Training in progress, step 1150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47b9a2cfb5d827890098fe64e850aeaac9bcd5c19d855922f5746d06e17ed00
+oid sha256:847b02ea6b5dcacf2ba31391c0399f758f14d0815ccad3f7b70c82822ffabbaf
 size 18516456

last-checkpoint/global_step1150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b830f1cfc3113e45ad76fcbc9afac4cf862dd17dd24fb84e9dfd5ffb30c30fe
+size 27700976

last-checkpoint/global_step1150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8699f67ef02ea4c620535fe6f5d6980bcfc0498bbdf0f8503772f92599cf7a03
+size 27700976

last-checkpoint/global_step1150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5417e0f4750c39f591940a0681341cfbd2f0e112c3e3616f7a4e48bc7ce581
+size 27700976

last-checkpoint/global_step1150/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:a79e251d90f97f562fd85fea593c6e14d9b1fbc314b3592a821f8be0c4a7f0b2
+size 27700976

last-checkpoint/global_step1150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338ba64e4044385351dedf46a2f7a310a402d7578a8d6abd7949e5a0e591e43f
+size 411571

last-checkpoint/global_step1150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241d9f30e7b5a561a452b13f8f8f9f2467d7c1443966c685398de1994a521101
+size 411507

last-checkpoint/global_step1150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38baf92a17f702c40181c34f75451abcfddcb1a9b6177c74f95fe31dc35063e1
+size 411507

last-checkpoint/global_step1150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c647d5e377bc6b57f168137d5e742f515c0e81c2bcb3b83c95ae19edbaae531
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step1100
+global_step1150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9fea52fb92cc51e76feeb2b139ce35723c0cb651da383e4f7eec2606ed6c2a
+oid sha256:274dc3860ee0c7f4d5348f60910a4b568498c04adfefb89f905b1c78a82c1312
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5820ebfcc2e1cfe1ad2619a05ea9a484ff21635e13e386bf14abd302f2c0f7
+oid sha256:e9aa441491b9ca89e796944520fa1db332a67c0a1a920be83edd2d96d741716d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8d96a68e732fca41980516622a50990bbd3ee989e72076a35c8608d9b4d136
+oid sha256:c1ee3434533b24fb771504fa8cceb5c2ea25fe0de1641128feaceccc65afe6ed
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6f1db6d09f4d89a9b2bd8dc8eeb99f1fada2ec04376e23b5a7a13004994005
+oid sha256:93b4a44be1335173d2e3120bd0d1e6346f3e832d8935752c70ce1e98f017fa87
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0c7456eafeee3179566bb381c9153771d7e0f21738d2398944d053915d0651
+oid sha256:7d461c8d7517d4b88333bff7984fc3bfc149292198b04bbc18a49aee698ffb5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7743102312088013,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1100",
-  "epoch": 0.56657223796034,
+  "epoch": 0.5923255215039918,
   "eval_steps": 50,
-  "global_step": 1100,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1965,11 +1965,100 @@
       "eval_steps_per_second": 0.931,
       "num_input_tokens_seen": 12865992,
       "step": 1100
+    },
+    {
+      "epoch": 0.5691475663147051,
+      "grad_norm": 1.6435842633079423,
+      "learning_rate": 8.07106356344834e-05,
+      "loss": 0.8335,
+      "num_input_tokens_seen": 12924448,
+      "step": 1105
+    },
+    {
+      "epoch": 0.5717228946690703,
+      "grad_norm": 1.2281943545237959,
+      "learning_rate": 8.051838793910038e-05,
+      "loss": 0.8267,
+      "num_input_tokens_seen": 12982912,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5742982230234355,
+      "grad_norm": 1.4138823100284208,
+      "learning_rate": 8.032541847934146e-05,
+      "loss": 0.8866,
+      "num_input_tokens_seen": 13041424,
+      "step": 1115
+    },
+    {
+      "epoch": 0.5768735513778007,
+      "grad_norm": 0.6515311059204204,
+      "learning_rate": 8.013173181896283e-05,
+      "loss": 0.8446,
+      "num_input_tokens_seen": 13099888,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5794488797321659,
+      "grad_norm": 0.7537544303655812,
+      "learning_rate": 7.993733253868256e-05,
+      "loss": 0.8176,
+      "num_input_tokens_seen": 13158344,
+      "step": 1125
+    },
+    {
+      "epoch": 0.582024208086531,
+      "grad_norm": 1.3613777296967222,
+      "learning_rate": 7.974222523607236e-05,
+      "loss": 0.8138,
+      "num_input_tokens_seen": 13216840,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5845995364408962,
+      "grad_norm": 0.6640843445520798,
+      "learning_rate": 7.954641452544865e-05,
+      "loss": 0.8204,
+      "num_input_tokens_seen": 13275328,
+      "step": 1135
+    },
+    {
+      "epoch": 0.5871748647952614,
+      "grad_norm": 0.6917895597906035,
+      "learning_rate": 7.934990503776363e-05,
+      "loss": 0.8485,
+      "num_input_tokens_seen": 13333784,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5897501931496266,
+      "grad_norm": 0.45542718993625547,
+      "learning_rate": 7.915270142049566e-05,
+      "loss": 0.8191,
+      "num_input_tokens_seen": 13392280,
+      "step": 1145
+    },
+    {
+      "epoch": 0.5923255215039918,
+      "grad_norm": 0.618954778582039,
+      "learning_rate": 7.89548083375394e-05,
+      "loss": 0.8185,
+      "num_input_tokens_seen": 13450720,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5923255215039918,
+      "eval_loss": 0.7827339768409729,
+      "eval_runtime": 16.0127,
+      "eval_samples_per_second": 3.747,
+      "eval_steps_per_second": 0.937,
+      "num_input_tokens_seen": 13450720,
+      "step": 1150
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 12865992,
+  "num_input_tokens_seen": 13450720,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1984,7 +2073,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 722443216093184.0,
+  "total_flos": 755277071908864.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null