Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe5cbe35a88ef710f3cbcb09d183cf6a01a80120a07c1f1c1add1a61f625d21
+oid sha256:f45a95a1a8ff2ad810b585c7494c31c2afa0aeafcf4997f463d8e0c121c801d9
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1e5ba8b54ae168471803d1f5e75b552adbc6223c61d6736ed1c2e5544b30de
+oid sha256:c3ae8484ab8110ac5cf4777a8376e88b789dc0e16f2bb6f42c29a7c3a573cdb8
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e6e7628d14b6ec55d580c68216d7f8b8cc24a38fff4c022374507c3a3d64fba
+oid sha256:f62b2b785a9c6cc399c552008f69c71b4ff902b5813fdef2e1d9fca68fe6e96b
 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": 0.028676470588235293,
+  "epoch": 0.03676470588235294,
   "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": 8.2632,
       "step": 35
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 2.4054322242736816,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.2349,
+      "step": 40
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "eval_loss": 2.1164493560791016,
+      "eval_runtime": 56.0657,
+      "eval_samples_per_second": 10.22,
+      "eval_steps_per_second": 5.119,
+      "step": 40
+    },
+    {
+      "epoch": 0.03308823529411765,
+      "grad_norm": 2.259829044342041,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.6449,
+      "step": 45
+    },
+    {
+      "epoch": 0.03676470588235294,
+      "grad_norm": 2.5194344520568848,
+      "learning_rate": 0.0,
+      "loss": 8.4466,
+      "step": 50
+    },
+    {
+      "epoch": 0.03676470588235294,
+      "eval_loss": 2.1157116889953613,
+      "eval_runtime": 55.9108,
+      "eval_samples_per_second": 10.248,
+      "eval_steps_per_second": 5.133,
+      "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": 1.112316825305088e+16,
+  "total_flos": 1.4260472119296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null