Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55382d84797424bf555d465074d1d58ecfa91cc23250d3509fdb9cd78d1cbeff
+oid sha256:82e427cc7e624394004d64620be182b50bd10e2a67a34cf622de25a3f138b7e0
 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 sha256:735c0136eff0398146cf3a3ab763ebac3d070d48f89a182a5573fd655e7afdaf
+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 sha256:6bf8140665399fdea0be80da5aa6d4bba2b8fc3ed75218ea7ea9597294354c6e
+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 sha256:051f89f797fb6f86de484b54f48bb5b36e77703038f5c839a589563e8769d8fc
+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 sha256:130206d3a04e9a463582348d97149ab8817702228f3aa905b7b20377e4f453d3
+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 sha256:8779534db128a38380f8ecdd5b697bdb59a398f35fe4ad4de1318e871fcc0e6f
+oid sha256:5e969c9b0ecef9c1209a6397ff63db034af1cc51341323dc3dc14016347fe871
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8268976211547852,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-500",
-  "epoch": 0.25753283543651817,
+  "best_metric": 0.7909801602363586,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-550",
+  "epoch": 0.28328611898017,
   "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": 0.764,
       "num_input_tokens_seen": 5848048,
       "step": 500
+    },
+    {
+      "epoch": 0.26010816379088336,
+      "grad_norm": 4.216936754020565,
+      "learning_rate": 9.826583551051483e-05,
+      "loss": 0.8566,
+      "num_input_tokens_seen": 5906512,
+      "step": 505
+    },
+    {
+      "epoch": 0.2626834921452485,
+      "grad_norm": 10.456282683777822,
+      "learning_rate": 9.820978249400773e-05,
+      "loss": 0.8365,
+      "num_input_tokens_seen": 5965024,
+      "step": 510
+    },
+    {
+      "epoch": 0.2652588204996137,
+      "grad_norm": 2.334974931865165,
+      "learning_rate": 9.81528544373233e-05,
+      "loss": 0.8882,
+      "num_input_tokens_seen": 6023496,
+      "step": 515
+    },
+    {
+      "epoch": 0.2678341488539789,
+      "grad_norm": 0.6948827424617825,
+      "learning_rate": 9.809505237374426e-05,
+      "loss": 0.8799,
+      "num_input_tokens_seen": 6082000,
+      "step": 520
+    },
+    {
+      "epoch": 0.2704094772083441,
+      "grad_norm": 0.8415524888602947,
+      "learning_rate": 9.80363773524172e-05,
+      "loss": 0.8758,
+      "num_input_tokens_seen": 6140480,
+      "step": 525
+    },
+    {
+      "epoch": 0.27298480556270927,
+      "grad_norm": 1.3536520282199265,
+      "learning_rate": 9.797683043833345e-05,
+      "loss": 0.8644,
+      "num_input_tokens_seen": 6198968,
+      "step": 530
+    },
+    {
+      "epoch": 0.2755601339170744,
+      "grad_norm": 4.556188528469967,
+      "learning_rate": 9.791641271230982e-05,
+      "loss": 0.8453,
+      "num_input_tokens_seen": 6257464,
+      "step": 535
+    },
+    {
+      "epoch": 0.2781354622714396,
+      "grad_norm": 2.890141630286954,
+      "learning_rate": 9.78551252709689e-05,
+      "loss": 0.8533,
+      "num_input_tokens_seen": 6315944,
+      "step": 540
+    },
+    {
+      "epoch": 0.2807107906258048,
+      "grad_norm": 4.471490037342243,
+      "learning_rate": 9.779296922671923e-05,
+      "loss": 0.8575,
+      "num_input_tokens_seen": 6374408,
+      "step": 545
+    },
+    {
+      "epoch": 0.28328611898017,
+      "grad_norm": 3.174906426420603,
+      "learning_rate": 9.77299457077351e-05,
+      "loss": 0.8666,
+      "num_input_tokens_seen": 6432936,
+      "step": 550
+    },
+    {
+      "epoch": 0.28328611898017,
+      "eval_loss": 0.7909801602363586,
+      "eval_runtime": 19.8739,
+      "eval_samples_per_second": 3.019,
+      "eval_steps_per_second": 0.755,
+      "num_input_tokens_seen": 6432936,
+      "step": 550
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 5848048,
+  "num_input_tokens_seen": 6432936,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -916,7 +1005,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 385817567035392.0,
+  "total_flos": 424412082339840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null