Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1095ad76aeb3b544f8be21d2125ca8182c3e259a054e479a7aca94b127472500
+oid sha256:3f835ab704076251920cf2b8962fae46425c86f13bf23b263ea491970ab32fff
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca565d92285d5280f60264f3fbcb1e4509c3c2b9966f5dc26a995b33d81f2893
+oid sha256:c00cbe52a34df92ea41781343738e7b6760bc3d8ca8b22e941bac785c6a48f44
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3ba56a9898bfda216d3b1f75e9e6c6fbb66b131d3905195c470a33236a6337
+oid sha256:4c3dcd9f7435f3a7c6e0f3af0f13d316dbf2622c99366d1714ae2ce223b49c0d
 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": 0.004385101897399859,
+  "epoch": 0.005621925509486999,
   "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": 4.5395,
       "step": 35
+    },
+    {
+      "epoch": 0.0044975404075896,
+      "grad_norm": 7.599331378936768,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3345,
+      "step": 40
+    },
+    {
+      "epoch": 0.0044975404075896,
+      "eval_loss": 0.7689247131347656,
+      "eval_runtime": 318.8736,
+      "eval_samples_per_second": 11.744,
+      "eval_steps_per_second": 5.874,
+      "step": 40
+    },
+    {
+      "epoch": 0.005059732958538299,
+      "grad_norm": 9.167427062988281,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1992,
+      "step": 45
+    },
+    {
+      "epoch": 0.005621925509486999,
+      "grad_norm": 4.255470275878906,
+      "learning_rate": 0.0,
+      "loss": 2.8511,
+      "step": 50
+    },
+    {
+      "epoch": 0.005621925509486999,
+      "eval_loss": 0.7447236180305481,
+      "eval_runtime": 319.088,
+      "eval_samples_per_second": 11.737,
+      "eval_steps_per_second": 5.87,
+      "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": 5737208610816000.0,
+  "total_flos": 7435422359617536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null