Training in progress, step 650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1513791e52117a6d639f05fdddf98b812e9b7c86a4830e79581dc7ae45e41a8
+oid sha256:3ae4ae60a26ee99e11a2e5ab6fb595036c6ed6a11a5c18815e41835fd861d1bc
 size 18516456

last-checkpoint/global_step650/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eef2952c199856a9fcf62051a5b2ab7c2f8370321900cbcaae7ed004133b4c4
+size 27700976

last-checkpoint/global_step650/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:db74a445318eaaff0a6999434cc220fb4f7ccc28d808a5796953bcfcee002d5a
+size 27700976

last-checkpoint/global_step650/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:ece5498497c6a7ba1102982002c1c274bb424b8a8bacb73b0653ec4d2d4bca6a
+size 27700976

last-checkpoint/global_step650/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f8192475e214e8f6683656a8f114c5e3c53003c057186a9b5628689b634ba7
+size 27700976

last-checkpoint/global_step650/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d2a717f34038e4b5233e0e7ad841d4c46a075d159b8407dd5f2e81acde48dd
+size 411571

last-checkpoint/global_step650/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5993695ce009775d7279eea0388f12ae416392537b3d54d2b2f8f3b716ffabc9
+size 411507

last-checkpoint/global_step650/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77f3fb1b5c101cecf264192e8b86fc1c3f2ecf4f47550830eab354ff674beb3
+size 411507

last-checkpoint/global_step650/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeae3481e62915481d3b6289b00da7b260e3fa552df9978394109f43cd099b42
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step600
+global_step650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81e3916b1392c4c49afb171dee5415c15f5a5a5af8749b28195fcfa0596699c
+oid sha256:8044e4c53158c210a17648ba8f2dc2d25a25bbfc55f686015542618eb652a33e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a781038dd714b87b8adb1aac8dbc8217ceb607428a992133954ad522365236e
+oid sha256:4cd85d7fa425e7888c973f1c2985ac15ca21b5e6171fe140a401c2bc75ca46ff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9446c3db15f382a5546f13622787fc99392a5e0bc8a9ca2da1838de7ab621a37
+oid sha256:d7915667371a58f1598639e0d1c20a0c59c783c14580cd040a6631eb4ea2311e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f11e7a6b3faa884fc23044e3772ff9dd72c257f02e121665061e2a03d518bd9
+oid sha256:35dd78929ad7f0fbf37fdb1284e8edf0424350f6e6ce1cd5a3ee78979af3d3cb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76b388bede074656df32b92902ac42b965557bfee0c930366af07d8382b1b4a
+oid sha256:8cd94ecf5c982ee0e060d3e07a575ce03dc3b0f289b5e32a1f65d3b6366a8a0e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8908902406692505,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-300",
-  "epoch": 0.3090394025238218,
+  "epoch": 0.3347926860674736,
   "eval_steps": 50,
-  "global_step": 600,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,11 +1075,100 @@
       "eval_steps_per_second": 0.876,
       "num_input_tokens_seen": 7017576,
       "step": 600
+    },
+    {
+      "epoch": 0.311614730878187,
+      "grad_norm": 0.3545950949033049,
+      "learning_rate": 9.55911532374151e-05,
+      "loss": 0.9019,
+      "num_input_tokens_seen": 7076032,
+      "step": 605
+    },
+    {
+      "epoch": 0.31419005923255217,
+      "grad_norm": 0.2355627006333952,
+      "learning_rate": 9.549077815930636e-05,
+      "loss": 0.8956,
+      "num_input_tokens_seen": 7134536,
+      "step": 610
+    },
+    {
+      "epoch": 0.31676538758691736,
+      "grad_norm": 0.17552483625655946,
+      "learning_rate": 9.538932721758474e-05,
+      "loss": 0.898,
+      "num_input_tokens_seen": 7193032,
+      "step": 615
+    },
+    {
+      "epoch": 0.3193407159412825,
+      "grad_norm": 0.1749010635522076,
+      "learning_rate": 9.528680281157999e-05,
+      "loss": 0.8991,
+      "num_input_tokens_seen": 7251568,
+      "step": 620
+    },
+    {
+      "epoch": 0.3219160442956477,
+      "grad_norm": 0.19885182954224315,
+      "learning_rate": 9.518320736600943e-05,
+      "loss": 0.8961,
+      "num_input_tokens_seen": 7310072,
+      "step": 625
+    },
+    {
+      "epoch": 0.3244913726500129,
+      "grad_norm": 0.4778756508206831,
+      "learning_rate": 9.507854333092063e-05,
+      "loss": 0.8994,
+      "num_input_tokens_seen": 7368560,
+      "step": 630
+    },
+    {
+      "epoch": 0.32706670100437807,
+      "grad_norm": 0.4123272743887767,
+      "learning_rate": 9.497281318163346e-05,
+      "loss": 0.8925,
+      "num_input_tokens_seen": 7427040,
+      "step": 635
+    },
+    {
+      "epoch": 0.32964202935874326,
+      "grad_norm": 0.34409942667705734,
+      "learning_rate": 9.486601941868154e-05,
+      "loss": 0.9087,
+      "num_input_tokens_seen": 7485552,
+      "step": 640
+    },
+    {
+      "epoch": 0.3322173577131084,
+      "grad_norm": 0.43327107411223276,
+      "learning_rate": 9.475816456775313e-05,
+      "loss": 0.8924,
+      "num_input_tokens_seen": 7544040,
+      "step": 645
+    },
+    {
+      "epoch": 0.3347926860674736,
+      "grad_norm": 0.6643023904352003,
+      "learning_rate": 9.464925117963133e-05,
+      "loss": 0.904,
+      "num_input_tokens_seen": 7602512,
+      "step": 650
+    },
+    {
+      "epoch": 0.3347926860674736,
+      "eval_loss": 0.90328449010849,
+      "eval_runtime": 16.1444,
+      "eval_samples_per_second": 3.716,
+      "eval_steps_per_second": 0.929,
+      "num_input_tokens_seen": 7602512,
+      "step": 650
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 7017576,
+  "num_input_tokens_seen": 7602512,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1094,7 +1183,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 394023670644736.0,
+  "total_flos": 426870884270080.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null