Training in progress, step 11450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e1585cc4b434bda55aa62dcf220f7cf2435c298689413f9bb652f6fb53da2ee
+oid sha256:68cea41d369dc23f0b22ce5093ea9ddb94820fdd87d358036225990b2bdffd5e
 size 29034840

last-checkpoint/global_step11450/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:dfaae5456983e29bb70e9c0d50aa373dce449cbafb8c2ff890c82bdc1969fdc9
+size 43429616

last-checkpoint/global_step11450/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:bd38d786d5792daeba4e64f43d2b820e0c4046b165db10781ccb3a26da1416b1
+size 43429616

last-checkpoint/global_step11450/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:e8164b4a453b05da63ca727b6167f0f8bc0182a3b493898ec554706e93d295cc
+size 43429616

last-checkpoint/global_step11450/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d157481cd5ab3196f37c35421ef473bfec596360796c78f5dd75be4bc2fc44f
+size 43429616

last-checkpoint/global_step11450/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9881a6d1a199aa2a59b275dc673f44bfd05e17fbea8b6557ec9b35859d3525
+size 637299

last-checkpoint/global_step11450/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cf6f81a7dfc86d0e1b3b666df678df801d72b83e73cb988d9be7458a7103d2
+size 637171

last-checkpoint/global_step11450/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11164bc46a4df99eaafd24698852dcd32779f3ab44f9553315126ae55b398085
+size 637171

last-checkpoint/global_step11450/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efc028464fd32f8e0b9830e18e9237b48d58bc62f961a5ad3f0d2830c082c5f9
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step11400
+global_step11450

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27648483919bf6db61bc01bdc08d8433f1eb24e83aac7f139542c05da435ddb
+oid sha256:138a62505cd5d4ba76dbcc36bbb4ebacd047551381d043eb17a39d0fab9d3ddb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfb347c5b75d89470fe0836fe28917c7357455657faee86c6d63bcebf4d2364
+oid sha256:8a6a9ebe8b345f5601f0ffce0f7102520bfefe4c275cc1dc008e7af3add0f288
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784373446df3f533577379aca34fdc3d78674dfd62151a3124bbcd593cc45985
+oid sha256:8ea47c887b6bb35e2b120484479df524c546c1063219ad4dacc1538d185f5c1f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd05d8ba8e5381dd14b88a432136176dbc3553bfe0868349d69d1ddfcb01223
+oid sha256:d3d84598bf5ba1bcf12922835f257cacde2424631348644ed1b5f307a8056362
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27cd5dd8b545df66df0f76dc60e9970f057069194a0bb0e6af5e90abad0f56cc
+oid sha256:a39564ce27ec935973949df05f5fb0f31f5a25991e5f7822325bbf9c9819049f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.04092838987708092,
   "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-9050",
-  "epoch": 1.396680040427552,
+  "epoch": 1.4028054270925852,
   "eval_steps": 50,
-  "global_step": 11400,
+  "global_step": 11450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -20299,11 +20299,100 @@
       "eval_steps_per_second": 0.767,
       "num_input_tokens_seen": 76204736,
       "step": 11400
+    },
+    {
+      "epoch": 1.3972925790940554,
+      "grad_norm": 1.5623136082019815,
+      "learning_rate": 2.2839874191098527e-05,
+      "loss": 0.246,
+      "num_input_tokens_seen": 76238512,
+      "step": 11405
+    },
+    {
+      "epoch": 1.3979051177605586,
+      "grad_norm": 1.0900294085981546,
+      "learning_rate": 2.2797364005612624e-05,
+      "loss": 0.207,
+      "num_input_tokens_seen": 76271944,
+      "step": 11410
+    },
+    {
+      "epoch": 1.398517656427062,
+      "grad_norm": 1.4912846379601163,
+      "learning_rate": 2.275488173239519e-05,
+      "loss": 0.2436,
+      "num_input_tokens_seen": 76305032,
+      "step": 11415
+    },
+    {
+      "epoch": 1.3991301950935653,
+      "grad_norm": 2.109179171015616,
+      "learning_rate": 2.271242741503669e-05,
+      "loss": 0.2002,
+      "num_input_tokens_seen": 76338824,
+      "step": 11420
+    },
+    {
+      "epoch": 1.3997427337600685,
+      "grad_norm": 1.2906027232155004,
+      "learning_rate": 2.267000109709896e-05,
+      "loss": 0.2215,
+      "num_input_tokens_seen": 76372360,
+      "step": 11425
+    },
+    {
+      "epoch": 1.400355272426572,
+      "grad_norm": 1.3383037733897587,
+      "learning_rate": 2.2627602822115083e-05,
+      "loss": 0.2445,
+      "num_input_tokens_seen": 76405752,
+      "step": 11430
+    },
+    {
+      "epoch": 1.4009678110930752,
+      "grad_norm": 1.678282337381254,
+      "learning_rate": 2.2585232633589402e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 76439832,
+      "step": 11435
+    },
+    {
+      "epoch": 1.4015803497595787,
+      "grad_norm": 32.488609000866205,
+      "learning_rate": 2.2542890574997372e-05,
+      "loss": 0.1915,
+      "num_input_tokens_seen": 76473504,
+      "step": 11440
+    },
+    {
+      "epoch": 1.402192888426082,
+      "grad_norm": 1.6132573142338857,
+      "learning_rate": 2.2500576689785645e-05,
+      "loss": 0.1851,
+      "num_input_tokens_seen": 76507384,
+      "step": 11445
+    },
+    {
+      "epoch": 1.4028054270925852,
+      "grad_norm": 1.353999319125173,
+      "learning_rate": 2.245829102137196e-05,
+      "loss": 0.2203,
+      "num_input_tokens_seen": 76541376,
+      "step": 11450
+    },
+    {
+      "epoch": 1.4028054270925852,
+      "eval_loss": 0.13985607028007507,
+      "eval_runtime": 19.3404,
+      "eval_samples_per_second": 3.102,
+      "eval_steps_per_second": 0.776,
+      "num_input_tokens_seen": 76541376,
+      "step": 11450
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 76204736,
+  "num_input_tokens_seen": 76541376,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -20318,7 +20407,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4779843103358976.0,
+  "total_flos": 4800958720114688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null