad_norm": 4.093006904445721,
+      "learning_rate": 8.960590861978265e-05,
+      "loss": 0.5046,
+      "num_input_tokens_seen": 8867720,
+      "step": 845
+    },
+    {
+      "epoch": 0.21890291012104043,
+      "grad_norm": 11.397392997722068,
+      "learning_rate": 8.945702546981969e-05,
+      "loss": 0.5063,
+      "num_input_tokens_seen": 8919608,
+      "step": 850
+    },
+    {
+      "epoch": 0.21890291012104043,
+      "eval_loss": 0.5525640249252319,
+      "eval_runtime": 39.0469,
+      "eval_samples_per_second": 3.073,
+      "eval_steps_per_second": 0.768,
+      "num_input_tokens_seen": 8919608,
+      "step": 850
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 8393696,
+  "num_input_tokens_seen": 8919608,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1450,7 +1539,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 553685057798144.0,
+  "total_flos": 588414853316608.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null