Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cff6105b8f58789467fb22eee33e99f75f597d5a1aca9afeb1074093bcfc2e
+oid sha256:c7eef3fedc5cf1cc5eb163b0fb4d936f5256c229ff83acbc3c79fe6f72a6b5ac
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63dddde6dbdcab0e59a262821edbd130e64b97bebb70b785940a6b4a96022c18
+oid sha256:5ced1d727bb2fcf69118de26242750efceaa0e1fb9f907cb8dd5c5bea562f2bc
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.0026904437507545313,
+  "epoch": 0.003449286859941707,
   "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": 41.5072,
       "step": 35
+    },
+    {
+      "epoch": 0.0027594294879533655,
+      "grad_norm": 0.30724793672561646,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 41.5077,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027594294879533655,
+      "eval_loss": 10.375277519226074,
+      "eval_runtime": 38.2716,
+      "eval_samples_per_second": 159.492,
+      "eval_steps_per_second": 79.746,
+      "step": 40
+    },
+    {
+      "epoch": 0.0031043581739475363,
+      "grad_norm": 0.2692151963710785,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 41.4986,
+      "step": 45
+    },
+    {
+      "epoch": 0.003449286859941707,
+      "grad_norm": 0.25719091296195984,
+      "learning_rate": 0.0,
+      "loss": 41.5103,
+      "step": 50
+    },
+    {
+      "epoch": 0.003449286859941707,
+      "eval_loss": 10.375199317932129,
+      "eval_runtime": 38.6994,
+      "eval_samples_per_second": 157.729,
+      "eval_steps_per_second": 78.864,
+      "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": 1899196317696.0,
+  "total_flos": 2431741231104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null