Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d159d3ba185322d9f83c53738ceab5e5c90742b79ccfaf680796d68d03ad7724
+oid sha256:e9d5ec3c39553916ddeed05ebc73c5ecc3358eb275ee803834c3cbefd37b2102
 size 29034840

last-checkpoint/global_step2399/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:c4577996b31a6b8a56e9904449dc510f2e89b1a976d452770e5e328bc6a0f199
+size 43429616

last-checkpoint/global_step2399/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2761daf2b7b3495246b19cf153163e9196305cdbb7009bcc566438f93ec17064
+size 43429616

last-checkpoint/global_step2399/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871748468fe9fc78e000545dab697fda41763346312ee75b29a300747db57657
+size 43429616

last-checkpoint/global_step2399/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264ed4f45d0a81458eca0848ba1c849cd1034e602ecce07f7629a6cf5712ab1e
+size 43429616

last-checkpoint/global_step2399/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b9c23eef2a4c3db1e183f63421a1cd0bcd927687f7473fa1ffdaec4b0fe396
+size 637299

last-checkpoint/global_step2399/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9aaebcfa876d33eec282f09be9bf7e06877cddd316fe66ac4c9b8df8087de3e
+size 637171

last-checkpoint/global_step2399/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e27213c0a50dcec5a10490092aff333ead082a73f56d0f2799679c8c1a09a9
+size 637171

last-checkpoint/global_step2399/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731e9d8fb7898d90d13c8d1d4ff5aeae78a7f020be87f4292f1693c89020d687
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2349
+global_step2399

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681faefe4cf303ca7f9bc3073b09b166da4f558d55bee3d5eee90ba5d83159bb
+oid sha256:6b8aff7a1897a7eaf48c78ea1f8115c061edfa2b6fa42280e2c1c58fe66b1f8a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0fb250f1d137fb55cef85743a342508178b4fe3a20c6793c82e279730ea280b
+oid sha256:1d73a7524f07999ef35d5d9b107dcc1678eae2ada841644e1bd00ec0734368c2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a0d7cfaa34f7e3738b4ef4989d693ed7864fed3b2a44ef1b6892fdcf026bb9
+oid sha256:149a2ed30e88bf94d622f8d7693f382286a49ac536a3f63efc50cab63f6b9f39
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a82aabe23bc62e289ef7d075c79f353bbc81286ec0f8964eabda4209d630e10
+oid sha256:18f12c1b5aae2b7d4bb968649839fc7ff1ce6131508baad4b633693b04cee910
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612a67548dc5f963b4ad7edb95989ed33dc109c454a3a196b8ccaf386ef2286b
+oid sha256:6242510adeb4d59877ccb2f625a69ecf628b2bfccb966d6143251f5bc2806c24
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.22014015913009644,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-2250",
-  "epoch": 1.210146793716199,
+  "epoch": 1.2359000772598505,
   "eval_steps": 50,
-  "global_step": 2350,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4190,11 +4190,100 @@
       "eval_steps_per_second": 0.759,
       "num_input_tokens_seen": 27479840,
       "step": 2350
+    },
+    {
+      "epoch": 1.212722122070564,
+      "grad_norm": 9.144283973474371,
+      "learning_rate": 3.6678798011291674e-05,
+      "loss": 0.242,
+      "num_input_tokens_seen": 27538344,
+      "step": 2355
+    },
+    {
+      "epoch": 1.2152974504249292,
+      "grad_norm": 12.80063906167105,
+      "learning_rate": 3.647360065838348e-05,
+      "loss": 0.2451,
+      "num_input_tokens_seen": 27596808,
+      "step": 2360
+    },
+    {
+      "epoch": 1.2178727787792945,
+      "grad_norm": 3.44448459243246,
+      "learning_rate": 3.6268648818777105e-05,
+      "loss": 0.2237,
+      "num_input_tokens_seen": 27655272,
+      "step": 2365
+    },
+    {
+      "epoch": 1.2204481071336595,
+      "grad_norm": 14.301919876267943,
+      "learning_rate": 3.606394621248709e-05,
+      "loss": 0.2033,
+      "num_input_tokens_seen": 27713784,
+      "step": 2370
+    },
+    {
+      "epoch": 1.2230234354880247,
+      "grad_norm": 11.349699284999199,
+      "learning_rate": 3.585949655500429e-05,
+      "loss": 0.2741,
+      "num_input_tokens_seen": 27772248,
+      "step": 2375
+    },
+    {
+      "epoch": 1.22559876384239,
+      "grad_norm": 4.036313729279471,
+      "learning_rate": 3.5655303557228335e-05,
+      "loss": 0.2677,
+      "num_input_tokens_seen": 27830704,
+      "step": 2380
+    },
+    {
+      "epoch": 1.228174092196755,
+      "grad_norm": 5.042006341816937,
+      "learning_rate": 3.545137092540035e-05,
+      "loss": 0.2117,
+      "num_input_tokens_seen": 27889160,
+      "step": 2385
+    },
+    {
+      "epoch": 1.2307494205511202,
+      "grad_norm": 4.191635671104207,
+      "learning_rate": 3.524770236103556e-05,
+      "loss": 0.2216,
+      "num_input_tokens_seen": 27947608,
+      "step": 2390
+    },
+    {
+      "epoch": 1.2333247489054855,
+      "grad_norm": 13.530120109841187,
+      "learning_rate": 3.504430156085629e-05,
+      "loss": 0.28,
+      "num_input_tokens_seen": 28006112,
+      "step": 2395
+    },
+    {
+      "epoch": 1.2359000772598505,
+      "grad_norm": 23.252663154179324,
+      "learning_rate": 3.484117221672465e-05,
+      "loss": 0.2766,
+      "num_input_tokens_seen": 28064552,
+      "step": 2400
+    },
+    {
+      "epoch": 1.2359000772598505,
+      "eval_loss": 0.2361450344324112,
+      "eval_runtime": 19.8674,
+      "eval_samples_per_second": 3.02,
+      "eval_steps_per_second": 0.755,
+      "num_input_tokens_seen": 28064552,
+      "step": 2400
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 27479840,
+  "num_input_tokens_seen": 28064552,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4209,7 +4298,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1813240829706240.0,
+  "total_flos": 1851822579122176.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null