Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88097aa8d2b8bc7bd37a8c37fa6bf46a8e40aa38110e0e35da8bde7975e004dd
+oid sha256:4a023ead4210bd58a5b60db3e3c4ccee9e6fc437fccd4564be24add2c77a54c5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a943551839cad5ef9aa167910c7703cdda493db63765390368600ceedf4e635c
+oid sha256:447f66b597ced490451d0e521cbb138db4a2ea4461a6bc9752ff351da0f44766
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87e4caf284f84836b86fbb9d15f85d95c4be4769dd1ae693ef400a82f62b7ca
+oid sha256:8d67ec2502bdc1e0e180e8abf6116d9abc6b553d1b08b70fa10e367a53ed7cc9
 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": 0.05621621621621622,
+  "epoch": 0.07207207207207207,
   "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": 5.3514,
       "step": 35
+    },
+    {
+      "epoch": 0.05765765765765766,
+      "grad_norm": 8.90640926361084,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.224,
+      "step": 40
+    },
+    {
+      "epoch": 0.05765765765765766,
+      "eval_loss": 1.3918262720108032,
+      "eval_runtime": 24.6816,
+      "eval_samples_per_second": 11.871,
+      "eval_steps_per_second": 5.956,
+      "step": 40
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 10.465152740478516,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.6809,
+      "step": 45
+    },
+    {
+      "epoch": 0.07207207207207207,
+      "grad_norm": 11.144843101501465,
+      "learning_rate": 0.0,
+      "loss": 6.1119,
+      "step": 50
+    },
+    {
+      "epoch": 0.07207207207207207,
+      "eval_loss": 1.3903932571411133,
+      "eval_runtime": 24.5969,
+      "eval_samples_per_second": 11.912,
+      "eval_steps_per_second": 5.976,
+      "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": 7010679143792640.0,
+  "total_flos": 8938615908335616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null