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:a2f80bd690bc795873881cc7d6fbbfb5d0a39aeffd95276d0c64b484fdd1c405
+oid sha256:0c36ae1653ebe65cb975db489cc5392a944aa8d2909a75b015c87a3a889894d3
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04879fe79286b7dabbb85f58b958ea459dd3b8ba332ce0d3d8621594e2107405
+oid sha256:a1cbbecee073d6bfc16f04d42e1c1d059a7af339d5fbd88897464cf78194e8ed
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b7f58f46be17989edce51431a5206319271ef30c1df04cc9f420e21f1886cd
+oid sha256:4433e01c2d64304a8fb12293bdc1ad43baac3583ca9ff48a5b5a4dd55ea2ff4b
 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": 0.004799114009721282,
+  "epoch": 0.006152710268873439,
   "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": 44.2922,
       "step": 35
+    },
+    {
+      "epoch": 0.004922168215098751,
+      "grad_norm": 1.2450387477874756,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.2717,
+      "step": 40
+    },
+    {
+      "epoch": 0.004922168215098751,
+      "eval_loss": 11.067696571350098,
+      "eval_runtime": 20.0292,
+      "eval_samples_per_second": 170.851,
+      "eval_steps_per_second": 85.425,
+      "step": 40
+    },
+    {
+      "epoch": 0.005537439241986095,
+      "grad_norm": 1.2475357055664062,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.264,
+      "step": 45
+    },
+    {
+      "epoch": 0.006152710268873439,
+      "grad_norm": 1.1453238725662231,
+      "learning_rate": 0.0,
+      "loss": 44.2775,
+      "step": 50
+    },
+    {
+      "epoch": 0.006152710268873439,
+      "eval_loss": 11.066289901733398,
+      "eval_runtime": 20.0405,
+      "eval_samples_per_second": 170.754,
+      "eval_steps_per_second": 85.377,
+      "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": 482240102400.0,
+  "total_flos": 617267331072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null