Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637d017e8d4d94ab07a703145f2af78722084a2aaf476d5f6576729ec37c71f4
+oid sha256:ee4d20084c020812db6dbd79fbf4828c8db14c421e8619ec1b2d21ffca81b370
 size 29034840

last-checkpoint/global_step2300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678a9b5732737aca693a692027a2fca58520bacbc2fd74858ce14fb50ea950aa
+size 43429616

last-checkpoint/global_step2300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51640bcb832d11cfa66b85ac4d5a0a1e4dcb6cb7699c6770641be394b6cd7f86
+size 43429616

last-checkpoint/global_step2300/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:dc3b18117a0c11f90f07c0ffe42d108346b9cd20094e1147c934bd68f2dbe3c9
+size 43429616

last-checkpoint/global_step2300/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d9f16603bfef06d1ebc09fa347405e9431d188f350b0274bf5e8cfe70df68c
+size 43429616

last-checkpoint/global_step2300/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fa8b00108fdb11131034658fba7089061501022b3de6f5e243a3686a644276
+size 637299

last-checkpoint/global_step2300/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf246967f429ff75d5cfa4a4b8804f191fdc81e48b9cd0c807a5b4a379efc21
+size 637171

last-checkpoint/global_step2300/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5404d462155135ee507d74ac8a0754e37f4d4a952bf81ff326ba7ab6b40985
+size 637171

last-checkpoint/global_step2300/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30995616fd56844cf161de30a81dacea08f0a755be391d0f4ff601fe522ca55a
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2250
+global_step2300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3187a61ccc2722c440dc24ae4a6eefe6b9e5daccf9e92473bbb4483c7751ea77
+oid sha256:1d25cbcbbaa0866ea9c7365cb49b84e805db119693e615f5a1898a6ebfe997e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f2a0df922fb3337cf2562745ebe8d5adf433ca45cb4e3da33a21b48183c000
+oid sha256:a883389afac12125c2c6bf62631b7de0220fdb0020d24cd0c6e8f8858dd3b362
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d84b5276f687f44c9af60b1e41cd7b93a6d1659e36831a7bc021b5635d663b
+oid sha256:577d49de6d60035e159d9ebb1e6eabef79a55787b14ecea93a6a93c242661779
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d69159433c88b97106cf21b92eb5a3f66f0c826aa268d82a47b3faed1ac86cd
+oid sha256:b5f2dd1c21e06806a9ce39eeab45734dfb8a62b829f91a86d1f65f13102d6242
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f09364fdb885abeed72e22e296309c763b98e8380e640753aee0cb72764dc9df
+oid sha256:4affa863c39f4a87a7aa62bb6d8ea5d9ce72773cba2b4ccffc763273823a37b1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.25809118151664734,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2150",
-  "epoch": 0.6646971935007385,
+  "best_metric": 0.24180778861045837,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2300",
+  "epoch": 0.6794682422451994,
   "eval_steps": 50,
-  "global_step": 2250,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4012,11 +4012,100 @@
       "eval_steps_per_second": 0.782,
       "num_input_tokens_seen": 23366784,
       "step": 2250
+    },
+    {
+      "epoch": 0.6661742983751846,
+      "grad_norm": 1.646844160605743,
+      "learning_rate": 7.965145576879423e-05,
+      "loss": 0.3135,
+      "num_input_tokens_seen": 23418504,
+      "step": 2255
+    },
+    {
+      "epoch": 0.6676514032496307,
+      "grad_norm": 4.433343767927195,
+      "learning_rate": 7.955303314631898e-05,
+      "loss": 0.3268,
+      "num_input_tokens_seen": 23469840,
+      "step": 2260
+    },
+    {
+      "epoch": 0.6691285081240768,
+      "grad_norm": 2.741861673744247,
+      "learning_rate": 7.945443421074436e-05,
+      "loss": 0.2706,
+      "num_input_tokens_seen": 23521416,
+      "step": 2265
+    },
+    {
+      "epoch": 0.670605612998523,
+      "grad_norm": 13.390920032881771,
+      "learning_rate": 7.935565955031064e-05,
+      "loss": 0.2044,
+      "num_input_tokens_seen": 23573176,
+      "step": 2270
+    },
+    {
+      "epoch": 0.672082717872969,
+      "grad_norm": 4.093699227168353,
+      "learning_rate": 7.925670975430644e-05,
+      "loss": 0.2724,
+      "num_input_tokens_seen": 23625080,
+      "step": 2275
+    },
+    {
+      "epoch": 0.6735598227474151,
+      "grad_norm": 1.060930943475367,
+      "learning_rate": 7.915758541306523e-05,
+      "loss": 0.2543,
+      "num_input_tokens_seen": 23677096,
+      "step": 2280
+    },
+    {
+      "epoch": 0.6750369276218612,
+      "grad_norm": 2.1755423246760515,
+      "learning_rate": 7.90582871179619e-05,
+      "loss": 0.2372,
+      "num_input_tokens_seen": 23729168,
+      "step": 2285
+    },
+    {
+      "epoch": 0.6765140324963073,
+      "grad_norm": 8.00546036386453,
+      "learning_rate": 7.895881546140902e-05,
+      "loss": 0.2695,
+      "num_input_tokens_seen": 23780568,
+      "step": 2290
+    },
+    {
+      "epoch": 0.6779911373707533,
+      "grad_norm": 7.074026968521074,
+      "learning_rate": 7.885917103685353e-05,
+      "loss": 0.3282,
+      "num_input_tokens_seen": 23831360,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6794682422451994,
+      "grad_norm": 1.221854745565416,
+      "learning_rate": 7.875935443877305e-05,
+      "loss": 0.2481,
+      "num_input_tokens_seen": 23883032,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6794682422451994,
+      "eval_loss": 0.24180778861045837,
+      "eval_runtime": 18.9575,
+      "eval_samples_per_second": 3.165,
+      "eval_steps_per_second": 0.791,
+      "num_input_tokens_seen": 23883032,
+      "step": 2300
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 23366784,
+  "num_input_tokens_seen": 23883032,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4031,7 +4120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1541699557392384.0,
+  "total_flos": 1575723931533312.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null