Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847b02ea6b5dcacf2ba31391c0399f758f14d0815ccad3f7b70c82822ffabbaf
+oid sha256:39e915e79b012114953a1589b00c8900ef9e4855bec6bd8aa9a11edc484871cf
 size 18516456

last-checkpoint/global_step1200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0efb098c1694146a0e80a979cced9a620aed1aae2dc6be201be025df62aa8560
+size 27700976

last-checkpoint/global_step1200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138b961bc4780fb95a2c2c0be19299c9e15f089b5b0257206d15e151de3a79e7
+size 27700976

last-checkpoint/global_step1200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce61ce78c8129b1837242abef544068fc1b7402b9b5509d695b968c9d67e6b3
+size 27700976

last-checkpoint/global_step1200/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:e357c3f771375bd330948d92edd3f7b22f7595fa97b82118d77c7c77aef77d65
+size 27700976

last-checkpoint/global_step1200/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e13644f376cff9c47ad54225b89c561303f550f5f81e911927275a74532578
+size 411571

last-checkpoint/global_step1200/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7cd6c3ef468d7af13347f379bf79f473002553e17b730bd6803e1c5952b5e8
+size 411507

last-checkpoint/global_step1200/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9227fd633733be3bf14e37d1ea43270c97c1eede4ac8b497b846f4b82dcbede2
+size 411507

last-checkpoint/global_step1200/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13309a3c326c80e7d577358f945ca86270023863ef39e39a8d67522dd8d0fed
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step1150
+global_step1200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274dc3860ee0c7f4d5348f60910a4b568498c04adfefb89f905b1c78a82c1312
+oid sha256:a209a0c0025f9ce8e2beeba50c1f0828d5c34a2482310fcd0bf5fc24c2c67be2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9aa441491b9ca89e796944520fa1db332a67c0a1a920be83edd2d96d741716d
+oid sha256:a67fb929b8c51f9b1c6ff9f11366e57e55128a1d36df85a9d37a008b49017a75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ee3434533b24fb771504fa8cceb5c2ea25fe0de1641128feaceccc65afe6ed
+oid sha256:1b9ef3b0c0978d0b611f4257c939f1c2c6f07e6227bfea6675532d285b0b64a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b4a44be1335173d2e3120bd0d1e6346f3e832d8935752c70ce1e98f017fa87
+oid sha256:0183d14c8ed52ee533139532e9bcf7bc34ec297a064845b35741cb501d92675f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d461c8d7517d4b88333bff7984fc3bfc149292198b04bbc18a49aee698ffb5c
+oid sha256:16e0cffc6b063574ed312ee2198c86d3dddf2450d0400f042fdc08bd22dcbc7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7743102312088013,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1100",
-  "epoch": 0.5923255215039918,
+  "best_metric": 0.7593821287155151,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1200",
+  "epoch": 0.6180788050476436,
   "eval_steps": 50,
-  "global_step": 1150,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2054,11 +2054,100 @@
       "eval_steps_per_second": 0.937,
       "num_input_tokens_seen": 13450720,
       "step": 1150
+    },
+    {
+      "epoch": 0.5949008498583569,
+      "grad_norm": 1.5827740829243289,
+      "learning_rate": 7.875623046909544e-05,
+      "loss": 0.8168,
+      "num_input_tokens_seen": 13509200,
+      "step": 1155
+    },
+    {
+      "epoch": 0.5974761782127221,
+      "grad_norm": 2.344942216339615,
+      "learning_rate": 7.855697251155967e-05,
+      "loss": 0.7749,
+      "num_input_tokens_seen": 13567656,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6000515065670873,
+      "grad_norm": 2.7313469239045305,
+      "learning_rate": 7.835703917741212e-05,
+      "loss": 0.9132,
+      "num_input_tokens_seen": 13626136,
+      "step": 1165
+    },
+    {
+      "epoch": 0.6026268349214525,
+      "grad_norm": 0.7410043911446527,
+      "learning_rate": 7.81564351951057e-05,
+      "loss": 0.8308,
+      "num_input_tokens_seen": 13684608,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6052021632758177,
+      "grad_norm": 0.5628590604115411,
+      "learning_rate": 7.795516530895414e-05,
+      "loss": 0.8011,
+      "num_input_tokens_seen": 13743080,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6077774916301828,
+      "grad_norm": 1.2008934424824649,
+      "learning_rate": 7.775323427901993e-05,
+      "loss": 0.8309,
+      "num_input_tokens_seen": 13801552,
+      "step": 1180
+    },
+    {
+      "epoch": 0.610352819984548,
+      "grad_norm": 1.2914156288367256,
+      "learning_rate": 7.755064688100171e-05,
+      "loss": 0.8089,
+      "num_input_tokens_seen": 13860064,
+      "step": 1185
+    },
+    {
+      "epoch": 0.6129281483389132,
+      "grad_norm": 1.420806774436513,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.8089,
+      "num_input_tokens_seen": 13918552,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6155034766932784,
+      "grad_norm": 0.8352922832465102,
+      "learning_rate": 7.714352216101055e-05,
+      "loss": 0.8511,
+      "num_input_tokens_seen": 13977056,
+      "step": 1195
+    },
+    {
+      "epoch": 0.6180788050476436,
+      "grad_norm": 0.6321587989106885,
+      "learning_rate": 7.693899446759727e-05,
+      "loss": 0.8061,
+      "num_input_tokens_seen": 14035544,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6180788050476436,
+      "eval_loss": 0.7593821287155151,
+      "eval_runtime": 16.1368,
+      "eval_samples_per_second": 3.718,
+      "eval_steps_per_second": 0.93,
+      "num_input_tokens_seen": 14035544,
+      "step": 1200
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 13450720,
+  "num_input_tokens_seen": 14035544,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -2073,7 +2162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 755277071908864.0,
+  "total_flos": 788117261910016.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null