Training in progress, step 10650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efff59a8dfdb426f07826c23a939f85aab101658026fbf75533653a8b5df925c
+oid sha256:4d437bc70c4c04c351d9b268de8b986e9c10960030d11d9b5cc0a07a032d4e75
 size 29034840

last-checkpoint/global_step10650/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:c261636c3df0562dd1476438915bacee16d685655a6be339b6c2fcb39887b82b
+size 43429616

last-checkpoint/global_step10650/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06071e93820617bbbaf8d2ac106d765d8e77239b0921a89abbab4afc88bf4f54
+size 43429616

last-checkpoint/global_step10650/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959532c115c4ffdb9439d0ddd4b7af71f9bc386acfc816a8011d28cb419036d0
+size 43429616

last-checkpoint/global_step10650/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:ba42b8d4967ffcb9d5e350e75e85706faf9742570daa843fd8beb4d291c238fb
+size 43429616

last-checkpoint/global_step10650/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563087516e6fc6458e3ec0687e1eb861035d70ea480ab603abc913afb64230ae
+size 637299

last-checkpoint/global_step10650/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32e04c4bb15deccc3d759468c493aa07253776f77e1d1d4f931e4d0e7693c08
+size 637171

last-checkpoint/global_step10650/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb160edf404eef880dca232404353124e40f3b51c2a88e1049faf0c32723eaa
+size 637171

last-checkpoint/global_step10650/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b605490906905eb8c61c8c35c3fc5fbd32f8ba12f748993ee9098045dbcde9
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step10600
+global_step10650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d068fa3893075ee1f3734ae61bde214f2b383710020b17e4b0144277ef2c8ed
+oid sha256:882705638474934670faaaf11f480a9ca965116088d43b545d3c16f14930bd88
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb21b65f7281d8536c3cc0b3c6111256af84cf7f9fb2e2726dd4b856eedd503e
+oid sha256:5b49e541bf1b6ee313511bcb33f9c57c56d53d3ca5fc5060ada8ae009ad408c0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0dfce90b09c94cf3afb2c615c52e59b724bf93e397eb5e394191771bf3b7e79
+oid sha256:c575f73a7906ffee30747f33b3ff9d606e71678d1c70f907532bff0706c91b26
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2a724f05da69e3c66c731d3e6b3a4400ebb12f09d01fccc1c611af5fcdf7c7
+oid sha256:ad85b3229606911aae4c7db32cce537b0b9493ac5a6f9cb5cde256955cbe0543
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac505c1187bc32b3d5a79c3d5d9ccd7b1844ca245c7820fc47bcbd41dc0ba70b
+oid sha256:284555ebd24f2f7c70a3cb7790c9d4c47d92d96814317f7156c53c32553482a5
 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": 1.2986738537870204,
+  "epoch": 1.3047992404520534,
   "eval_steps": 50,
-  "global_step": 10600,
+  "global_step": 10650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18875,11 +18875,100 @@
       "eval_steps_per_second": 0.76,
       "num_input_tokens_seen": 70832136,
       "step": 10600
+    },
+    {
+      "epoch": 1.2992863924535236,
+      "grad_norm": 1.035231554256891,
+      "learning_rate": 2.996992509055528e-05,
+      "loss": 0.218,
+      "num_input_tokens_seen": 70866120,
+      "step": 10605
+    },
+    {
+      "epoch": 1.299898931120027,
+      "grad_norm": 1.501133744865775,
+      "learning_rate": 2.992352904582717e-05,
+      "loss": 0.215,
+      "num_input_tokens_seen": 70899936,
+      "step": 10610
+    },
+    {
+      "epoch": 1.3005114697865303,
+      "grad_norm": 1.50291918580223,
+      "learning_rate": 2.9877153601302893e-05,
+      "loss": 0.222,
+      "num_input_tokens_seen": 70933288,
+      "step": 10615
+    },
+    {
+      "epoch": 1.3011240084530336,
+      "grad_norm": 1.2133468261955178,
+      "learning_rate": 2.9830798804567716e-05,
+      "loss": 0.2343,
+      "num_input_tokens_seen": 70967296,
+      "step": 10620
+    },
+    {
+      "epoch": 1.3017365471195368,
+      "grad_norm": 1.1725568338460373,
+      "learning_rate": 2.9784464703185666e-05,
+      "loss": 0.2402,
+      "num_input_tokens_seen": 71000784,
+      "step": 10625
+    },
+    {
+      "epoch": 1.3023490857860403,
+      "grad_norm": 1.0014305965405448,
+      "learning_rate": 2.973815134469958e-05,
+      "loss": 0.2326,
+      "num_input_tokens_seen": 71034616,
+      "step": 10630
+    },
+    {
+      "epoch": 1.3029616244525435,
+      "grad_norm": 1.3780511441318963,
+      "learning_rate": 2.9691858776630965e-05,
+      "loss": 0.2387,
+      "num_input_tokens_seen": 71067488,
+      "step": 10635
+    },
+    {
+      "epoch": 1.303574163119047,
+      "grad_norm": 1.544176148681233,
+      "learning_rate": 2.964558704648003e-05,
+      "loss": 0.2606,
+      "num_input_tokens_seen": 71100848,
+      "step": 10640
+    },
+    {
+      "epoch": 1.3041867017855502,
+      "grad_norm": 1.5606371132464487,
+      "learning_rate": 2.959933620172559e-05,
+      "loss": 0.2349,
+      "num_input_tokens_seen": 71134040,
+      "step": 10645
+    },
+    {
+      "epoch": 1.3047992404520534,
+      "grad_norm": 1.3061543164710514,
+      "learning_rate": 2.9553106289825028e-05,
+      "loss": 0.2106,
+      "num_input_tokens_seen": 71167464,
+      "step": 10650
+    },
+    {
+      "epoch": 1.3047992404520534,
+      "eval_loss": 0.14994314312934875,
+      "eval_runtime": 19.5296,
+      "eval_samples_per_second": 3.072,
+      "eval_steps_per_second": 0.768,
+      "num_input_tokens_seen": 71167464,
+      "step": 10650
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 70832136,
+  "num_input_tokens_seen": 71167464,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -18894,7 +18983,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4442976695222272.0,
+  "total_flos": 4464001544224768.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null