Training in progress, step 10250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45d5830c2e09f370b3d63c8ba834333afe356f626320b42c74a5ee1fe9417ef
+oid sha256:9fc5774c9df6adb72d705f6357d315d1cb1f8a764462f2261c3bb6c216301f7e
 size 29034840

last-checkpoint/global_step10250/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:cec68e65913aebe39f4eb74acaf96f60d072f325c8f39002fd5cc3da33959a0c
+size 43429616

last-checkpoint/global_step10250/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:df3415018f52cc4f2178429dbaf5ec51eaf7f5bf3b8c32cd5d6c3e080472df9a
+size 43429616

last-checkpoint/global_step10250/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d92eca28c10b89c4a934bee7694a1ed1e0ca66f037dee5cb679074cfd22c03
+size 43429616

last-checkpoint/global_step10250/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0e2ee0cf9dfaadabac276ea96ef0c17938fc107ac37f6367e773b735a44dca
+size 43429616

last-checkpoint/global_step10250/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7b736001ad86a8669401097883c0277e6fcf3a5f5e2ba1177f4a7d156bf2ff
+size 637299

last-checkpoint/global_step10250/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bd133b15ed88e3a5f89fb82437db02b00b1981e6befb242aec34989b073fd6
+size 637171

last-checkpoint/global_step10250/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7248e36bda999a4b628e034b01dcf9154612f80501cc301abb060742afb360f
+size 637171

last-checkpoint/global_step10250/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb53d701ed255a5acc99f9f3abb5816f93f1962bba140fb0b64353dec6dd061
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step10200
+global_step10250

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c742bef4e9bd4396f69ec57fa3bd186faf61932dc3a3e366435e42756967d6
+oid sha256:2f056a53812532c8eea64720388ddeec4af0eb9b78a0ed96303c86ce2ee596b3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68921b2f8e05186da263a9a77a4b36025ed43aca0639d90191be06bdef3b767
+oid sha256:94c8e73ab3bb491da899e642f6405ca797bb6c902d4320bda989f042a1918d60
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2efaab0dbf0012b03c39da2b9cc6388d50975e301c40d4015caf7f591c7d11
+oid sha256:2ec8327d99b8c9a858ccd02458ffc83b73f95e377f63f0b5f4c74dde75dc3f63
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9174784682317bb501948a41f1be2d5af58713ba3a3b62566dbb9e9f137c6b
+oid sha256:e9b2ce77f073808db654467abc3de83271e9005b2c29729f678fae36d45ed253
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a3e5820ba1c22bd9113df8ca1abded61b49b208d64e1c8f74ef02411fd9798
+oid sha256:60c8c4283b06b2e2d011931ad83e31fe12e1f667844dbc02550185988a55f5fe
 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": 1.2496707604667545,
+  "epoch": 1.2557961471317878,
   "eval_steps": 50,
-  "global_step": 10200,
+  "global_step": 10250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18163,11 +18163,100 @@
       "eval_steps_per_second": 0.774,
       "num_input_tokens_seen": 68143912,
       "step": 10200
+    },
+    {
+      "epoch": 1.2502832991332578,
+      "grad_norm": 1.001666242768362,
+      "learning_rate": 3.374410176413117e-05,
+      "loss": 0.1799,
+      "num_input_tokens_seen": 68177808,
+      "step": 10205
+    },
+    {
+      "epoch": 1.250895837799761,
+      "grad_norm": 1.1619611459217376,
+      "learning_rate": 3.369621366519453e-05,
+      "loss": 0.2216,
+      "num_input_tokens_seen": 68211568,
+      "step": 10210
+    },
+    {
+      "epoch": 1.2515083764662644,
+      "grad_norm": 1.512127989535974,
+      "learning_rate": 3.364834229535946e-05,
+      "loss": 0.2399,
+      "num_input_tokens_seen": 68244728,
+      "step": 10215
+    },
+    {
+      "epoch": 1.2521209151327677,
+      "grad_norm": 1.0875182289832053,
+      "learning_rate": 3.360048770374618e-05,
+      "loss": 0.2358,
+      "num_input_tokens_seen": 68278040,
+      "step": 10220
+    },
+    {
+      "epoch": 1.2527334537992711,
+      "grad_norm": 0.8613903903159598,
+      "learning_rate": 3.3552649939457634e-05,
+      "loss": 0.2189,
+      "num_input_tokens_seen": 68312056,
+      "step": 10225
+    },
+    {
+      "epoch": 1.2533459924657744,
+      "grad_norm": 1.453305242065048,
+      "learning_rate": 3.350482905157952e-05,
+      "loss": 0.2465,
+      "num_input_tokens_seen": 68345568,
+      "step": 10230
+    },
+    {
+      "epoch": 1.2539585311322776,
+      "grad_norm": 1.2514525034214972,
+      "learning_rate": 3.345702508918024e-05,
+      "loss": 0.2393,
+      "num_input_tokens_seen": 68379152,
+      "step": 10235
+    },
+    {
+      "epoch": 1.254571069798781,
+      "grad_norm": 1.2592102919373869,
+      "learning_rate": 3.34092381013108e-05,
+      "loss": 0.27,
+      "num_input_tokens_seen": 68412584,
+      "step": 10240
+    },
+    {
+      "epoch": 1.2551836084652843,
+      "grad_norm": 1.0958982494471285,
+      "learning_rate": 3.336146813700482e-05,
+      "loss": 0.2215,
+      "num_input_tokens_seen": 68446232,
+      "step": 10245
+    },
+    {
+      "epoch": 1.2557961471317878,
+      "grad_norm": 0.8092653699300046,
+      "learning_rate": 3.3313715245278434e-05,
+      "loss": 0.2368,
+      "num_input_tokens_seen": 68479264,
+      "step": 10250
+    },
+    {
+      "epoch": 1.2557961471317878,
+      "eval_loss": 0.1966872662305832,
+      "eval_runtime": 19.1612,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 0.783,
+      "num_input_tokens_seen": 68479264,
+      "step": 10250
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 68143912,
+  "num_input_tokens_seen": 68479264,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -18182,7 +18271,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4274338021900288.0,
+  "total_flos": 4295385059295232.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null