Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0a41144b9d8eea3b3f1de8e9e5e7c14c303c31098798928859d47cbd861a53
+oid sha256:d1513791e52117a6d639f05fdddf98b812e9b7c86a4830e79581dc7ae45e41a8
 size 18516456

last-checkpoint/global_step600/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:e001b716b7761d5f26afeeeca60792842fe9e83b9ffa87219c288d1151b43cea
+size 27700976

last-checkpoint/global_step600/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:c980c157626ebe0b6572e765fb0ca4e03fdf830e1af619ed547c028b1adfc05f
+size 27700976

last-checkpoint/global_step600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5e4e4bafd0c2065fb0b393c899470e5c04f884ad18922da69ffd600b76e537
+size 27700976

last-checkpoint/global_step600/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:be505a41635be61a02fd592e1b7127e678696e4df49f6079916360dd93072365
+size 27700976

last-checkpoint/global_step600/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b052900c51a35b486cf1d169e3f9bb43bb347a08993f04f7d2bc876d77a5b629
+size 411571

last-checkpoint/global_step600/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b726a6dc7d1f23f8e05626afada1a90c9c1803525016cb7066d9182d7a16c3
+size 411507

last-checkpoint/global_step600/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac220097d807b06f51202705dab924ba89f125ce707bbea38c4bed916e8188fa
+size 411507

last-checkpoint/global_step600/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb0263e2815855153236c96d52c7c09d14d37a34a30e5fc2a8bd3e9bb7ee1d7
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step550
+global_step600

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae78313eb528c8d3695eebaf4de3539bd0a0bc6ee18c66af1ee183442f1758a0
+oid sha256:a81e3916b1392c4c49afb171dee5415c15f5a5a5af8749b28195fcfa0596699c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b38031f60d9e88601d369ef46bcdcf2b5b03f2cb4ba93853bcb2328df7ebb7c
+oid sha256:9a781038dd714b87b8adb1aac8dbc8217ceb607428a992133954ad522365236e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58092375c93d237cd0e3149aecfbf83e2acdae46279e07a32920d01cb507e64
+oid sha256:9446c3db15f382a5546f13622787fc99392a5e0bc8a9ca2da1838de7ab621a37
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83cd4bbff9962da7ec6787fcea8d65df7096917f9a5902e249ba7aee8887fe5f
+oid sha256:1f11e7a6b3faa884fc23044e3772ff9dd72c257f02e121665061e2a03d518bd9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8b881f6464ee76e192f8a5dbebbec89a38d087d3502270b9c7e6038613f3b2
+oid sha256:b76b388bede074656df32b92902ac42b965557bfee0c930366af07d8382b1b4a
 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": 0.28328611898017,
+  "epoch": 0.3090394025238218,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -986,11 +986,100 @@
       "eval_steps_per_second": 0.883,
       "num_input_tokens_seen": 6432936,
       "step": 550
+    },
+    {
+      "epoch": 0.28586144733453517,
+      "grad_norm": 0.5334970266367584,
+      "learning_rate": 9.653522193117013e-05,
+      "loss": 0.8981,
+      "num_input_tokens_seen": 6491400,
+      "step": 555
+    },
+    {
+      "epoch": 0.28843677568890036,
+      "grad_norm": 0.33261202813259866,
+      "learning_rate": 9.644573182726035e-05,
+      "loss": 0.9041,
+      "num_input_tokens_seen": 6549872,
+      "step": 560
+    },
+    {
+      "epoch": 0.2910121040432655,
+      "grad_norm": 0.19122862132727417,
+      "learning_rate": 9.63551432749426e-05,
+      "loss": 0.9024,
+      "num_input_tokens_seen": 6608296,
+      "step": 565
+    },
+    {
+      "epoch": 0.2935874323976307,
+      "grad_norm": 0.27778009425329764,
+      "learning_rate": 9.626345841664953e-05,
+      "loss": 0.9002,
+      "num_input_tokens_seen": 6666768,
+      "step": 570
+    },
+    {
+      "epoch": 0.2961627607519959,
+      "grad_norm": 0.3065314332046026,
+      "learning_rate": 9.617067942074153e-05,
+      "loss": 0.9035,
+      "num_input_tokens_seen": 6725248,
+      "step": 575
+    },
+    {
+      "epoch": 0.29873808910636107,
+      "grad_norm": 0.24431496415058412,
+      "learning_rate": 9.607680848145558e-05,
+      "loss": 0.9019,
+      "num_input_tokens_seen": 6783680,
+      "step": 580
+    },
+    {
+      "epoch": 0.30131341746072626,
+      "grad_norm": 0.27088193021301504,
+      "learning_rate": 9.598184781885318e-05,
+      "loss": 0.9001,
+      "num_input_tokens_seen": 6842144,
+      "step": 585
+    },
+    {
+      "epoch": 0.3038887458150914,
+      "grad_norm": 0.33893098113605125,
+      "learning_rate": 9.588579967876806e-05,
+      "loss": 0.8961,
+      "num_input_tokens_seen": 6900656,
+      "step": 590
+    },
+    {
+      "epoch": 0.3064640741694566,
+      "grad_norm": 0.3038921833221806,
+      "learning_rate": 9.578866633275288e-05,
+      "loss": 0.9,
+      "num_input_tokens_seen": 6959128,
+      "step": 595
+    },
+    {
+      "epoch": 0.3090394025238218,
+      "grad_norm": 0.48929637235055645,
+      "learning_rate": 9.569045007802559e-05,
+      "loss": 0.9046,
+      "num_input_tokens_seen": 7017576,
+      "step": 600
+    },
+    {
+      "epoch": 0.3090394025238218,
+      "eval_loss": 0.9053278565406799,
+      "eval_runtime": 17.1218,
+      "eval_samples_per_second": 3.504,
+      "eval_steps_per_second": 0.876,
+      "num_input_tokens_seen": 7017576,
+      "step": 600
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 6432936,
+  "num_input_tokens_seen": 7017576,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1005,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 361192817164288.0,
+  "total_flos": 394023670644736.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null