Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef73e2283ef0a8265cb8500b9ad3f8507559811b231f9ac4422b8beb4ea24ca
+oid sha256:80957d4d61fd32f325d1e1389afae72c016da18ced07ab4e480f80b2f80d1f1d
 size 18516456

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 sha256:2b3b41ba55200d920320eff5fa1315f1f113d1b1c434e47e8ab87efd7abca436
+size 27700976

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 sha256:64993108326120b5b609c448a2563715bb5e3c6d99c0642a59f06352820dcb46
+size 27700976

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:a9be39eb1fc36958fe6bb6cd68f427727561b7b8b0f6172648c8f4c61d000ea3
+size 27700976

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 sha256:07f13221716bd22ef08f503210147b437b204d8a18b1daa271ff3f264f68c1ca
+size 27700976

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 sha256:6c90eea3ce34f15daaff9c9681a7d74ccecf6838cb52d2b24db102d117308bce
+size 411571

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:ce46a2ea3eceb9f00da73dd7f2d7d284f5cdb22b8af5b88634ee12736d91d06b
+size 411507

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:fb904050e7bc7ad93f63e761b3f5399ec807ef4590b8af8d961b124317a9d65f
+size 411507

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 sha256:43d272e6fb20b6249063feaf7246d0e06ce38ced0dd4de671f629b8555a80690
+size 411507

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 sha256:2a1c59a2217a7993f4a6258f4be38869d3dc42c6bc2349bde5d4858846c79cb4
+oid sha256:586e8022fc0be60f50aebd58453b59ef73708ef9c9ee879c0bef0b407e787025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6319106221199036,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1600",
-  "epoch": 0.9013649240278135,
+  "epoch": 0.9271182075714653,
   "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": 0.936,
       "num_input_tokens_seen": 20468200,
       "step": 1750
+    },
+    {
+      "epoch": 0.9039402523821787,
+      "grad_norm": 4.616122198129487,
+      "learning_rate": 5.145873693974188e-05,
+      "loss": 0.5248,
+      "num_input_tokens_seen": 20526696,
+      "step": 1755
+    },
+    {
+      "epoch": 0.9065155807365439,
+      "grad_norm": 5.322590172525407,
+      "learning_rate": 5.12156668275638e-05,
+      "loss": 0.4756,
+      "num_input_tokens_seen": 20585160,
+      "step": 1760
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 4.002252878507737,
+      "learning_rate": 5.097256796468598e-05,
+      "loss": 0.4405,
+      "num_input_tokens_seen": 20643672,
+      "step": 1765
+    },
+    {
+      "epoch": 0.9116662374452743,
+      "grad_norm": 5.58017966349683,
+      "learning_rate": 5.072944610043232e-05,
+      "loss": 0.5201,
+      "num_input_tokens_seen": 20702152,
+      "step": 1770
+    },
+    {
+      "epoch": 0.9142415657996394,
+      "grad_norm": 4.688576373892097,
+      "learning_rate": 5.048630698467081e-05,
+      "loss": 0.4662,
+      "num_input_tokens_seen": 20760664,
+      "step": 1775
+    },
+    {
+      "epoch": 0.9168168941540046,
+      "grad_norm": 4.984086874604376,
+      "learning_rate": 5.024315636767738e-05,
+      "loss": 0.5376,
+      "num_input_tokens_seen": 20819144,
+      "step": 1780
+    },
+    {
+      "epoch": 0.9193922225083698,
+      "grad_norm": 4.470690620190923,
+      "learning_rate": 5e-05,
+      "loss": 0.5174,
+      "num_input_tokens_seen": 20877624,
+      "step": 1785
+    },
+    {
+      "epoch": 0.921967550862735,
+      "grad_norm": 4.1127649145734795,
+      "learning_rate": 4.9756843632322626e-05,
+      "loss": 0.4273,
+      "num_input_tokens_seen": 20936112,
+      "step": 1790
+    },
+    {
+      "epoch": 0.9245428792171002,
+      "grad_norm": 5.1892527739805185,
+      "learning_rate": 4.9513693015329197e-05,
+      "loss": 0.4646,
+      "num_input_tokens_seen": 20994608,
+      "step": 1795
+    },
+    {
+      "epoch": 0.9271182075714653,
+      "grad_norm": 6.8574703914708985,
+      "learning_rate": 4.9270553899567686e-05,
+      "loss": 0.412,
+      "num_input_tokens_seen": 21053080,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9271182075714653,
+      "eval_loss": 0.6768696904182434,
+      "eval_runtime": 15.9758,
+      "eval_samples_per_second": 3.756,
+      "eval_steps_per_second": 0.939,
+      "num_input_tokens_seen": 21053080,
+      "step": 1800
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 20468200,
+  "num_input_tokens_seen": 21053080,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3141,7 +3230,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1149340689891328.0,
+  "total_flos": 1182185020981248.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null