Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f092c8551b39f72b2480ed050635fbcee05ba27bc1999c55e842ece4cdbe8b
+oid sha256:703d6c7e98f4bf68731cde74c5b20cc8e4bb82cbcfea9af1822815e13d9fd381
 size 29034840

last-checkpoint/global_step1800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007e09fbadb8592f88e97176443687fca48eab7f5db9c1bbf9c938c3ed3192a6
+size 43429616

last-checkpoint/global_step1800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdfbde74aa32ffe4f8d135bf570e392a9f9a1def80871981b9b6ed0bda1af8f
+size 43429616

last-checkpoint/global_step1800/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b78d4331a9f341772b0453cd7d7c4821bd7f356c524cb0d19deb86dc12f825a
+size 43429616

last-checkpoint/global_step1800/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c2ea98bf8d297d2d3a0840da8aa8b09b47b43d9f17d8af91b84f8f4ab50698
+size 43429616

last-checkpoint/global_step1800/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b04f4e9069181e25525c87fbf11d999a2d4abd07f3eb50097501d9dd0542fec
+size 637299

last-checkpoint/global_step1800/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8237e9df6dbc2214b6b3530b5a9dd66ba4d4334b0ef1e1f4ab5b6012172e97a
+size 637171

last-checkpoint/global_step1800/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3e2db29e2e998fbb06c7913097998b93745165aef55c2291b5a721e12abbfa
+size 637171

last-checkpoint/global_step1800/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59280c3fd7f89f5dcc1f73643489f2258fbd2902aeb5a6835cc2a6d4eadbd71
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1750
+global_step1800

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222e5f04f66dfcca4efb2d648f5a480d56c2a07755d7a1bae8232d01d4b479ce
+oid sha256:4d76f093328c54f2b94a10b8b50dc92fc99ceff9e3949d050a70042526f1d0eb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150a9cfa07bd33135b1b8b22033907e44137689de662dda0a482f3af84c5a1ff
+oid sha256:54b172dd00cba9f005761d85fb0804f751caf6e1cc8294d1873354a890cb9909
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c0d7619e94c90efa0c89a1f208db53b48c726519761710da6fbc31a80651d8
+oid sha256:ec6adef733bd7630aa48eff1a6edaabc275d67293dcb0b7a64d71451405d489d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa66a4b2f749b1ec7e8868668dc670ff3f6d8df765a5249122f980ae5aae6a54
+oid sha256:6ce1c4ba1932c0f698bef90e0e4e74ded1e0db5fc35282a0815899b8be759e67
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46be255d8fc53b179b832135261a9566900d19a45a6e3b7aa116fe2096be8b96
+oid sha256:df430b942be14b68acaf59a6a16e4c1e563f436ec4bae0ac022a9110d0fbea5b
 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": 0.51698670605613,
+  "epoch": 0.5317577548005908,
   "eval_steps": 50,
-  "global_step": 1750,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3122,11 +3122,100 @@
       "eval_steps_per_second": 0.772,
       "num_input_tokens_seen": 18169344,
       "step": 1750
+    },
+    {
+      "epoch": 0.518463810930576,
+      "grad_norm": 9.533140259257635,
+      "learning_rate": 8.850728393614902e-05,
+      "loss": 0.2966,
+      "num_input_tokens_seen": 18221144,
+      "step": 1755
+    },
+    {
+      "epoch": 0.5199409158050221,
+      "grad_norm": 1.1902233180287396,
+      "learning_rate": 8.842926829362446e-05,
+      "loss": 0.3101,
+      "num_input_tokens_seen": 18272752,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5214180206794683,
+      "grad_norm": 5.4464127921059635,
+      "learning_rate": 8.835102338247064e-05,
+      "loss": 0.2545,
+      "num_input_tokens_seen": 18325888,
+      "step": 1765
+    },
+    {
+      "epoch": 0.5228951255539144,
+      "grad_norm": 4.908248580861331,
+      "learning_rate": 8.827254966949593e-05,
+      "loss": 0.3223,
+      "num_input_tokens_seen": 18378016,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5243722304283605,
+      "grad_norm": 8.878082941549529,
+      "learning_rate": 8.819384762287373e-05,
+      "loss": 0.2714,
+      "num_input_tokens_seen": 18431240,
+      "step": 1775
+    },
+    {
+      "epoch": 0.5258493353028065,
+      "grad_norm": 1.3922104834090385,
+      "learning_rate": 8.811491771213964e-05,
+      "loss": 0.3438,
+      "num_input_tokens_seen": 18482832,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5273264401772526,
+      "grad_norm": 6.15513486850916,
+      "learning_rate": 8.803576040818873e-05,
+      "loss": 0.2324,
+      "num_input_tokens_seen": 18534992,
+      "step": 1785
+    },
+    {
+      "epoch": 0.5288035450516987,
+      "grad_norm": 5.349889126448278,
+      "learning_rate": 8.795637618327269e-05,
+      "loss": 0.2259,
+      "num_input_tokens_seen": 18587752,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5302806499261448,
+      "grad_norm": 11.727285406275136,
+      "learning_rate": 8.7876765510997e-05,
+      "loss": 0.2468,
+      "num_input_tokens_seen": 18640440,
+      "step": 1795
+    },
+    {
+      "epoch": 0.5317577548005908,
+      "grad_norm": 2.562809564221474,
+      "learning_rate": 8.779692886631812e-05,
+      "loss": 0.3127,
+      "num_input_tokens_seen": 18691928,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5317577548005908,
+      "eval_loss": 0.3499237596988678,
+      "eval_runtime": 19.3376,
+      "eval_samples_per_second": 3.103,
+      "eval_steps_per_second": 0.776,
+      "num_input_tokens_seen": 18691928,
+      "step": 1800
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 18169344,
+  "num_input_tokens_seen": 18691928,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3141,7 +3230,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1198665362571264.0,
+  "total_flos": 1233113797361664.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null