Training in progress, step 2150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24a4c37b80664a17b4612dbf43f560521041adc8bc0cc8d0182857100b9274e
+oid sha256:d1c3e74f99d6e6f70e37f4de247287b17ec6f7280a9a5e1856338be701a8ce67
 size 29034840

last-checkpoint/global_step2150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a37074e1b9eb8e7e9741d473741a29e69e4b377cc39bfa3bdc1b874fdf4dcf4
+size 43429616

last-checkpoint/global_step2150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef5eca98db54a12f7191e212555dc8082ff9e4eb5ea2b8f4903048a9dbc5271
+size 43429616

last-checkpoint/global_step2150/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:c41db3d5f00ed6b63921253518c9905e9dd3a8a7c16da5981495ee681e6bf324
+size 43429616

last-checkpoint/global_step2150/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:d91c14ff719858e547048aad542d5932f543e422aae2f8c24c9a253b735c22d5
+size 43429616

last-checkpoint/global_step2150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a104173fae309cddd5cec659a0d42963dd55180042b7dffd3c0a9f5330d16c
+size 637299

last-checkpoint/global_step2150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c382bb29b9b9b93ee74ce79ebdc7427abdd4946c08810e6ab54148107b238730
+size 637171

last-checkpoint/global_step2150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d55d5f44769829dccf11857c354f886ec28168ac4145aad5146200fcbf91acf
+size 637171

last-checkpoint/global_step2150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5959cc89357511b968c257c43a7386704691106ffbfe1db32582fe21f5f1e6b3
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2100
+global_step2150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1ddd7e7b4dc44903837b0414e4659f8383cd8f16b41dd396d4eaf5b9829f79
+oid sha256:b105708e2c99c8661b46698b8ccc5799ac83c1f0fc6a30c2d41c9fbfb349d480
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeddfb77fe4d3b495c4e08307767e08df90e96ef241c3eb80d5f75adec393e80
+oid sha256:bc44cd2015d8c8fc2f109f07c797876873a52f478c57b0350b8a2cf5dcb17f25
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6260196fabb00061b1f1c8de6288382570dc14d02d2aa308050ca858880a97
+oid sha256:9843dec201b5a542ebd69abfc596f99ad5a000cf81dab52c6a2c52a5b9224ea7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea023bc5b1def54e0c49389175c0fae812f5f764c502525ce775d993d5ab2c03
+oid sha256:2296f0efda653dd4c7e861f5a867baa09d6d8bb50e57bc69af930268b40de9ef
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3830a1cbcf9a648c99ec3b1dc2ae21133bcdd817f5603e9cff209ca0e0afc75
+oid sha256:b804035c19d1fffbc2b920172de721087c798cb2e8bcad45f6808db2d808af75
 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": 0.620384047267356,
+  "best_metric": 0.25809118151664734,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2150",
+  "epoch": 0.6351550960118169,
   "eval_steps": 50,
-  "global_step": 2100,
+  "global_step": 2150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3745,11 +3745,100 @@
       "eval_steps_per_second": 0.778,
       "num_input_tokens_seen": 21813984,
       "step": 2100
+    },
+    {
+      "epoch": 0.621861152141802,
+      "grad_norm": 11.844781107327274,
+      "learning_rate": 8.251927504753426e-05,
+      "loss": 0.3018,
+      "num_input_tokens_seen": 21865304,
+      "step": 2105
+    },
+    {
+      "epoch": 0.6233382570162481,
+      "grad_norm": 1.4332555229426183,
+      "learning_rate": 8.24264100077388e-05,
+      "loss": 0.2725,
+      "num_input_tokens_seen": 21918568,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6248153618906942,
+      "grad_norm": 16.587502798944953,
+      "learning_rate": 8.233335151230646e-05,
+      "loss": 0.3103,
+      "num_input_tokens_seen": 21970352,
+      "step": 2115
+    },
+    {
+      "epoch": 0.6262924667651403,
+      "grad_norm": 2.1746923737074333,
+      "learning_rate": 8.224010011642326e-05,
+      "loss": 0.2868,
+      "num_input_tokens_seen": 22021312,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6277695716395865,
+      "grad_norm": 20.536802693642485,
+      "learning_rate": 8.21466563764261e-05,
+      "loss": 0.335,
+      "num_input_tokens_seen": 22073496,
+      "step": 2125
+    },
+    {
+      "epoch": 0.6292466765140325,
+      "grad_norm": 2.23347350807466,
+      "learning_rate": 8.205302084979937e-05,
+      "loss": 0.3764,
+      "num_input_tokens_seen": 22124088,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6307237813884786,
+      "grad_norm": 1.4129621191965986,
+      "learning_rate": 8.19591940951717e-05,
+      "loss": 0.2681,
+      "num_input_tokens_seen": 22175824,
+      "step": 2135
+    },
+    {
+      "epoch": 0.6322008862629247,
+      "grad_norm": 1.1767190413631534,
+      "learning_rate": 8.186517667231259e-05,
+      "loss": 0.2619,
+      "num_input_tokens_seen": 22227376,
+      "step": 2140
+    },
+    {
+      "epoch": 0.6336779911373708,
+      "grad_norm": 1.5721543022398727,
+      "learning_rate": 8.1770969142129e-05,
+      "loss": 0.2516,
+      "num_input_tokens_seen": 22279928,
+      "step": 2145
+    },
+    {
+      "epoch": 0.6351550960118169,
+      "grad_norm": 1.1838050704992382,
+      "learning_rate": 8.167657206666217e-05,
+      "loss": 0.2387,
+      "num_input_tokens_seen": 22332144,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6351550960118169,
+      "eval_loss": 0.25809118151664734,
+      "eval_runtime": 19.3071,
+      "eval_samples_per_second": 3.108,
+      "eval_steps_per_second": 0.777,
+      "num_input_tokens_seen": 22332144,
+      "step": 2150
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 21813984,
+  "num_input_tokens_seen": 22332144,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3764,7 +3853,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1439243507597312.0,
+  "total_flos": 1473404374351872.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null