Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdde134a211d113ac15985ca670d8214e7b0ef4860c3a3926ee43121c0822b6
+oid sha256:83713538d7c41870e13178745ef172d71bfaba5ed873b0c7d6d31c872dec52a0
 size 29034840

last-checkpoint/global_step2300/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:c480d4e96a0bd563639b1776b600fa1c047335754c66e02c46c99cffe4037311
+size 43429616

last-checkpoint/global_step2300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc0760fe049d3fe1bd0af0fdf9a5bf355726668c6f32520fa8e32029accb34a
+size 43429616

last-checkpoint/global_step2300/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:e61aef05def6fd2d52ec80bdf2244163052aec271c3348bf360a7fa6458946f4
+size 43429616

last-checkpoint/global_step2300/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d3589648f3344e9d14f0b2a2e30b012d43fc0c721730a9b8ed0a02ad5e6bb9
+size 43429616

last-checkpoint/global_step2300/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fa8b00108fdb11131034658fba7089061501022b3de6f5e243a3686a644276
+size 637299

last-checkpoint/global_step2300/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf246967f429ff75d5cfa4a4b8804f191fdc81e48b9cd0c807a5b4a379efc21
+size 637171

last-checkpoint/global_step2300/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5404d462155135ee507d74ac8a0754e37f4d4a952bf81ff326ba7ab6b40985
+size 637171

last-checkpoint/global_step2300/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30995616fd56844cf161de30a81dacea08f0a755be391d0f4ff601fe522ca55a
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2250
+global_step2300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3187a61ccc2722c440dc24ae4a6eefe6b9e5daccf9e92473bbb4483c7751ea77
+oid sha256:1d25cbcbbaa0866ea9c7365cb49b84e805db119693e615f5a1898a6ebfe997e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f2a0df922fb3337cf2562745ebe8d5adf433ca45cb4e3da33a21b48183c000
+oid sha256:a883389afac12125c2c6bf62631b7de0220fdb0020d24cd0c6e8f8858dd3b362
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d84b5276f687f44c9af60b1e41cd7b93a6d1659e36831a7bc021b5635d663b
+oid sha256:577d49de6d60035e159d9ebb1e6eabef79a55787b14ecea93a6a93c242661779
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d69159433c88b97106cf21b92eb5a3f66f0c826aa268d82a47b3faed1ac86cd
+oid sha256:b5f2dd1c21e06806a9ce39eeab45734dfb8a62b829f91a86d1f65f13102d6242
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6909ad505e808e7099dbcdd8062e5535575cbfa3b4d3a7b7d3390e6a93ed3b49
+oid sha256:25aeb77fef385fcfd5658b6aaea11fb8aa276239b7ba19a4f3504b86f45fbcc9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4194311797618866,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-1800",
-  "epoch": 0.5794488797321659,
+  "epoch": 0.5923255215039918,
   "eval_steps": 50,
-  "global_step": 2250,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4012,11 +4012,100 @@
       "eval_steps_per_second": 0.787,
       "num_input_tokens_seen": 23626952,
       "step": 2250
+    },
+    {
+      "epoch": 0.5807365439093485,
+      "grad_norm": 7.013960747751967,
+      "learning_rate": 2.7931010410023518e-05,
+      "loss": 0.3544,
+      "num_input_tokens_seen": 23680112,
+      "step": 2255
+    },
+    {
+      "epoch": 0.582024208086531,
+      "grad_norm": 4.605744038285181,
+      "learning_rate": 2.771308221117309e-05,
+      "loss": 0.3467,
+      "num_input_tokens_seen": 23731896,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5833118722637136,
+      "grad_norm": 4.9921005761457895,
+      "learning_rate": 2.749568110121545e-05,
+      "loss": 0.3374,
+      "num_input_tokens_seen": 23784616,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5845995364408962,
+      "grad_norm": 4.366796972583381,
+      "learning_rate": 2.7278812221718924e-05,
+      "loss": 0.3509,
+      "num_input_tokens_seen": 23836920,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5858872006180788,
+      "grad_norm": 3.5862787852890876,
+      "learning_rate": 2.7062480701664488e-05,
+      "loss": 0.3014,
+      "num_input_tokens_seen": 23890792,
+      "step": 2275
+    },
+    {
+      "epoch": 0.5871748647952614,
+      "grad_norm": 7.030699453643037,
+      "learning_rate": 2.6846691657324473e-05,
+      "loss": 0.4672,
+      "num_input_tokens_seen": 23943264,
+      "step": 2280
+    },
+    {
+      "epoch": 0.588462528972444,
+      "grad_norm": 3.981559816955943,
+      "learning_rate": 2.663145019214163e-05,
+      "loss": 0.2817,
+      "num_input_tokens_seen": 23995760,
+      "step": 2285
+    },
+    {
+      "epoch": 0.5897501931496266,
+      "grad_norm": 4.699964630974459,
+      "learning_rate": 2.6416761396608362e-05,
+      "loss": 0.3538,
+      "num_input_tokens_seen": 24048696,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5910378573268091,
+      "grad_norm": 8.241455514660794,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 0.3018,
+      "num_input_tokens_seen": 24102248,
+      "step": 2295
+    },
+    {
+      "epoch": 0.5923255215039918,
+      "grad_norm": 3.2050310147654604,
+      "learning_rate": 2.598906211098643e-05,
+      "loss": 0.3322,
+      "num_input_tokens_seen": 24154624,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5923255215039918,
+      "eval_loss": 0.4960116744041443,
+      "eval_runtime": 38.142,
+      "eval_samples_per_second": 3.146,
+      "eval_steps_per_second": 0.787,
+      "num_input_tokens_seen": 24154624,
+      "step": 2300
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 23626952,
+  "num_input_tokens_seen": 24154624,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4031,7 +4120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1558781764042752.0,
+  "total_flos": 1593572224925696.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null