Training in progress, step 12150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f9bec96083a891f3438cab2c26316ec1499869b2b26db0b4e2a48daa1e00a5
+oid sha256:af0f9e937a2dbaf537ac173984164282e59a37c80c7e58522d9ee4148ff9c733
 size 29034840

last-checkpoint/global_step12150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037eec4cdbc368d17f6cfec3a783c8058303de3373aa2a91549f2ebabe7b1f29
+size 43429616

last-checkpoint/global_step12150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3e09f3c0eaaaa5f7302e6c905ba8eb537ba74a38fc2c22d1cfe2d3b7055a59
+size 43429616

last-checkpoint/global_step12150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59083fcd9c130dfc286e1144a3563e7b8ebf4952e9367b4a514e934cfce82060
+size 43429616

last-checkpoint/global_step12150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8beba7123c06e80ee8ea761ae31a7e59f8a8ed851f5bd88750bf59d5b72676e0
+size 43429616

last-checkpoint/global_step12150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a9c7ae97d414610f673832d5c375f0393e05fae13b6f25edef64a4b472a1fb
+size 637299

last-checkpoint/global_step12150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542f98aedda710ef50b9920971aac1ec30afb81dc11d1be9b26239172afcc41f
+size 637171

last-checkpoint/global_step12150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9bc8b75f762e1a4d3de1be879ebeb1528fda2a7ef7e19e217ab1c45ceff43a
+size 637171

last-checkpoint/global_step12150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75d4fe0dae9b2c1521fde91805e9b14b39452645bad9af7c35e356a2b3b0dcb
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step12100
+global_step12150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6f825717ceea198c3ce0f04915aca1c16c0bb509bbd145db76dbd4a99c9d5b
+oid sha256:c6307efa24539f25205494058ac21269eb4472c24196e1ee8b02057608ce4d24
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d4f787632a6686bc299de503d88bae878f5a0b875b2b57461e244d6dc0a50d
+oid sha256:104d067239480b773fb429ce7cf6fef608773d731045e564129e32bad2f89f87
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786154629886f0d9562482b0a72397580d924824117000607870f5021f20fe66
+oid sha256:6b31a105b7d05e94e9b867f006f5892a5f0e0d40a8f25f6fc4e1ae7b27248e3c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa28293999d2a2e89e66bc31521ce53ee26e044c86805d442d225527ba42cd66
+oid sha256:21975035cfdc76b4d274d6b419772538d54271629fee8e9459ef219c0b502f8c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae86561d86c2835dd608e393a799012632ed15b3dd6b29aaddccb6d0ec942292
+oid sha256:52419b8ff63153cdbaca6da836a3cad296cdecb3457c63b7ac611396d56073f0
 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": 1.482435453738017,
+  "epoch": 1.4885608404030504,
   "eval_steps": 50,
-  "global_step": 12100,
+  "global_step": 12150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21545,11 +21545,100 @@
       "eval_steps_per_second": 0.771,
       "num_input_tokens_seen": 80912808,
       "step": 12100
+    },
+    {
+      "epoch": 1.4830479924045206,
+      "grad_norm": 1.350213028954588,
+      "learning_rate": 1.7179086747792705e-05,
+      "loss": 0.2205,
+      "num_input_tokens_seen": 80945688,
+      "step": 12105
+    },
+    {
+      "epoch": 1.4836605310710238,
+      "grad_norm": 1.7138932429222575,
+      "learning_rate": 1.7140894904108396e-05,
+      "loss": 0.2271,
+      "num_input_tokens_seen": 80979064,
+      "step": 12110
+    },
+    {
+      "epoch": 1.4842730697375273,
+      "grad_norm": 1.8330956643913292,
+      "learning_rate": 1.7102736776721383e-05,
+      "loss": 0.219,
+      "num_input_tokens_seen": 81012720,
+      "step": 12115
+    },
+    {
+      "epoch": 1.4848856084040305,
+      "grad_norm": 1.14443147495106,
+      "learning_rate": 1.7064612404785196e-05,
+      "loss": 0.1997,
+      "num_input_tokens_seen": 81046296,
+      "step": 12120
+    },
+    {
+      "epoch": 1.4854981470705337,
+      "grad_norm": 1.3913689156054243,
+      "learning_rate": 1.7026521827418786e-05,
+      "loss": 0.2113,
+      "num_input_tokens_seen": 81079272,
+      "step": 12125
+    },
+    {
+      "epoch": 1.4861106857370372,
+      "grad_norm": 1.023101620622787,
+      "learning_rate": 1.698846508370639e-05,
+      "loss": 0.1786,
+      "num_input_tokens_seen": 81113592,
+      "step": 12130
+    },
+    {
+      "epoch": 1.4867232244035404,
+      "grad_norm": 1.429552357254653,
+      "learning_rate": 1.695044221269752e-05,
+      "loss": 0.2348,
+      "num_input_tokens_seen": 81146704,
+      "step": 12135
+    },
+    {
+      "epoch": 1.487335763070044,
+      "grad_norm": 1.5634928291725132,
+      "learning_rate": 1.6912453253406958e-05,
+      "loss": 0.224,
+      "num_input_tokens_seen": 81179856,
+      "step": 12140
+    },
+    {
+      "epoch": 1.4879483017365471,
+      "grad_norm": 1.2283588996234667,
+      "learning_rate": 1.687449824481469e-05,
+      "loss": 0.1995,
+      "num_input_tokens_seen": 81213312,
+      "step": 12145
+    },
+    {
+      "epoch": 1.4885608404030504,
+      "grad_norm": 1.3793598486147676,
+      "learning_rate": 1.683657722586582e-05,
+      "loss": 0.2078,
+      "num_input_tokens_seen": 81247096,
+      "step": 12150
+    },
+    {
+      "epoch": 1.4885608404030504,
+      "eval_loss": 0.1698664128780365,
+      "eval_runtime": 19.6604,
+      "eval_samples_per_second": 3.052,
+      "eval_steps_per_second": 0.763,
+      "num_input_tokens_seen": 81247096,
+      "step": 12150
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 80912808,
+  "num_input_tokens_seen": 81247096,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -21564,7 +21653,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5075174483034112.0,
+  "total_flos": 5096107533664256.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null