Training in progress, step 750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5f3724b5d59ea4e0a9371b33e20124137112f04ac962fd4bc5e834b083db05
+oid sha256:b80d0303f147dcd83f97c68d1de338e51e85f076089eb9eec3b8eff422c8bc34
 size 18516456

last-checkpoint/global_step750/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:a10baa950729cba886265be9ae3297a797d1a563529b79fd37bbab7e23e50705
+size 27700976

last-checkpoint/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91eaca47d12ba0676ccade07b28eb590f19a3780366bbd8b3fa5eb4f6a38619e
+size 27700976

last-checkpoint/global_step750/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:b306483a8da253ae83e769790477b1b2011fd346e91017da21e2c455f048aed8
+size 27700976

last-checkpoint/global_step750/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fcdb855034311c0f40a3de5596e146ab9bc1025d6d5bafe8a45b389db1d98c
+size 27700976

last-checkpoint/global_step750/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa751255b9d484acd655459378bb8b72f91109c691d64bfc34761c4482ac4ac3
+size 411571

last-checkpoint/global_step750/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94f3782d8f3cea94cdaad193aa9183d7002335cebd8149f92715121a02bb71e
+size 411507

last-checkpoint/global_step750/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1d154884bdfe4eb65ceace27198db48fcf736453df0b71d12ed7d4b85531d7
+size 411507

last-checkpoint/global_step750/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e84cbb1188d1e661ae0a82169a8dafd393234eefdf44c3a3a11c248f9d54a08
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step700
+global_step750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d74de51245105e1fbf57a6707ef3538b353952485508f6e2f8f74dc5d479d4
+oid sha256:66b4ef73f3603a1b91082ee108fa8299ebe45fb3cdeec7d0bdca1982af5bf07d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0617c9eb6cf7df57b2e0bb53cfe17c05f0910de56fe5b14427fe39ab54a44782
+oid sha256:882eccb2a272cf97cd645050bd077c971e48e78584f717a1b1cc9b5f1c9326dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed68a365057022897d9645ee60902a77102f43215dcdf2ddd5d3842b6a8446d8
+oid sha256:1626bac54f5806a604b7efdd749c5b65d63bbb40fc55c3744aae6130aa24f3de
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ebaa0c302cadbdfcd9f8ee2289e35ecf9c9fc8c9968fc0c05f100dac20c6b9
+oid sha256:40cf83ff997228172cf0b991f9d5209728ccf2f0a75841db5e31e647779a1ad2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9089a2e73aa73e2c09752311bdfa67c1ed286ab83bb4bc61dbf851e8193bb593
+oid sha256:a2ccf9d8c4b5840071603429d56208abefd14e276e9351f1160a607485df78ae
 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": 0.3605459696111254,
+  "epoch": 0.38629925315477726,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1253,11 +1253,100 @@
       "eval_steps_per_second": 0.928,
       "num_input_tokens_seen": 8187320,
       "step": 700
+    },
+    {
+      "epoch": 0.3631212979654906,
+      "grad_norm": 0.3215674690491891,
+      "learning_rate": 9.338209491537257e-05,
+      "loss": 0.8998,
+      "num_input_tokens_seen": 8245776,
+      "step": 705
+    },
+    {
+      "epoch": 0.3656966263198558,
+      "grad_norm": 0.36428692362396536,
+      "learning_rate": 9.326068709243727e-05,
+      "loss": 0.8999,
+      "num_input_tokens_seen": 8304280,
+      "step": 710
+    },
+    {
+      "epoch": 0.36827195467422097,
+      "grad_norm": 0.280459809393624,
+      "learning_rate": 9.313825614787177e-05,
+      "loss": 0.8983,
+      "num_input_tokens_seen": 8362728,
+      "step": 715
+    },
+    {
+      "epoch": 0.37084728302858616,
+      "grad_norm": 0.1819339731162554,
+      "learning_rate": 9.301480497718593e-05,
+      "loss": 0.892,
+      "num_input_tokens_seen": 8421224,
+      "step": 720
+    },
+    {
+      "epoch": 0.37342261138295135,
+      "grad_norm": 0.23784840563699303,
+      "learning_rate": 9.289033650001817e-05,
+      "loss": 0.9034,
+      "num_input_tokens_seen": 8479720,
+      "step": 725
+    },
+    {
+      "epoch": 0.3759979397373165,
+      "grad_norm": 0.24070744588741375,
+      "learning_rate": 9.276485366006634e-05,
+      "loss": 0.895,
+      "num_input_tokens_seen": 8538192,
+      "step": 730
+    },
+    {
+      "epoch": 0.3785732680916817,
+      "grad_norm": 0.24846723619231478,
+      "learning_rate": 9.263835942501807e-05,
+      "loss": 0.8973,
+      "num_input_tokens_seen": 8596664,
+      "step": 735
+    },
+    {
+      "epoch": 0.3811485964460469,
+      "grad_norm": 0.2601614440419362,
+      "learning_rate": 9.251085678648072e-05,
+      "loss": 0.8972,
+      "num_input_tokens_seen": 8655128,
+      "step": 740
+    },
+    {
+      "epoch": 0.38372392480041206,
+      "grad_norm": 0.30194733839751087,
+      "learning_rate": 9.238234875991046e-05,
+      "loss": 0.8987,
+      "num_input_tokens_seen": 8713624,
+      "step": 745
+    },
+    {
+      "epoch": 0.38629925315477726,
+      "grad_norm": 0.3015609177439829,
+      "learning_rate": 9.225283838454111e-05,
+      "loss": 0.9005,
+      "num_input_tokens_seen": 8772104,
+      "step": 750
+    },
+    {
+      "epoch": 0.38629925315477726,
+      "eval_loss": 0.8981761336326599,
+      "eval_runtime": 16.0177,
+      "eval_samples_per_second": 3.746,
+      "eval_steps_per_second": 0.936,
+      "num_input_tokens_seen": 8772104,
+      "step": 750
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 8187320,
+  "num_input_tokens_seen": 8772104,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1272,7 +1361,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 459709441638400.0,
+  "total_flos": 492548696834048.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null