Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108e0788f92795d6051b044525d61737b3bc23716a9f7c614d440d436efc257b
+oid sha256:0c37f5e6f0629e7e82238587845985d5cac8df5a2dc02523bf1a3329b4f40ecc
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a842d99f5924ec232355e902b17cf2cc32bf330db6494365521286b7d3ed90
+oid sha256:7a96862441b87395cbabb49637fa031f81ff911224eb666f359956dc36fbe726
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:a080d3277fb6ccb5ed989cb90ca2c5dbb10923ca8748d5a82c16ca3dd1e9dbd3
 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": 0.05473684210526316,
+  "epoch": 0.07017543859649122,
   "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": 43.7472,
       "step": 35
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 5.840606689453125,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 43.6562,
+      "step": 40
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "eval_loss": 10.899812698364258,
+      "eval_runtime": 1.4235,
+      "eval_samples_per_second": 210.752,
+      "eval_steps_per_second": 105.376,
+      "step": 40
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 5.924816608428955,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 43.5953,
+      "step": 45
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 5.921303749084473,
+      "learning_rate": 0.0,
+      "loss": 43.5959,
+      "step": 50
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 10.889740943908691,
+      "eval_runtime": 1.4388,
+      "eval_samples_per_second": 208.502,
+      "eval_steps_per_second": 104.251,
+      "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": 376147279872.0,
+  "total_flos": 482240102400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null