Training in progress, step 2600, checkpoint

last-checkpoint/adapter_config.json

@@ -19,7 +19,7 @@
   "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "^(?!.*patch_embed).*(?:up_proj|proj|fc2|fc1|qkv|o_proj|k_proj|gate_proj|v_proj|down_proj|q_proj).*",
+  "target_modules": "^(?!.*patch_embed).*(?:q_proj|proj|k_proj|v_proj|gate_proj|qkv|fc1|down_proj|up_proj|fc2|o_proj).*",
   "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171dfcb8bb8ac5a7df90ac9ee419e7a8a301f24e9f99f3e8664ab7c1ada5f55f
+oid sha256:f9418bf839b17997d0032898161f489316f534597155456a79fb57e1a059c9d3
 size 29034840

last-checkpoint/global_step2600/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:f61486daf0d430385454fdd31aa30e693142f01740a2b6e7ce8d75809b257dda
+size 43429616

last-checkpoint/global_step2600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48783103c45ecd2c745ac442b7833aaee98098f2cb95830ba3a269d63abbd3ac
+size 43429616

last-checkpoint/global_step2600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b9ea79de632a682b5e614797d194f779f1e0cb07f25160ad0ebd22d400ac8a
+size 43429616

last-checkpoint/global_step2600/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:f3df0676b92b80fd5168d9ec1f16531f1b90262c3c0293cb020ec48e9e941b4c
+size 43429616

last-checkpoint/global_step2600/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06c1edf5573ebf180456ac8e79b27035da8422278df6229d734a61e80963bb5
+size 637299

last-checkpoint/global_step2600/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3588ff3fd4fbda470bc5a673c3c50769804379c554333fff06ec2c1a7c2dd9b4
+size 637171

last-checkpoint/global_step2600/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e208bd20abccf743edac4b577df53bdacc162cd172a2bc0f269b16959280cfb
+size 637171

last-checkpoint/global_step2600/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff63d2250896cea5174b821ffb96b2aa3f9721fbfc8d1d1e21a6ce5cee640c1
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2550
+global_step2600

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0362dfd92e8da01e4a0deedcbd1c493b8162d5d1d84d5a4c1cd210c556f2cf9b
+oid sha256:91caf226cd72269cf1248d5f2f1a1d0c92100844814086cd6878cfb06293dc0c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65c5adee1a22c5343e38495a6905880496fb22d5e3ec5b16b87aadb731969d2
+oid sha256:3a2264023ead4b957c8737f57b7f130753adf9857726b38e1a7c000a4c721672
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d8858483b0c6944d55621cc2633469e3e0d04c48b6671eee92d4abab2352c2
+oid sha256:3af91d2c27fa6123938cc5723642d3bc4b5f5e9e58a6f0d15fdf45fd12cb685e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca42ef4f7a2f8c2285c4cf6cef585dcc0b132b21e8bb33d96d53b6db837f5e54
+oid sha256:57930146d6b40a72f7f121792ad7f144f1863c40a705666c20e64c1e1c54a94a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb561d82386bf4b227a10b6e6e08effab17d0e684e1cd302e30cfc0a843bd1df
+oid sha256:51d19c5591b92170b594a14288df1f8fed02718a1409cb25856483f8dff91ef9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4145541489124298,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-2350",
-  "epoch": 0.6567087303631213,
+  "epoch": 0.6695853721349472,
   "eval_steps": 50,
-  "global_step": 2550,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4546,11 +4546,100 @@
       "eval_steps_per_second": 0.783,
       "num_input_tokens_seen": 26776816,
       "step": 2550
+    },
+    {
+      "epoch": 0.6579963945403039,
+      "grad_norm": 4.114015193521732,
+      "learning_rate": 1.5957425910206785e-05,
+      "loss": 0.3547,
+      "num_input_tokens_seen": 26829304,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6592840587174865,
+      "grad_norm": 3.0843395555920994,
+      "learning_rate": 1.577973551359877e-05,
+      "loss": 0.281,
+      "num_input_tokens_seen": 26881272,
+      "step": 2560
+    },
+    {
+      "epoch": 0.660571722894669,
+      "grad_norm": 1.2091864940073456,
+      "learning_rate": 1.560285443129296e-05,
+      "loss": 0.2814,
+      "num_input_tokens_seen": 26934104,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6618593870718517,
+      "grad_norm": 3.2274724027367263,
+      "learning_rate": 1.542678684655306e-05,
+      "loss": 0.2602,
+      "num_input_tokens_seen": 26986248,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6631470512490343,
+      "grad_norm": 4.701885261412978,
+      "learning_rate": 1.5251536923403426e-05,
+      "loss": 0.336,
+      "num_input_tokens_seen": 27038528,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6644347154262168,
+      "grad_norm": 8.345266437633946,
+      "learning_rate": 1.5077108806530581e-05,
+      "loss": 0.2867,
+      "num_input_tokens_seen": 27090792,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6657223796033994,
+      "grad_norm": 1.737622406149806,
+      "learning_rate": 1.4903506621185192e-05,
+      "loss": 0.2898,
+      "num_input_tokens_seen": 27143544,
+      "step": 2585
+    },
+    {
+      "epoch": 0.667010043780582,
+      "grad_norm": 3.3292538558539,
+      "learning_rate": 1.4730734473084568e-05,
+      "loss": 0.2955,
+      "num_input_tokens_seen": 27195632,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6682977079577647,
+      "grad_norm": 3.0195263199381492,
+      "learning_rate": 1.4558796448315504e-05,
+      "loss": 0.281,
+      "num_input_tokens_seen": 27248472,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6695853721349472,
+      "grad_norm": 2.0014947688908067,
+      "learning_rate": 1.4387696613237612e-05,
+      "loss": 0.3075,
+      "num_input_tokens_seen": 27301776,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6695853721349472,
+      "eval_loss": 0.4504788815975189,
+      "eval_runtime": 65.1834,
+      "eval_samples_per_second": 1.841,
+      "eval_steps_per_second": 0.46,
+      "num_input_tokens_seen": 27301776,
+      "step": 2600
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 26776816,
+  "num_input_tokens_seen": 27301776,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4565,7 +4654,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1766674781700096.0,
+  "total_flos": 1801229350993920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2ceb98c0b4a50d3909c4f866386ff0e5093b24fd71a2054110090af7b4ef0e
+oid sha256:9ed8b409e805b958140d9c8d6cad43f19d2d8518b89641bfc2a345391a819bfe
 size 7416