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:c194e4011ebc3d53bf21924236aa69f02cd3e886bdcc096049ceabfa8e037964
+oid sha256:40f0e52182147fdabf2ddf1a520d0249faf099e8bb9941553d5a51b579af5e1c
 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 sha256:0c9631c106cb8b26664f394a3d23049a6f4c0d0bc6a6a8495950b281ae140f7e
+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:fe823b5b1c88136ad94b5c3a9d0afea951c64b43a6156d5e8670e2bbf78a2f7f
+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:a89a70cce1ec47138d3922ec3f729aca85f6c3337c0181dbfe59769ff36db918
+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 sha256:4fd1efff697a8e5667983434a9fc17a802976818d4ec8406c787241c33647977
+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 sha256:3e24eaa8963cd872c048c2c655789d678b8c3fcd1c77ca0d663feee5857d2e34
+oid sha256:feb4015894f59edc29c71bc4938b5d4ab98daad34a38a3d387b308b3b1d4b280
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5219093561172485,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-800",
-  "epoch": 0.21890291012104043,
+  "best_metric": 0.49604204297065735,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-900",
+  "epoch": 0.23177955189286634,
   "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": 0.768,
       "num_input_tokens_seen": 8919608,
       "step": 850
+    },
+    {
+      "epoch": 0.22019057429822303,
+      "grad_norm": 4.339535962830116,
+      "learning_rate": 8.930720915538487e-05,
+      "loss": 0.5853,
+      "num_input_tokens_seen": 8971048,
+      "step": 855
+    },
+    {
+      "epoch": 0.22147823847540563,
+      "grad_norm": 6.118436891847819,
+      "learning_rate": 8.915646321965614e-05,
+      "loss": 0.5534,
+      "num_input_tokens_seen": 9022936,
+      "step": 860
+    },
+    {
+      "epoch": 0.2227659026525882,
+      "grad_norm": 3.3997835203618667,
+      "learning_rate": 8.900479122779712e-05,
+      "loss": 0.5623,
+      "num_input_tokens_seen": 9075336,
+      "step": 865
+    },
+    {
+      "epoch": 0.2240535668297708,
+      "grad_norm": 4.188326935911128,
+      "learning_rate": 8.885219676687277e-05,
+      "loss": 0.5561,
+      "num_input_tokens_seen": 9127688,
+      "step": 870
+    },
+    {
+      "epoch": 0.22534123100695339,
+      "grad_norm": 5.220175192497493,
+      "learning_rate": 8.869868344576459e-05,
+      "loss": 0.5449,
+      "num_input_tokens_seen": 9180624,
+      "step": 875
+    },
+    {
+      "epoch": 0.22662889518413598,
+      "grad_norm": 2.2022914161050577,
+      "learning_rate": 8.854425489508532e-05,
+      "loss": 0.5062,
+      "num_input_tokens_seen": 9233176,
+      "step": 880
+    },
+    {
+      "epoch": 0.22791655936131858,
+      "grad_norm": 4.62379059067999,
+      "learning_rate": 8.838891476709288e-05,
+      "loss": 0.5033,
+      "num_input_tokens_seen": 9286688,
+      "step": 885
+    },
+    {
+      "epoch": 0.22920422353850115,
+      "grad_norm": 3.639684630492015,
+      "learning_rate": 8.823266673560426e-05,
+      "loss": 0.4845,
+      "num_input_tokens_seen": 9339600,
+      "step": 890
+    },
+    {
+      "epoch": 0.23049188771568374,
+      "grad_norm": 4.131757647310936,
+      "learning_rate": 8.807551449590846e-05,
+      "loss": 0.5595,
+      "num_input_tokens_seen": 9391536,
+      "step": 895
+    },
+    {
+      "epoch": 0.23177955189286634,
+      "grad_norm": 4.771128685196347,
+      "learning_rate": 8.791746176467907e-05,
+      "loss": 0.5251,
+      "num_input_tokens_seen": 9443616,
+      "step": 900
+    },
+    {
+      "epoch": 0.23177955189286634,
+      "eval_loss": 0.49604204297065735,
+      "eval_runtime": 39.5289,
+      "eval_samples_per_second": 3.036,
+      "eval_steps_per_second": 0.759,
+      "num_input_tokens_seen": 9443616,
+      "step": 900
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 8919608,
+  "num_input_tokens_seen": 9443616,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1539,7 +1628,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 588414853316608.0,
+  "total_flos": 622973818765312.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null