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:b0478a278d020ac09ed3bf4c5f4ec50c3571f4063fbf98d621693a875d5dfbf1
+oid sha256:2832545186258ea8fc5f9f76f5537b0deca341779e884f9f90be0326bd599778
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a700c55d52c98485afd979514995d1161dcb9edb8ee3a31c2439a8dbd783f97
+oid sha256:5390db862feda8db6edc80160e963df0756e67bace1ee63ac1caa2dc6845d7fe
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2fdc42fb050d24550532fb049fa3b2d471046efdb168a01d12eb825c2eb25e
+oid sha256:96777d5e32689bdaea2aa3f6b38795b44c765255e2a8d2469ee90a6dc7b7d3e3
 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": 0.011020840692334864,
+  "epoch": 0.01412928293889085,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 3.3887,
       "step": 35
+    },
+    {
+      "epoch": 0.01130342635111268,
+      "grad_norm": 8.75986385345459,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3271,
+      "step": 40
+    },
+    {
+      "epoch": 0.01130342635111268,
+      "eval_loss": 3.2006571292877197,
+      "eval_runtime": 46.1457,
+      "eval_samples_per_second": 32.289,
+      "eval_steps_per_second": 16.145,
+      "step": 40
+    },
+    {
+      "epoch": 0.012716354645001766,
+      "grad_norm": 10.265480041503906,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1251,
+      "step": 45
+    },
+    {
+      "epoch": 0.01412928293889085,
+      "grad_norm": 10.496199607849121,
+      "learning_rate": 0.0,
+      "loss": 2.9414,
+      "step": 50
+    },
+    {
+      "epoch": 0.01412928293889085,
+      "eval_loss": 3.158576011657715,
+      "eval_runtime": 46.2368,
+      "eval_samples_per_second": 32.225,
+      "eval_steps_per_second": 16.113,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 997588715175936.0,
+  "total_flos": 1278959891251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null