Training in progress, step 10000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631a5c86aa988584fd6fd8d5a0cb756846cc35eb4e83266e3c3a1bd1efbe8675
+oid sha256:7f3df1923d9fa4d4ba4210c00d4064b1217e6de0d9fae21da85801e619830098
 size 29034840

last-checkpoint/global_step10000/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:d240048f026803dbddd1724523a7ca2de2827f7f4046a28bec7612506c1f4896
+size 43429616

last-checkpoint/global_step10000/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:af9d739eaf611dfc542e6970b3bce4c233d874be1a835af91983ff1b48e6133d
+size 43429616

last-checkpoint/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b477d28fcd4876c45a421b65b72bef6e5547331943356dd7c2650f53908619
+size 43429616

last-checkpoint/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d791eb0fa00dd6deff37b2ce257dec0682492c7016877770930a3b66f7357d
+size 43429616

last-checkpoint/global_step10000/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f670f971061ee5ccc2ce8949c62d7f3b28e9592fb01ed74d60690c0b63dfeab
+size 637299

last-checkpoint/global_step10000/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2394d91162704cf4261ad592249df26cc4f13718fa706ae188428fdb800ea63f
+size 637171

last-checkpoint/global_step10000/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b35d849abccc721fe708faa4eb82c9af45fdf8e6aa0031f673275451eba8cc8
+size 637171

last-checkpoint/global_step10000/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de57588d8117b8dd97d287d5f926e84cda7a969757a2ba316ac4f8aff113557
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step9950
+global_step10000

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab7c6843889748cea19edd36fe5fbfaff72ee3e41effe7fe89f29203c14111c
+oid sha256:08cce78177d96f46cb05953508580d717e9ab4cfa0af96f68f8fbf922cd3832f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e43d2fa2c10094840ce71d7e9e55fbc58ee7f77c0b03b1db8fd6f075f9c0f27
+oid sha256:2dd5e724cd1bc66d3308b441566c50035a5b4cfe9d731ef333cb45aff2efa0a8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2f22d92415d5cf3cbddae9ec0efda5499dc3d500ac143d48fc150eef2a1189
+oid sha256:db95c164a3f9f096591c54d374b04e63d0f313de87d240a7e902ed5ba07a81ca
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b645698b8b37cd361689496ae39c89be8d967d0363195d1218e27662fac1a63a
+oid sha256:9ac2f9e5ecbefb231e5ddf28d7401794dd06330430a1d71c9e093f1b6b293b05
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f314e8881b07c179180285733449c92a86d3f742ada2b7d4c7cec319acb0388b
+oid sha256:f1e4f4d6952a4344fd27915c35f70bbe655fc6d5c21ec3a8fcbb8a3a75429e23
 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": 1.2190438271415882,
+  "epoch": 1.2251692138066215,
   "eval_steps": 50,
-  "global_step": 9950,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17718,11 +17718,100 @@
       "eval_steps_per_second": 0.735,
       "num_input_tokens_seen": 66462256,
       "step": 9950
+    },
+    {
+      "epoch": 1.2196563658080917,
+      "grad_norm": 1.4544809627964557,
+      "learning_rate": 3.615874587797381e-05,
+      "loss": 0.2162,
+      "num_input_tokens_seen": 66495928,
+      "step": 9955
+    },
+    {
+      "epoch": 1.220268904474595,
+      "grad_norm": 1.314166192503101,
+      "learning_rate": 3.6110084317858005e-05,
+      "loss": 0.2371,
+      "num_input_tokens_seen": 66529384,
+      "step": 9960
+    },
+    {
+      "epoch": 1.2208814431410984,
+      "grad_norm": 1.8272913355200002,
+      "learning_rate": 3.606143701000271e-05,
+      "loss": 0.2425,
+      "num_input_tokens_seen": 66563312,
+      "step": 9965
+    },
+    {
+      "epoch": 1.2214939818076016,
+      "grad_norm": 1.1190635076196744,
+      "learning_rate": 3.6012804004324326e-05,
+      "loss": 0.228,
+      "num_input_tokens_seen": 66596840,
+      "step": 9970
+    },
+    {
+      "epoch": 1.2221065204741048,
+      "grad_norm": 1.417082438708923,
+      "learning_rate": 3.596418535072451e-05,
+      "loss": 0.2407,
+      "num_input_tokens_seen": 66630168,
+      "step": 9975
+    },
+    {
+      "epoch": 1.2227190591406083,
+      "grad_norm": 1.5615601472935723,
+      "learning_rate": 3.591558109909025e-05,
+      "loss": 0.2049,
+      "num_input_tokens_seen": 66663848,
+      "step": 9980
+    },
+    {
+      "epoch": 1.2233315978071115,
+      "grad_norm": 1.061850813247257,
+      "learning_rate": 3.586699129929373e-05,
+      "loss": 0.1661,
+      "num_input_tokens_seen": 66698912,
+      "step": 9985
+    },
+    {
+      "epoch": 1.223944136473615,
+      "grad_norm": 1.0446245994987036,
+      "learning_rate": 3.5818416001192276e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 66732112,
+      "step": 9990
+    },
+    {
+      "epoch": 1.2245566751401182,
+      "grad_norm": 1.0453311293261525,
+      "learning_rate": 3.576985525462841e-05,
+      "loss": 0.2364,
+      "num_input_tokens_seen": 66765832,
+      "step": 9995
+    },
+    {
+      "epoch": 1.2251692138066215,
+      "grad_norm": 1.022044445150293,
+      "learning_rate": 3.572130910942964e-05,
+      "loss": 0.2736,
+      "num_input_tokens_seen": 66798760,
+      "step": 10000
+    },
+    {
+      "epoch": 1.2251692138066215,
+      "eval_loss": 0.15618817508220673,
+      "eval_runtime": 20.4016,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.735,
+      "num_input_tokens_seen": 66798760,
+      "step": 10000
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 66462256,
+  "num_input_tokens_seen": 66798760,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -17737,7 +17826,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4168859985248256.0,
+  "total_flos": 4189946547535872.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null