Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364d970c0898c9aa3378ce697d8c156c845bc89c410b474424ed0f6f28d86575
+oid sha256:73467ea1ed97e925adf2917879e548677b9d96e9d65d80d0ea25c65250831ebe
 size 29034840

last-checkpoint/global_step1600/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:db44c651d1205a4ffc6b64d1bda33a96f664bfb88dbb1ca8f4e70efc85551158
+size 43429616

last-checkpoint/global_step1600/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:b9236952598c5fdc3e6cc6955a86a2d8e019c1947aab171d15d9134eed78171b
+size 43429616

last-checkpoint/global_step1600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb6a6e411c76e9260f78617d1be8fa0f2ea549caf0500e151fbf5e2cfdf405f
+size 43429616

last-checkpoint/global_step1600/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:a484aa770157fce9e258d8ab3eba9c016ae0889b35b3110f180f3d868e26a7d6
+size 43429616

last-checkpoint/global_step1600/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4afb4aaf2fe09b00f009636090ac8140a92a92061b0beb56860dbb1563a322
+size 637299

last-checkpoint/global_step1600/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99752500f7623dfbbb0b804e1c22e1cbd188635e5967f6ff430fde200bbb865f
+size 637171

last-checkpoint/global_step1600/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3c8ffb4a388a7c685af82e29e62c38dac41b19f00d659db4227bfe73f04b08
+size 637171

last-checkpoint/global_step1600/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab2075b924174a0c53aaeb6926f645d6f84f031f1c7a5a84a1e25330a267f11
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1550
+global_step1600

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1e48a120d69830576f7b582aa6cc46f0ca41d30015a7a674eaec3dcdfc0f09
+oid sha256:9279ed4b01716237e789d2631c1f29bc5d43c5633c014d4401de21b672c1b355
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbabb9273d3983e52a4a981b5f60f8c2e19da375765d05bb9f2caad284b9652
+oid sha256:ca1990d68e57c70df5c56d395dd3f3befbe07b380521f4144677c20f6fe2a3eb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554ac925bb9c9ea292b7a41caac1cf75285511cf8aa440f37090891ee457a178
+oid sha256:e0790066885525e1b9a9390a40ae27abd57abb47f031abface27890732f9e684
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be5e00123fc0a321e41599b50e07be02f4c165504c601192e5c73f5f5437c30
+oid sha256:1325a2034fe48ebad4f00ac8a2b32ab5c4c43c2497712169a8e3b1112363d916
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff20f7ad4c3f084d2ca3cdf144a9c716a7288c4cbc23f49744772554732ab7ea
+oid sha256:62282c037a983d19544e509ed880c9744baa4fc67a0800fdb043c257f3c8ac9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28714123368263245,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-1550",
-  "epoch": 0.45790251107828656,
+  "epoch": 0.4726735598227474,
   "eval_steps": 50,
-  "global_step": 1550,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2766,11 +2766,100 @@
       "eval_steps_per_second": 0.787,
       "num_input_tokens_seen": 16091960,
       "step": 1550
+    },
+    {
+      "epoch": 0.45937961595273263,
+      "grad_norm": 2.40581004555412,
+      "learning_rate": 9.143472182578547e-05,
+      "loss": 0.3501,
+      "num_input_tokens_seen": 16143672,
+      "step": 1555
+    },
+    {
+      "epoch": 0.4608567208271787,
+      "grad_norm": 4.013146156526438,
+      "learning_rate": 9.136624370500554e-05,
+      "loss": 0.2684,
+      "num_input_tokens_seen": 16195776,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4623338257016248,
+      "grad_norm": 11.075749009255755,
+      "learning_rate": 9.129751879363052e-05,
+      "loss": 0.3294,
+      "num_input_tokens_seen": 16247752,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4638109305760709,
+      "grad_norm": 1.5049575714077101,
+      "learning_rate": 9.122854750167254e-05,
+      "loss": 0.2906,
+      "num_input_tokens_seen": 16300680,
+      "step": 1570
+    },
+    {
+      "epoch": 0.465288035450517,
+      "grad_norm": 4.448041589727679,
+      "learning_rate": 9.115933024061365e-05,
+      "loss": 0.3498,
+      "num_input_tokens_seen": 16352000,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4667651403249631,
+      "grad_norm": 9.574179858800763,
+      "learning_rate": 9.108986742340331e-05,
+      "loss": 0.3262,
+      "num_input_tokens_seen": 16403784,
+      "step": 1580
+    },
+    {
+      "epoch": 0.46824224519940916,
+      "grad_norm": 5.326539404357799,
+      "learning_rate": 9.102015946445601e-05,
+      "loss": 0.318,
+      "num_input_tokens_seen": 16455080,
+      "step": 1585
+    },
+    {
+      "epoch": 0.46971935007385524,
+      "grad_norm": 17.72769299345548,
+      "learning_rate": 9.095020677964874e-05,
+      "loss": 0.3257,
+      "num_input_tokens_seen": 16507712,
+      "step": 1590
+    },
+    {
+      "epoch": 0.4711964549483013,
+      "grad_norm": 6.912966772855359,
+      "learning_rate": 9.08800097863185e-05,
+      "loss": 0.3253,
+      "num_input_tokens_seen": 16559392,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4726735598227474,
+      "grad_norm": 3.3138006639125344,
+      "learning_rate": 9.080956890325985e-05,
+      "loss": 0.3879,
+      "num_input_tokens_seen": 16609960,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4726735598227474,
+      "eval_loss": 0.3135533034801483,
+      "eval_runtime": 19.3013,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 0.777,
+      "num_input_tokens_seen": 16609960,
+      "step": 1600
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 16091960,
+  "num_input_tokens_seen": 16609960,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -2785,7 +2874,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1061592778407936.0,
+  "total_flos": 1095801178423296.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null