Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2604e713adfd5ff8fff3e76524b74b5484d4e4df2c3ddf9459067c342c4d295
+oid sha256:dca569a5bee748c34c51ac0d5b0f16a410ab4a71a296a7c172247ce0d6801519
 size 29034840

last-checkpoint/global_step900/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:ce9f5392302612002fef358fde0e7f6f4d7930bd85ca39b4ccadf3e35ec527a2
+size 43429616

last-checkpoint/global_step900/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:e7fd03ef73f13a5f642a2a63469ec5fb1da3f7a708d488660ccb4dc3e8b83555
+size 43429616

last-checkpoint/global_step900/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:aee70bb579dfa57fb6ad3b18a5d3cdad2be777077c46fcb523727e225c970391
+size 43429616

last-checkpoint/global_step900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eff7aa86298b36602e11144d5d197575c29ab1a5267d726c14a5d6c537bc77f
+size 43429616

last-checkpoint/global_step900/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7162c4e09532f9490922bccb0dbbcfe539972e0f3d49af32428a76030c053274
+size 637299

last-checkpoint/global_step900/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1fabfaa7ff216589f1f45e0de64de68782d934b86fc832996ada7c681c3bd9
+size 637171

last-checkpoint/global_step900/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68864aa3523e8a7232f1228e6e0dba67ac184874fa8332362ced37b3cbe041a
+size 637171

last-checkpoint/global_step900/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834a420bd57a2a0fe552734d61c0bcc178574ff6e356d461ed6815bc79695c74
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step850
+global_step900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c9044354f826de248840acaaec171f816609c147a664089731a0570deef948
+oid sha256:b8f22ced19e790cc864cefe3b7c711d9ae631c44f95d42fb4829688cc3de0153
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f4c4013326db4e7267b656aaf72b86570f8aeee91ad39242a416cf8b963191
+oid sha256:3e0407513eba77d34cbf3adf0e59a58bd80716f4f00f414854253637e82be43d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e910793831957d8685c316138c33eef8867edf60052477dc9ad6ec0c6da901
+oid sha256:6060636c023258ce9b965e244b8a58b4c99d5784dde4405b39737550ef50cd4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfd0d71ef5a6c58d9f1d46851f4b1e699ca8a50ab3223cfb39668895cffeef2
+oid sha256:c24ccdfdcde39cb2265c82c50c36ffdfcc670f757aba4bcf4bb0fdc6d1373c4c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63e21db765af1a20657ecdebe434ff7baf8429eec4fb44a9d43fe347139b971
+oid sha256:728e48e0d034d64ded7c746a218c0b746489e6573b6bc352ba39a730bda96bbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7039459347724915,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-850",
-  "epoch": 0.43780582024208087,
+  "epoch": 0.4635591037857327,
   "eval_steps": 50,
-  "global_step": 850,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1520,11 +1520,100 @@
       "eval_steps_per_second": 0.758,
       "num_input_tokens_seen": 9941896,
       "step": 850
+    },
+    {
+      "epoch": 0.44038114859644606,
+      "grad_norm": 8.584709523479143,
+      "learning_rate": 9.22997419657528e-05,
+      "loss": 0.6829,
+      "num_input_tokens_seen": 10000336,
+      "step": 855
+    },
+    {
+      "epoch": 0.44295647695081125,
+      "grad_norm": 9.894526327436065,
+      "learning_rate": 9.218577901126713e-05,
+      "loss": 0.6971,
+      "num_input_tokens_seen": 10058816,
+      "step": 860
+    },
+    {
+      "epoch": 0.4455318053051764,
+      "grad_norm": 6.844807331677797,
+      "learning_rate": 9.207105035634397e-05,
+      "loss": 0.7239,
+      "num_input_tokens_seen": 10117320,
+      "step": 865
+    },
+    {
+      "epoch": 0.4481071336595416,
+      "grad_norm": 9.911971184322747,
+      "learning_rate": 9.195555808338603e-05,
+      "loss": 0.7113,
+      "num_input_tokens_seen": 10175824,
+      "step": 870
+    },
+    {
+      "epoch": 0.45068246201390677,
+      "grad_norm": 11.42729729117445,
+      "learning_rate": 9.183930428865622e-05,
+      "loss": 0.685,
+      "num_input_tokens_seen": 10234288,
+      "step": 875
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 6.6164653318829005,
+      "learning_rate": 9.17222910822396e-05,
+      "loss": 0.6804,
+      "num_input_tokens_seen": 10292736,
+      "step": 880
+    },
+    {
+      "epoch": 0.45583311872263715,
+      "grad_norm": 9.566984327413312,
+      "learning_rate": 9.160452058800504e-05,
+      "loss": 0.7056,
+      "num_input_tokens_seen": 10351224,
+      "step": 885
+    },
+    {
+      "epoch": 0.4584084470770023,
+      "grad_norm": 8.37543764212447,
+      "learning_rate": 9.148599494356671e-05,
+      "loss": 0.7234,
+      "num_input_tokens_seen": 10409736,
+      "step": 890
+    },
+    {
+      "epoch": 0.4609837754313675,
+      "grad_norm": 8.118764978921215,
+      "learning_rate": 9.136671630024527e-05,
+      "loss": 0.7505,
+      "num_input_tokens_seen": 10468240,
+      "step": 895
+    },
+    {
+      "epoch": 0.4635591037857327,
+      "grad_norm": 8.91603360160678,
+      "learning_rate": 9.124668682302882e-05,
+      "loss": 0.7378,
+      "num_input_tokens_seen": 10526712,
+      "step": 900
+    },
+    {
+      "epoch": 0.4635591037857327,
+      "eval_loss": 0.7197856903076172,
+      "eval_runtime": 19.6818,
+      "eval_samples_per_second": 3.048,
+      "eval_steps_per_second": 0.762,
+      "num_input_tokens_seen": 10526712,
+      "step": 900
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 9941896,
+  "num_input_tokens_seen": 10526712,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1539,7 +1628,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 655954683887616.0,
+  "total_flos": 694543977283584.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null