Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae4ae60a26ee99e11a2e5ab6fb595036c6ed6a11a5c18815e41835fd861d1bc
+oid sha256:cb5f3724b5d59ea4e0a9371b33e20124137112f04ac962fd4bc5e834b083db05
 size 18516456

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 sha256:959a125ff18cd438ec4c80e2c5c95463a0446d6e8fccc4f0e5522dd9314fca8f
+size 27700976

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 sha256:08682e5ba6f3c3889ec79756688eb2a1e839e2e0b2d8d9b28484ef9db0d1b829
+size 27700976

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 sha256:2b29ae75df4490c491c4301676ec1b8d1154fed1e0a211aa5943a6f16f309cd9
+size 27700976

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:c9f755f55700d124eeb27776705e0e11433122a60b2aa0650a5420a931faeaf9
+size 27700976

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:e217f19544c300bb2d3991b8a514f4a179cf76123f6edfd5999fba2e2243a4c8
+size 411571

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 sha256:4368d7486d6127b13167c50cbc627b3993283a681daf72643efce836dd5d545a
+size 411507

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 sha256:297e66e1bbff69bd1001231f461fc0448f550fb8d4cbe1bafd584eac352ee3d0
+size 411507

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 sha256:59cbd2781ce6dd216ab1f908839e903ed36677341205d2403154d114808faa0e
+size 411507

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 sha256:8cd94ecf5c982ee0e060d3e07a575ce03dc3b0f289b5e32a1f65d3b6366a8a0e
+oid sha256:9089a2e73aa73e2c09752311bdfa67c1ed286ab83bb4bc61dbf851e8193bb593
 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": 0.3347926860674736,
+  "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": 0.929,
       "num_input_tokens_seen": 7602512,
       "step": 650
+    },
+    {
+      "epoch": 0.3373680144218388,
+      "grad_norm": 0.620349194493935,
+      "learning_rate": 9.453928183013385e-05,
+      "loss": 0.8929,
+      "num_input_tokens_seen": 7660968,
+      "step": 655
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 0.18611846349930314,
+      "learning_rate": 9.442825912005202e-05,
+      "loss": 0.9078,
+      "num_input_tokens_seen": 7719448,
+      "step": 660
+    },
+    {
+      "epoch": 0.34251867113056916,
+      "grad_norm": 0.4448289413172567,
+      "learning_rate": 9.431618567508933e-05,
+      "loss": 0.8963,
+      "num_input_tokens_seen": 7777928,
+      "step": 665
+    },
+    {
+      "epoch": 0.34509399948493436,
+      "grad_norm": 0.6187189362250411,
+      "learning_rate": 9.420306414579925e-05,
+      "loss": 0.9134,
+      "num_input_tokens_seen": 7836424,
+      "step": 670
+    },
+    {
+      "epoch": 0.3476693278392995,
+      "grad_norm": 0.35247743418537675,
+      "learning_rate": 9.408889720752266e-05,
+      "loss": 0.8984,
+      "num_input_tokens_seen": 7894904,
+      "step": 675
+    },
+    {
+      "epoch": 0.3502446561936647,
+      "grad_norm": 0.20652916455346712,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.8997,
+      "num_input_tokens_seen": 7953432,
+      "step": 680
+    },
+    {
+      "epoch": 0.3528199845480299,
+      "grad_norm": 0.4289996063998063,
+      "learning_rate": 9.385743792892982e-05,
+      "loss": 0.8926,
+      "num_input_tokens_seen": 8011888,
+      "step": 685
+    },
+    {
+      "epoch": 0.35539531290239507,
+      "grad_norm": 0.13764054506536547,
+      "learning_rate": 9.374015106265968e-05,
+      "loss": 0.9008,
+      "num_input_tokens_seen": 8070344,
+      "step": 690
+    },
+    {
+      "epoch": 0.35797064125676026,
+      "grad_norm": 0.22142459689499855,
+      "learning_rate": 9.362182973536569e-05,
+      "loss": 0.8986,
+      "num_input_tokens_seen": 8128816,
+      "step": 695
+    },
+    {
+      "epoch": 0.3605459696111254,
+      "grad_norm": 0.3234539650829873,
+      "learning_rate": 9.35024767453647e-05,
+      "loss": 0.8972,
+      "num_input_tokens_seen": 8187320,
+      "step": 700
+    },
+    {
+      "epoch": 0.3605459696111254,
+      "eval_loss": 0.9028835892677307,
+      "eval_runtime": 16.1635,
+      "eval_samples_per_second": 3.712,
+      "eval_steps_per_second": 0.928,
+      "num_input_tokens_seen": 8187320,
+      "step": 700
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "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": 426870884270080.0,
+  "total_flos": 459709441638400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null