Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f299ed065d076e986e51213d7bf889152797a26591dce7e23c56b2cecc05e88
+oid sha256:9637897eed1592d2d482e3090638e19cf1f19ebaae7ca0874cfe9fa7a0f34af2
 size 29034840

last-checkpoint/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b01b9e430f2710b81c6b92378e0c3ce44b48055454229f6cb73b50aedc64d47
+size 43429616

last-checkpoint/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7556b8d4bd28531abff384f75c5d5213c595b1ae36b8228de71ead7ec3ca7977
+size 43429616

last-checkpoint/global_step200/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:d45b3f8a44ffc528838848732ad254738d53cfcf9cd5e442df7e0b0b87a05259
+size 43429616

last-checkpoint/global_step200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121e763f96625efd69ec96d2af62ed25b0b8c9571a49971dbd882a8a20f8bcbb
+size 43429616

last-checkpoint/global_step200/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c8aed679b2d5c060599974f1ab45390fb83c42d37e4ed63003977054cda112
+size 637299

last-checkpoint/global_step200/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ceb1154d5065a4632b1731df2acb5e51080a1f0388344212eaec5524452314
+size 637171

last-checkpoint/global_step200/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30465b90efa0eb73fc80dc870a336c0cc691a34eaf088821a381a9f71ee7d652
+size 637171

last-checkpoint/global_step200/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab524daca08828de12f8863c12ac5a32a74f179700a4a2850b77f7debcf459b3
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step150
+global_step200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70cc56408014c410353d4dd58ae9b03f4be043f5f800324f66fd8e20e99b840e
+oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d1438e98cc9c53a6852464635ce62e9788e61eb3646b73e33813f487c4b6ae
+oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4388add9cec90932f8ff0100d27a0574d98e1bad52ff89d44e31967d2b4fbfde
+oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a705d6dfaae4f2c1b4b2be6b25a6eb521ffae6fcba21cc1531e97b60037ed079
+oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c587ef55825cdfdbac47c29c3bd8a2996263c16833a5bd6aaa2fb014bea1e9d1
+oid sha256:fdde69e82f45c9368fe627c2082d010eb77a8ceb0b2354f60caa089407a428a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7309949994087219,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-150",
-  "epoch": 0.03862992531547772,
+  "best_metric": 0.7274295687675476,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-200",
+  "epoch": 0.05150656708730363,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -274,11 +274,100 @@
       "eval_steps_per_second": 0.785,
       "num_input_tokens_seen": 1573376,
       "step": 150
+    },
+    {
+      "epoch": 0.03991758949266031,
+      "grad_norm": 0.5536144453733772,
+      "learning_rate": 9.11764705882353e-05,
+      "loss": 0.738,
+      "num_input_tokens_seen": 1626136,
+      "step": 155
+    },
+    {
+      "epoch": 0.04120525366984291,
+      "grad_norm": 0.5151715191704441,
+      "learning_rate": 9.411764705882353e-05,
+      "loss": 0.7579,
+      "num_input_tokens_seen": 1678760,
+      "step": 160
+    },
+    {
+      "epoch": 0.042492917847025496,
+      "grad_norm": 0.5209077394596254,
+      "learning_rate": 9.705882352941177e-05,
+      "loss": 0.7502,
+      "num_input_tokens_seen": 1731240,
+      "step": 165
+    },
+    {
+      "epoch": 0.043780582024208085,
+      "grad_norm": 0.721213601237688,
+      "learning_rate": 0.0001,
+      "loss": 0.7448,
+      "num_input_tokens_seen": 1783816,
+      "step": 170
+    },
+    {
+      "epoch": 0.045068246201390674,
+      "grad_norm": 0.48666007914879555,
+      "learning_rate": 9.999940874631277e-05,
+      "loss": 0.6648,
+      "num_input_tokens_seen": 1834592,
+      "step": 175
+    },
+    {
+      "epoch": 0.04635591037857327,
+      "grad_norm": 0.5136600613696797,
+      "learning_rate": 9.999763499923432e-05,
+      "loss": 0.7759,
+      "num_input_tokens_seen": 1888176,
+      "step": 180
+    },
+    {
+      "epoch": 0.04764357455575586,
+      "grad_norm": 0.6706281530046975,
+      "learning_rate": 9.999467880071402e-05,
+      "loss": 0.7167,
+      "num_input_tokens_seen": 1940280,
+      "step": 185
+    },
+    {
+      "epoch": 0.04893123873293845,
+      "grad_norm": 0.5159139445497618,
+      "learning_rate": 9.999054022066641e-05,
+      "loss": 0.7483,
+      "num_input_tokens_seen": 1993096,
+      "step": 190
+    },
+    {
+      "epoch": 0.050218902910121044,
+      "grad_norm": 0.40251006129746847,
+      "learning_rate": 9.998521935696953e-05,
+      "loss": 0.7464,
+      "num_input_tokens_seen": 2045648,
+      "step": 195
+    },
+    {
+      "epoch": 0.05150656708730363,
+      "grad_norm": 0.4811730853311867,
+      "learning_rate": 9.997871633546257e-05,
+      "loss": 0.7594,
+      "num_input_tokens_seen": 2099008,
+      "step": 200
+    },
+    {
+      "epoch": 0.05150656708730363,
+      "eval_loss": 0.7274295687675476,
+      "eval_runtime": 38.079,
+      "eval_samples_per_second": 3.151,
+      "eval_steps_per_second": 0.788,
+      "num_input_tokens_seen": 2099008,
+      "step": 200
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 1573376,
+  "num_input_tokens_seen": 2099008,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -293,7 +382,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 103777530806272.0,
+  "total_flos": 138478836776960.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null