Training in progress, step 716, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac97a50257be4997c608aae1f33f065181cc26841d4bcd8cdc645f409aa6467d
+oid sha256:5839c56a7ebbb855418005599ed317701c3dad1fdcfa37e3e1edb39544ead19a
 size 29034840

last-checkpoint/global_step715/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:c4eb4fadb32557a6d0d6d240781f07b2fa03be9416a0d95221e596e2efebe96d
+size 43429616

last-checkpoint/global_step715/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:d0a6d8b23054139f76fa940db6c7c3a16bd5542b2a03c68ff779206b281f9700
+size 43429616

last-checkpoint/global_step715/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a62bfa0c222cd0ac55de0f877c8a787767909618917ea7174c8b5f47273844
+size 43429616

last-checkpoint/global_step715/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba15b5bd9a28b498643a3f475da7868dca647f40ebbf3321396fa4aee460b8d
+size 43429616

last-checkpoint/global_step715/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dec229ba9ae0c4ce1e432cadfaa06ef2fababb1a2a66fe151bf06fd339d10f
+size 637299

last-checkpoint/global_step715/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adadb9013dbb6a121fe16835ae2aa6586adf0669ea7ed3f9f4253523a9c20c5b
+size 637171

last-checkpoint/global_step715/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a590d37400a819cc26c0b53852893e9d20c304b04cdfaa75cec3aca5ef449e
+size 637171

last-checkpoint/global_step715/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee70917044df6fdad1dd031f197eebd914ca857c3020ccffcd1a82745a748a4f
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step699
+global_step715

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a248426d28408e97f4b7517c7a252c88e2753983bb43ec02f73b9cab4fb795
+oid sha256:b2f1968e5962488bcd89a0ea5140dc5e5943a684fb456f3fffdbfccebf22377b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.794740617275238,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily/lora/sft/checkpoint-700",
-  "epoch": 1.9521815008726002,
+  "epoch": 1.9968586387434555,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 716,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1253,11 +1253,35 @@
       "eval_steps_per_second": 0.795,
       "num_input_tokens_seen": 10902632,
       "step": 700
+    },
+    {
+      "epoch": 1.9661431064572426,
+      "grad_norm": 23.84213538429929,
+      "learning_rate": 7.196961434052796e-08,
+      "loss": 0.8029,
+      "num_input_tokens_seen": 10980576,
+      "step": 705
+    },
+    {
+      "epoch": 1.9801047120418849,
+      "grad_norm": 7.4190814811781145,
+      "learning_rate": 2.1416057033352144e-08,
+      "loss": 0.7942,
+      "num_input_tokens_seen": 11058552,
+      "step": 710
+    },
+    {
+      "epoch": 1.994066317626527,
+      "grad_norm": 6.100028794501354,
+      "learning_rate": 5.949317655462583e-10,
+      "loss": 0.7964,
+      "num_input_tokens_seen": 11136520,
+      "step": 715
     }
   ],
   "logging_steps": 5,
   "max_steps": 716,
-  "num_input_tokens_seen": 10902632,
+  "num_input_tokens_seen": 11152104,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1267,12 +1291,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 737224437268480.0,
+  "total_flos": 754095660204032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null