Training in progress, step 10500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8edf7966575f7d3701653b2fca9b0412bc222ec3b462a6c9529e461d38d6b9
+oid sha256:b8d17e4ac1922b3b009b0441e4f23f57726b4432ea932d4686a1aef432e963e3
 size 29034840

last-checkpoint/global_step10500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39803de5f3cab621efcad66df6edb06f93dd3024d3d4ba45c23a78e56283bd11
+size 43429616

last-checkpoint/global_step10500/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:eac19b103de19325c8b6574f119b1394e85648f5022a7287d05f49d962f3f375
+size 43429616

last-checkpoint/global_step10500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b94fc927c8980056e792da6d30c7c5fb6d52c138e9faf27fc1b504057f73a58
+size 43429616

last-checkpoint/global_step10500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eab4b5c36881c47ccfe8c9b41f37342741d0675e9d351f6c1e31856cb74589e
+size 43429616

last-checkpoint/global_step10500/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b1cee03c5adc8833c8a9ad52ccf094534d0c1e7c65c0bcdf92155704178802
+size 637299

last-checkpoint/global_step10500/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7bb2179fa70729795457a7d59c8a632bca9a9640e67ad8aebee248cedc1ddb
+size 637171

last-checkpoint/global_step10500/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d889a4e2ffb7278748d62c21d05a58d7d475328c28e3bb21d7eb68add72b50
+size 637171

last-checkpoint/global_step10500/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d5033ad95169cf8daae72dbe96b6bfe516fa0954b5058456576b8a177e3c11
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step10450
+global_step10500

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728c4e2a8ee1d2ed42b3586a4c3cac5b8fbb9fdca53167fd48cf8caf96987518
+oid sha256:27f6f0b2337c7c5342568f690a1a630820f0f7912e2617c2ee4bdf3b2273c58a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e818ca5561167b20b2d1eadae23ef7dfb90bfbf49ff2932c7d035446f9f3308d
+oid sha256:1c5ad122a1cbddebdb43d69442adf338df9d9155f1a74059213b8d26c0343020
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9ae8590f6a84b7b264a99934b6cb306a13089ad904020884db757e1c77945a
+oid sha256:bec97a6c7e73f53f20fcbb3d1403565335abff825f648c78e21edbd6cfce71e1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6dbe1ec1980d7726aec0058d16ed92fa46fb441c65518943aecc4b0155fa42e
+oid sha256:1452f94c82a5c5c17fa2934a580b006500aa2f10bfef7a50848d264c11551ced
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b0c1e81998443d9840edc6cac740fbae2d7dbf17c82e810da7dbdfc0ef4135
+oid sha256:8caa67f44b3047a29030350d4e2c45631cad2ecb6ddc3b07f7572889a975252d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.04092838987708092,
   "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-9050",
-  "epoch": 1.2802976937919206,
+  "epoch": 1.2864230804569539,
   "eval_steps": 50,
-  "global_step": 10450,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18608,11 +18608,100 @@
       "eval_steps_per_second": 0.775,
       "num_input_tokens_seen": 69822376,
       "step": 10450
+    },
+    {
+      "epoch": 1.280910232458424,
+      "grad_norm": 1.1661386976448556,
+      "learning_rate": 3.137114865108448e-05,
+      "loss": 0.2298,
+      "num_input_tokens_seen": 69856272,
+      "step": 10455
+    },
+    {
+      "epoch": 1.2815227711249273,
+      "grad_norm": 1.4222630401322578,
+      "learning_rate": 3.1324156830457265e-05,
+      "loss": 0.2138,
+      "num_input_tokens_seen": 69890232,
+      "step": 10460
+    },
+    {
+      "epoch": 1.2821353097914305,
+      "grad_norm": 0.8283643883513497,
+      "learning_rate": 3.127718417286806e-05,
+      "loss": 0.1803,
+      "num_input_tokens_seen": 69924584,
+      "step": 10465
+    },
+    {
+      "epoch": 1.2827478484579338,
+      "grad_norm": 0.8441760490687942,
+      "learning_rate": 3.1230230726514924e-05,
+      "loss": 0.2116,
+      "num_input_tokens_seen": 69957760,
+      "step": 10470
+    },
+    {
+      "epoch": 1.2833603871244372,
+      "grad_norm": 1.4391335558179372,
+      "learning_rate": 3.118329653957617e-05,
+      "loss": 0.23,
+      "num_input_tokens_seen": 69991520,
+      "step": 10475
+    },
+    {
+      "epoch": 1.2839729257909407,
+      "grad_norm": 1.5114333017997594,
+      "learning_rate": 3.113638166021032e-05,
+      "loss": 0.2256,
+      "num_input_tokens_seen": 70025056,
+      "step": 10480
+    },
+    {
+      "epoch": 1.284585464457444,
+      "grad_norm": 1.4891257632314518,
+      "learning_rate": 3.1089486136556154e-05,
+      "loss": 0.233,
+      "num_input_tokens_seen": 70058384,
+      "step": 10485
+    },
+    {
+      "epoch": 1.2851980031239472,
+      "grad_norm": 1.1182418086711492,
+      "learning_rate": 3.104261001673253e-05,
+      "loss": 0.2252,
+      "num_input_tokens_seen": 70091384,
+      "step": 10490
+    },
+    {
+      "epoch": 1.2858105417904504,
+      "grad_norm": 1.2968262300781201,
+      "learning_rate": 3.099575334883846e-05,
+      "loss": 0.2096,
+      "num_input_tokens_seen": 70125232,
+      "step": 10495
+    },
+    {
+      "epoch": 1.2864230804569539,
+      "grad_norm": 1.3468668615560726,
+      "learning_rate": 3.0948916180952904e-05,
+      "loss": 0.2345,
+      "num_input_tokens_seen": 70158672,
+      "step": 10500
+    },
+    {
+      "epoch": 1.2864230804569539,
+      "eval_loss": 0.16857217252254486,
+      "eval_runtime": 19.7222,
+      "eval_samples_per_second": 3.042,
+      "eval_steps_per_second": 0.761,
+      "num_input_tokens_seen": 70158672,
+      "step": 10500
     }
   ],
   "logging_steps": 5,
   "max_steps": 16324,
-  "num_input_tokens_seen": 69822376,
+  "num_input_tokens_seen": 70158672,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -18627,7 +18716,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4379630441201664.0,
+  "total_flos": 4400730856226816.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null