Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c07c45cd740f6c38df8b73c4bc4f9f8c11bd6712886d745d8476e5ba112852
+oid sha256:a111e8798c83c643eeba02e2a149e66e3437bb97bb843d76a35308962c3f1d78
 size 29034840

last-checkpoint/global_step2099/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3908f123db8cae3a945e895d5aa1a25ac06fead96ab3d44f58999c89ede68a1e
+size 43429616

last-checkpoint/global_step2099/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:c87aab36c08b6bda15ecb4f5a883590379e836f53870ca7d87391088cd1f3778
+size 43429616

last-checkpoint/global_step2099/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d47c521ed24c4713fe79fad87b641b58f7e9b18218d342415d15e68d1675e8
+size 43429616

last-checkpoint/global_step2099/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6332f495af7a2bd28833ac9d8356f39a73edd88a1a16862d6d97bb8e1ba7e240
+size 43429616

last-checkpoint/global_step2099/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170819cf1e1ec40f1c64f0f8a28739309ccba0083ab91beb471c76cc01917bb0
+size 637299

last-checkpoint/global_step2099/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cea1f1d451e7ba08fb0317e93f359869010a66eb50256a9b0a830427271d537
+size 637171

last-checkpoint/global_step2099/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a405978cb31a944c3cf457970ae9b8c0a96c904b42cddc15e4901dc4de49c64
+size 637171

last-checkpoint/global_step2099/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f57c64158a3a073300bf316e496206fb6d7f6f6ccd70d8f76a94d610905b5a
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2049
+global_step2099

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1ddd7e7b4dc44903837b0414e4659f8383cd8f16b41dd396d4eaf5b9829f79
+oid sha256:b105708e2c99c8661b46698b8ccc5799ac83c1f0fc6a30c2d41c9fbfb349d480
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeddfb77fe4d3b495c4e08307767e08df90e96ef241c3eb80d5f75adec393e80
+oid sha256:bc44cd2015d8c8fc2f109f07c797876873a52f478c57b0350b8a2cf5dcb17f25
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6260196fabb00061b1f1c8de6288382570dc14d02d2aa308050ca858880a97
+oid sha256:9843dec201b5a542ebd69abfc596f99ad5a000cf81dab52c6a2c52a5b9224ea7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea023bc5b1def54e0c49389175c0fae812f5f764c502525ce775d993d5ab2c03
+oid sha256:2296f0efda653dd4c7e861f5a867baa09d6d8bb50e57bc69af930268b40de9ef
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041c9bf0c91e6ca81e97b14bb8b67e4083823b3129e241af387f768dc73002f8
+oid sha256:7e06f479f50d6b90756aab0e5f1d2b8944be9014d46f9719fade9db1f0995f9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2472737729549408,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-1950",
-  "epoch": 1.0556270924542879,
+  "epoch": 1.0813803759979397,
   "eval_steps": 50,
-  "global_step": 2050,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3656,11 +3656,100 @@
       "eval_steps_per_second": 0.773,
       "num_input_tokens_seen": 23971048,
       "step": 2050
+    },
+    {
+      "epoch": 1.0582024208086531,
+      "grad_norm": 11.207729973488336,
+      "learning_rate": 4.929706304405748e-05,
+      "loss": 0.217,
+      "num_input_tokens_seen": 24029544,
+      "step": 2055
+    },
+    {
+      "epoch": 1.0607777491630184,
+      "grad_norm": 10.285736762582813,
+      "learning_rate": 4.9084072903884345e-05,
+      "loss": 0.2132,
+      "num_input_tokens_seen": 24088008,
+      "step": 2060
+    },
+    {
+      "epoch": 1.0633530775173834,
+      "grad_norm": 6.469754305471942,
+      "learning_rate": 4.887109938840783e-05,
+      "loss": 0.2438,
+      "num_input_tokens_seen": 24146480,
+      "step": 2065
+    },
+    {
+      "epoch": 1.0659284058717486,
+      "grad_norm": 7.546288384087562,
+      "learning_rate": 4.8658146363241406e-05,
+      "loss": 0.2623,
+      "num_input_tokens_seen": 24204984,
+      "step": 2070
+    },
+    {
+      "epoch": 1.0685037342261139,
+      "grad_norm": 4.658066041307915,
+      "learning_rate": 4.844521769362654e-05,
+      "loss": 0.2041,
+      "num_input_tokens_seen": 24263456,
+      "step": 2075
+    },
+    {
+      "epoch": 1.071079062580479,
+      "grad_norm": 6.232031131112278,
+      "learning_rate": 4.823231724436271e-05,
+      "loss": 0.246,
+      "num_input_tokens_seen": 24321960,
+      "step": 2080
+    },
+    {
+      "epoch": 1.0736543909348442,
+      "grad_norm": 10.347547308861373,
+      "learning_rate": 4.801944887973714e-05,
+      "loss": 0.2857,
+      "num_input_tokens_seen": 24380464,
+      "step": 2085
+    },
+    {
+      "epoch": 1.0762297192892094,
+      "grad_norm": 7.357894649180612,
+      "learning_rate": 4.7806616463454715e-05,
+      "loss": 0.2577,
+      "num_input_tokens_seen": 24438976,
+      "step": 2090
+    },
+    {
+      "epoch": 1.0788050476435747,
+      "grad_norm": 9.485170393194913,
+      "learning_rate": 4.759382385856779e-05,
+      "loss": 0.2523,
+      "num_input_tokens_seen": 24497448,
+      "step": 2095
+    },
+    {
+      "epoch": 1.0813803759979397,
+      "grad_norm": 6.0022045554501045,
+      "learning_rate": 4.738107492740619e-05,
+      "loss": 0.2805,
+      "num_input_tokens_seen": 24555904,
+      "step": 2100
+    },
+    {
+      "epoch": 1.0813803759979397,
+      "eval_loss": 0.3205481469631195,
+      "eval_runtime": 19.3676,
+      "eval_samples_per_second": 3.098,
+      "eval_steps_per_second": 0.774,
+      "num_input_tokens_seen": 24555904,
+      "step": 2100
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 23971048,
+  "num_input_tokens_seen": 24555904,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -3675,7 +3764,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1581709155893248.0,
+  "total_flos": 1620301350436864.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null