Training in progress, step 11950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8de84e70949c404703b483e8ebea4616aa76e5550ebb518d001960ca8ef412
+oid sha256:a57664fd8d118ea748563fac31ce8b78efe07e2901fabe33b4a76bc7345922c9
 size 29034840

last-checkpoint/global_step11950/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6733855f172a5e17147ab58fec551e4ea68d38f7c8b043a81415f2f81de978ae
+size 43429616

last-checkpoint/global_step11950/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:a14fd26ce8b1c99df35716828da1813b8c9f7e648038e92de7f170e8f1e8df78
+size 43429616

last-checkpoint/global_step11950/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:b11be5688b759767dfe0b26e8b368c3ec9a825be029288bdd45daf1f8dc9e542
+size 43429616

last-checkpoint/global_step11950/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7293d5975b919a36400df7829d4e0f36d37efa4d5c7e4240a2f5634fd26f338a
+size 43429616

last-checkpoint/global_step11950/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5f271fa2f28b74adf81f2429845e7461d0523805e900a34230860e44d7b755
+size 637299

last-checkpoint/global_step11950/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc694465bd460fe216d014082735cf94361930876706b4b89d8a5eb4a3e00493
+size 637171

last-checkpoint/global_step11950/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093cb3139bae9ab33a671e4a148753a1bab1b301804a6384f38f53ee9d737d84
+size 637171

last-checkpoint/global_step11950/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e862425fb635b75ddaac1025f544ee91d4d7524b13c28cc38af2a83613c7a45
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step11900
+global_step11950

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2a68c98af16e47cb51ea6c0d0f4754f4a9407b30762d8f82e852b8e76a4608
+oid sha256:08e63a1507ec8e6eb80eb4db3a04627f60726c8dfe128fa7ae48233814d3c7f7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509f6201054bbd37b518f6dab3ae8c057b4576b4a4b8e4e1585626d0721f975c
+oid sha256:1f71e62374e9d96336f152733a8b55ad85a31bf315e29c8dae76917a6d5e9f50
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec94ec63816216d52664e59485f0d6307134f2239d5479100054cf3405e88af1
+oid sha256:397b8002672366d97746debf09460a776c5721f87ae8f9aeb54c1b99133afdf5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e323bec972f8af2e04175c687b7e671d36cc07f3e45d61c276284be2f0eccc
+oid sha256:4f1601c6a8a6f02b3ac80fc66c7243adaee34f52863db1b04674d7ba56e1a4a4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3e1129e4ae45d39f9b6a7f47b9533d694c97a78bedd9094c78473d467ee729
+oid sha256:85333fd159e56c8beb00c8b6eec934d4a08a9b94a3fe141d6435a974bade77a4
 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": 1.4579339070778843,
+  "epoch": 1.4640592937429175,
   "eval_steps": 50,
-  "global_step": 11900,
+  "global_step": 11950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21189,11 +21189,100 @@
       "eval_steps_per_second": 0.778,
       "num_input_tokens_seen": 79560856,
       "step": 11900
+    },
+    {
+      "epoch": 1.4585464457443877,
+      "grad_norm": 1.3679759784014216,
+      "learning_rate": 1.8733954145586564e-05,
+      "loss": 0.1984,
+      "num_input_tokens_seen": 79594856,
+      "step": 11905
+    },
+    {
+      "epoch": 1.459158984410891,
+      "grad_norm": 1.5475246361886241,
+      "learning_rate": 1.869444614855496e-05,
+      "loss": 0.2249,
+      "num_input_tokens_seen": 79628416,
+      "step": 11910
+    },
+    {
+      "epoch": 1.4597715230773942,
+      "grad_norm": 1.2083117859520573,
+      "learning_rate": 1.865497027374209e-05,
+      "loss": 0.2391,
+      "num_input_tokens_seen": 79661656,
+      "step": 11915
+    },
+    {
+      "epoch": 1.4603840617438975,
+      "grad_norm": 0.8092871912401626,
+      "learning_rate": 1.861552656165359e-05,
+      "loss": 0.1946,
+      "num_input_tokens_seen": 79695424,
+      "step": 11920
+    },
+    {
+      "epoch": 1.460996600410401,
+      "grad_norm": 1.8712024643764127,
+      "learning_rate": 1.857611505276216e-05,
+      "loss": 0.2245,
+      "num_input_tokens_seen": 79728696,
+      "step": 11925
+    },
+    {
+      "epoch": 1.4616091390769042,
+      "grad_norm": 1.708438260077005,
+      "learning_rate": 1.8536735787507447e-05,
+      "loss": 0.2071,
+      "num_input_tokens_seen": 79762584,
+      "step": 11930
+    },
+    {
+      "epoch": 1.4622216777434076,
+      "grad_norm": 1.3106131028698333,
+      "learning_rate": 1.849738880629597e-05,
+      "loss": 0.1768,
+      "num_input_tokens_seen": 79796928,
+      "step": 11935
+    },
+    {
+      "epoch": 1.4628342164099108,
+      "grad_norm": 1.4141721431066059,
+      "learning_rate": 1.8458074149501153e-05,
+      "loss": 0.223,
+      "num_input_tokens_seen": 79830296,
+      "step": 11940
+    },
+    {
+      "epoch": 1.463446755076414,
+      "grad_norm": 1.2084116693938611,
+      "learning_rate": 1.8418791857463287e-05,
+      "loss": 0.1694,
+      "num_input_tokens_seen": 79864528,
+      "step": 11945
+    },
+    {
+      "epoch": 1.4640592937429175,
+      "grad_norm": 1.2782206880022664,
+      "learning_rate": 1.8379541970489366e-05,
+      "loss": 0.1818,
+      "num_input_tokens_seen": 79898064,
+      "step": 11950
+    },
+    {
+      "epoch": 1.4640592937429175,
+      "eval_loss": 0.1088213175535202,
+      "eval_runtime": 19.4183,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 0.772,
+      "num_input_tokens_seen": 79898064,
+      "step": 11950
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 79560856,
+  "num_input_tokens_seen": 79898064,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -21208,7 +21297,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4990354859491328.0,
+  "total_flos": 5011542192029696.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null