Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27521aa61ab60994459f7a66e127ceceefc64cbf06ab00766cda449f4102a8c6
+oid sha256:987bf492e334de8578dcb0858c4f5d6096c8e9d87b18f8be460f1af69feee713
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b858369dbea5a602d4df14c141403512b9923bc33cb8b49ee8a273dcf7794683
+oid sha256:f2e810c9f70ea4de96c3f858410c39f20e20210441f92b36e144f76072049fab
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403d78fc4d0bbf580f6d2dc44b7bd36e5d64a00f7534f687f00dd21eab9686e7
+oid sha256:efdda3df82bd042eb7620eab16c33dfd2717c88fb488132468cd82bc877349a6
 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": 0.04785276073619632,
+  "epoch": 0.06134969325153374,
   "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": 0.1425,
       "step": 35
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "grad_norm": 0.47639739513397217,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.129,
+      "step": 40
+    },
+    {
+      "epoch": 0.049079754601226995,
+      "eval_loss": 0.12366819381713867,
+      "eval_runtime": 24.1511,
+      "eval_samples_per_second": 14.244,
+      "eval_steps_per_second": 7.122,
+      "step": 40
+    },
+    {
+      "epoch": 0.05521472392638037,
+      "grad_norm": 0.6678445339202881,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.136,
+      "step": 45
+    },
+    {
+      "epoch": 0.06134969325153374,
+      "grad_norm": 0.6876235008239746,
+      "learning_rate": 0.0,
+      "loss": 0.1143,
+      "step": 50
+    },
+    {
+      "epoch": 0.06134969325153374,
+      "eval_loss": 0.12126629799604416,
+      "eval_runtime": 24.1173,
+      "eval_samples_per_second": 14.264,
+      "eval_steps_per_second": 7.132,
+      "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": 3100603450392576.0,
+  "total_flos": 4025783512203264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null