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:fc56b1cdf95af5254c8f443ef03de8ade282bd85f75a164a049363b33610ab98
+oid sha256:45275ba8875152be22ad05ae58d38ee5402edcfc929764e6205857a09bac621a
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d983c3704dd8fa753b4456b3584c392f96ced8e54fa02c0a606b0de4bf3d1b
+oid sha256:4ff636bcbb5bd82aeb0787e0a54708db5b3085ef5c1b97ac3799395cd92c780a
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0473a82658c627429c106558fb3bb262aa9211c031722dafa14ae2d5bab0f9e
+oid sha256:fc8b30dc45df2e7849e049e2f88f3af04b8eb2fec3f79a4131192a96147a0392
 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": 0.22807017543859648,
+  "epoch": 0.29239766081871343,
   "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": 3.2517,
       "step": 35
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "grad_norm": 3.5481719970703125,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.9318,
+      "step": 40
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "eval_loss": 3.1777260303497314,
+      "eval_runtime": 4.0747,
+      "eval_samples_per_second": 17.67,
+      "eval_steps_per_second": 8.835,
+      "step": 40
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 5.325904369354248,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2349,
+      "step": 45
+    },
+    {
+      "epoch": 0.29239766081871343,
+      "grad_norm": 3.5925145149230957,
+      "learning_rate": 0.0,
+      "loss": 3.0101,
+      "step": 50
+    },
+    {
+      "epoch": 0.29239766081871343,
+      "eval_loss": 3.164489507675171,
+      "eval_runtime": 4.0276,
+      "eval_samples_per_second": 17.877,
+      "eval_steps_per_second": 8.938,
+      "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": 1950379589763072.0,
+  "total_flos": 2500486653542400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null