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:e470a7312966ac506e60fed47092ca459f2f086beab59e5b25dca2bf59a21f73
+oid sha256:cdf5f54c0020018c5eca1b4c1055878f2c1e58bfa3f188c951ed0eed9b279f0d
 size 18516456

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 sha256:0d7588db812bab425924f1d00f7d3253a69a0df1e0e50dd679f1dbd305f5584f
+size 27700976

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:cf88782f06694860d81f0d5c8069259cec602afb588601c5062edb6a03d763e4
+size 27700976

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 sha256:334ed4c0c6f60305b89445cb8541c3f0758999d4eeac7fcda188d84d85f23824
+size 27700976

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 sha256:093234ca5f7b5a8219f276f71d1f61b3d4a31e6e737be35f63a9a58a9ba01cde
+size 27700976

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 sha256:7234e34a93ba129f360afd7e4671ea4ec12ed34e881f1d256d7ca7e6eb1beca0
+size 411571

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:ef284a886c71e441515bb4ddb38641d3db3759acda8d381b94eeabfbdb16dbae
+size 411507

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:f00d47842911b16cee9844d402b0ee6a63b826625851472d046966cc48855138
+size 411507

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 sha256:105abd94c9ebf288806f56c08a1751a5530e581bf52c16a7a8d8e0c1b0c4e212
+size 411507

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:d71a7ba4d3f18f2d8b75b4d8773a5d2a13dce7aa34d7060fa3e4c5c241599a29
+oid sha256:33f198cd3e0b21f350098b16849fc1ced7c1d5261e89a1c503f4a0d3ce688f30
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6319106221199036,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1600",
-  "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": 0.937,
       "num_input_tokens_seen": 27479840,
       "step": 2350
+    },
+    {
+      "epoch": 1.212722122070564,
+      "grad_norm": 8.004400275953609,
+      "learning_rate": 2.3678391856132204e-05,
+      "loss": 0.352,
+      "num_input_tokens_seen": 27538344,
+      "step": 2355
+    },
+    {
+      "epoch": 1.2152974504249292,
+      "grad_norm": 8.385547193425513,
+      "learning_rate": 2.3471967400628513e-05,
+      "loss": 0.347,
+      "num_input_tokens_seen": 27596808,
+      "step": 2360
+    },
+    {
+      "epoch": 1.2178727787792945,
+      "grad_norm": 3.9234442237475435,
+      "learning_rate": 2.3266170337008398e-05,
+      "loss": 0.3667,
+      "num_input_tokens_seen": 27655272,
+      "step": 2365
+    },
+    {
+      "epoch": 1.2204481071336595,
+      "grad_norm": 6.584480429736488,
+      "learning_rate": 2.306100553240274e-05,
+      "loss": 0.3311,
+      "num_input_tokens_seen": 27713784,
+      "step": 2370
+    },
+    {
+      "epoch": 1.2230234354880247,
+      "grad_norm": 5.791637874835276,
+      "learning_rate": 2.2856477838989456e-05,
+      "loss": 0.2964,
+      "num_input_tokens_seen": 27772248,
+      "step": 2375
+    },
+    {
+      "epoch": 1.22559876384239,
+      "grad_norm": 5.663503226529594,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.3683,
+      "num_input_tokens_seen": 27830704,
+      "step": 2380
+    },
+    {
+      "epoch": 1.228174092196755,
+      "grad_norm": 9.657080260273457,
+      "learning_rate": 2.244935311899829e-05,
+      "loss": 0.3819,
+      "num_input_tokens_seen": 27889160,
+      "step": 2385
+    },
+    {
+      "epoch": 1.2307494205511202,
+      "grad_norm": 4.757552901440964,
+      "learning_rate": 2.224676572098007e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 27947608,
+      "step": 2390
+    },
+    {
+      "epoch": 1.2333247489054855,
+      "grad_norm": 5.188072586185411,
+      "learning_rate": 2.2044834691045873e-05,
+      "loss": 0.4267,
+      "num_input_tokens_seen": 28006112,
+      "step": 2395
+    },
+    {
+      "epoch": 1.2359000772598505,
+      "grad_norm": 7.221389028269126,
+      "learning_rate": 2.184356480489432e-05,
+      "loss": 0.3486,
+      "num_input_tokens_seen": 28064552,
+      "step": 2400
+    },
+    {
+      "epoch": 1.2359000772598505,
+      "eval_loss": 0.7410638928413391,
+      "eval_runtime": 15.945,
+      "eval_samples_per_second": 3.763,
+      "eval_steps_per_second": 0.941,
+      "num_input_tokens_seen": 28064552,
+      "step": 2400
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "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": 1543122079449088.0,
+  "total_flos": 1575955876020224.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null