Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773fa93fe76ab7791629b47f41ded64ca562e499258b5e51bef7f87bbd1862d4
+oid sha256:df3898b16fc9232168ae9bcfe2823e6d3f902f3efb969b364202021e53fcc69f
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:571bb9bd682830424c8b3d51e3c5b5c7060d9da83a72eec0ee61f1b8e66b2801
+oid sha256:908eb2d9ed320b5d18a7d372bea69fcca5fc46e0166c8d6cd9292bd42b259fcd
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd8cea30ce7a2b77d26a2e7c8d59aa8e60e47700db2c54a576edce7ea1b2144
+oid sha256:be7eebdff0930537621e4dd5c14cea8a32371d047edcec30d48c3e2257acf8fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6258776328986961,
+  "epoch": 0.802407221664995,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 9.353,
       "eval_steps_per_second": 4.676,
       "step": 39
+    },
+    {
+      "epoch": 0.641925777331996,
+      "grad_norm": 0.1265319287776947,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4436,
+      "step": 40
+    },
+    {
+      "epoch": 0.6579739217652959,
+      "grad_norm": 0.11708834022283554,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 2.507,
+      "step": 41
+    },
+    {
+      "epoch": 0.6740220661985958,
+      "grad_norm": 0.12580640614032745,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.5904,
+      "step": 42
+    },
+    {
+      "epoch": 0.6900702106318957,
+      "grad_norm": 0.12004761397838593,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.5087,
+      "step": 43
+    },
+    {
+      "epoch": 0.7061183550651956,
+      "grad_norm": 0.11525596678256989,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.4277,
+      "step": 44
+    },
+    {
+      "epoch": 0.7221664994984955,
+      "grad_norm": 0.12065120041370392,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4564,
+      "step": 45
+    },
+    {
+      "epoch": 0.7382146439317954,
+      "grad_norm": 0.12320233881473541,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.4538,
+      "step": 46
+    },
+    {
+      "epoch": 0.7542627883650953,
+      "grad_norm": 0.11359357833862305,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.5531,
+      "step": 47
+    },
+    {
+      "epoch": 0.7703109327983951,
+      "grad_norm": 0.11881112307310104,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.4245,
+      "step": 48
+    },
+    {
+      "epoch": 0.7863590772316951,
+      "grad_norm": 0.12177315354347229,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.601,
+      "step": 49
+    },
+    {
+      "epoch": 0.802407221664995,
+      "grad_norm": 0.11372490227222443,
+      "learning_rate": 0.0,
+      "loss": 2.6062,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.949113679609856e+16,
+  "total_flos": 2.498903514336461e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null