Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f975073a4841062b5daf91657dfe14caee96e290d27a9c5a4d81065bd0ce73d
+oid sha256:6483e1b7cf54cd95d5b959c22790be0c404bba512e554dc075b49228a6dda5a4
 size 10624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a719e44549c7062cb371247272e0d7ebc8b096072a7d67bf308f69420f05a1
+oid sha256:542abe76aec11ccdada1ad11892e18347f16c77a505452c96376b33c37c9a892
 size 26562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0142a686d2f42ce8f779f95a994c62a8be5e12e27afd368335d9d4d2472185ef
+oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
 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": 0.0020449629678180505,
+  "epoch": 0.0026217473946385265,
   "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": 12.4549,
       "step": 35
+    },
+    {
+      "epoch": 0.0020973979157108214,
+      "grad_norm": 0.0029871268197894096,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 12.4555,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020973979157108214,
+      "eval_loss": 12.453027725219727,
+      "eval_runtime": 110.644,
+      "eval_samples_per_second": 72.575,
+      "eval_steps_per_second": 36.288,
+      "step": 40
+    },
+    {
+      "epoch": 0.002359572655174674,
+      "grad_norm": 0.005952336825430393,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.4553,
+      "step": 45
+    },
+    {
+      "epoch": 0.0026217473946385265,
+      "grad_norm": 0.0046081626787781715,
+      "learning_rate": 0.0,
+      "loss": 12.4562,
+      "step": 50
+    },
+    {
+      "epoch": 0.0026217473946385265,
+      "eval_loss": 12.453025817871094,
+      "eval_runtime": 110.6277,
+      "eval_samples_per_second": 72.586,
+      "eval_steps_per_second": 36.293,
+      "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": 4252925952.0,
+  "total_flos": 5421858816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null