Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ad4a76028a7f83ee44275d3e3a7c646bb4cd4ceb75431117f2d8b0f219b774
+oid sha256:7156b16f127d3e2296e6ada4ebf9cbb8c48381f16d088d0a874a522c40e99a16
 size 29034840

last-checkpoint/global_step450/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:a06e1adc0a80d44504c1dee1034eca4ca2963ada9c46ca490451212b5e42fbd2
+size 43429616

last-checkpoint/global_step450/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7851ab2d0a65baa1034c92407e075dd34b436bdc15606a42192d3eeb5625274e
+size 43429616

last-checkpoint/global_step450/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092821d92b2be112f83a63e8e11290ed76faf8f75d97035c702643fbdee6fc73
+size 43429616

last-checkpoint/global_step450/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:f2c4afd4a5961b09abdb5fb5f9e5b29c3f2a8f6df9ebd068bb2b373e6cf53991
+size 43429616

last-checkpoint/global_step450/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c43b6581640ec9140a8e671944ff69d96a0284c4069ddbe5a73547523d050e
+size 637299

last-checkpoint/global_step450/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7b078653231149a903bc00280c61fc902a6ebe6078af02817b5efd13e9ef2b
+size 637171

last-checkpoint/global_step450/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3014bb4485c273ec85ee6adab304455dcd75b99ca668f9c10e04f1ebc443fec8
+size 637171

last-checkpoint/global_step450/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23e7a4eb8e027c3a1e9ed72ab3097610a2c4faa00790d4b003da7cdb06018e2
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step400
+global_step450

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543ef05f530d40ee20b8d626b07a69b86597aca643e48897571062f973efe84f
+oid sha256:7dbc6521b0b64cb12d818506108fcf257a4089ca8a9b1e453776ed3e032e7176
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a23f732e43838ce0398d2636885ac16badbb9bcbc04d1406069ba3027bc5ae0
+oid sha256:2b13e3da1b0679cab1bab94f893e385a9a224d3335b5a6f62602f33c2be88d03
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10cce960e7068b051c05e35ed6160656be9091c63f13796ac2ed7e9c84e5a72
+oid sha256:6a24f0e0f117b5a8236e0d12594c0c358f41ef00068d4460002e95ad1cc3cb1c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f6049e212b1df5cefc5d834afcd8cc052c73f1457449e9fe8a38d514f54078
+oid sha256:e46e4eab6c4a25d84ad36ddf1357401788adeeb6388c03cefa35a63b52ee7610
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7779b5dd7047c5846ea43ed002061c3588a7e29e0d9f0ca42655eab3f8410e99
+oid sha256:581bd51b94cb26100e335b86a6da2b6d11272f4e7dfeb8188f963bb8c6dcbb27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8932263255119324,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-300",
-  "epoch": 0.20602626834921453,
+  "epoch": 0.23177955189286634,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -719,11 +719,100 @@
       "eval_steps_per_second": 0.757,
       "num_input_tokens_seen": 4678384,
       "step": 400
+    },
+    {
+      "epoch": 0.2086015967035797,
+      "grad_norm": 0.4854922483196253,
+      "learning_rate": 9.920168738030807e-05,
+      "loss": 0.8951,
+      "num_input_tokens_seen": 4736904,
+      "step": 405
+    },
+    {
+      "epoch": 0.2111769250579449,
+      "grad_norm": 0.4537032287993717,
+      "learning_rate": 9.916332757010799e-05,
+      "loss": 0.9131,
+      "num_input_tokens_seen": 4795376,
+      "step": 410
+    },
+    {
+      "epoch": 0.21375225341231008,
+      "grad_norm": 0.46655140937482126,
+      "learning_rate": 9.912407541224213e-05,
+      "loss": 0.8923,
+      "num_input_tokens_seen": 4853880,
+      "step": 415
+    },
+    {
+      "epoch": 0.21632758176667524,
+      "grad_norm": 0.3608301258843965,
+      "learning_rate": 9.908393161916374e-05,
+      "loss": 0.9026,
+      "num_input_tokens_seen": 4912360,
+      "step": 420
+    },
+    {
+      "epoch": 0.21890291012104043,
+      "grad_norm": 0.5055648531803498,
+      "learning_rate": 9.904289691950979e-05,
+      "loss": 0.905,
+      "num_input_tokens_seen": 4970872,
+      "step": 425
+    },
+    {
+      "epoch": 0.22147823847540563,
+      "grad_norm": 0.3171606869940592,
+      "learning_rate": 9.900097205808789e-05,
+      "loss": 0.8941,
+      "num_input_tokens_seen": 5029304,
+      "step": 430
+    },
+    {
+      "epoch": 0.2240535668297708,
+      "grad_norm": 0.5798722428230844,
+      "learning_rate": 9.895815779586262e-05,
+      "loss": 0.9031,
+      "num_input_tokens_seen": 5087800,
+      "step": 435
+    },
+    {
+      "epoch": 0.22662889518413598,
+      "grad_norm": 0.5751083474979835,
+      "learning_rate": 9.891445490994182e-05,
+      "loss": 0.8975,
+      "num_input_tokens_seen": 5146312,
+      "step": 440
+    },
+    {
+      "epoch": 0.22920422353850115,
+      "grad_norm": 1.2316619525123293,
+      "learning_rate": 9.886986419356246e-05,
+      "loss": 0.901,
+      "num_input_tokens_seen": 5204800,
+      "step": 445
+    },
+    {
+      "epoch": 0.23177955189286634,
+      "grad_norm": 0.5953254293558816,
+      "learning_rate": 9.88243864560762e-05,
+      "loss": 0.9062,
+      "num_input_tokens_seen": 5263304,
+      "step": 450
+    },
+    {
+      "epoch": 0.23177955189286634,
+      "eval_loss": 0.9007609486579895,
+      "eval_runtime": 20.8827,
+      "eval_samples_per_second": 2.873,
+      "eval_steps_per_second": 0.718,
+      "num_input_tokens_seen": 5263304,
+      "step": 450
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 4678384,
+  "num_input_tokens_seen": 5263304,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -738,7 +827,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 308638862540800.0,
+  "total_flos": 347233811955712.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null