Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4709ac7890db563cedfc9593a73be6ffe73b6111dd9fd8fdc9d8017c84f30b92
+oid sha256:a24a4c37b80664a17b4612dbf43f560521041adc8bc0cc8d0182857100b9274e
 size 29034840

last-checkpoint/global_step2100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ed30ed84b974a6cf4cd074f31ea2b62dfbdf0a8cab4c7a836398205dee97cb
+size 43429616

last-checkpoint/global_step2100/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:b8f2daa244be2c27823ce1258727d687c9f82aae1ffed91aa74574e55eaf02eb
+size 43429616

last-checkpoint/global_step2100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837eefbed5e44ee11d16a7a2d903a8c3aef22ba2989f963648f90d605d907e2e
+size 43429616

last-checkpoint/global_step2100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bc0b0b4105b53ca3d3a240bbdde592787c13a1b9e96060d1c0cb6ebfb570b3
+size 43429616

last-checkpoint/global_step2100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeda14a8789d1fd88f7eebe00675f2572359184439f7c4c60b672fbdb030c435
+size 637299

last-checkpoint/global_step2100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec295f73f879f7574e82192c1ccc1329fd81288043991b95b358440fd8f90f7
+size 637171

last-checkpoint/global_step2100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abae9bad6bb987038dcd73f0e19d994e45cae40e20cd055d436706a0b5fe6064
+size 637171

last-checkpoint/global_step2100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bfaf44e1fb94ad73e3fc28120b85b71fc1b7b472586a7f8b29d56ad2e71f3c
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2050
+global_step2100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a695de1db3382235d3f8ae213672491aa2fdc3ba3be96403a089077ad3c2bf
+oid sha256:5d1ddd7e7b4dc44903837b0414e4659f8383cd8f16b41dd396d4eaf5b9829f79
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2025b170fa1d4693537c2d73f89a6495c58940d033678742a74810c0154a6a7
+oid sha256:eeddfb77fe4d3b495c4e08307767e08df90e96ef241c3eb80d5f75adec393e80
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0865c4d7d921b23a22c91c2f3b2c6cca03dae0eb27c43dee575c9602605c94d6
+oid sha256:9e6260196fabb00061b1f1c8de6288382570dc14d02d2aa308050ca858880a97
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4ec19d9df4417359523e8cc4d27875614c1021ebcc6391b27632aa7897b7ea
+oid sha256:ea023bc5b1def54e0c49389175c0fae812f5f764c502525ce775d993d5ab2c03
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce13f8f9c6f0eafa8c41a1ffb7cafd5f8d08bfe9e6dca6219533d00474bd826
+oid sha256:d3830a1cbcf9a648c99ec3b1dc2ae21133bcdd817f5603e9cff209ca0e0afc75
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28714123368263245,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-1550",
-  "epoch": 0.6056129985228951,
+  "epoch": 0.620384047267356,
   "eval_steps": 50,
-  "global_step": 2050,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3656,11 +3656,100 @@
       "eval_steps_per_second": 0.776,
       "num_input_tokens_seen": 21291664,
       "step": 2050
+    },
+    {
+      "epoch": 0.6070901033973413,
+      "grad_norm": 1.4664266327354816,
+      "learning_rate": 8.343716407399019e-05,
+      "loss": 0.2338,
+      "num_input_tokens_seen": 21344232,
+      "step": 2055
+    },
+    {
+      "epoch": 0.6085672082717873,
+      "grad_norm": 1.440796404258189,
+      "learning_rate": 8.334626387025197e-05,
+      "loss": 0.3026,
+      "num_input_tokens_seen": 21396160,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6100443131462334,
+      "grad_norm": 3.112422612662143,
+      "learning_rate": 8.325516472303792e-05,
+      "loss": 0.2898,
+      "num_input_tokens_seen": 21448032,
+      "step": 2065
+    },
+    {
+      "epoch": 0.6115214180206795,
+      "grad_norm": 7.791629500233522,
+      "learning_rate": 8.316386717584463e-05,
+      "loss": 0.3265,
+      "num_input_tokens_seen": 21499144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6129985228951256,
+      "grad_norm": 7.664415048315268,
+      "learning_rate": 8.307237177335239e-05,
+      "loss": 0.2513,
+      "num_input_tokens_seen": 21551328,
+      "step": 2075
+    },
+    {
+      "epoch": 0.6144756277695717,
+      "grad_norm": 7.353575088308837,
+      "learning_rate": 8.298067906142182e-05,
+      "loss": 0.2864,
+      "num_input_tokens_seen": 21603800,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6159527326440177,
+      "grad_norm": 6.877908422150131,
+      "learning_rate": 8.288878958709072e-05,
+      "loss": 0.243,
+      "num_input_tokens_seen": 21656480,
+      "step": 2085
+    },
+    {
+      "epoch": 0.6174298375184638,
+      "grad_norm": 7.551272364447902,
+      "learning_rate": 8.279670389857079e-05,
+      "loss": 0.2711,
+      "num_input_tokens_seen": 21708824,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6189069423929099,
+      "grad_norm": 1.5109531594598573,
+      "learning_rate": 8.27044225452443e-05,
+      "loss": 0.2475,
+      "num_input_tokens_seen": 21760744,
+      "step": 2095
+    },
+    {
+      "epoch": 0.620384047267356,
+      "grad_norm": 10.98724867961312,
+      "learning_rate": 8.26119460776609e-05,
+      "loss": 0.1826,
+      "num_input_tokens_seen": 21813984,
+      "step": 2100
+    },
+    {
+      "epoch": 0.620384047267356,
+      "eval_loss": 0.5386325716972351,
+      "eval_runtime": 19.2817,
+      "eval_samples_per_second": 3.112,
+      "eval_steps_per_second": 0.778,
+      "num_input_tokens_seen": 21813984,
+      "step": 2100
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 21291664,
+  "num_input_tokens_seen": 21813984,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3675,7 +3764,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1404747848351744.0,
+  "total_flos": 1439243507597312.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null