Training in progress, step 1750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9914360b2dead740bb4f8973f7876b182880fd878912194cb890333ef7f606
+oid sha256:0ef73e2283ef0a8265cb8500b9ad3f8507559811b231f9ac4422b8beb4ea24ca
 size 18516456

last-checkpoint/global_step1750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9fae63a7e44699fdfa04e2a64bd0cee94e2d47eef691bac08448532285e8a7
+size 27700976

last-checkpoint/global_step1750/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:c5583adcea1a5be6aef8847ec3fe33fca89339e049bea5960f733fa00fc47b3a
+size 27700976

last-checkpoint/global_step1750/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942a54668d6e20d41b592b24432607bd4bc5d74a15c32e13e5395c88ee124f83
+size 27700976

last-checkpoint/global_step1750/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:d2eb932b7b0a4a13c81baa3321767b78c6662a1534d360912037f0bbcf7dd28d
+size 27700976

last-checkpoint/global_step1750/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc762ab4c4fa09aee66d1cdc3bd9c18b0e089540ff771b477c3f14712574bd78
+size 411571

last-checkpoint/global_step1750/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a5367ee82bfa4de533d053692b6361c80607824890bd86394bf93f0d1a7afc
+size 411507

last-checkpoint/global_step1750/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d996e234024b2b7cc1ed78e09085b9a5e4f18cfe3e6a9cdac547a6936e86ad
+size 411507

last-checkpoint/global_step1750/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80240f90b65712451f890a49680db51de5c309d6547f38e60d8ee2aec311d7c
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step1700
+global_step1750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7c17922709137dd2f358be87cc431f7959a56821e2d051582e81679e2d388e
+oid sha256:222e5f04f66dfcca4efb2d648f5a480d56c2a07755d7a1bae8232d01d4b479ce
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf0ec3cc431efdc1cb595b27e74fc020021d53f5c11850d7490a79bf42b71d6
+oid sha256:150a9cfa07bd33135b1b8b22033907e44137689de662dda0a482f3af84c5a1ff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148fd0a663c121acf74d815964bc0d08d07065e8503b03adfd967fdaf63a6abc
+oid sha256:c0c0d7619e94c90efa0c89a1f208db53b48c726519761710da6fbc31a80651d8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56589f6c34527656fe0dc752874cfc1460efbb5c0c3f874c4cd09d6415dd16c1
+oid sha256:aa66a4b2f749b1ec7e8868668dc670ff3f6d8df765a5249122f980ae5aae6a54
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcafe96450339d5b6e4ff3a8d909c473a6afaab9bb34bc798805cded569190ca
+oid sha256:2a1c59a2217a7993f4a6258f4be38869d3dc42c6bc2349bde5d4858846c79cb4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6319106221199036,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1600",
-  "epoch": 0.8756116404841617,
+  "epoch": 0.9013649240278135,
   "eval_steps": 50,
-  "global_step": 1700,
+  "global_step": 1750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3033,11 +3033,100 @@
       "eval_steps_per_second": 0.93,
       "num_input_tokens_seen": 19883504,
       "step": 1700
+    },
+    {
+      "epoch": 0.8781869688385269,
+      "grad_norm": 4.527262723362309,
+      "learning_rate": 5.388659258287102e-05,
+      "loss": 0.5823,
+      "num_input_tokens_seen": 19942000,
+      "step": 1705
+    },
+    {
+      "epoch": 0.8807622971928921,
+      "grad_norm": 4.628112845411063,
+      "learning_rate": 5.364412597363759e-05,
+      "loss": 0.5446,
+      "num_input_tokens_seen": 20000440,
+      "step": 1710
+    },
+    {
+      "epoch": 0.8833376255472573,
+      "grad_norm": 6.077375809046342,
+      "learning_rate": 5.3401573180287426e-05,
+      "loss": 0.5769,
+      "num_input_tokens_seen": 20058920,
+      "step": 1715
+    },
+    {
+      "epoch": 0.8859129539016225,
+      "grad_norm": 6.492863688878202,
+      "learning_rate": 5.315893993922986e-05,
+      "loss": 0.5614,
+      "num_input_tokens_seen": 20117416,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8884882822559876,
+      "grad_norm": 5.332057542240503,
+      "learning_rate": 5.29162319887768e-05,
+      "loss": 0.5215,
+      "num_input_tokens_seen": 20175936,
+      "step": 1725
+    },
+    {
+      "epoch": 0.8910636106103528,
+      "grad_norm": 3.8772752615113077,
+      "learning_rate": 5.26734550690071e-05,
+      "loss": 0.4968,
+      "num_input_tokens_seen": 20234368,
+      "step": 1730
+    },
+    {
+      "epoch": 0.893638938964718,
+      "grad_norm": 4.886426418731965,
+      "learning_rate": 5.243061492163073e-05,
+      "loss": 0.5029,
+      "num_input_tokens_seen": 20292856,
+      "step": 1735
+    },
+    {
+      "epoch": 0.8962142673190832,
+      "grad_norm": 4.031774194047053,
+      "learning_rate": 5.2187717289852955e-05,
+      "loss": 0.5249,
+      "num_input_tokens_seen": 20351272,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8987895956734484,
+      "grad_norm": 5.344580011428224,
+      "learning_rate": 5.1944767918238624e-05,
+      "loss": 0.5801,
+      "num_input_tokens_seen": 20409744,
+      "step": 1745
+    },
+    {
+      "epoch": 0.9013649240278135,
+      "grad_norm": 3.923379435953565,
+      "learning_rate": 5.170177255257618e-05,
+      "loss": 0.546,
+      "num_input_tokens_seen": 20468200,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9013649240278135,
+      "eval_loss": 0.672294020652771,
+      "eval_runtime": 16.0203,
+      "eval_samples_per_second": 3.745,
+      "eval_steps_per_second": 0.936,
+      "num_input_tokens_seen": 20468200,
+      "step": 1750
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 19883504,
+  "num_input_tokens_seen": 20468200,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3052,7 +3141,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1116505381011456.0,
+  "total_flos": 1149340689891328.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null