Training in progress, step 2650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:273fcf9e0b0197d44caacef12013e816c21f5d50361370148cdbf9380973f3f1
+oid sha256:827ad766e3a13984fdb182a9e1ff3663479a4a48e1ebea8bd0fa17625232d440
 size 18516456

last-checkpoint/global_step2649/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:d2b8b863f065477a0c40a5eede162578edbe6fd787a379d77ea32c01096bd2f0
+size 27700976

last-checkpoint/global_step2649/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:ccd9ed8c3f4189afca7b9b42f08145b379927ea4d344c52f2c32782785b9f665
+size 27700976

last-checkpoint/global_step2649/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671300e3ae3ba0a81972b9ff040af49caa347ab4420c349f8ab1d9062a74d019
+size 27700976

last-checkpoint/global_step2649/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b641c32a40965f349b0d85732aa748416355167ab1f70e4a8e58128db5bddc0
+size 27700976

last-checkpoint/global_step2649/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2fba811b3d3680bbb95ae1d35a4a8ff72f871b681760e1f8c2a1331494a1d85
+size 411571

last-checkpoint/global_step2649/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0edc40941eb6c7b6893992d22c466389a0f4c35083eecf5e4b3ef79cd43ce5
+size 411507

last-checkpoint/global_step2649/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392c683814beae79e971d20e2dff1be4d32e72639e37b8144ae68462dee3fed6
+size 411507

last-checkpoint/global_step2649/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ea766ce87c859064beb69b922a66ee40f6159fdc3d2a718f2ac2dd7b599ff6
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step2599
+global_step2649

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf1e520c0ffd0912cdaf36292baf0834dd187b6292436dd343acbd7d39f37df
+oid sha256:9e599331812a34463d102d64a4034a0b702a893f362f752003aa577fe71dcc1d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480a3937172137fc1b4a3886bc929d7dd5dd0507aebd6b20448e5d03ffe9f33f
+oid sha256:5ed431e5e71393a0174ad2fd492755f8c1142596f1af3bfe7827c1f8f815dd80
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc7d6afeed03ecf805019b6cd001604bbcd5e4ef0cbc38e4dc6f5587e48dbf2
+oid sha256:a2e70789f26a9f56b6b779e87cb1a405615af81562a256e5afe579f40972e827
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c0ace59112a18d7f177314d1a9eb2b6b894f2028df1dd368b8c67c8732e18d
+oid sha256:7c8c18bc74d5211e761da269c814d7da0687633993838ec22e81ac939a14e91b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d19c5591b92170b594a14288df1f8fed02718a1409cb25856483f8dff91ef9
+oid sha256:bfcf85c736e61a53c653b2d1f3342ce104fa9dc3f2c57b7753ecb2c25635e267
 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": 1.338913211434458,
+  "epoch": 1.3646664949781098,
   "eval_steps": 50,
-  "global_step": 2600,
+  "global_step": 2650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4635,11 +4635,100 @@
       "eval_steps_per_second": 0.923,
       "num_input_tokens_seen": 30403640,
       "step": 2600
+    },
+    {
+      "epoch": 1.341488539788823,
+      "grad_norm": 6.900087606750275,
+      "learning_rate": 1.4217439014387251e-05,
+      "loss": 0.3037,
+      "num_input_tokens_seen": 30462128,
+      "step": 2605
+    },
+    {
+      "epoch": 1.3440638681431882,
+      "grad_norm": 9.361737062462586,
+      "learning_rate": 1.404802767838176e-05,
+      "loss": 0.2905,
+      "num_input_tokens_seen": 30520616,
+      "step": 2610
+    },
+    {
+      "epoch": 1.3466391964975535,
+      "grad_norm": 11.101564672040755,
+      "learning_rate": 1.3879466611824199e-05,
+      "loss": 0.317,
+      "num_input_tokens_seen": 30579024,
+      "step": 2615
+    },
+    {
+      "epoch": 1.3492145248519187,
+      "grad_norm": 5.213355428878847,
+      "learning_rate": 1.371175980120864e-05,
+      "loss": 0.2794,
+      "num_input_tokens_seen": 30637464,
+      "step": 2620
+    },
+    {
+      "epoch": 1.3517898532062838,
+      "grad_norm": 4.8688198861459915,
+      "learning_rate": 1.3544911212825906e-05,
+      "loss": 0.3056,
+      "num_input_tokens_seen": 30695936,
+      "step": 2625
+    },
+    {
+      "epoch": 1.354365181560649,
+      "grad_norm": 9.002025840794365,
+      "learning_rate": 1.337892479266974e-05,
+      "loss": 0.2712,
+      "num_input_tokens_seen": 30754408,
+      "step": 2630
+    },
+    {
+      "epoch": 1.356940509915014,
+      "grad_norm": 4.793656741683869,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 0.2615,
+      "num_input_tokens_seen": 30812848,
+      "step": 2635
+    },
+    {
+      "epoch": 1.3595158382693793,
+      "grad_norm": 5.128300113893045,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 0.2661,
+      "num_input_tokens_seen": 30871344,
+      "step": 2640
+    },
+    {
+      "epoch": 1.3620911666237445,
+      "grad_norm": 6.038434247454305,
+      "learning_rate": 1.2886177695085078e-05,
+      "loss": 0.3272,
+      "num_input_tokens_seen": 30929824,
+      "step": 2645
+    },
+    {
+      "epoch": 1.3646664949781098,
+      "grad_norm": 5.501317116522042,
+      "learning_rate": 1.2723678998574512e-05,
+      "loss": 0.2962,
+      "num_input_tokens_seen": 30988344,
+      "step": 2650
+    },
+    {
+      "epoch": 1.3646664949781098,
+      "eval_loss": 0.7657458186149597,
+      "eval_runtime": 16.0821,
+      "eval_samples_per_second": 3.731,
+      "eval_steps_per_second": 0.933,
+      "num_input_tokens_seen": 30988344,
+      "step": 2650
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 30403640,
+  "num_input_tokens_seen": 30988344,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4654,7 +4743,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1707311142797312.0,
+  "total_flos": 1740143807954944.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null