Training in progress, step 650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168cc62ce0f9bc823e9f05cfca486c4f8b12cfdb3adf1b70687137fa417f7b65
+oid sha256:e67d46cdc279c111f3d8b6cd0c68158fe4239ea365a1c2b31f1709a759de013a
 size 29034840

last-checkpoint/global_step650/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d01bfba78120d96959b055843024bd09f10360c10a51370c7a04ad4ca16e2b
+size 43429616

last-checkpoint/global_step650/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:d43719e39bbb6e731c70986b000f026aaef64ad5e576c03421efc74a249aef17
+size 43429616

last-checkpoint/global_step650/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e58ddb882ce83931caddad7c8eb62c51d3a029a7669ac2a1fa9911be812fc8f
+size 43429616

last-checkpoint/global_step650/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:e20c6a185c2c8c974c38b0c9335e9f3a0acb549e7128f771e2b77df5c5c0896e
+size 43429616

last-checkpoint/global_step650/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9450a0ced61d6c33a66cdf1b2511022f0ec24416b17e1f16ed49dc98ff62dd
+size 637299

last-checkpoint/global_step650/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01b9093c4ff061c6453535b14beda5a9d96a531472a58effac685152d63de95
+size 637171

last-checkpoint/global_step650/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3bfb0ef98b44969e473f6d5c11a92b5a607c48dc2a278b5d72591611de4079
+size 637171

last-checkpoint/global_step650/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41c42f45b9260afbaae285e2a90de1413db2108ea931952bc69942ea6f19e1e
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step600
+global_step650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81e3916b1392c4c49afb171dee5415c15f5a5a5af8749b28195fcfa0596699c
+oid sha256:8044e4c53158c210a17648ba8f2dc2d25a25bbfc55f686015542618eb652a33e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a781038dd714b87b8adb1aac8dbc8217ceb607428a992133954ad522365236e
+oid sha256:4cd85d7fa425e7888c973f1c2985ac15ca21b5e6171fe140a401c2bc75ca46ff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9446c3db15f382a5546f13622787fc99392a5e0bc8a9ca2da1838de7ab621a37
+oid sha256:d7915667371a58f1598639e0d1c20a0c59c783c14580cd040a6631eb4ea2311e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f11e7a6b3faa884fc23044e3772ff9dd72c257f02e121665061e2a03d518bd9
+oid sha256:35dd78929ad7f0fbf37fdb1284e8edf0424350f6e6ce1cd5a3ee78979af3d3cb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97a1e2f2542883d462e18c679fb75515cd51cbf96416fbbbdc7ed7d003e43a9
+oid sha256:97610cd95fe06fdca35f3af5c085e6621fc4c4d7c3ecef7fbe6456b650501b2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.787663459777832,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-600",
-  "epoch": 0.3090394025238218,
+  "epoch": 0.3347926860674736,
   "eval_steps": 50,
-  "global_step": 600,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,11 +1075,100 @@
       "eval_steps_per_second": 0.765,
       "num_input_tokens_seen": 7017576,
       "step": 600
+    },
+    {
+      "epoch": 0.311614730878187,
+      "grad_norm": 6.69798043480266,
+      "learning_rate": 9.697977204284973e-05,
+      "loss": 0.8925,
+      "num_input_tokens_seen": 7076032,
+      "step": 605
+    },
+    {
+      "epoch": 0.31419005923255217,
+      "grad_norm": 5.067921055882507,
+      "learning_rate": 9.690643253456297e-05,
+      "loss": 0.8159,
+      "num_input_tokens_seen": 7134536,
+      "step": 610
+    },
+    {
+      "epoch": 0.31676538758691736,
+      "grad_norm": 7.400939684061883,
+      "learning_rate": 9.683224164278264e-05,
+      "loss": 0.826,
+      "num_input_tokens_seen": 7193032,
+      "step": 615
+    },
+    {
+      "epoch": 0.3193407159412825,
+      "grad_norm": 5.898525799199162,
+      "learning_rate": 9.675720071412365e-05,
+      "loss": 0.8187,
+      "num_input_tokens_seen": 7251568,
+      "step": 620
+    },
+    {
+      "epoch": 0.3219160442956477,
+      "grad_norm": 11.267105316774332,
+      "learning_rate": 9.66813111106296e-05,
+      "loss": 0.8524,
+      "num_input_tokens_seen": 7310072,
+      "step": 625
+    },
+    {
+      "epoch": 0.3244913726500129,
+      "grad_norm": 6.703970582399643,
+      "learning_rate": 9.660457420974819e-05,
+      "loss": 0.7966,
+      "num_input_tokens_seen": 7368560,
+      "step": 630
+    },
+    {
+      "epoch": 0.32706670100437807,
+      "grad_norm": 6.945445265294353,
+      "learning_rate": 9.652699140430608e-05,
+      "loss": 0.799,
+      "num_input_tokens_seen": 7427040,
+      "step": 635
+    },
+    {
+      "epoch": 0.32964202935874326,
+      "grad_norm": 7.0684293091171595,
+      "learning_rate": 9.644856410248369e-05,
+      "loss": 0.8477,
+      "num_input_tokens_seen": 7485552,
+      "step": 640
+    },
+    {
+      "epoch": 0.3322173577131084,
+      "grad_norm": 7.165086711244158,
+      "learning_rate": 9.636929372778963e-05,
+      "loss": 0.7867,
+      "num_input_tokens_seen": 7544040,
+      "step": 645
+    },
+    {
+      "epoch": 0.3347926860674736,
+      "grad_norm": 9.185933515393563,
+      "learning_rate": 9.628918171903485e-05,
+      "loss": 0.8367,
+      "num_input_tokens_seen": 7602512,
+      "step": 650
+    },
+    {
+      "epoch": 0.3347926860674736,
+      "eval_loss": 0.7940558791160583,
+      "eval_runtime": 19.7641,
+      "eval_samples_per_second": 3.036,
+      "eval_steps_per_second": 0.759,
+      "num_input_tokens_seen": 7602512,
+      "step": 650
     }
   ],
   "logging_steps": 5,
   "max_steps": 3882,
-  "num_input_tokens_seen": 7017576,
+  "num_input_tokens_seen": 7602512,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1094,7 +1183,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 462990180876288.0,
+  "total_flos": 501587549356032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null