Training in progress, step 12050, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1082457bebc6ec3cbfedcbeb51773ce1a8a48f6301c6edb5b36375b688353dc
+oid sha256:0aa8be01ed41d78f5cb91727b0ee4495a5902d02aafacf9c474f86f7b188b169
 size 29034840

last-checkpoint/global_step12050/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:a69d7666ac5fa34855a35efd3dfa91e58b536cda8bf3c99147bc2a01a3c65b2f
+size 43429616

last-checkpoint/global_step12050/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:aedbb3436e09b12812e025c3d1c53342afd2424eeb7015aeff659b7b0cea8ee5
+size 43429616

last-checkpoint/global_step12050/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d33d3d53245dba84825275a93459904a47377d8c7b2d48de3c8630ad58f0bf2
+size 43429616

last-checkpoint/global_step12050/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037dc136424cb6e55e629f34f9c438c2a3177441360ebb584b869141db1c2e47
+size 43429616

last-checkpoint/global_step12050/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9e443159bcff8047d50243ab903eb837952222018d575b5a6a434fb9f040ff
+size 637299

last-checkpoint/global_step12050/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd04400728eab031a3c22aaf92e0467fdb5015f70804dab8f8e11295e960d858
+size 637171

last-checkpoint/global_step12050/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809b92e24be0104676786d18919cfa7de6e93d7497c5fecd919af35252b2f992
+size 637171

last-checkpoint/global_step12050/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbe9991b913c523041c72fae123d2ff3e11f8b8b82d6ff68c3079b7656d213f
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step12000
+global_step12050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c19f1aa2e9d61d357b6204eae1219eaf78e21bc8b326b4ae45539d10d19b552e
+oid sha256:6aec83bf15dfafe4589c119a7a2bd846ae65921d6ef4a7b5d9016bc52d6cef06
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dddbc25c1e4accbb8ee3e8c21c61d1a8d47c2223f777e10f16a31d9fe3716bd1
+oid sha256:8863cb3ec22fc18603dd5ee56ca2604a395fdf3317758dc81e635063c376ff18
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44dfda6d0cf493b706b65c41a9191234d5faf1a15068d781e2015b936fbf1040
+oid sha256:08d617533e32ae08748c955afd3c7e0e6836cd9079f1712aa3c1ba2e81ea22f4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52156225dccd5afb40ba3b9bf5ef7185d674a38c6e5cda245b57dc54a65ecdf
+oid sha256:bf52a7e0c79577685582dca7c527468cc931649ace827b6add90343a39853568
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae47c8c40a05ad370051cd694712264f349dd136bc69f50e79d1844afc8bc9b4
+oid sha256:878049e47346ed2fcd4fb685bcbfa218cde3339d8b1e692d243ba2cae5aca4eb
 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": 1.4701846804079508,
+  "epoch": 1.4763100670729838,
   "eval_steps": 50,
-  "global_step": 12000,
+  "global_step": 12050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21367,11 +21367,100 @@
       "eval_steps_per_second": 0.779,
       "num_input_tokens_seen": 80238176,
       "step": 12000
+    },
+    {
+      "epoch": 1.470797219074454,
+      "grad_norm": 1.3650626475832663,
+      "learning_rate": 1.7949943442447054e-05,
+      "loss": 0.2321,
+      "num_input_tokens_seen": 80271304,
+      "step": 12005
+    },
+    {
+      "epoch": 1.4714097577409575,
+      "grad_norm": 1.4498555054760127,
+      "learning_rate": 1.7911085548045863e-05,
+      "loss": 0.2077,
+      "num_input_tokens_seen": 80305440,
+      "step": 12010
+    },
+    {
+      "epoch": 1.4720222964074607,
+      "grad_norm": 1.9320148006473867,
+      "learning_rate": 1.7872260579659437e-05,
+      "loss": 0.2186,
+      "num_input_tokens_seen": 80339392,
+      "step": 12015
+    },
+    {
+      "epoch": 1.472634835073964,
+      "grad_norm": 1.7689702342289593,
+      "learning_rate": 1.7833468577125584e-05,
+      "loss": 0.2285,
+      "num_input_tokens_seen": 80372552,
+      "step": 12020
+    },
+    {
+      "epoch": 1.4732473737404674,
+      "grad_norm": 1.2111102544083923,
+      "learning_rate": 1.7794709580248237e-05,
+      "loss": 0.2289,
+      "num_input_tokens_seen": 80406488,
+      "step": 12025
+    },
+    {
+      "epoch": 1.4738599124069707,
+      "grad_norm": 0.9294510047497031,
+      "learning_rate": 1.7755983628797508e-05,
+      "loss": 0.2,
+      "num_input_tokens_seen": 80441080,
+      "step": 12030
+    },
+    {
+      "epoch": 1.4744724510734741,
+      "grad_norm": 1.171807497448012,
+      "learning_rate": 1.7717290762509603e-05,
+      "loss": 0.1899,
+      "num_input_tokens_seen": 80474952,
+      "step": 12035
+    },
+    {
+      "epoch": 1.4750849897399774,
+      "grad_norm": 1.4068816507329411,
+      "learning_rate": 1.7678631021086755e-05,
+      "loss": 0.2064,
+      "num_input_tokens_seen": 80508448,
+      "step": 12040
+    },
+    {
+      "epoch": 1.4756975284064806,
+      "grad_norm": 1.3514871036305516,
+      "learning_rate": 1.76400044441972e-05,
+      "loss": 0.2092,
+      "num_input_tokens_seen": 80542456,
+      "step": 12045
+    },
+    {
+      "epoch": 1.4763100670729838,
+      "grad_norm": 1.6884641291870757,
+      "learning_rate": 1.7601411071475175e-05,
+      "loss": 0.2262,
+      "num_input_tokens_seen": 80575888,
+      "step": 12050
+    },
+    {
+      "epoch": 1.4763100670729838,
+      "eval_loss": 0.10674486309289932,
+      "eval_runtime": 19.5696,
+      "eval_samples_per_second": 3.066,
+      "eval_steps_per_second": 0.766,
+      "num_input_tokens_seen": 80575888,
+      "step": 12050
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 80238176,
+  "num_input_tokens_seen": 80575888,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -21386,7 +21475,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5032876634275840.0,
+  "total_flos": 5054045476093952.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null