Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d8ca26ac84f31eb3e10d7cb1a5a1172ff9ef0879255e66931100eac461270bb
+oid sha256:fe853b1446921e0499f852961ea461ce18082fa25b6aa914ce8b957bd57f6f71
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab52c60e4970aee8e83795050e478a9b66afacece224eb202b42707cff1153b
+oid sha256:283308ab6b8c3a2fcbca5736282905a851b2f32f9f23cbb97792200e18819592
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10177ba4b0cfe4bef6f12698f94fbc66659931101eb6a166445976be8cd0bf0d
+oid sha256:a24caa68f9851aa3526ce9ff61ef195cc86de1c21ed4c172de8f5fb0862aa6d1
 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": 0.0005409285246174491,
+  "epoch": 0.0006934981084839091,
   "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": 0.0356,
       "step": 35
+    },
+    {
+      "epoch": 0.0005547984867871273,
+      "grad_norm": 0.15996599197387695,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0201,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005547984867871273,
+      "eval_loss": 0.029385773465037346,
+      "eval_runtime": 998.9003,
+      "eval_samples_per_second": 30.391,
+      "eval_steps_per_second": 15.196,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006241482976355182,
+      "grad_norm": 0.20267634093761444,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0171,
+      "step": 45
+    },
+    {
+      "epoch": 0.0006934981084839091,
+      "grad_norm": 0.5985381007194519,
+      "learning_rate": 0.0,
+      "loss": 0.0319,
+      "step": 50
+    },
+    {
+      "epoch": 0.0006934981084839091,
+      "eval_loss": 0.028885377570986748,
+      "eval_runtime": 999.0425,
+      "eval_samples_per_second": 30.387,
+      "eval_steps_per_second": 15.194,
+      "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": 1265549023641600.0,
+  "total_flos": 1621484686540800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null