Training in progress, step 1750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40488b690d3cbb62aef973e623da597fed2f1f503eac48f0d6e9e0140377208a
+oid sha256:95cb389d8c3bb8b023cd12cb33d7b6158b8a28b87779d6ac67f1897a141b861b
 size 29034840

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 sha256:2e8347056f1292ff97b1d73659503a0507b0653d32cc7a12e8ff9a1335f37028
+size 43429616

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 sha256:2cbf33845645e53961a3c6bbb0a1d7cf348afeabd1d176afadd7cdfbca377cca
+size 43429616

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:e35335e72d59742db35a88656b081cd053a9d171496abe9eee765199e679e519
+size 43429616

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 sha256:1296baea3815cacda5acc196065ffa65a15808a01253fad978a91e114aff5889
+size 43429616

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 sha256:32f8c5b1da88eb2c3bd967f43f6931692786200c22aa97a202ebf66082557677
+size 637299

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 sha256:037fcd6af5c00ed77baab88df849e8698d197844c05cc017806d8e74ae2f1b95
+size 637171

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 sha256:99970103805cf54854383f6ea3849fdf6038c8a68a2a992a04bd9ebaf6f4251d
+size 637171

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:cd3d1f71573606393b3cb5f1deddf23fe9aa63fa2404d1a9570e793efcfa8328
+size 637171

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": 0.4339977502822876,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-1250",
-  "epoch": 0.43780582024208087,
+  "best_metric": 0.4234265685081482,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-1750",
+  "epoch": 0.45068246201390677,
   "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": 0.786,
       "num_input_tokens_seen": 17845600,
       "step": 1700
+    },
+    {
+      "epoch": 0.43909348441926344,
+      "grad_norm": 6.805905061208508,
+      "learning_rate": 5.388659258287102e-05,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 17897920,
+      "step": 1705
+    },
+    {
+      "epoch": 0.44038114859644606,
+      "grad_norm": 6.964220035587859,
+      "learning_rate": 5.364412597363759e-05,
+      "loss": 0.3599,
+      "num_input_tokens_seen": 17950920,
+      "step": 1710
+    },
+    {
+      "epoch": 0.4416688127736286,
+      "grad_norm": 6.2080800188283956,
+      "learning_rate": 5.3401573180287426e-05,
+      "loss": 0.3681,
+      "num_input_tokens_seen": 18003280,
+      "step": 1715
+    },
+    {
+      "epoch": 0.44295647695081125,
+      "grad_norm": 6.3073464125282195,
+      "learning_rate": 5.315893993922986e-05,
+      "loss": 0.4005,
+      "num_input_tokens_seen": 18056296,
+      "step": 1720
+    },
+    {
+      "epoch": 0.4442441411279938,
+      "grad_norm": 4.274996116585604,
+      "learning_rate": 5.29162319887768e-05,
+      "loss": 0.3513,
+      "num_input_tokens_seen": 18108904,
+      "step": 1725
+    },
+    {
+      "epoch": 0.4455318053051764,
+      "grad_norm": 2.3776496789610224,
+      "learning_rate": 5.26734550690071e-05,
+      "loss": 0.373,
+      "num_input_tokens_seen": 18160696,
+      "step": 1730
+    },
+    {
+      "epoch": 0.446819469482359,
+      "grad_norm": 5.321325318314331,
+      "learning_rate": 5.243061492163073e-05,
+      "loss": 0.4246,
+      "num_input_tokens_seen": 18213760,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4481071336595416,
+      "grad_norm": 4.658819445189394,
+      "learning_rate": 5.2187717289852955e-05,
+      "loss": 0.3703,
+      "num_input_tokens_seen": 18266424,
+      "step": 1740
+    },
+    {
+      "epoch": 0.4493947978367242,
+      "grad_norm": 4.197790185757161,
+      "learning_rate": 5.1944767918238624e-05,
+      "loss": 0.3763,
+      "num_input_tokens_seen": 18318984,
+      "step": 1745
+    },
+    {
+      "epoch": 0.45068246201390677,
+      "grad_norm": 8.378009104226413,
+      "learning_rate": 5.170177255257618e-05,
+      "loss": 0.3767,
+      "num_input_tokens_seen": 18371928,
+      "step": 1750
+    },
+    {
+      "epoch": 0.45068246201390677,
+      "eval_loss": 0.4234265685081482,
+      "eval_runtime": 38.3269,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 0.783,
+      "num_input_tokens_seen": 18371928,
+      "step": 1750
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 17845600,
+  "num_input_tokens_seen": 18371928,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3052,7 +3141,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1177420775555072.0,
+  "total_flos": 1212133561860096.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null