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:a4aa4da84e67477a6e38dc79286fb62813a7f0412ad9a3d6d2793c7fc88cf587
+oid sha256:57d65f8035bd06ef164f32f38b14f039ac9c780e4af96297f04a56748998ed8a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81899a161748307b756207869ea145862ac809a16424fe640a91261c9d536ae
+oid sha256:224123b52a1d46a3e65f934328067d508a51cc01645424271c80141fd5246e99
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b749ebea7d33bb52b46501c471232f9e1fee56709d9c15875c3cc01be831450
+oid sha256:870d380716567dc6542e99554878b6a6d21998f17c6ed37742af713ad84ea93a
 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": 0.0014710597287969371,
+  "epoch": 0.0018859740112781246,
   "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": 0.0654,
       "step": 35
+    },
+    {
+      "epoch": 0.0015087792090224996,
+      "grad_norm": 0.07317674160003662,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1076,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015087792090224996,
+      "eval_loss": 0.1012507826089859,
+      "eval_runtime": 1696.1955,
+      "eval_samples_per_second": 6.581,
+      "eval_steps_per_second": 3.291,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016973766101503122,
+      "grad_norm": 0.11006845533847809,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0926,
+      "step": 45
+    },
+    {
+      "epoch": 0.0018859740112781246,
+      "grad_norm": 0.23720782995224,
+      "learning_rate": 0.0,
+      "loss": 0.0909,
+      "step": 50
+    },
+    {
+      "epoch": 0.0018859740112781246,
+      "eval_loss": 0.10078078508377075,
+      "eval_runtime": 1696.233,
+      "eval_samples_per_second": 6.581,
+      "eval_steps_per_second": 3.291,
+      "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": 1.2392080462577664e+16,
+  "total_flos": 1.5906252534054912e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null