Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3f322dae10822dacfe9f1a7fd463469b2b4a03323e7477e29c4899f3708c98
+oid sha256:dd192dd85ff6446dfa29041091b7f433f1d6a850202807fb731b90087b71d2ec
 size 29034840

last-checkpoint/global_step1100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b254c4923956754c829205480b8ed6bef5fdd7fb4374c449e85185583f2c400
+size 43429616

last-checkpoint/global_step1100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f89af0942ad2fd6a9b7c9d91597fa24745ff35f644725845429983cfe6b71d
+size 43429616

last-checkpoint/global_step1100/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:c06b6a7e0284a58136be5c1deaaa23d001a55873f4d136b8364cf59ac6dba9f1
+size 43429616

last-checkpoint/global_step1100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c75e95dfd43760a63920a59a38f5157c18e39a021e7aea8a6a451c93c38c7f0
+size 43429616

last-checkpoint/global_step1100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6cd40d86e3ba7e47e81f57e484777f5a58e7125cded52155185f70841f69006
+size 637299

last-checkpoint/global_step1100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6872c9275849e88f75362917c53338d35f1f143dd618226b67d07e1be2013b
+size 637171

last-checkpoint/global_step1100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3510ce005dba7068599a4d71567997fed9c2f2d69cb6ff22bf564135f06c926d
+size 637171

last-checkpoint/global_step1100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1d70a92f96fad919c2f11dec877b197d8438c82e818e72cc3d6cd8c45bfc86
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1050
+global_step1100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67db742b8aa1744a8224bf2a1f79d89caff63b15f78a455d92bb666df82183ea
+oid sha256:9d9fea52fb92cc51e76feeb2b139ce35723c0cb651da383e4f7eec2606ed6c2a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f9acb7e6f8bbfb305c3601c71eb6189af24942fab5f99046412c03bb10c3eb
+oid sha256:1b5820ebfcc2e1cfe1ad2619a05ea9a484ff21635e13e386bf14abd302f2c0f7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:713783338342f7486f6f186abd03c5963a0d22368f403efb2bf903ed083d2b64
+oid sha256:eb8d96a68e732fca41980516622a50990bbd3ee989e72076a35c8608d9b4d136
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83aaec0b5b7d8a2da4577075066cf434ce6e9feb9327edbea6677a2e51d76466
+oid sha256:ce6f1db6d09f4d89a9b2bd8dc8eeb99f1fada2ec04376e23b5a7a13004994005
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccde9da0d23fd32800f01283cdb6c677def9ab43edb7232a9c4c4e9101a14cc0
+oid sha256:1d0c7456eafeee3179566bb381c9153771d7e0f21738d2398944d053915d0651
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6621683239936829,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-900",
-  "epoch": 0.12863311996569785,
+  "best_metric": 0.6174182295799255,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-1100",
+  "epoch": 0.13475850663073108,
   "eval_steps": 50,
-  "global_step": 1050,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1876,11 +1876,100 @@
       "eval_steps_per_second": 0.776,
       "num_input_tokens_seen": 7215776,
       "step": 1050
+    },
+    {
+      "epoch": 0.12924565863220117,
+      "grad_norm": 3.8028164296566516,
+      "learning_rate": 8.259242386389973e-05,
+      "loss": 0.5912,
+      "num_input_tokens_seen": 7249440,
+      "step": 1055
+    },
+    {
+      "epoch": 0.1298581972987045,
+      "grad_norm": 6.137278679473767,
+      "learning_rate": 8.240764101059912e-05,
+      "loss": 0.521,
+      "num_input_tokens_seen": 7283432,
+      "step": 1060
+    },
+    {
+      "epoch": 0.1304707359652078,
+      "grad_norm": 3.7500573615659376,
+      "learning_rate": 8.222209171180883e-05,
+      "loss": 0.5359,
+      "num_input_tokens_seen": 7317360,
+      "step": 1065
+    },
+    {
+      "epoch": 0.13108327463171113,
+      "grad_norm": 6.360476685600312,
+      "learning_rate": 8.203578035579715e-05,
+      "loss": 0.5271,
+      "num_input_tokens_seen": 7352112,
+      "step": 1070
+    },
+    {
+      "epoch": 0.13169581329821445,
+      "grad_norm": 1.7458123705897874,
+      "learning_rate": 8.184871134885513e-05,
+      "loss": 0.5044,
+      "num_input_tokens_seen": 7384880,
+      "step": 1075
+    },
+    {
+      "epoch": 0.13230835196471777,
+      "grad_norm": 7.172013405019242,
+      "learning_rate": 8.166088911519235e-05,
+      "loss": 0.5953,
+      "num_input_tokens_seen": 7418368,
+      "step": 1080
+    },
+    {
+      "epoch": 0.1329208906312211,
+      "grad_norm": 2.476642615613007,
+      "learning_rate": 8.147231809683236e-05,
+      "loss": 0.5123,
+      "num_input_tokens_seen": 7451872,
+      "step": 1085
+    },
+    {
+      "epoch": 0.1335334292977244,
+      "grad_norm": 13.817194120585148,
+      "learning_rate": 8.128300275350756e-05,
+      "loss": 0.5632,
+      "num_input_tokens_seen": 7485712,
+      "step": 1090
+    },
+    {
+      "epoch": 0.13414596796422773,
+      "grad_norm": 2.20726405661794,
+      "learning_rate": 8.109294756255375e-05,
+      "loss": 0.5144,
+      "num_input_tokens_seen": 7519168,
+      "step": 1095
+    },
+    {
+      "epoch": 0.13475850663073108,
+      "grad_norm": 5.79546351031941,
+      "learning_rate": 8.090215701880419e-05,
+      "loss": 0.5307,
+      "num_input_tokens_seen": 7552920,
+      "step": 1100
+    },
+    {
+      "epoch": 0.13475850663073108,
+      "eval_loss": 0.6174182295799255,
+      "eval_runtime": 19.257,
+      "eval_samples_per_second": 3.116,
+      "eval_steps_per_second": 0.779,
+      "num_input_tokens_seen": 7552920,
+      "step": 1100
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 7215776,
+  "num_input_tokens_seen": 7552920,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1895,7 +1984,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 453990561742848.0,
+  "total_flos": 475129840533504.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null