Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5682b2eafe76e843b3c252d9efdff6d8e222ea2c09fcb985ed44476c6c49d3c0
+oid sha256:3e3aaf9e6c8d830995b2a237a6a326491ecc141ce2f9713c7cafa4ab230f17cb
 size 29034840

last-checkpoint/global_step450/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:d5c814ad588b1665f2b04d0687e9a2e36e4add22db1e7d4a157a85a1e5dcbc00
+size 43429616

last-checkpoint/global_step450/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:d9d1bf853471ab45c77df069f67590378cc45e763121492de3a880e050e5387b
+size 43429616

last-checkpoint/global_step450/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c7c9115f51b9a82946db16ad5410c547718f1a13c8703a0865244932e60537
+size 43429616

last-checkpoint/global_step450/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a9db1b2a23e12f16a96377f5b5f03a144a90e62ecc5a6634e7ee8832c81cd1
+size 43429616

last-checkpoint/global_step450/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c43b6581640ec9140a8e671944ff69d96a0284c4069ddbe5a73547523d050e
+size 637299

last-checkpoint/global_step450/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7b078653231149a903bc00280c61fc902a6ebe6078af02817b5efd13e9ef2b
+size 637171

last-checkpoint/global_step450/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3014bb4485c273ec85ee6adab304455dcd75b99ca668f9c10e04f1ebc443fec8
+size 637171

last-checkpoint/global_step450/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23e7a4eb8e027c3a1e9ed72ab3097610a2c4faa00790d4b003da7cdb06018e2
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step400
+global_step450

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543ef05f530d40ee20b8d626b07a69b86597aca643e48897571062f973efe84f
+oid sha256:7dbc6521b0b64cb12d818506108fcf257a4089ca8a9b1e453776ed3e032e7176
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a23f732e43838ce0398d2636885ac16badbb9bcbc04d1406069ba3027bc5ae0
+oid sha256:2b13e3da1b0679cab1bab94f893e385a9a224d3335b5a6f62602f33c2be88d03
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10cce960e7068b051c05e35ed6160656be9091c63f13796ac2ed7e9c84e5a72
+oid sha256:6a24f0e0f117b5a8236e0d12594c0c358f41ef00068d4460002e95ad1cc3cb1c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f6049e212b1df5cefc5d834afcd8cc052c73f1457449e9fe8a38d514f54078
+oid sha256:e46e4eab6c4a25d84ad36ddf1357401788adeeb6388c03cefa35a63b52ee7610
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa1113b4807f273646ff4a5c640f26a2f072e0ac3eba31e530c029f936b8156
+oid sha256:312387a763149a43bd97e3a38958946d432aa6037fb7604fcd6a6729912e1b32
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7038857936859131,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-400",
-  "epoch": 0.11816838995568685,
+  "epoch": 0.1329394387001477,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -719,11 +719,100 @@
       "eval_steps_per_second": 0.787,
       "num_input_tokens_seen": 4142592,
       "step": 400
+    },
+    {
+      "epoch": 0.11964549483013294,
+      "grad_norm": 4.400494365327609,
+      "learning_rate": 9.997401438591772e-05,
+      "loss": 0.6209,
+      "num_input_tokens_seen": 4194920,
+      "step": 405
+    },
+    {
+      "epoch": 0.12112259970457903,
+      "grad_norm": 4.518582133930376,
+      "learning_rate": 9.996992844441495e-05,
+      "loss": 0.6576,
+      "num_input_tokens_seen": 4247048,
+      "step": 410
+    },
+    {
+      "epoch": 0.12259970457902511,
+      "grad_norm": 2.6773114089558043,
+      "learning_rate": 9.996554438282022e-05,
+      "loss": 0.6851,
+      "num_input_tokens_seen": 4299728,
+      "step": 415
+    },
+    {
+      "epoch": 0.1240768094534712,
+      "grad_norm": 10.583849604294256,
+      "learning_rate": 9.996086222728879e-05,
+      "loss": 0.6288,
+      "num_input_tokens_seen": 4351088,
+      "step": 420
+    },
+    {
+      "epoch": 0.1255539143279173,
+      "grad_norm": 5.18430085456359,
+      "learning_rate": 9.995588200575439e-05,
+      "loss": 0.667,
+      "num_input_tokens_seen": 4403016,
+      "step": 425
+    },
+    {
+      "epoch": 0.12703101920236337,
+      "grad_norm": 3.624202284960618,
+      "learning_rate": 9.995060374792892e-05,
+      "loss": 0.6747,
+      "num_input_tokens_seen": 4453880,
+      "step": 430
+    },
+    {
+      "epoch": 0.12850812407680945,
+      "grad_norm": 8.193068077958594,
+      "learning_rate": 9.994502748530244e-05,
+      "loss": 0.6594,
+      "num_input_tokens_seen": 4505616,
+      "step": 435
+    },
+    {
+      "epoch": 0.12998522895125553,
+      "grad_norm": 6.0681139183306145,
+      "learning_rate": 9.993915325114288e-05,
+      "loss": 0.6727,
+      "num_input_tokens_seen": 4558384,
+      "step": 440
+    },
+    {
+      "epoch": 0.13146233382570163,
+      "grad_norm": 3.998790148445953,
+      "learning_rate": 9.993298108049582e-05,
+      "loss": 0.6526,
+      "num_input_tokens_seen": 4611184,
+      "step": 445
+    },
+    {
+      "epoch": 0.1329394387001477,
+      "grad_norm": 3.1838689643423392,
+      "learning_rate": 9.992651101018445e-05,
+      "loss": 0.5661,
+      "num_input_tokens_seen": 4663320,
+      "step": 450
+    },
+    {
+      "epoch": 0.1329394387001477,
+      "eval_loss": 0.7132604718208313,
+      "eval_runtime": 18.996,
+      "eval_samples_per_second": 3.159,
+      "eval_steps_per_second": 0.79,
+      "num_input_tokens_seen": 4663320,
+      "step": 450
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 4142592,
+  "num_input_tokens_seen": 4663320,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -738,7 +827,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 273245789749248.0,
+  "total_flos": 307607720951808.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null