Training in progress, step 750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8b8b0d35e964892c4538367f208dcb82426a1165c1fe8d9ec6ab99f0299952
+oid sha256:87a05b954f6ad396e106053a5bf73274eb4671d1ca4b7518421076c40296fc81
 size 29034840

last-checkpoint/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdf3a0693bea36f402ce1ba4fe57537b0823ae9ed524dc7d6f915dc67c85dd8
+size 43429616

last-checkpoint/global_step750/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:eaba375ba8e10fb1d10e83cbcdc6fd00f9fee9f58f0458c57c0bd8732cb80a5d
+size 43429616

last-checkpoint/global_step750/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:ec3c4abbc30f92b4860a5c61d44fd2577b8365be30936d562e293a745076e7cd
+size 43429616

last-checkpoint/global_step750/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9753134f6593118672c497761e949545267f45e52527068e5483550bd2453f6a
+size 43429616

last-checkpoint/global_step750/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7ceefcf5f9aaf423f675a59b70c7f49dd63bf2969dd0f241c706afca330069
+size 637299

last-checkpoint/global_step750/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f0e9d3d0064652385de4668d7d1493464ea47cc90272985cc5f82378fe9407
+size 637171

last-checkpoint/global_step750/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2747d5b9a430ea06aa5e313062964f76ced72bafedfb86736e283a3440555b
+size 637171

last-checkpoint/global_step750/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df739d3279f7e7c62c77653c661bc9074781cffe48c2820c6dcb897ac09d46b
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step700
+global_step750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d74de51245105e1fbf57a6707ef3538b353952485508f6e2f8f74dc5d479d4
+oid sha256:66b4ef73f3603a1b91082ee108fa8299ebe45fb3cdeec7d0bdca1982af5bf07d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0617c9eb6cf7df57b2e0bb53cfe17c05f0910de56fe5b14427fe39ab54a44782
+oid sha256:882eccb2a272cf97cd645050bd077c971e48e78584f717a1b1cc9b5f1c9326dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed68a365057022897d9645ee60902a77102f43215dcdf2ddd5d3842b6a8446d8
+oid sha256:1626bac54f5806a604b7efdd749c5b65d63bbb40fc55c3744aae6130aa24f3de
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ebaa0c302cadbdfcd9f8ee2289e35ecf9c9fc8c9968fc0c05f100dac20c6b9
+oid sha256:40cf83ff997228172cf0b991f9d5209728ccf2f0a75841db5e31e647779a1ad2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01460e95e3e56a90233dbd46a8dfe9605b67858d03a9beec52437f5ab98bbf42
+oid sha256:fb90ddaf9f2555f7a751dcba5b295eed1e25f610d0357becbe825d3cf6fda52d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5883122682571411,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-600",
-  "epoch": 0.206794682422452,
+  "best_metric": 0.4665524661540985,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-750",
+  "epoch": 0.22156573116691286,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1253,11 +1253,100 @@
       "eval_steps_per_second": 0.785,
       "num_input_tokens_seen": 7262832,
       "step": 700
+    },
+    {
+      "epoch": 0.20827178729689808,
+      "grad_norm": 5.1484150923671,
+      "learning_rate": 9.92029461479909e-05,
+      "loss": 0.5151,
+      "num_input_tokens_seen": 7314520,
+      "step": 705
+    },
+    {
+      "epoch": 0.20974889217134415,
+      "grad_norm": 10.902688361325707,
+      "learning_rate": 9.918108001438283e-05,
+      "loss": 0.6158,
+      "num_input_tokens_seen": 7365368,
+      "step": 710
+    },
+    {
+      "epoch": 0.21122599704579026,
+      "grad_norm": 6.960249994011121,
+      "learning_rate": 9.915892046694464e-05,
+      "loss": 0.5164,
+      "num_input_tokens_seen": 7417296,
+      "step": 715
+    },
+    {
+      "epoch": 0.21270310192023634,
+      "grad_norm": 6.138105593354917,
+      "learning_rate": 9.913646763787992e-05,
+      "loss": 0.5823,
+      "num_input_tokens_seen": 7469640,
+      "step": 720
+    },
+    {
+      "epoch": 0.21418020679468242,
+      "grad_norm": 5.865897561310743,
+      "learning_rate": 9.911372166114208e-05,
+      "loss": 0.5145,
+      "num_input_tokens_seen": 7521520,
+      "step": 725
+    },
+    {
+      "epoch": 0.21565731166912852,
+      "grad_norm": 14.330290158050401,
+      "learning_rate": 9.909068267243336e-05,
+      "loss": 0.571,
+      "num_input_tokens_seen": 7573880,
+      "step": 730
+    },
+    {
+      "epoch": 0.2171344165435746,
+      "grad_norm": 6.90669118248274,
+      "learning_rate": 9.906735080920413e-05,
+      "loss": 0.4638,
+      "num_input_tokens_seen": 7625896,
+      "step": 735
+    },
+    {
+      "epoch": 0.21861152141802068,
+      "grad_norm": 6.310395883326308,
+      "learning_rate": 9.904372621065206e-05,
+      "loss": 0.5449,
+      "num_input_tokens_seen": 7676528,
+      "step": 740
+    },
+    {
+      "epoch": 0.22008862629246675,
+      "grad_norm": 27.446565035007364,
+      "learning_rate": 9.901980901772126e-05,
+      "loss": 0.5505,
+      "num_input_tokens_seen": 7728240,
+      "step": 745
+    },
+    {
+      "epoch": 0.22156573116691286,
+      "grad_norm": 5.6934624405279655,
+      "learning_rate": 9.899559937310148e-05,
+      "loss": 0.514,
+      "num_input_tokens_seen": 7779872,
+      "step": 750
+    },
+    {
+      "epoch": 0.22156573116691286,
+      "eval_loss": 0.4665524661540985,
+      "eval_runtime": 19.1629,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 0.783,
+      "num_input_tokens_seen": 7779872,
+      "step": 750
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 7262832,
+  "num_input_tokens_seen": 7779872,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1272,7 +1361,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 479089626185728.0,
+  "total_flos": 513213288415232.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null