Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56eaf4c227ce8139a59064befffba82e062b43ce41d4a938db72d66c7114306e
+oid sha256:8f682c4f26b2d865ab23e7546659c851c99ad1ed58aaaeda4b6412b57ead1e67
 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 sha256:804dde53739597d1b62fd143bb75331f242f6775ddd40ceaf1b246b07ca798c4
+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:fe36b63f6ae194ce571b13ddccdbbbf40b261b7b7199b259d6947dd5bff29fc5
+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:b9a86ddd2cba7a8df350f57a357f7fd8bb353f18c48de8bf9bca0f2817ed4274
+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 sha256:479e4221d177ae6a20fb229bdcdf3bf2e6962b6a3d32f031a72a02969daf5a1f
+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:a0594a06a960a2b82b79ae3375fcc5157d04c096adbc8e37daafab8145646afd
+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 sha256:602bae77c5e406ad93d955e22f82404c93c6d54927e02491854e9d1b05064fd2
+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 sha256:62e29c7a76a09448e9c9a0f2bf6ede9bafd0bf3776d255f4d3e4a617869514ec
+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:f47a3e9d4caf314582b7b91a420e64941ca9a069f6f32e6e6bbdd05a980a717e
+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 sha256:65b528e84c03e8ffc52c2f65ef3aac75c997d75a46c226da178dbce4844a5221
+oid sha256:a5668efa7a2d3e6e82cce1fb88dafdddf66e36e9f594edbe8b5128192eff0e46
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4378110468387604,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-1050",
-  "epoch": 0.310192023633678,
+  "epoch": 0.3249630723781389,
   "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": 0.318,
       "num_input_tokens_seen": 10897528,
       "step": 1050
+    },
+    {
+      "epoch": 0.31166912850812406,
+      "grad_norm": 12.581621849544964,
+      "learning_rate": 9.697255249394527e-05,
+      "loss": 0.3724,
+      "num_input_tokens_seen": 10949888,
+      "step": 1055
+    },
+    {
+      "epoch": 0.31314623338257014,
+      "grad_norm": 6.318957148146118,
+      "learning_rate": 9.693056158509992e-05,
+      "loss": 0.4483,
+      "num_input_tokens_seen": 11001208,
+      "step": 1060
+    },
+    {
+      "epoch": 0.31462333825701627,
+      "grad_norm": 5.822614134671903,
+      "learning_rate": 9.688829068899483e-05,
+      "loss": 0.4133,
+      "num_input_tokens_seen": 11052368,
+      "step": 1065
+    },
+    {
+      "epoch": 0.31610044313146235,
+      "grad_norm": 6.115498616882066,
+      "learning_rate": 9.684574005781772e-05,
+      "loss": 0.5406,
+      "num_input_tokens_seen": 11104008,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3175775480059084,
+      "grad_norm": 12.381439695843321,
+      "learning_rate": 9.680290994542523e-05,
+      "loss": 0.4148,
+      "num_input_tokens_seen": 11155888,
+      "step": 1075
+    },
+    {
+      "epoch": 0.3190546528803545,
+      "grad_norm": 5.292808434292701,
+      "learning_rate": 9.675980060734138e-05,
+      "loss": 0.4169,
+      "num_input_tokens_seen": 11207352,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3205317577548006,
+      "grad_norm": 5.275144555938926,
+      "learning_rate": 9.671641230075604e-05,
+      "loss": 0.4706,
+      "num_input_tokens_seen": 11257672,
+      "step": 1085
+    },
+    {
+      "epoch": 0.32200886262924666,
+      "grad_norm": 7.458715041450571,
+      "learning_rate": 9.667274528452344e-05,
+      "loss": 0.3736,
+      "num_input_tokens_seen": 11309944,
+      "step": 1090
+    },
+    {
+      "epoch": 0.32348596750369274,
+      "grad_norm": 8.390618541362887,
+      "learning_rate": 9.662879981916054e-05,
+      "loss": 0.4413,
+      "num_input_tokens_seen": 11361032,
+      "step": 1095
+    },
+    {
+      "epoch": 0.3249630723781389,
+      "grad_norm": 14.65510134410483,
+      "learning_rate": 9.658457616684555e-05,
+      "loss": 0.4624,
+      "num_input_tokens_seen": 11413120,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3249630723781389,
+      "eval_loss": 0.5300672650337219,
+      "eval_runtime": 19.0076,
+      "eval_samples_per_second": 3.157,
+      "eval_steps_per_second": 0.789,
+      "num_input_tokens_seen": 11413120,
+      "step": 1100
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 10897528,
+  "num_input_tokens_seen": 11413120,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1895,7 +1984,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 718894119518208.0,
+  "total_flos": 752909914210304.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null