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:cd486cb7baac43b8cd310a5e79caaa468a71d2dd8d2b3d9ba4a0e193c37d36f0
+oid sha256:5662c9d87bcb8984d7d99fda215661bc6b160ff5e1633da0d3ddc61a823d2e03
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e9d3434ce16d8a09768175d9b857dc5d895366a281bf83f930a6f71c31f9e19
+oid sha256:a77894c814c543cd02f7d9412a7d8a662dd271446ad6be6a236c7a5e17375a3e
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f25f8eea8571597026dda96f73b919287a9200c6e4dab4ab5ef591c476ce27
+oid sha256:d9015db3f50142282f6391ebfe978db185004125b0af3ca5cde9bcf9c114b823
 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": 0.02908819690471751,
+  "epoch": 0.037292560134253215,
   "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": 2.9688,
       "step": 35
+    },
+    {
+      "epoch": 0.029834048107402575,
+      "grad_norm": 1.3166542053222656,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.0629,
+      "step": 40
+    },
+    {
+      "epoch": 0.029834048107402575,
+      "eval_loss": 2.962273120880127,
+      "eval_runtime": 4.1252,
+      "eval_samples_per_second": 136.962,
+      "eval_steps_per_second": 68.602,
+      "step": 40
+    },
+    {
+      "epoch": 0.03356330412082789,
+      "grad_norm": 1.2153655290603638,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7989,
+      "step": 45
+    },
+    {
+      "epoch": 0.037292560134253215,
+      "grad_norm": 1.268468976020813,
+      "learning_rate": 0.0,
+      "loss": 3.0314,
+      "step": 50
+    },
+    {
+      "epoch": 0.037292560134253215,
+      "eval_loss": 2.9579854011535645,
+      "eval_runtime": 4.1214,
+      "eval_samples_per_second": 137.091,
+      "eval_steps_per_second": 68.667,
+      "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": 83571638796288.0,
+  "total_flos": 106950200131584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null