Training in progress, step 1150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c92d201c343dd983a22c7fe6d61ce77cf92ee8cd85263b720e40f9ba6a14e5
+oid sha256:ad37ecfc8f56cfb958ea72a1146b5dd079374376e542f0312701bdbcbb5deae5
 size 29034840

last-checkpoint/global_step1150/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:ca8a10436260e618014a2b4be40396eaebb8403c6df01b2cbcb1b8aa674fcd6a
+size 43429616

last-checkpoint/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b29fd3e42b02a0adcea87482aa72e33972b31215f1f79a1b20fc474b64830ee
+size 43429616

last-checkpoint/global_step1150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7451401a8c4d48ff12340bcb65dad7b7fe4d4bbc57787fc077709274ea1b62
+size 43429616

last-checkpoint/global_step1150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c5c85cc22f71e8ae3b26b29873d81eae73e21c9fa93f8c1e6286760b0c056d
+size 43429616

last-checkpoint/global_step1150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa758cf6fa59b0c76382480e4cb3a02f4e3bcc7c5814e40e5eff7203544b973f
+size 637299

last-checkpoint/global_step1150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a739833690f638f8f3ea52ef250f6914f0d6cc7cf09d4ba85216fa45aed5b895
+size 637171

last-checkpoint/global_step1150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a9559916dc6f652d640305c67706ef9b17164de4b12a7f651920cf80c4d653
+size 637171

last-checkpoint/global_step1150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a93cc4afb60025355716cc53e16bf4936ae88fb37858092e9cfc5c70e1b9a9
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1100
+global_step1150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9fea52fb92cc51e76feeb2b139ce35723c0cb651da383e4f7eec2606ed6c2a
+oid sha256:274dc3860ee0c7f4d5348f60910a4b568498c04adfefb89f905b1c78a82c1312
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5820ebfcc2e1cfe1ad2619a05ea9a484ff21635e13e386bf14abd302f2c0f7
+oid sha256:e9aa441491b9ca89e796944520fa1db332a67c0a1a920be83edd2d96d741716d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8d96a68e732fca41980516622a50990bbd3ee989e72076a35c8608d9b4d136
+oid sha256:c1ee3434533b24fb771504fa8cceb5c2ea25fe0de1641128feaceccc65afe6ed
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6f1db6d09f4d89a9b2bd8dc8eeb99f1fada2ec04376e23b5a7a13004994005
+oid sha256:93b4a44be1335173d2e3120bd0d1e6346f3e832d8935752c70ce1e98f017fa87
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0c7456eafeee3179566bb381c9153771d7e0f21738d2398944d053915d0651
+oid sha256:7d461c8d7517d4b88333bff7984fc3bfc149292198b04bbc18a49aee698ffb5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4798590838909149,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-1100",
-  "epoch": 0.28328611898017,
+  "best_metric": 0.45381438732147217,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-1150",
+  "epoch": 0.2961627607519959,
   "eval_steps": 50,
-  "global_step": 1100,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1965,11 +1965,100 @@
       "eval_steps_per_second": 0.737,
       "num_input_tokens_seen": 11547008,
       "step": 1100
+    },
+    {
+      "epoch": 0.28457378315735254,
+      "grad_norm": 11.308296783543483,
+      "learning_rate": 8.07106356344834e-05,
+      "loss": 0.4927,
+      "num_input_tokens_seen": 11600032,
+      "step": 1105
+    },
+    {
+      "epoch": 0.28586144733453517,
+      "grad_norm": 4.902660398367944,
+      "learning_rate": 8.051838793910038e-05,
+      "loss": 0.4353,
+      "num_input_tokens_seen": 11652120,
+      "step": 1110
+    },
+    {
+      "epoch": 0.28714911151171774,
+      "grad_norm": 4.185631754620407,
+      "learning_rate": 8.032541847934146e-05,
+      "loss": 0.4891,
+      "num_input_tokens_seen": 11705184,
+      "step": 1115
+    },
+    {
+      "epoch": 0.28843677568890036,
+      "grad_norm": 6.049695709018542,
+      "learning_rate": 8.013173181896283e-05,
+      "loss": 0.4497,
+      "num_input_tokens_seen": 11758032,
+      "step": 1120
+    },
+    {
+      "epoch": 0.28972443986608293,
+      "grad_norm": 4.598736726589848,
+      "learning_rate": 7.993733253868256e-05,
+      "loss": 0.4927,
+      "num_input_tokens_seen": 11810736,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2910121040432655,
+      "grad_norm": 41.010822412039396,
+      "learning_rate": 7.974222523607236e-05,
+      "loss": 0.4853,
+      "num_input_tokens_seen": 11863152,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2922997682204481,
+      "grad_norm": 5.591270811303827,
+      "learning_rate": 7.954641452544865e-05,
+      "loss": 0.4458,
+      "num_input_tokens_seen": 11914536,
+      "step": 1135
+    },
+    {
+      "epoch": 0.2935874323976307,
+      "grad_norm": 4.526048407550314,
+      "learning_rate": 7.934990503776363e-05,
+      "loss": 0.3976,
+      "num_input_tokens_seen": 11966064,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2948750965748133,
+      "grad_norm": 4.778105875378293,
+      "learning_rate": 7.915270142049566e-05,
+      "loss": 0.508,
+      "num_input_tokens_seen": 12018928,
+      "step": 1145
+    },
+    {
+      "epoch": 0.2961627607519959,
+      "grad_norm": 8.075837130866274,
+      "learning_rate": 7.89548083375394e-05,
+      "loss": 0.4553,
+      "num_input_tokens_seen": 12071088,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2961627607519959,
+      "eval_loss": 0.45381438732147217,
+      "eval_runtime": 38.3303,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 0.783,
+      "num_input_tokens_seen": 12071088,
+      "step": 1150
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 11547008,
+  "num_input_tokens_seen": 12071088,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1984,7 +2073,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 761815920803840.0,
+  "total_flos": 796381052928000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null