Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80d0303f147dcd83f97c68d1de338e51e85f076089eb9eec3b8eff422c8bc34
+oid sha256:618ddb5842b77a277ba2fb75499d245929924ad35e8899db3bc116e2707491d1
 size 18516456

last-checkpoint/global_step800/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:e13bc46742e9ac6b8826aaf99222596ad1b3d3642e6e019519e69780060aa8cb
+size 27700976

last-checkpoint/global_step800/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:ebdaadb5ca1a803780a150d856fb183d325ff11b1fa39f812fd71d111080857d
+size 27700976

last-checkpoint/global_step800/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c14ef3f1938255ceaa58d153907ddc24c7932c78f0b755a852b5df87f86a0e7
+size 27700976

last-checkpoint/global_step800/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8be0645c05ec7ac3928e44a3087fe670a26826c0c9ecd5a2c78c5e2a015ec6
+size 27700976

last-checkpoint/global_step800/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b3ecca13012e7c7b1a2ef21b153dca6f20a38d9a089a9aae9d9df28bdbd80e
+size 411571

last-checkpoint/global_step800/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080d4cee83c2987351a8f8936bb25b274b59e0bccfc2c831b3ccf7466a42f4ec
+size 411507

last-checkpoint/global_step800/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4822198856a96d2b689d013db79d5a9307c4e3bff2580679b724c54d055d3a
+size 411507

last-checkpoint/global_step800/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337cc0ab48878ede739aca0b4a98eff5a797126a290e7e34991a9f09dbbf1305
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step750
+global_step800

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b4ef73f3603a1b91082ee108fa8299ebe45fb3cdeec7d0bdca1982af5bf07d
+oid sha256:b4f003069486a57c6ac033f30cf4c4213eb6b7d659bab68a5a50fdb8da7c4118
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882eccb2a272cf97cd645050bd077c971e48e78584f717a1b1cc9b5f1c9326dc
+oid sha256:a016ef89b4392d083b2c15a7cf06a39bc61a759f648cf6dc03f1c32b89a526aa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1626bac54f5806a604b7efdd749c5b65d63bbb40fc55c3744aae6130aa24f3de
+oid sha256:9b56fe0893036dc052d18d90feba4328b90ea71561942150b07406ac3d7a700e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40cf83ff997228172cf0b991f9d5209728ccf2f0a75841db5e31e647779a1ad2
+oid sha256:c0c203d12c2c308dab785ed672c9ca27fb6a2f72acd1e1552d1516c7b0006013
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ccf9d8c4b5840071603429d56208abefd14e276e9351f1160a607485df78ae
+oid sha256:5d85b710a5709549c0b4daddcc052f2ed242a5d916ac9ca030c805e7ff501c88
 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": 0.38629925315477726,
+  "epoch": 0.41205253669842906,
   "eval_steps": 50,
-  "global_step": 750,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1342,11 +1342,100 @@
       "eval_steps_per_second": 0.936,
       "num_input_tokens_seen": 8772104,
       "step": 750
+    },
+    {
+      "epoch": 0.3888745815091424,
+      "grad_norm": 0.44991480631292463,
+      "learning_rate": 9.21223287233121e-05,
+      "loss": 0.8973,
+      "num_input_tokens_seen": 8830568,
+      "step": 755
+    },
+    {
+      "epoch": 0.3914499098635076,
+      "grad_norm": 0.22570310903133853,
+      "learning_rate": 9.199082286279622e-05,
+      "loss": 0.8974,
+      "num_input_tokens_seen": 8889072,
+      "step": 760
+    },
+    {
+      "epoch": 0.3940252382178728,
+      "grad_norm": 0.22090133233732026,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 0.8985,
+      "num_input_tokens_seen": 8947568,
+      "step": 765
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 0.23738058530347297,
+      "learning_rate": 9.172483500792244e-05,
+      "loss": 0.8935,
+      "num_input_tokens_seen": 9006056,
+      "step": 770
+    },
+    {
+      "epoch": 0.39917589492660316,
+      "grad_norm": 0.41232659301572594,
+      "learning_rate": 9.159035930421658e-05,
+      "loss": 0.8985,
+      "num_input_tokens_seen": 9064592,
+      "step": 775
+    },
+    {
+      "epoch": 0.40175122328096835,
+      "grad_norm": 0.2004855543001356,
+      "learning_rate": 9.145489998237902e-05,
+      "loss": 0.9105,
+      "num_input_tokens_seen": 9123096,
+      "step": 780
+    },
+    {
+      "epoch": 0.4043265516353335,
+      "grad_norm": 0.16209487510237375,
+      "learning_rate": 9.131846024604274e-05,
+      "loss": 0.8925,
+      "num_input_tokens_seen": 9181576,
+      "step": 785
+    },
+    {
+      "epoch": 0.4069018799896987,
+      "grad_norm": 0.24319930530142153,
+      "learning_rate": 9.11810433220276e-05,
+      "loss": 0.8955,
+      "num_input_tokens_seen": 9240048,
+      "step": 790
+    },
+    {
+      "epoch": 0.40947720834406387,
+      "grad_norm": 0.24311562892750557,
+      "learning_rate": 9.104265246026415e-05,
+      "loss": 0.8986,
+      "num_input_tokens_seen": 9298528,
+      "step": 795
+    },
+    {
+      "epoch": 0.41205253669842906,
+      "grad_norm": 0.2891177185942039,
+      "learning_rate": 9.090329093371666e-05,
+      "loss": 0.8881,
+      "num_input_tokens_seen": 9357016,
+      "step": 800
+    },
+    {
+      "epoch": 0.41205253669842906,
+      "eval_loss": 0.8973079919815063,
+      "eval_runtime": 16.1396,
+      "eval_samples_per_second": 3.718,
+      "eval_steps_per_second": 0.929,
+      "num_input_tokens_seen": 9357016,
+      "step": 800
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 8772104,
+  "num_input_tokens_seen": 9357016,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1361,7 +1450,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492548696834048.0,
+  "total_flos": 525396292665344.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null