Training in progress, step 11500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68cea41d369dc23f0b22ce5093ea9ddb94820fdd87d358036225990b2bdffd5e
+oid sha256:96f4be8b5414724649632d19c3aee71659aba6767d726068b454891f52d3e43e
 size 29034840

last-checkpoint/global_step11500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4384bdcd496e52e5e36bb8f94c461aa5ad574794a7308108470e9e717f47d1
+size 43429616

last-checkpoint/global_step11500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff463df776d5e5370947a0bd6966d4a6aceef6c6391ca4f29948a19e0fcad7b
+size 43429616

last-checkpoint/global_step11500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be65baf7918e4fc18de8b14c77103a6ec0c217adf4437956e852bb82fa9507e
+size 43429616

last-checkpoint/global_step11500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf328711c28e894443c29a1ac2fc7a53efc3a8c994712c2dc8f9c53f2707541
+size 43429616

last-checkpoint/global_step11500/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f676f2cd03c769c01929b2e089b4522b1c84d1e741f4d1291af25a32e03de97
+size 637299

last-checkpoint/global_step11500/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c855fb4bb31aca5312245e12649276d57bcc66d0a44909dbecc2533205181195
+size 637171

last-checkpoint/global_step11500/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44e8f5705a5b12dfababc60b143785ef0e49d24e0539fc89f43e5555bf2a37c
+size 637171

last-checkpoint/global_step11500/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0548885e504f95fc3a30f670e473c4f1a0b19c32a20b20489674ddccc1ae6159
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step11450
+global_step11500

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138a62505cd5d4ba76dbcc36bbb4ebacd047551381d043eb17a39d0fab9d3ddb
+oid sha256:a8624d7dbea6b0bfbee612f374f3ca1479d58940a3f7f81e0f255b5acf00a98f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6a9ebe8b345f5601f0ffce0f7102520bfefe4c275cc1dc008e7af3add0f288
+oid sha256:033b3cecd2abc755b65afde94a0bfa4ab3d5e9ce350e6259d1335531f6b15ead
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea47c887b6bb35e2b120484479df524c546c1063219ad4dacc1538d185f5c1f
+oid sha256:b4a659d96606470c68743db7a44e95915e6de25517838964670dd2a15ff16264
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d84598bf5ba1bcf12922835f257cacde2424631348644ed1b5f307a8056362
+oid sha256:d1dc4e4e8414a28fda061c3e335783b4e88dd0e581f6ca10cc704305b81f4eb5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39564ce27ec935973949df05f5fb0f31f5a25991e5f7822325bbf9c9819049f
+oid sha256:b63a541347f55fb360937d1ccc2d6065f98b6903cd246a4581a0a7eb1ffe6611
 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": 1.4028054270925852,
+  "epoch": 1.4089308137576184,
   "eval_steps": 50,
-  "global_step": 11450,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -20388,11 +20388,100 @@
       "eval_steps_per_second": 0.776,
       "num_input_tokens_seen": 76541376,
       "step": 11450
+    },
+    {
+      "epoch": 1.4034179657590886,
+      "grad_norm": 0.939110259463709,
+      "learning_rate": 2.241603361314505e-05,
+      "loss": 0.2098,
+      "num_input_tokens_seen": 76575016,
+      "step": 11455
+    },
+    {
+      "epoch": 1.4040305044255919,
+      "grad_norm": 0.9265842466420994,
+      "learning_rate": 2.2373804508464707e-05,
+      "loss": 0.1934,
+      "num_input_tokens_seen": 76608464,
+      "step": 11460
+    },
+    {
+      "epoch": 1.4046430430920953,
+      "grad_norm": 1.5517003693518743,
+      "learning_rate": 2.233160375066168e-05,
+      "loss": 0.2108,
+      "num_input_tokens_seen": 76641856,
+      "step": 11465
+    },
+    {
+      "epoch": 1.4052555817585985,
+      "grad_norm": 1.4439917361643635,
+      "learning_rate": 2.2289431383037594e-05,
+      "loss": 0.218,
+      "num_input_tokens_seen": 76675760,
+      "step": 11470
+    },
+    {
+      "epoch": 1.4058681204251018,
+      "grad_norm": 1.507292547909062,
+      "learning_rate": 2.2247287448864952e-05,
+      "loss": 0.2457,
+      "num_input_tokens_seen": 76709472,
+      "step": 11475
+    },
+    {
+      "epoch": 1.406480659091605,
+      "grad_norm": 1.3901602936201654,
+      "learning_rate": 2.2205171991387104e-05,
+      "loss": 0.198,
+      "num_input_tokens_seen": 76743120,
+      "step": 11480
+    },
+    {
+      "epoch": 1.4070931977581085,
+      "grad_norm": 1.1735039185052853,
+      "learning_rate": 2.2163085053818173e-05,
+      "loss": 0.2278,
+      "num_input_tokens_seen": 76776432,
+      "step": 11485
+    },
+    {
+      "epoch": 1.407705736424612,
+      "grad_norm": 1.4687257536230054,
+      "learning_rate": 2.2121026679343028e-05,
+      "loss": 0.2212,
+      "num_input_tokens_seen": 76809752,
+      "step": 11490
+    },
+    {
+      "epoch": 1.4083182750911152,
+      "grad_norm": 1.2054513198472594,
+      "learning_rate": 2.2078996911117182e-05,
+      "loss": 0.2273,
+      "num_input_tokens_seen": 76843064,
+      "step": 11495
+    },
+    {
+      "epoch": 1.4089308137576184,
+      "grad_norm": 1.2331838011316778,
+      "learning_rate": 2.2036995792266852e-05,
+      "loss": 0.2274,
+      "num_input_tokens_seen": 76876640,
+      "step": 11500
+    },
+    {
+      "epoch": 1.4089308137576184,
+      "eval_loss": 0.14584578573703766,
+      "eval_runtime": 19.654,
+      "eval_samples_per_second": 3.053,
+      "eval_steps_per_second": 0.763,
+      "num_input_tokens_seen": 76876640,
+      "step": 11500
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 76541376,
+  "num_input_tokens_seen": 76876640,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -20407,7 +20496,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4800958720114688.0,
+  "total_flos": 4822004093026304.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null