Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d6d14f8c29da8cdb8be1658c159a9d27e00215388ecaf0c21dc7d9ce80b66e
+oid sha256:8ea0b12291caef0384f7fd3bc0b1e4fc7815f7b867e0e565a267ef13238fd6a9
 size 29034840

last-checkpoint/global_step550/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404b0fc604b3f7b9510dc1d2d9f73378777d3cc1650ecf62e6013178b86df089
+size 43429616

last-checkpoint/global_step550/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ddf6c2b7fc0914636775966ff46b52649452ca9677fd31adc8ef827ee8c46f8
+size 43429616

last-checkpoint/global_step550/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:dbd201e14e8bc36621608ee22a4dd0a7e7fa64ba00e281c3405ea9a3f6ed49f1
+size 43429616

last-checkpoint/global_step550/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211f53152ca6696db7f31ba8043540fd487a13aae01fe3c3247100d7d8d34386
+size 43429616

last-checkpoint/global_step550/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f1e88f3bf0a1ab4f6fdcbce21f2206f381a04328feda2f67246fb4023f22be
+size 637299

last-checkpoint/global_step550/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096829d7819569a0a45c1f1ccd20ed09f7c621736d3582368c85eb1f4d51d913
+size 637171

last-checkpoint/global_step550/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fa69fa8e76e9121e0fe023594a90145c030a6aa13d4e5007cb9f1a4268ed73
+size 637171

last-checkpoint/global_step550/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15fb48a94b40a9b7267e646ab4d8caeff42e109740ea9800d79bc394acc6b40
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step500
+global_step550

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd1f02cb20d3f4f7e0dd26fea62af57e5e71316163f926a28ed6cf89a9f3777
+oid sha256:ae78313eb528c8d3695eebaf4de3539bd0a0bc6ee18c66af1ee183442f1758a0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6d54ba2aa85e2f895439a1b787ec947b848a1c34ea5a3a28821572bf2b9fec
+oid sha256:1b38031f60d9e88601d369ef46bcdcf2b5b03f2cb4ba93853bcb2328df7ebb7c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6927d26551cddd8e35b34b43e79bd58f8b6027b6a481bb6a563a3652addeb4
+oid sha256:f58092375c93d237cd0e3149aecfbf83e2acdae46279e07a32920d01cb507e64
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8295b1be8e66b4b30cb905dc48cfc717c027e427937b8142d00ae9de8106c6a
+oid sha256:83cd4bbff9962da7ec6787fcea8d65df7096917f9a5902e249ba7aee8887fe5f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938da5f0b93537debcb2a90ed511f9cb6684c34d5cc24b3eeea4c7db619e8fb7
+oid sha256:48642e777392e25274bb934c3caefd33d14bddceae2e006daf244ac2f6537412
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6505001187324524,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-500",
-  "epoch": 0.14771048744460857,
+  "epoch": 0.16248153618906944,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -897,11 +897,100 @@
       "eval_steps_per_second": 0.792,
       "num_input_tokens_seen": 5183664,
       "step": 500
+    },
+    {
+      "epoch": 0.14918759231905465,
+      "grad_norm": 11.975231950682153,
+      "learning_rate": 9.983569116887128e-05,
+      "loss": 0.573,
+      "num_input_tokens_seen": 5234920,
+      "step": 505
+    },
+    {
+      "epoch": 0.15066469719350073,
+      "grad_norm": 13.701425113518031,
+      "learning_rate": 9.982564982146327e-05,
+      "loss": 0.6261,
+      "num_input_tokens_seen": 5287312,
+      "step": 510
+    },
+    {
+      "epoch": 0.15214180206794684,
+      "grad_norm": 6.956866723254775,
+      "learning_rate": 9.981531121472811e-05,
+      "loss": 0.6072,
+      "num_input_tokens_seen": 5340240,
+      "step": 515
+    },
+    {
+      "epoch": 0.1536189069423929,
+      "grad_norm": 5.293847645949678,
+      "learning_rate": 9.980467541034584e-05,
+      "loss": 0.565,
+      "num_input_tokens_seen": 5392600,
+      "step": 520
+    },
+    {
+      "epoch": 0.155096011816839,
+      "grad_norm": 3.5333148010719357,
+      "learning_rate": 9.979374247176956e-05,
+      "loss": 0.6188,
+      "num_input_tokens_seen": 5445168,
+      "step": 525
+    },
+    {
+      "epoch": 0.15657311669128507,
+      "grad_norm": 2.715838950258193,
+      "learning_rate": 9.978251246422505e-05,
+      "loss": 0.6069,
+      "num_input_tokens_seen": 5496384,
+      "step": 530
+    },
+    {
+      "epoch": 0.15805022156573117,
+      "grad_norm": 7.400638197441027,
+      "learning_rate": 9.977098545471046e-05,
+      "loss": 0.5805,
+      "num_input_tokens_seen": 5548264,
+      "step": 535
+    },
+    {
+      "epoch": 0.15952732644017725,
+      "grad_norm": 8.936418653401088,
+      "learning_rate": 9.975916151199579e-05,
+      "loss": 0.6383,
+      "num_input_tokens_seen": 5599216,
+      "step": 540
+    },
+    {
+      "epoch": 0.16100443131462333,
+      "grad_norm": 7.142901090509074,
+      "learning_rate": 9.974704070662254e-05,
+      "loss": 0.5845,
+      "num_input_tokens_seen": 5650816,
+      "step": 545
+    },
+    {
+      "epoch": 0.16248153618906944,
+      "grad_norm": 18.523556086651276,
+      "learning_rate": 9.973462311090336e-05,
+      "loss": 0.5957,
+      "num_input_tokens_seen": 5703016,
+      "step": 550
+    },
+    {
+      "epoch": 0.16248153618906944,
+      "eval_loss": 0.6883422136306763,
+      "eval_runtime": 19.183,
+      "eval_samples_per_second": 3.128,
+      "eval_steps_per_second": 0.782,
+      "num_input_tokens_seen": 5703016,
+      "step": 550
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 5183664,
+  "num_input_tokens_seen": 5703016,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -916,7 +1005,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 341890836201472.0,
+  "total_flos": 376097589690368.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null