Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67d46cdc279c111f3d8b6cd0c68158fe4239ea365a1c2b31f1709a759de013a
+oid sha256:086f56d8253ad2de065083ad9ed3e401f206ca6169266148720dc9056e97e11d
 size 29034840

last-checkpoint/global_step700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd9660af62d03296045b76792c76fdd9cd1bfc7c53492a1599f6b67d7a48317
+size 43429616

last-checkpoint/global_step700/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:d56985c9ce25564c02f637b19f88557f60fa453b0df988ca8bba5e7bfa14df97
+size 43429616

last-checkpoint/global_step700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a39001e7b1938d07665b62309720203060c26b8f08d1b1e8f5740c71cfa763
+size 43429616

last-checkpoint/global_step700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b7803c640a3eb1aeb12efa6bc7a9345531f1f9a2c619024ccf46c78b577d64
+size 43429616

last-checkpoint/global_step700/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1016e4296788968087a2a2e95f3a62ee2c6085b5340c3e92171dae571481ea55
+size 637299

last-checkpoint/global_step700/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb87f12b7ce572b38ad895ddc218de834da4bf60ec37d070e1017300431fe756
+size 637171

last-checkpoint/global_step700/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d458531685f08f79fecf5600b5b32a91ce3e7e9e5c6bf39ed77dc64a6777d6
+size 637171

last-checkpoint/global_step700/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6548dde312f71fd6a7a282d97e0df54d5ebeb16b695ea5d8f6c774bbc1ca3bb
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step650
+global_step700

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8044e4c53158c210a17648ba8f2dc2d25a25bbfc55f686015542618eb652a33e
+oid sha256:e7d74de51245105e1fbf57a6707ef3538b353952485508f6e2f8f74dc5d479d4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd85d7fa425e7888c973f1c2985ac15ca21b5e6171fe140a401c2bc75ca46ff
+oid sha256:0617c9eb6cf7df57b2e0bb53cfe17c05f0910de56fe5b14427fe39ab54a44782
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7915667371a58f1598639e0d1c20a0c59c783c14580cd040a6631eb4ea2311e
+oid sha256:ed68a365057022897d9645ee60902a77102f43215dcdf2ddd5d3842b6a8446d8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dd78929ad7f0fbf37fdb1284e8edf0424350f6e6ce1cd5a3ee78979af3d3cb
+oid sha256:63ebaa0c302cadbdfcd9f8ee2289e35ecf9c9fc8c9968fc0c05f100dac20c6b9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97610cd95fe06fdca35f3af5c085e6621fc4c4d7c3ecef7fbe6456b650501b2b
+oid sha256:c2f570b3fae67de7e649855487e96bf548cf918d7ba3d40d1baf265735ed69a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.787663459777832,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-600",
-  "epoch": 0.3347926860674736,
+  "best_metric": 0.7318872809410095,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-700",
+  "epoch": 0.3605459696111254,
   "eval_steps": 50,
-  "global_step": 650,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1164,11 +1164,100 @@
       "eval_steps_per_second": 0.759,
       "num_input_tokens_seen": 7602512,
       "step": 650
+    },
+    {
+      "epoch": 0.3373680144218388,
+      "grad_norm": 6.586425160827751,
+      "learning_rate": 9.620822953030652e-05,
+      "loss": 0.8131,
+      "num_input_tokens_seen": 7660968,
+      "step": 655
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 6.92970378602844,
+      "learning_rate": 9.612643863094163e-05,
+      "loss": 0.8348,
+      "num_input_tokens_seen": 7719448,
+      "step": 660
+    },
+    {
+      "epoch": 0.34251867113056916,
+      "grad_norm": 8.35228285894448,
+      "learning_rate": 9.604381050550038e-05,
+      "loss": 0.8289,
+      "num_input_tokens_seen": 7777928,
+      "step": 665
+    },
+    {
+      "epoch": 0.34509399948493436,
+      "grad_norm": 12.894782157020227,
+      "learning_rate": 9.596034665373916e-05,
+      "loss": 0.7758,
+      "num_input_tokens_seen": 7836424,
+      "step": 670
+    },
+    {
+      "epoch": 0.3476693278392995,
+      "grad_norm": 13.409694970235305,
+      "learning_rate": 9.587604859058334e-05,
+      "loss": 0.8189,
+      "num_input_tokens_seen": 7894904,
+      "step": 675
+    },
+    {
+      "epoch": 0.3502446561936647,
+      "grad_norm": 8.783205826578632,
+      "learning_rate": 9.579091784609984e-05,
+      "loss": 0.8221,
+      "num_input_tokens_seen": 7953432,
+      "step": 680
+    },
+    {
+      "epoch": 0.3528199845480299,
+      "grad_norm": 8.368380903445857,
+      "learning_rate": 9.570495596546926e-05,
+      "loss": 0.8378,
+      "num_input_tokens_seen": 8011888,
+      "step": 685
+    },
+    {
+      "epoch": 0.35539531290239507,
+      "grad_norm": 6.7086179135551145,
+      "learning_rate": 9.561816450895793e-05,
+      "loss": 0.7529,
+      "num_input_tokens_seen": 8070344,
+      "step": 690
+    },
+    {
+      "epoch": 0.35797064125676026,
+      "grad_norm": 8.476897088436242,
+      "learning_rate": 9.55305450518895e-05,
+      "loss": 0.7311,
+      "num_input_tokens_seen": 8128816,
+      "step": 695
+    },
+    {
+      "epoch": 0.3605459696111254,
+      "grad_norm": 10.427785019598666,
+      "learning_rate": 9.544209918461642e-05,
+      "loss": 0.774,
+      "num_input_tokens_seen": 8187320,
+      "step": 700
+    },
+    {
+      "epoch": 0.3605459696111254,
+      "eval_loss": 0.7318872809410095,
+      "eval_runtime": 19.6917,
+      "eval_samples_per_second": 3.047,
+      "eval_steps_per_second": 0.762,
+      "num_input_tokens_seen": 8187320,
+      "step": 700
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 7602512,
+  "num_input_tokens_seen": 8187320,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1183,7 +1272,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 501587549356032.0,
+  "total_flos": 540175003287552.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null